CN114417007A - Recommendation method and related equipment for financial products - Google Patents
Recommendation method and related equipment for financial products Download PDFInfo
- Publication number
- CN114417007A CN114417007A CN202111572374.7A CN202111572374A CN114417007A CN 114417007 A CN114417007 A CN 114417007A CN 202111572374 A CN202111572374 A CN 202111572374A CN 114417007 A CN114417007 A CN 114417007A
- Authority
- CN
- China
- Prior art keywords
- business
- theme
- user
- target
- determining
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000006399 behavior Effects 0.000 claims description 37
- 238000004590 computer program Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Software Systems (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a recommendation method and related equipment for financial products, belonging to the technical field of recommendation systems, wherein the method comprises the following steps: acquiring a knowledge graph corresponding to a first user to be recommended; determining a target parameter corresponding to each service theme according to the knowledge graph; determining a target recommendation score corresponding to each service theme according to the initial recommendation score and the target parameter corresponding to each service theme; and determining a target business theme in each business theme according to the target recommendation score, and pushing product information of the financial product related to the target business theme to a terminal related to the first user, wherein the target recommendation score of the target business theme is larger than a preset score. In the invention, the target business theme which is expected by the user is determined by the knowledge map obtained by the financial products purchased or browsed by the user, so that the financial products related to the target business theme are recommended to the user, the recommendation accuracy of the financial products is improved, and the recommendation precision of the financial products is higher.
Description
Technical Field
The invention relates to the technical field of recommendation systems, in particular to a recommendation method and related equipment for financial products.
Background
With the improvement of living standard of people, people have more and more idle funds. People can buy financial products through idle funds, so that the wealth of the people is increased.
Currently, when a customer purchases a financial product, the financial product platform makes a recommendation based on the asset amount of the customer and a historical purchase record, but the asset amount may be a small part of idle funds of the customer, and the recommendation of the financial product is not accurate.
Disclosure of Invention
The invention provides a recommendation method and related equipment for financial products, which are used for solving the problem of low recommendation precision of the financial products.
In one aspect, the present invention provides a method for recommending financial products, including:
acquiring a knowledge graph corresponding to a first user to be recommended, wherein the product knowledge graph comprises a plurality of connection relations between business topics and financial products, each business topic is connected with one or more financial products, the business topics are connected with the financial products through common attribute features, and the financial products are financial products purchased or browsed by the first user;
determining a target parameter corresponding to each business topic according to the knowledge graph, wherein the target parameter comprises at least one of a first number of attribute features, a second number of paths and operation information of a first user, and the paths are connection paths of the financial products and the business topics;
determining a target recommendation score corresponding to each service theme according to the initial recommendation score corresponding to each service theme and the target parameters;
and determining a target business theme in each business theme according to the target recommendation score, and pushing product information of the financial product associated with the target business theme to a terminal associated with the first user, wherein the target recommendation score of the target business theme is larger than a preset score.
