CN113590955A - Target recommendation user determination method and device, electronic equipment and storage medium - Google Patents

Target recommendation user determination method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113590955A
CN113590955A CN202110872374.2A CN202110872374A CN113590955A CN 113590955 A CN113590955 A CN 113590955A CN 202110872374 A CN202110872374 A CN 202110872374A CN 113590955 A CN113590955 A CN 113590955A
Authority
CN
China
Prior art keywords
exposure
recommendation
live broadcast
broadcast room
recommended
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110872374.2A
Other languages
Chinese (zh)
Inventor
王璐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Douyu Network Technology Co Ltd
Original Assignee
Wuhan Douyu Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wuhan Douyu Network Technology Co Ltd filed Critical Wuhan Douyu Network Technology Co Ltd
Priority to CN202110872374.2A priority Critical patent/CN113590955A/en
Publication of CN113590955A publication Critical patent/CN113590955A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The embodiment of the invention discloses a target recommendation user determination method, a target recommendation user determination device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, and obtains exposure demand parameters of a target live broadcast room to be exposed and constraint conditions corresponding to the exposure recommendation function; determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure demand parameters and the constraint conditions; and determining the target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended. By the scheme of the embodiment of the invention, the exposure amount meeting the expectation of the current live broadcast room to be exposed is obtained, and the exposure accuracy of the current live broadcast room to be exposed is improved.

Description

Target recommendation user determination method and device, electronic equipment and storage medium
Technical Field
The embodiment of the invention relates to the technical field of live broadcast rooms, in particular to a target recommendation user determining method and device, electronic equipment and a storage medium.
Background
On a live broadcast platform, an important operation problem is to support the flow of some specific live broadcast rooms, that is, assist the live broadcast rooms to obtain a certain exposure flow, and the live broadcast rooms may be a well-known anchor who has just signed a contract, or an anchor which may need key culture and medium-small anchors with development potential.
The flow supporting scheme of the conventional live broadcast room comprises the following steps: the method adopts a forced insertion mode, namely, the direct broadcasting room needing to be supported is forcibly specified to be exposed at a specific position of each user access page. Obviously, the experience brought to the user by the conventional live broadcast room flow support scheme is poor, and the user cannot click the live broadcast room if the user is not interested, so that the purpose of flow support of the live broadcast room cannot be achieved.
Disclosure of Invention
The invention provides a target recommendation user determination method, a target recommendation user determination device, electronic equipment and a storage medium, which are used for enabling a current live broadcast room to be exposed to obtain expected exposure and improving the exposure accuracy of the current live broadcast room to be exposed.
In a first aspect, an embodiment of the present invention provides a method for determining a target recommended user, where the method includes:
acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, wherein the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, a priority of the live broadcast room to be exposed and recommendation probabilities of users to be recommended, the first benefit influence value is determined based on the loss of a platform and the probability of the preset exposure, which are caused by the fact that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probabilities of the users to be recommended and recommendation probabilities of historical watching values;
acquiring exposure demand parameters of a target live broadcast room to be exposed and constraint conditions corresponding to the exposure recommendation function;
determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure demand parameters and the constraint conditions;
and determining the target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended.
Optionally, the preset exposure recommendation function is obtained; wherein, the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, and comprises:
determining a degree of exposure uniformity in the exposure recommendation function based on the following formula:
Figure BDA0003189609700000021
wherein r iskThe number of requests of a user k to be recommended is shown; n iskRepresenting the number of live broadcast rooms which can be exposed by a user k to be recommended after each request; j is a live broadcast room required to reach a preset exposure; Γ (j) represents a set of directional users of the live broadcast room j that need to reach a preset exposure; z (gamma (j)) represents all directional user sets of the live broadcast room j needing to reach the preset exposure; vjIs the priority of the live broadcast room to be exposed; thetajThe exposure value of the live broadcast room j which needs to reach the preset exposure value accounts for the ratio; x is the number ofkjRepresenting the recommendation probability of the user k to be recommended of the live broadcast room j needing to reach the preset exposure;
determining a first benefit influence value corresponding to underexposure in the exposure recommendation function based on the following formula:
Figure BDA0003189609700000031
wherein p isjThe loss brought to the platform by the fact that the expressed exposure does not reach the preset exposure; u. ofjRepresenting the probability that the live broadcast room j needing to reach the preset exposure dose does not reach the preset exposure dose;
determining a second benefit influence value corresponding to the actual exposure in the exposure recommendation function based on the following formula:
Figure BDA0003189609700000032
wherein, ckjRepresenting a historical watching numerical value of the user k to be recommended to the live broadcast room j needing to reach the preset exposure;
and weighting the exposure uniformity, the first benefit influence value corresponding to the underexposure and the second benefit influence value corresponding to the actual exposure to obtain the exposure recommendation function.
Optionally, the weighting the exposure uniformity, the first benefit influence value corresponding to the underexposure, and the second benefit influence value corresponding to the actual exposure to obtain the exposure recommendation function includes:
determining the exposure recommendation function based on the following formula:
Figure BDA0003189609700000033
wherein λ is a constant for balancing the platform benefit impact value and whether the live broadcast room reaches the preset exposure.
Optionally, the constraint condition corresponding to the exposure recommendation function includes:
Figure BDA0003189609700000034
Figure BDA0003189609700000035
xkj,uj≥0；
rkxkj≤fj；
nkxkj≤1；
wherein f isjRepresenting the actual exposure threshold of the user to be recommended per day。
Optionally, the determining, according to the exposure recommendation function, the exposure requirement parameters, and the constraint conditions, recommendation probabilities respectively corresponding to users to be recommended in the target live broadcast room to be exposed includes:
constructing a first dual variable and a second dual variable, and respectively determining an analytic value of the first dual variable and an analytic value of the second dual variable;
and determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the analytic value of the first dual variable, the analytic value of the second dual variable, the exposure requirement parameters and the constraint conditions.
Optionally, the constructing a first dual variable and a second dual variable, and determining an analytic value of the exposure recommendation function according to the analytic values of the first dual variable and the second dual variable includes:
determining an analytic value of the first dual variable based on:
Figure BDA0003189609700000041
wherein (alpha)j)*Is a first dual variable; l is the learning rate; djRepresenting the preset exposure amount needed to be reached by the live broadcast room j;
determining an analytic value of the second dual variable based on:
Figure BDA0003189609700000042
wherein M iskAlpha is the preset exposure amount required to be achievedj+λckjIs measured.
Optionally, the determining a target recommendation user of the target live broadcast room to be exposed based on each recommendation probability respectively corresponding to each user to be recommended includes:
respectively comparing each recommendation probability with a preset probability threshold;
and if the compared current recommendation probability is greater than the preset probability threshold, determining the user to be recommended corresponding to the current recommendation probability as the target recommendation user in the target live broadcast room to be exposed.
In a second aspect, an embodiment of the present invention further provides a target recommended user determining apparatus, where the apparatus includes:
the exposure recommendation function acquisition module is used for acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, wherein the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, a priority of the live broadcast room to be exposed and recommendation probabilities of users to be recommended, the first benefit influence value is determined based on the loss of a platform and the probability of the preset exposure, which are caused by the fact that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probabilities of the users to be recommended and recommendation probabilities of historical watching values;
the exposure requirement parameter and constraint condition acquisition module is used for acquiring each exposure requirement parameter of a target live broadcast room to be exposed and each constraint condition corresponding to the exposure recommendation function;
a recommendation probability determining module, configured to determine, according to the exposure recommendation function, the exposure requirement parameters, and the constraint conditions, recommendation probabilities corresponding to users to be recommended in the target live broadcast room to be exposed;
and the target recommendation user determination module is used for determining the target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method for targeted recommended user determination as provided by any of the embodiments of the invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the target recommended user determination method provided in any embodiment of the present invention.
The technical scheme of the embodiment of the invention specifically comprises the following steps: acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, the priority of the live broadcast room to be exposed and the recommendation probability of each user to be recommended, the first benefit influence value is determined based on the loss of a platform caused by the fact that the preset exposure is not reached and the probability that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probability of each user to be recommended and the historical viewing numerical value of each user to be recommended; acquiring exposure demand parameters of a target live broadcast room to be exposed and constraint conditions corresponding to exposure recommendation functions; determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure requirement parameters and the constraint conditions; and further determining target recommendation users of the target live broadcast room to be exposed based on recommendation probabilities respectively corresponding to the users to be recommended. According to the technical scheme of the embodiment of the invention, each exposure requirement parameter of the live broadcast room to be exposed is obtained, each recommendation probability of each user to be recommended corresponding to the live broadcast room to be exposed is determined based on a preset exposure recommendation function and a constraint condition corresponding to the exposure recommendation function, a target recommendation user is finally determined based on each recommendation probability, and the live broadcast room to be exposed is recommended to the target recommendation user, so that the current live broadcast room to be exposed is enabled to obtain expected exposure, and the exposure accuracy of the current live broadcast room to be exposed is improved.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, a brief description is given below of the drawings used in describing the embodiments. It should be clear that the described figures are only views of some of the embodiments of the invention to be described, not all, and that for a person skilled in the art, other figures can be derived from these figures without inventive effort.
Fig. 1 is a flowchart illustrating a target recommended user determination method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a target recommended user determination device according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a target recommendation user determination method according to an embodiment of the present invention, which is applicable to a case of recommending a live broadcast room to a user, and more specifically, to a case of recommending a live broadcast room to be exposed, which needs to reach a preset exposure amount, to a user to be recommended. The method may be performed by a targeted recommended user determination apparatus, which may be implemented by means of software and/or hardware.
Before describing the technical solution of the present embodiment, an application scenario of the present embodiment is described in an exemplary manner, and of course, the application scenario is only an optional application scenario, and the technical solution of the present embodiment may also be applied to other application scenarios, which is not limited in the present embodiment. Specifically, exemplary application scenarios of the present embodiment include: at present, on a live broadcast platform, an important operation problem is to support the flow of some specific live broadcast rooms, which may be a well-known anchor just signed up, a medium-small anchor with development potential and an anchor with important culture in a guild.
The conventional scheme supports the flow of the live broadcast room by adopting a forced insertion method, namely, the live broadcast room is forcibly exposed at a specific position for each user to be recommended, the experience of the user to be recommended is poor by the method, the live broadcast room cannot be clicked if the user is not interested, actual benefits cannot be brought to a platform, in addition, the exposure amount cannot be controlled, and the waste of the flow is likely to be caused.
In order to scientifically distribute traffic and achieve the purpose of really supporting a live broadcast room, the technical scheme of the embodiment provides a target recommendation user determination method, a target recommendation user determination device, electronic equipment and a storage medium. Specifically, according to the technical scheme of the embodiment of the invention, each exposure requirement parameter of the live broadcast room to be exposed is obtained, each recommendation probability of each user to be recommended corresponding to the live broadcast room to be exposed is determined based on a preset exposure recommendation function and a constraint condition corresponding to the exposure recommendation function, a target recommendation user is finally determined based on each recommendation probability, and the live broadcast room to be exposed is recommended to the target recommendation user, so that the current live broadcast room to be exposed can obtain expected exposure, and the exposure accuracy of the current live broadcast room to be exposed is improved.
As shown in fig. 1, the technical solution of this embodiment specifically includes the following steps:
s110, acquiring a preset exposure recommendation function; the exposure recommendation function comprises exposure uniformity, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure.
In the embodiment of the invention, the exposure recommendation function is a pre-constructed target optimization function, and the exposure recommendation function can determine an optimized exposure recommendation scheme based on the acquired exposure demand data of the live broadcast room, namely which users recommend the exposure and how much exposure is recommended by each user, so that the current live broadcast room to be exposed can obtain the expected exposure according with the current live broadcast room to be exposed, and the exposure accuracy of the current live broadcast room to be exposed is improved.
The exposure recommendation function comprises exposure uniformity, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure. Specifically, the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, the priority of the live broadcast room to be exposed and the recommendation probability of each user to be recommended, the first benefit influence value is determined based on the loss of the platform caused by the fact that the preset exposure amount is not reached and the probability that the preset exposure amount is not reached, and the second benefit influence value is determined based on the recommendation probability of each user to be recommended and the historical watching numerical value.