In an embodiment, the target parameter includes the first quantity, and the step of determining the target recommendation score corresponding to each of the service topics according to the initial recommendation score corresponding to each of the service topics and the target parameter includes:
determining a maximum number among the respective first numbers;
determining a first correction value corresponding to each business topic according to the maximum number and a first number corresponding to each business topic, wherein the first number and the first correction value are in a positive correlation;
and correcting the initial recommendation score corresponding to the service theme according to the first correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
In an embodiment, the target parameter includes the second number, and the step of determining the target recommendation score corresponding to each service topic according to the initial recommendation score corresponding to each service topic and the target parameter includes:
determining the path weight of each path corresponding to the business theme according to the second quantity corresponding to the business theme, wherein the path weight and the second quantity are in a negative correlation relationship;
determining the length of each path, and determining the product of the length of the path and the path weight to obtain a numerical value corresponding to the path;
determining a second correction value corresponding to the business theme according to the sum of the numerical values corresponding to the paths corresponding to the business theme;
and correcting the initial recommendation score corresponding to the service theme according to the second correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
In an embodiment, the target parameter includes operation information of a first user, and the step of determining the target recommendation score corresponding to each service topic according to the initial recommendation score corresponding to each service topic and the target parameter includes:
acquiring the operation behavior of the first user on each path according to the operation information;
determining the behavior weight corresponding to the path according to the type of the operation behavior corresponding to the path;
determining a third correction value corresponding to the business theme according to the sum of the behavior weights corresponding to each path of the business theme;
and correcting the initial recommendation score corresponding to the service theme according to the third correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
In an embodiment, the target parameter includes operation information of a first user, and the step of determining the target recommendation score corresponding to each service topic according to the initial recommendation score corresponding to each service topic and the target parameter includes:
acquiring operation information of each second user, wherein the first user is any one of the second users;
determining the user operation times of each attribute feature corresponding to the service theme according to the operation information corresponding to each second user;
determining the heat value of the service theme according to the user operation times of each attribute feature corresponding to the service theme;
determining a fourth correction value corresponding to the service theme according to the heat value corresponding to the theme service, wherein the heat value and the fourth correction value are in a positive correlation;
and correcting the initial recommendation score corresponding to the service theme according to the fourth correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
In an embodiment, the step of obtaining the knowledge graph corresponding to the first user to be recommended includes:
acquiring operation information of the first user, and determining each financial product purchased or browsed by the first user according to the operation information of the first user;
generating each business theme according to the attribute characteristics of each financial product, and determining the attribute characteristics matched with each business theme in each attribute characteristic;
generating the business theme, the attribute characteristics and the icons corresponding to the financial products respectively;
and connecting the icon corresponding to the attribute characteristic with the icon of the business theme matched with the attribute characteristic, and connecting the icon corresponding to the attribute characteristic with the icon of the financial product to which the attribute characteristic belongs to obtain the knowledge graph.
In another aspect, the present invention provides a recommendation apparatus for a financial product, including:
the system comprises an acquisition module, a recommendation module and a recommendation module, wherein the acquisition module is used for acquiring a knowledge graph corresponding to a first user to be recommended, the product knowledge graph comprises a connection relation between a plurality of business topics and financial products, each business topic is connected with one or more financial products, the business topics are connected with the financial products through common attribute features, and the financial products are financial products purchased or browsed by the first user;
a determining module, configured to determine, according to the knowledge graph, a target parameter corresponding to each business topic, where the target parameter includes at least one of a first number of attribute features, a second number of paths, and operation information of a first user, and the paths are connection paths between the financial product and the business topic;
the determining module is further configured to determine a target recommendation score corresponding to each service topic according to the initial recommendation score corresponding to each service topic and the target parameter;
the determining module is further configured to determine a target business topic in each business topic according to the target recommendation score, and push product information of a financial product associated with the target business topic to a terminal associated with the first user, where the target recommendation score of the target business topic is greater than a preset score.
In another aspect, the present invention also provides a recommendation apparatus for a financial product, including: a memory and a processor;
the memory stores computer-executable instructions;
the processor executes the computer-executable instructions stored by the memory to cause the processor to perform the method of recommending financial products as described above.
In another aspect, the present invention also provides a computer-readable storage medium having stored therein computer-executable instructions for implementing the recommendation method for financial products as described above when executed by a processor.
In another aspect, the present invention also provides a computer program product comprising a computer program, which when executed by a processor, implements the method for recommending financial products as described above.