Optionally, the determination method for determining the exposure uniformity based on the directional user set of the target live broadcast room to be exposed, the priority of the live broadcast room to be exposed, and the recommendation probability of each user to be recommended may be determined based on the following formula:
Figure BDA0003189609700000091
wherein r iskThe number of requests of a user k to be recommended is shown; n iskRepresenting the number of live broadcast rooms which can be exposed by a user k to be recommended after each request; j is a live broadcast room required to reach a preset exposure; Γ (j) represents a set of directional users of the live broadcast room j that need to reach a preset exposure; z (gamma (j)) represents all directional user sets of the live broadcast room j needing to reach the preset exposure; vjIs the priority of the live broadcast room to be exposed; thetajThe exposure value of the live broadcast room j which needs to reach the preset exposure value accounts for the ratio; x is the number ofkjAnd representing the recommendation probability of the user k to be recommended of the live broadcast room j needing to reach the preset exposure.
In the present embodiment, the request number rkThe recommendation method is calculated according to the historical daily average request number of each user to be recommended, specifically, the process of one request is that the user to be recommended initiates a request for showing a plurality of live broadcast rooms to the back end, and the back end shows the request according to the specific showing of the user to be recommendedThe live broadcast room; the live broadcast room j that needs to reach the preset exposure is generally reserved by an exposure request that needs to reach the preset exposure.
Specifically, the meaning of the above formula in this embodiment is the probability x that any live broadcast room j that needs to reach the preset exposure is allocated to each user k to be recommendedkjThe ratio theta of the exposure to the exposure of the live broadcast room j to the preset exposure as much as possiblejAs close as possible so that the distribution probabilities can be as close as possible for the same demand without exposure non-uniformity, where the proximity is measured by a square, thus (x)kj-θj)2As small as possible while dividing by theta on the basis of the above resultsjThe flow ratio of different live broadcast rooms which need to reach the preset exposure is considered, so that the closeness degree of the different live broadcast rooms which need to reach the preset exposure is comparable; since the priority of each live broadcast room which needs to reach the preset exposure and the contribution capacity of each user to be recommended to the exposure are different, the exposure r which can be provided by the user k to be recommended needs to be multiplied on the basis of the above resultsknkAnd priority V of live broadcast room to be exposedj。
Optionally, the determination method for determining the first benefit influence value based on the loss of the platform caused by the condition that the preset exposure dose is not reached and the probability that the preset exposure dose is not reached may be determined based on the following formula:
Figure BDA0003189609700000101
wherein p isjThe loss brought to the platform by the fact that the expressed exposure does not reach the preset exposure; u. ofjAnd the probability that the live broadcast room j needing to reach the preset exposure dose does not reach the preset exposure dose is shown.
Specifically, the above formula means in this embodiment that the loss due to the missing amount p is not reached in the live broadcast room, and the loss due to the missing amount p is not reachedjMultiplying by the probability of deficit ujThereby obtaining a lost benefit impact value.
Optionally, the determination method for determining the second benefit influence value based on the recommendation probability of each user to be recommended to the recommendation probability of each user to be recommended and the historical viewing value may be determined based on the following formula:
Figure BDA0003189609700000102
wherein, ckjRepresenting a historical watching numerical value of the user k to be recommended to the live broadcast room j needing to reach the preset exposure;
and weighting the exposure uniformity, the first benefit influence value corresponding to underexposure and the second benefit influence value corresponding to actual exposure to obtain an exposure recommendation function.
Specifically, the meaning of the above formula in this embodiment is expressed as a revenue influence value brought to the platform by the exposure of the live broadcast room; wherein r isknkxkjckjThe number of viewing times that the user to be exposed can contribute to the live broadcast room j which needs to reach the preset exposure, namely the expected benefit obtained by clicking the conversion platform by the user to be recommended, is calculated by using the exposure r which can be provided by the user k to be recommendedknkMultiplying the probability x of the distribution of the to-be-recommended user k in the live broadcast room j needing to reach the preset exposure amount by the probability xkjObtaining the expected exposure amount r provided by the user to be recommended to the live broadcast room j needing to reach the preset exposure amountknkxkjRepresenting the actual exposure of the user to be recommended, and multiplying by ckjObtaining the number of watching times that the user to be exposed can contribute to the live broadcast room j needing to reach the preset exposure, namely rknkxkjckjAnd obtaining expected benefits obtained by clicking the conversion platform by the user to be recommended.
Weighting the acquired exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure to obtain an exposure recommendation function; alternatively, the following formula may be adopted to perform weighting processing on the above parameters to obtain the exposure recommendation function. Specifically, the exposure recommendation function is determined based on the following formula:
Figure BDA0003189609700000111
wherein λ is a constant for balancing the platform benefit impact value and whether the live broadcast room reaches the preset exposure.
And S120, acquiring exposure requirement parameters of the target live broadcast room to be exposed and constraint conditions corresponding to the exposure recommendation function.
In this embodiment, the exposure requirement parameter is a recommendation probability parameter for determining each recommendation probability parameter corresponding to each user to be recommended in the target live broadcast room to be exposed, that is, each exposure requirement parameter is substituted into the obtained exposure recommendation function to obtain each recommendation probability corresponding to each user to be recommended in the target live broadcast room.
Specifically, each exposure requirement parameter includes: request number r of user to be recommendedkThe number n of live broadcast rooms which can be exposed by the user to be recommended after each requestkThe method comprises the following steps of 1, collecting all directional users Z (gamma (j)) in a live broadcast room j needing to reach a preset exposure amount and in a live broadcast room j needing to reach the preset exposure amount; priority V of live broadcast room to be exposedjThe exposure amount ratio theta of the live broadcast room j needing to reach the preset exposure amountjAnd the loss p brought to the platform by the preset exposure is not reachedjProbability u that j of live broadcast room needing to reach preset exposure does not reach preset exposurejAnd the historical watching numerical value c of the user k to be recommended to the live broadcast room j needing to reach the preset exposurekj. Each exposure requirement parameter in this embodiment may be obtained by directly reading data, or may be obtained by performing calculation based on other parameters. For example: the exposure proportion theta of the live broadcast room j required to reach the preset exposurejCan be determined based on the following equation:
Figure BDA0003189609700000121
wherein d isjIndicating the preset exposure that the live room j needs to reach.