According to the recommendation method and the relevant equipment of the financial product, the knowledge map corresponding to the user to be recommended is obtained, the target parameters such as the number of attribute features, the number of paths and the operation information of the user corresponding to each service theme are determined according to the knowledge map, the target recommendation score corresponding to each service theme is determined according to the initial recommendation score and the target parameters corresponding to each service theme, the target service theme is determined according to the target recommendation score, and therefore the product information of the financial product related to the target service theme is pushed to the terminal related to the user. In the invention, the target business theme which is expected by the user is determined by the knowledge map obtained by the financial products purchased or browsed by the user, so that the financial products related to the target business theme are recommended to the user, the recommendation accuracy of the financial products is improved, and the recommendation precision of the financial products is higher.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a schematic diagram of a scenario for implementing a recommendation method for a financial product according to the present invention;
FIG. 2 is a flowchart illustrating a method for recommending financial products according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a detailed process of step S30 in the second embodiment of the method for recommending financial products according to the present invention;
FIG. 4 is a flowchart illustrating a detailed process of step S30 in the third embodiment of the method for recommending financial products according to the present invention;
FIG. 5 is a flowchart illustrating a detailed process of step S30 in the fourth embodiment of the method for recommending financial products according to the present invention;
FIG. 6 is a flowchart illustrating a detailed process of step S30 in the fifth embodiment of the method for recommending financial products according to the present invention;
FIG. 7 is a block diagram of an apparatus for recommending financial products according to the present invention;
fig. 8 is a schematic diagram of a hardware configuration of a recommendation apparatus for financial products according to the present invention.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
In the technical scheme of the present application, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the related information such as financial data or user data are all in accordance with the regulations of the relevant laws and regulations, and do not violate the good custom of the public order.
The invention provides a recommendation method of financial products, which can be realized through a scene schematic diagram shown in fig. 1. As shown in fig. 1, the financial product recommending apparatus 100 stores a user knowledge map 110. The knowledge-graph 110 includes a plurality of business topics, and the business topics are determined according to the characteristics of the financial products, for example, two business topics of "robust profit" and "high return rate" are generated according to financial product 1, financial product 2, financial product 3, and financial product 4. The financial product is a financial product viewed or purchased by the user. The business topics may be generated based on financial products, for example, each financial product in fig. 1 generates two business topics of "robust profit" and "high return rate" based on the generation paths a, b, c, d. The business topic is connected with a plurality of attribute features, for example, "robust profit" connects "T +1 account," net value, "" R2 risk, "" R1 risk, "" currency, "" real time account, "" N, "" P "8 attribute features, which are attribute features of financial products. In addition, the knowledge graph 110 further includes operation information (not shown in fig. 1) of the user, and the operation information includes viewing, sharing, paying attention, hanging a bill, and purchasing. The recommendation device 100 for financial products may determine a recommendation score of each service topic and the user according to the knowledge graph, so as to push the service topic with a higher recommendation score to the terminal of the user.
The following describes the technical solutions of the present invention and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Referring to fig. 2, fig. 2 is a first embodiment of a method for recommending a financial product according to the present invention, the method for recommending a financial product comprising the steps of:
step S10, acquiring a knowledge graph corresponding to a first user to be recommended, wherein the product knowledge graph comprises a plurality of connection relations between business topics and financial products, each business topic is connected with one or more financial products, the business topics are connected with the financial products through common attribute characteristics, and the financial products are financial products purchased or browsed by the first user.
In the present embodiment, the execution subject is a recommendation apparatus for financial products, and for convenience of description, the apparatus is hereinafter referred to as a recommendation apparatus for financial products. The knowledge graph of the user to be recommended is stored in the device. The user to be recommended is defined as the first user. The knowledge graph comprises a plurality of business topics and the connection relations of the financial products, each business topic is connected with one or more financial products, and the financial products are the financial products purchased or browsed by the first user. The business theme is connected with the financial product through common attribute characteristics. As shown in FIG. 1, financial product 1 is connected to the business topic "robust profit" through attribute features "T +1 Account" and "equity type". The business theme is generated by extracting the attribute characteristics of different financial products. For example, a business topic with a high return rate is defined as a business topic with a number of repeated throws greater than 1000 and a proportion of repeated throws greater than 10%, and a business topic with a low return rate is defined as a business topic with a maximum return of less than 1% in the last year and a maximum return of less than 2% in the last three years. The knowledge-graph may be transmitted to the device by an external device or generated by the device based on the operation information of the first user for each financial product. The operation information includes information of financial products browsed and purchased by the user. The operation information includes information of the first user on viewing, sharing, paying attention to, placing an order, purchasing and the like of the financial product.