Further, determining recommendation probabilities respectively corresponding to users to be recommended in the target live broadcast room to be exposed based on the exposure demand parameters and the exposure recommendation functions in the target live broadcast room to be exposed further requires obtaining constraint conditions corresponding to the exposure recommendation functions, and determining preferred recommendation probabilities under the constraint conditions.
Optionally, the constraint condition corresponding to the exposure recommendation function includes:
Figure BDA0003189609700000122
Figure BDA0003189609700000123
xkj,uj≥0；
rkxkj≤fj；
nkxkj≤1；
wherein f isjRepresenting the actual exposure threshold for each day of the user to be recommended.
Specifically, the above constraints are respectively defined as: the first constraint represents the actual exposure r of the user to be recommendedknkxkjPlus the probability of deficit ujSo that the preset exposure djCan be satisfied. The second and the third constraints are that the probability that the user to be recommended recommends the live broadcast room to be exposed is a variable in an interval of 0-1. The fourth constraint is that the total number of exposures per day of a recommended user in a live room j to be exposed cannot exceed an upper limit fj. A fifth constraint is that for live room j, the expected number of impressions in a request does not exceed 1.
In this embodiment, the fourth and fifth requirements are for the user experience, and too many presentations to a user every day in the same live broadcast room or repeated presentations in a request may impair the user experience.
S130, determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure requirement parameters and the constraint conditions.
In this embodiment, a first dual variable and a second dual variable for solving each recommendation probability are constructed, and an analytic value of the first dual variable and an analytic value of the second dual variable are solved respectively; further, determining recommendation probabilities respectively corresponding to users to be recommended in the target live broadcast room to be exposed based on the analytic values of the first dual variable and the analytic values of the second dual variable.
The first dual variable (α) is constructed in this embodimentj)*And a second dual variable (. beta.)k)*. Alternatively, for solving for the first dual variable (α)j)*For each j, initializing
Figure BDA0003189609700000131
And determining an iterative formula for the first pair of even variables:
Figure BDA0003189609700000132
wherein: l is the learning rate;
Figure BDA0003189609700000133
representing the actual exposure of the user to be recommended, djRepresenting the preset exposure amount needed to be reached by the live broadcast room j; the ratio result of the two shows the exposure rate of the contribution of the user to be recommended to the live broadcast room j which needs to reach the preset exposure; 1 minus the exposure rate indicates the exposure rate still needed; multiplying the priority of the live broadcast room to be exposed by the still needed exposure rate to show the priority degree of the exposure rate needed by the current live broadcast room to be exposed; the priority degree multiplied by the learning rate is used as an iteration updating value to update the first dual variable, and the updating iteration is stopped when the required inclusion rate is smaller than a preset exposure rate threshold value to obtain the analysis of the first dual variableThe value is obtained.
Specifically, after iteration is performed according to the above formula and the maximum iteration number T satisfying the iteration stop condition is obtained, the analytic value of the first pair of even variables is determined:
Figure BDA0003189609700000134
optionally, for solving for the second dual variable (β)k)*The analytical values of (a) to be mentioned are: due to betak≤max(αj+λckj) Thus for a set of directional users in live room j, α is calculatedj+λckjMaximum value Mk(ii) a Wherein M iskIs the maximum alpha in all live rooms required to reach the preset exposurej+λckjTaking a value, i.e.
Figure BDA0003189609700000141
In particular, the second dual variable (. beta.)k)*The analytic values of (a) include: let betak＝MkCalculate the initial F value, note
Figure BDA0003189609700000142
Further taking binary sites
Figure BDA0003189609700000143
Get betak＝skComputing
Figure BDA0003189609700000144
If it is
Figure BDA0003189609700000145
Is less than
Figure BDA0003189609700000146
Then take 0 to skGenerating a new binary site; if it is
Figure BDA0003189609700000147
Is greater than
Figure BDA0003189609700000148
Then at skTo MkGenerating new binary loci in the interval of (a); performing iteration updating based on the steps until the iteration stopping condition is met, and determining the maximum iteration number S; after the iteration number S, determining an analytic value of a second pair of even variables:
Figure BDA0003189609700000149
after determining the analytic value of the first dual variable and the analytic value of the second dual variable, approximately updating the dual variable on the contract side to obtain:
Figure BDA00031896097000001410
Figure BDA00031896097000001411
specifically, the recommendation probabilities respectively corresponding to the users k to be recommended in the target live broadcast room j to be exposed can be obtained based on the following formula:
Figure BDA00031896097000001412
s140, determining the target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended.
In this embodiment, the method for determining the target recommendation user of the target live broadcast room to be exposed may be: obtaining recommendation probabilities respectively corresponding to users to be recommended, and respectively comparing the recommendation probabilities with a preset probability threshold; and if the compared current recommendation probability is greater than a preset probability threshold, determining the user to be recommended corresponding to the current recommendation probability as the target recommendation user of the target live broadcast room to be exposed.
Of course, the recommendation probabilities respectively corresponding to the users to be recommended may also be obtained, the recommendation probabilities are ranked, the recommendation probability with the largest value is determined, and the user to be recommended corresponding to the recommendation probability with the largest value is determined as the target recommendation user in the target live broadcast room to be exposed. Of course, the method for determining the target recommended user based on the recommendation probability may also be determined according to the actual situation, which is not limited in this embodiment.
In some embodiments, a target recommendation probability corresponding to a target recommendation user is obtained, the target recommendation probability and each exposure requirement parameter of a target live broadcast room to be exposed are substituted into an exposure recommendation function for calculation, and an analysis value of the exposure recommendation function, namely, an exposure amount distributed by the target recommendation user is obtained, so that the exposure amount meeting an expectation of the current live broadcast room to be exposed is obtained.
The technical scheme of the embodiment of the invention specifically comprises the following steps: acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, the priority of the live broadcast room to be exposed and the recommendation probability of each user to be recommended, the first benefit influence value is determined based on the loss of a platform caused by the fact that the preset exposure is not reached and the probability that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probability of each user to be recommended and the historical viewing numerical value of each user to be recommended; acquiring exposure demand parameters of a target live broadcast room to be exposed and constraint conditions corresponding to exposure recommendation functions; determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure requirement parameters and the constraint conditions; and further determining target recommendation users of the target live broadcast room to be exposed based on recommendation probabilities respectively corresponding to the users to be recommended. According to the technical scheme of the embodiment of the invention, each exposure requirement parameter of the live broadcast room to be exposed is obtained, each recommendation probability of each user to be recommended corresponding to the live broadcast room to be exposed is determined based on a preset exposure recommendation function and a constraint condition corresponding to the exposure recommendation function, a target recommendation user is finally determined based on each recommendation probability, and the live broadcast room to be exposed is recommended to the target recommendation user, so that the current live broadcast room to be exposed is enabled to obtain expected exposure, and the exposure accuracy of the current live broadcast room to be exposed is improved.
The following is an embodiment of the target recommended user determining apparatus provided in the embodiments of the present invention, and the apparatus and the target recommended user determining method in the embodiments belong to the same inventive concept, and details that are not described in detail in the embodiment of the target recommended user determining apparatus may refer to the embodiment of the target recommended user determining method.
Example two
Fig. 2 is a schematic structural diagram of a target recommendation user determination device according to a second embodiment of the present invention, which is applicable to a case of recommending a live broadcast room to a user, and more specifically, to a case of recommending a live broadcast room to be exposed, which needs to reach a preset exposure amount, to a user to be recommended. The specific structure of the target recommendation user determination device comprises: an exposure recommendation function obtaining module 210, an exposure requirement parameter and constraint condition obtaining module 220, a recommendation probability determining module 230 and a target recommendation user determining module 240; wherein,
an exposure recommendation function obtaining module 210, configured to obtain a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, wherein the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, a priority of the live broadcast room to be exposed and recommendation probabilities of users to be recommended, the first benefit influence value is determined based on the loss of a platform and the probability of the preset exposure, which are caused by the fact that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probabilities of the users to be recommended and recommendation probabilities of historical watching values;
an exposure requirement parameter and constraint condition obtaining module 220, configured to obtain each exposure requirement parameter of a target live broadcast room to be exposed and each constraint condition corresponding to the exposure recommendation function;
a recommendation probability determining module 230, configured to determine, according to the exposure recommendation function, the exposure requirement parameters, and the constraint conditions, recommendation probabilities respectively corresponding to users to be recommended in the target live broadcast room to be exposed;
and a target recommendation user determining module 240, configured to determine a target recommendation user of the target live broadcast room to be exposed based on each recommendation probability corresponding to each user to be recommended.
The technical scheme of the embodiment of the invention specifically comprises the following steps: acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, wherein the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, a priority of the live broadcast room to be exposed and recommendation probabilities of users to be recommended, the first benefit influence value is determined based on the loss of a platform and the probability of the preset exposure, which are caused by the fact that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probabilities of the users to be recommended and recommendation probabilities of historical watching values; acquiring exposure demand parameters of a target live broadcast room to be exposed and constraint conditions corresponding to the exposure recommendation functions; determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure demand parameters and the constraint conditions; and further determining target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended. According to the technical scheme of the embodiment of the invention, each exposure requirement parameter of the live broadcast room to be exposed is obtained, each recommendation probability of each user to be recommended corresponding to the live broadcast room to be exposed is determined based on a preset exposure recommendation function and a constraint condition corresponding to the exposure recommendation function, a target recommendation user is finally determined based on each recommendation probability, and the live broadcast room to be exposed is recommended to the target recommendation user, so that the current live broadcast room to be exposed can obtain expected exposure, and the exposure accuracy of the current live broadcast room to be exposed is improved.
On the basis of the above embodiment, the exposure recommendation function obtaining module 210 includes:
an exposure uniformity determining unit, configured to determine the exposure uniformity in the exposure recommendation function based on the following formula:
Figure BDA0003189609700000181
wherein r iskThe number of requests of a user k to be recommended is shown; n iskRepresenting the number of live broadcast rooms which can be exposed by a user k to be recommended after each request; j is a live broadcast room required to reach a preset exposure; Γ (j) represents a set of directional users of the live broadcast room j that need to reach a preset exposure; z (gamma (j)) represents all directional user sets of the live broadcast room j needing to reach the preset exposure; vjIs the priority of the live broadcast room to be exposed; thetajThe exposure value of the live broadcast room j which needs to reach the preset exposure value accounts for the ratio; x is the number ofkjRepresenting the recommendation probability of the user k to be recommended of the live broadcast room j needing to reach the preset exposure;
a first benefit influence value determining unit, configured to determine a corresponding first benefit influence value when the exposure recommendation function is underexposed based on the following formula:
Figure BDA0003189609700000182
wherein p isjThe loss brought to the platform by the fact that the expressed exposure does not reach the preset exposure; u. ofjRepresenting the probability that the live broadcast room j needing to reach the preset exposure dose does not reach the preset exposure dose;
a second benefit influence value determination unit, configured to determine a second benefit influence value corresponding to an actual exposure in the exposure recommendation function based on the following formula:
Figure BDA0003189609700000183
wherein, ckjRepresenting a historical watching numerical value of the user k to be recommended to the live broadcast room j needing to reach the preset exposure;
and the exposure recommendation function determining unit is used for weighting the exposure uniformity, the first benefit influence value corresponding to the underexposure and the second benefit influence value corresponding to the actual exposure to obtain the exposure recommendation function.
On the basis of the above embodiment, the exposure recommendation function determining unit includes:
an exposure recommendation function determining subunit configured to determine the exposure recommendation function based on the following formula:
Figure BDA0003189609700000191
wherein λ is a constant for balancing the platform benefit impact value and whether the live broadcast room reaches the preset exposure.