Step S20, determining a target parameter corresponding to each business topic according to the knowledge graph, wherein the target parameter comprises at least one of a first number of attribute features, a second number of paths and operation information of the first user, and the paths are connection paths of the financial products and the business topics.
After determining the knowledge-graph, the apparatus may determine a target parameter corresponding to each business topic, where the target parameter includes at least one of a first number of attribute features, a second number of paths, and operation information of the first user. The first number is the number of attribute features of the business topic connection. The path is a connection path of the financial product with the business theme. Referring to fig. 1, the financial product 1 forms a path of "robust profit" by connecting two arrows of the business topic "robust profit" to account "through the feature attribute" T + 1.
And step S30, determining a target recommendation score corresponding to each service topic according to the initial recommendation score corresponding to each service topic and the target parameter.
Each business topic has a corresponding initial recommendation score, the initial recommendation score w0Can be flexibly configured and intervened according to market conditions and business experiences, and w0Can take values between 0 and 1. That is, the initial recommendation score may be set by a customer manager of the financial product institution, and the set initial recommendation score may be stored in the device. The device obtains the initial recommendation score corresponding to each business topic, and corrects the initial recommendation score based on the target parameters to determine the target recommendation score corresponding to the business topic. For example, the target parameter includes a first number of attribute features corresponding to the business topic, and if the number of the attribute features connected to the business topic is larger, the business topic is more appropriate for the first user to purchase a financial product, so that a correction value can be determined by the first number, and the larger the first number is, the larger the correction value is, so that the larger the target recommendation score obtained by correcting the initial recommendation score based on the correction value is.
Step S40, determining a target business theme in each business theme according to the target recommendation score, and pushing product information of the financial product related to the target business theme to a terminal related to the first user, wherein the target recommendation score of the target business theme is larger than a preset score.
After the target recommendation scores corresponding to the business topics are determined, whether the first user has purchase intention on the financial products related to the business topics needs to be estimated based on the target recommendation scores. The device stores a preset score, and if the target recommendation score is larger than the preset score, the business theme corresponding to the target recommendation score can be determined to be the business theme which is interested by the user. In this regard, the device determines the service theme with the target recommendation score larger than the preset score as a target service theme couple, and then pushes the product information of the financial product associated with the target service theme to the terminal associated with the first user.
In the technical scheme provided by this embodiment, a knowledge graph corresponding to a user to be recommended is obtained, target parameters such as the number of attribute features, the number of paths, operation information of the user and the like corresponding to each service topic are determined according to the knowledge graph, a target recommendation score corresponding to each service topic is determined according to an initial recommendation score and the target parameters corresponding to each service topic, and a target service topic is determined according to the target recommendation score, so that product information of a financial product related to the target service topic is pushed to a terminal related to the user. In the invention, the target business theme which is expected by the user is determined by the knowledge map obtained by the financial products purchased or browsed by the user, so that the financial products related to the target business theme are recommended to the user, the recommendation accuracy of the financial products is improved, and the recommendation precision of the financial products is higher.
Referring to fig. 3, fig. 3 shows a second embodiment of the method for recommending financial products according to the present invention, wherein step 30 includes:
in step S301, the maximum number is determined among the respective first numbers.
In this embodiment, the target parameter includes a first number. The apparatus determines a correction value based on the first amount, and obtains a target recommendation score by correcting the initial recommendation score based on the correction value, the correction value being defined as a first correction value. Specifically, the device determines the maximum number in each first number, and the maximum number represents the service topic with the most attribute features of the connection.