On the basis of the above embodiment, the constraint condition corresponding to the exposure recommendation function includes:
Figure BDA0003189609700000192
Figure BDA0003189609700000193
xkj,uj≥0；
rkxkj≤fj；
nkxkj≤1；
wherein f isjRepresenting the actual exposure threshold for each day of the user to be recommended.
On the basis of the above embodiment, the recommendation probability determining module 230 includes:
an analytic value determining unit, configured to construct a first dual variable and a second dual variable, and determine an analytic value of the first dual variable and an analytic value of the second dual variable, respectively;
and the recommendation probability determining unit is used for determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the analysis value of the first dual variable, the analysis value of the second dual variable, the exposure requirement parameters and the constraint conditions.
On the basis of the above embodiment, the analytic value determining unit includes:
a first analytic value determining subunit configured to determine an analytic value of the first dual variable based on the following formula:
Figure BDA0003189609700000201
wherein (alpha)j)*Is a first dual variable; l is the learning rate; djRepresenting the preset exposure amount needed to be reached by the live broadcast room j;
a second analytic value determining subunit, configured to determine an analytic value of the second dual variable based on the following formula:
Figure BDA0003189609700000202
wherein M iskAlpha is the preset exposure amount required to be achievedj+λckjIs measured.
On the basis of the above embodiment, the target recommendation user determining module 240 includes:
the comparison unit is used for comparing each recommendation probability with a preset probability threshold value;
and the target recommendation user determining unit is used for determining the user to be recommended corresponding to the current recommendation probability as the target recommendation user of the target live broadcast room to be exposed if the compared current recommendation probability is greater than the preset probability threshold.
The target recommendation user determination device provided by the embodiment of the invention can execute the target recommendation user determination method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
It should be noted that, in the embodiment of the target recommended user determining apparatus, the included units and modules are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
EXAMPLE III
Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. FIG. 3 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 3 is only an example and should not bring any limitations to the function and scope of use of the embodiments of the present invention.
As shown in FIG. 3, electronic device 12 is embodied in the form of a general purpose computing electronic device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 3, and commonly referred to as a "hard drive"). Although not shown in FIG. 3, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with electronic device 12, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 20. As shown in FIG. 3, the network adapter 20 communicates with the other modules of the electronic device 12 via the bus 18. It should be appreciated that although not shown in FIG. 3, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and sample data acquisition by running the program stored in the system memory 28, for example, implementing steps of a target recommended user determination method provided in this embodiment, where the target recommended user determination method includes:
acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, wherein the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, a priority of the live broadcast room to be exposed and recommendation probabilities of users to be recommended, the first benefit influence value is determined based on the loss of a platform and the probability of the preset exposure, which are caused by the fact that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probabilities of the users to be recommended and recommendation probabilities of historical watching values;
acquiring exposure demand parameters of a target live broadcast room to be exposed and constraint conditions corresponding to the exposure recommendation function;
determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure demand parameters and the constraint conditions;
and determining the target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended.
Of course, those skilled in the art can understand that the processor may also implement the technical solution of the sample data obtaining method provided in any embodiment of the present invention.
EXAMPLE five
The fifth embodiment provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements, for example, the steps of the target recommended user determination method provided in this embodiment, where the target recommended user determination method includes:
acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, wherein the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, a priority of the live broadcast room to be exposed and recommendation probabilities of users to be recommended, the first benefit influence value is determined based on the loss of a platform and the probability of the preset exposure, which are caused by the fact that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probabilities of the users to be recommended and recommendation probabilities of historical watching values;
acquiring exposure demand parameters of a target live broadcast room to be exposed and constraint conditions corresponding to the exposure recommendation function;
determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure demand parameters and the constraint conditions;
and determining the target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It will be understood by those skilled in the art that the modules or steps of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented by program code executable by a computing device, such that it may be stored in a memory device and executed by a computing device, or it may be separately fabricated into various integrated circuit modules, or it may be fabricated by fabricating a plurality of modules or steps thereof into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (10)

1. A target recommendation user determination method is characterized by comprising the following steps:
acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, wherein the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, a priority of the live broadcast room to be exposed and recommendation probabilities of users to be recommended, the first benefit influence value is determined based on the loss of a platform and the probability of the preset exposure, which are caused by the fact that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probabilities of the users to be recommended and recommendation probabilities of historical watching values;
acquiring exposure demand parameters of a target live broadcast room to be exposed and constraint conditions corresponding to the exposure recommendation function;
determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the exposure recommendation function, the exposure demand parameters and the constraint conditions;
and determining the target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended.
2. The method according to claim 1, wherein the obtaining of a preset exposure recommendation function; wherein, the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, and comprises:
determining a degree of exposure uniformity in the exposure recommendation function based on the following formula:
Figure FDA0003189609690000011
wherein r iskThe number of requests of a user k to be recommended is shown; n iskRepresenting the number of live broadcast rooms which can be exposed by a user k to be recommended after each request; j is a live broadcast room required to reach a preset exposure; Γ (j) represents a set of directional users of the live broadcast room j that need to reach a preset exposure; z (gamma (j)) represents all directional user sets of the live broadcast room j needing to reach the preset exposure; vjIs the priority of the live broadcast room to be exposed; thetajThe exposure value of the live broadcast room j which needs to reach the preset exposure value accounts for the ratio; x is the number ofkjRepresenting the recommendation probability of the user k to be recommended of the live broadcast room j needing to reach the preset exposure;
determining a first benefit influence value corresponding to underexposure in the exposure recommendation function based on the following formula:
Figure FDA0003189609690000021
wherein p isjThe loss brought to the platform by the fact that the expressed exposure does not reach the preset exposure; u. ofjRepresenting the probability that the live broadcast room j needing to reach the preset exposure dose does not reach the preset exposure dose;
determining a second benefit influence value corresponding to the actual exposure in the exposure recommendation function based on the following formula:
Figure FDA0003189609690000022
wherein, ckjRepresenting a historical watching numerical value of the user k to be recommended to the live broadcast room j needing to reach the preset exposure;
and weighting the exposure uniformity, the first benefit influence value corresponding to the underexposure and the second benefit influence value corresponding to the actual exposure to obtain the exposure recommendation function.
3. The method of claim 2, wherein the weighting the exposure uniformity, the first benefit influence value corresponding to the underexposure, and the second benefit influence value corresponding to the actual exposure to obtain the exposure recommendation function comprises:
determining the exposure recommendation function based on the following formula:
Figure FDA0003189609690000023
wherein λ is a constant for balancing the platform benefit impact value and whether the live broadcast room reaches the preset exposure.
4. The method of claim 2, wherein the constraint to which the exposure recommendation function corresponds comprises:
Figure FDA0003189609690000031
Figure FDA0003189609690000032
xkj,uj≥0；
rkxkj≤fj；
nkxkj≤1；
wherein j is a live broadcast room required to reach a preset exposure; Γ (j) represents a set of directional users of the live broadcast room j that need to reach a preset exposure; z (gamma (j)) represents all directional user sets of the live broadcast room j needing to reach the preset exposure; r iskThe number of requests of a user k to be recommended is shown; n iskRepresenting the number of live broadcast rooms which can be exposed by a user k to be recommended after each request; x is the number ofkjRepresenting the recommendation probability of the user k to be recommended of the live broadcast room j needing to reach the preset exposure; u. ofjRepresenting the probability that the live broadcast room j needing to reach the preset exposure dose does not reach the preset exposure dose; djRepresenting the preset exposure amount needed to be reached by the live broadcast room j; f. ofjRepresenting the actual exposure threshold for each day of the user to be recommended.
5. The method according to claim 1, wherein the determining, according to the exposure recommendation function, the exposure requirement parameters, and the constraint conditions, recommendation probabilities respectively corresponding to users to be recommended in the target live broadcast room to be exposed comprises:
constructing a first dual variable and a second dual variable, and respectively determining an analytic value of the first dual variable and an analytic value of the second dual variable;
and determining recommendation probabilities respectively corresponding to the users to be recommended in the target live broadcast room to be exposed according to the analytic value of the first dual variable, the analytic value of the second dual variable, the exposure requirement parameters and the constraint conditions.
6. The method of claim 5, wherein constructing a first dual variable and a second dual variable and determining an analytical value of the exposure recommendation function based on the analytical values of the first dual variable and the second dual variable comprises:
determining an analytic value of the first dual variable based on:
Figure FDA0003189609690000041
wherein (alpha)j)*Is a first dual variable; l is the learning rate; djRepresenting the preset exposure amount needed to be reached by the live broadcast room j;
determining an analytic value of the second dual variable based on:
Figure FDA0003189609690000042
wherein M iskAlpha is the preset exposure amount required to be achievedj+λckjIs measured.
7. The method according to claim 1, wherein the determining the target recommendation user of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended comprises:
respectively comparing each recommendation probability with a preset probability threshold;
and if the compared current recommendation probability is greater than the preset probability threshold, determining the user to be recommended corresponding to the current recommendation probability as the target recommendation user in the target live broadcast room to be exposed.
8. A target recommendation user determination device, comprising:
the exposure recommendation function acquisition module is used for acquiring a preset exposure recommendation function; the exposure recommendation function comprises an exposure uniformity degree, a first benefit influence value corresponding to underexposure and a second benefit influence value corresponding to actual exposure, wherein the exposure uniformity degree is determined based on a directional user set of a target live broadcast room to be exposed, a priority of the live broadcast room to be exposed and recommendation probabilities of users to be recommended, the first benefit influence value is determined based on the loss of a platform and the probability of the preset exposure, which are caused by the fact that the preset exposure is not reached, and the second benefit influence value is determined based on the recommendation probabilities of the users to be recommended and recommendation probabilities of historical watching values;
the exposure requirement parameter and constraint condition acquisition module is used for acquiring each exposure requirement parameter of a target live broadcast room to be exposed and each constraint condition corresponding to the exposure recommendation function;
a recommendation probability determining module, configured to determine, according to the exposure recommendation function, the exposure requirement parameters, and the constraint conditions, recommendation probabilities corresponding to users to be recommended in the target live broadcast room to be exposed;
and the target recommendation user determination module is used for determining the target recommendation users of the target live broadcast room to be exposed based on the recommendation probabilities respectively corresponding to the users to be recommended.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the target recommended user determination method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method for targeted recommended user determination according to any one of claims 1-7.
CN202110872374.2A 2021-07-30 2021-07-30 Target recommendation user determination method and device, electronic equipment and storage medium Pending CN113590955A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110872374.2A CN113590955A (en) 2021-07-30 2021-07-30 Target recommendation user determination method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110872374.2A CN113590955A (en) 2021-07-30 2021-07-30 Target recommendation user determination method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113590955A true CN113590955A (en) 2021-11-02

Family

ID=78252710

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110872374.2A Pending CN113590955A (en) 2021-07-30 2021-07-30 Target recommendation user determination method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113590955A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114095481A (en) * 2021-11-23 2022-02-25 百果园技术(新加坡)有限公司 Chat room putting method, device, equipment and storage medium
CN114595381A (en) * 2022-02-22 2022-06-07 平安科技（深圳）有限公司 Recommendation method, recommendation device, electronic device and storage medium