Step S302, determining a first correction value corresponding to each business topic according to the maximum number and a first number corresponding to each business topic, wherein the first number and the first correction value are in a positive correlation relationship.
The device determines a first correction value corresponding to each business topic based on the first number corresponding to each business topic by the maximum number. The larger the number of the attribute features connected with the service theme is, the larger the first correction value corresponding to the service theme is, that is, the first number and the first correction value are in positive correlation.
Step S303, according to the first correction value corresponding to the service theme, the initial recommendation score corresponding to the service theme is corrected to obtain a target recommendation score corresponding to the service theme.
After the first correction value corresponding to each business theme is determined, the initial recommendation score of the business theme can be determined to be corrected based on the first correction value of the business theme, and the target recommendation score corresponding to the business theme is obtained.
Specifically, the target recommendation score obtained by correcting the initial recommendation score by the first correction value can be represented by the following formula:
W＝W0X(1-log10 tnum/log10 tmax_num)
wherein, w0Is the initial recommendation score, W is the target recommendation score, (1-log)10 tnum/log10 tmax_num) Is a first correction value, tnumIs a first number, tmax_numIs the maximum number.
In the technical solution provided in this embodiment, the apparatus determines the maximum number among the first numbers, determines the first correction value corresponding to each service topic according to the maximum number and the first number corresponding to each service topic, and corrects the initial recommendation score corresponding to the service topic based on the first correction value of the service topic, thereby accurately obtaining the target recommendation score corresponding to the service topic.
Referring to fig. 4, fig. 4 shows a third embodiment of the method for recommending financial products according to the present invention, wherein step S30 includes:
step S304, determining the path weight of each path corresponding to the business theme according to the second quantity corresponding to the business theme, wherein the path weight and the second quantity are in a negative correlation relationship.
In this embodiment, the target parameter includes a second number of paths of the business topic connection. The knowledge graph includes multiple paths, and each business topic connects multiple paths, for example, the "robust profit" in fig. 1 connects 6 attribute features, so there are six paths for the "robust profit".
The device determines the path weight of each path based on the second number of paths connected by the service subject, and the larger the second number is, the pathsThe larger the path weight, i.e. the path weight is inversely related to the second number. The path weight may be given by
Characterization, p _ numjA second number of paths contained by the traffic topic numbered j. For example, there are six paths for "robust yield," and the path weight for each path for "robust yield" is 1/6.
Step S305, determining the length of each path, and determining the product of the length of the path and the path weight to obtain a value corresponding to the path.
Each path has a corresponding length. For example, in FIG. 1 "robust yield" connected to "monetary", the length of this path is 2; the financial product connects "T +1 to account" and "T +1 to account" connecting "robust profit", then the length of this path is 3. The apparatus determines the length of each path, and obtains a value corresponding to the path by determining the product of the length of the path and the path weight.
Step S306, determining a second correction value corresponding to the business theme according to the sum of the numerical values corresponding to the paths corresponding to the business theme.
The device can determine a second correction value corresponding to the business theme based on the sum of the numerical values corresponding to all paths of the business theme. It can be understood that, the fewer the paths of the business topic, the greater the path weight, the greater the second correction value of the business topic, and thus the greater the target recommendation score.
Step S307, according to the second correction value corresponding to the service theme, the initial recommendation score corresponding to the service theme is corrected to obtain a target recommendation score corresponding to the service theme.
The device can correct the initial recommendation score to obtain the target recommendation score based on the first correction value and the second correction value. Specifically, the target recommendation score may be characterized by the following formula:
wherein,
is the sum of the numerical values corresponding to each path of the service theme connection.
In the technical scheme provided by this embodiment, the second number of the device service theme paths determines the second correction value corresponding to the service theme, so that the initial recommendation score is corrected according to the second correction value to obtain an accurate target recommendation score.
Referring to fig. 5, fig. 5 shows a fourth embodiment of the method for recommending financial products according to the present invention, wherein step S30 includes:
and step S308, acquiring the operation behavior of the first user on each path according to the operation information.
In this embodiment, the target parameter includes operation information of the first user. And the device acquires the operation behavior of the first user on each path according to the operation information. The operation behaviors comprise operations of weighting, checking, sharing, paying attention and hanging lists. The device may configure corresponding behavior weights for different operational behaviors. In this regard, the apparatus determines, based on the operation information, an operation behavior of the first user on the financial product, and each attribute feature entered into the product has a corresponding operation behavior, so that the operation behavior of the attribute feature connected to the business topic is the operation behavior of the path where the attribute feature is located.
Step S309, determining a behavior weight corresponding to the path according to the type of the operation behavior corresponding to the path.
Each operational behavior may set a corresponding behavior weight, and thus, the apparatus may determine a behavior weight corresponding to the path based on the type of the operational behavior of the path.
Step S310, determining a third correction value corresponding to the business theme according to the sum of the behavior weights corresponding to each path of the business theme.
Step S311, according to the third correction value corresponding to the service theme, the initial recommendation score corresponding to the service theme is corrected to obtain the target recommendation score corresponding to the service theme.
The device obtains the behavior weights corresponding to each path of the business theme, so that the sum of the behavior weights of each path of the business theme is determined as a third correction value of the business theme, and the device corrects the initial recommendation score according to the third correction value to obtain a target recommendation score.
In this embodiment, the apparatus may correct the initial recommendation score by the first correction value, the second correction value, and the third correction value to obtain a target recommendation score, where the target recommendation score may be represented by the following formula:
where b is the behavior weight of the operational behavior of the path,
is the sum of the behavior weights of the various paths of the traffic topic.
In the technical scheme provided by this embodiment, the device obtains the operation behavior of the first user for each path based on the operation information of the user, determines the behavior weight corresponding to the path according to the type of the operation behavior corresponding to the path, determines a third correction value according to the sum of the behavior weights of each path of the service theme, and finally corrects the initial recommendation score accurately according to the third correction value of the service theme to obtain the target recommendation score of the service theme.
Referring to fig. 6, fig. 6 shows a fifth embodiment of the method for recommending financial products according to the present invention, wherein step S30 includes:
step S312, operation information of each second user is obtained, where the first user is any one of the second users.
In this embodiment, the target parameter includes operation information of the first user. The device needs to determine the correction value based on the heat of the business topic. Specifically, the device acquires operation information of each second user, where the second user is a user corresponding to all accounts stored in the device. The first user is any second user.
Step 313, determining the user operation times of each attribute feature corresponding to the service theme according to the operation information corresponding to each second user.
Step S314, determining the heat value of the business theme according to the user operation times of each attribute feature corresponding to the business theme.
The operation information is the operation information of the second user on the attribute characteristics of the second financial product, so the device can determine the user operation times of each attribute characteristic of each business theme according to the operation information of each second user. For example, it is determined that the financial product has been operated by 100 users according to each operation information, the number of user operations of the attribute feature corresponding to the financial product may also be 100, that is, the number of user operations of the attribute feature of the financial product connected by the service theme is also 100. The device can calculate the total user operation times of the business theme based on the user operation times of each attribute feature of the business theme, and can determine the heat value of the business theme through the total user operation times, wherein the heat value can be normalized, namely the value of the heat value is between 0 and 1.
Step S315, determining a fourth correction value corresponding to the business theme according to the heat value corresponding to the theme business, wherein the heat value and the fourth correction value are in positive correlation.
And step S316, correcting the initial recommendation score corresponding to the service theme according to the fourth correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
The device may determine a fourth correction value for the business topic based on the heat value, the greater the fourth correction value. And the device corrects the initial recommendation score corresponding to the service theme based on the fourth correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
In this embodiment, the apparatus may correct the target recommendation score obtained by correcting the initial recommendation score by the first correction value, the second correction value