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150229979A1 (en) * 2014-02-11 2015-08-13 The Nielsen Company (Us), Llc Methods and apparatus to calculate video-on-demand and dynamically inserted advertisement viewing probability
US20160292158A1 (en) * 2015-04-06 2016-10-06 Netflix, Inc. Global recommendation systems for overlapping media catalogs
CN107358593A (en) * 2017-06-16 2017-11-17 广东欧珀移动通信有限公司 Imaging method and device
US20180018700A1 (en) * 2015-06-26 2018-01-18 Tencent Technology (Shenzhen) Company Limited Method and Device and System for Processing Promotion Information
CN108520034A (en) * 2018-03-29 2018-09-11 广州优视网络科技有限公司 Using recommendation method, apparatus and computer equipment
CN109039678A (en) * 2017-06-08 2018-12-18 腾讯科技（深圳）有限公司 Control method, device, electronic equipment and the storage medium that promotion message plays
CN109547808A (en) * 2018-11-22 2019-03-29 北京达佳互联信息技术有限公司 Data processing method, device, server and storage medium
CN109951725A (en) * 2019-03-07 2019-06-28 武汉斗鱼鱼乐网络科技有限公司 A kind of recommended method and relevant device of direct broadcasting room
CN110225361A (en) * 2019-06-03 2019-09-10 武汉瓯越网视有限公司 Direct broadcasting room recommended method, storage medium, electronic equipment and system
US20190347708A1 (en) * 2018-01-10 2019-11-14 Beijing Sensetime Technology Development Co., Ltd Methods and apparatuses for deep learning-based recommendation, electronic devices, and media
CN110730385A (en) * 2018-07-16 2020-01-24 武汉斗鱼网络科技有限公司 Live broadcast room recommendation method and device, server and storage medium
US20200221181A1 (en) * 2019-01-07 2020-07-09 Alphonso Inc. Content Recommendation System and Method-Based Implicit Ratings
CN111510783A (en) * 2020-04-26 2020-08-07 咪咕动漫有限公司 Method, device, electronic equipment and storage medium for determining video exposure
US20210209491A1 (en) * 2020-09-01 2021-07-08 Beijing Baidu Netcom Science And Technology Co., Ltd. Method and apparatus for recommending content, device, and medium

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150229979A1 (en) * 2014-02-11 2015-08-13 The Nielsen Company (Us), Llc Methods and apparatus to calculate video-on-demand and dynamically inserted advertisement viewing probability
US20160292158A1 (en) * 2015-04-06 2016-10-06 Netflix, Inc. Global recommendation systems for overlapping media catalogs
US20180018700A1 (en) * 2015-06-26 2018-01-18 Tencent Technology (Shenzhen) Company Limited Method and Device and System for Processing Promotion Information
CN109039678A (en) * 2017-06-08 2018-12-18 腾讯科技（深圳）有限公司 Control method, device, electronic equipment and the storage medium that promotion message plays
CN107358593A (en) * 2017-06-16 2017-11-17 广东欧珀移动通信有限公司 Imaging method and device
US20190347708A1 (en) * 2018-01-10 2019-11-14 Beijing Sensetime Technology Development Co., Ltd Methods and apparatuses for deep learning-based recommendation, electronic devices, and media
CN108520034A (en) * 2018-03-29 2018-09-11 广州优视网络科技有限公司 Using recommendation method, apparatus and computer equipment
CN110730385A (en) * 2018-07-16 2020-01-24 武汉斗鱼网络科技有限公司 Live broadcast room recommendation method and device, server and storage medium
CN109547808A (en) * 2018-11-22 2019-03-29 北京达佳互联信息技术有限公司 Data processing method, device, server and storage medium
US20200221181A1 (en) * 2019-01-07 2020-07-09 Alphonso Inc. Content Recommendation System and Method-Based Implicit Ratings
CN109951725A (en) * 2019-03-07 2019-06-28 武汉斗鱼鱼乐网络科技有限公司 A kind of recommended method and relevant device of direct broadcasting room
CN110225361A (en) * 2019-06-03 2019-09-10 武汉瓯越网视有限公司 Direct broadcasting room recommended method, storage medium, electronic equipment and system
CN111510783A (en) * 2020-04-26 2020-08-07 咪咕动漫有限公司 Method, device, electronic equipment and storage medium for determining video exposure
US20210209491A1 (en) * 2020-09-01 2021-07-08 Beijing Baidu Netcom Science And Technology Co., Ltd. Method and apparatus for recommending content, device, and medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
包红云等: "集成组内标签与用户链接关系的Flickr组推荐模型", 模式识别与人工智能, vol. 26, no. 2, 15 February 2013 (2013-02-15), pages 176 - 181 *
张宴硕等: "算法推荐机制下的短视频创作与传播", 新媒体研究, no. 18, pages 128 - 130 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114095481A (en) * 2021-11-23 2022-02-25 百果园技术(新加坡)有限公司 Chat room putting method, device, equipment and storage medium
CN114095481B (en) * 2021-11-23 2024-03-12 百果园技术(新加坡)有限公司 Chat room delivery method, device, equipment and storage medium
CN114595381A (en) * 2022-02-22 2022-06-07 平安科技（深圳）有限公司 Recommendation method, recommendation device, electronic device and storage medium
CN114595381B (en) * 2022-02-22 2024-06-25 平安科技（深圳）有限公司 Recommendation method, recommendation device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
US9430299B2 (en) System, method and product for task allocation
CN109272348B (en) Method and device for determining number of active users, storage medium and electronic equipment
CN112016794B (en) Resource quota management method and device and electronic equipment
US12079476B2 (en) Data processing method, apparatus, device, and readable storage medium
CN113590955A (en) Target recommendation user determination method and device, electronic equipment and storage medium
CN112017042A (en) Resource quota determining method and device based on tweed distribution and electronic equipment
CN115134368A (en) Load balancing method, device, equipment and storage medium
CN110889725A (en) Online advertisement CTR estimation method, device, equipment and storage medium
CN110569190B (en) Transaction pressure testing method and device, electronic device and readable storage medium
CN110689425A (en) Method and device for pricing quota based on income and electronic equipment
CN115033248A (en) Code evaluation method, device, equipment and medium
CN112989236B (en) Information display method and device, electronic equipment and storage medium
CN110347973B (en) Method and device for generating information
CN111130984B (en) Method and apparatus for processing information
CN111311015A (en) Personalized click rate prediction method, device and readable storage medium
CN117273376A (en) Electric quantity prediction method, system, computer equipment and storage medium
CN116484033A (en) Media material determining method, device, medium and equipment
CN110009380A (en) Transaction data prediction technique, device, electronic equipment and computer storage medium
CN110768989B (en) Authority control method, device, equipment and storage medium based on cloud platform
CN113592263A (en) Resource return increment prediction method and device based on dynamic resource return increase ratio
CN115237931A (en) Method and system for updating sub-service processing result of service arrangement
CN113837569A (en) IT service personnel matching method, system, electronic device and medium
CN112749076B (en) Test method and device and electronic equipment
CN108958720B (en) System synthesis method, device, equipment and storage medium
CN113761343A (en) Information pushing method and device, terminal equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination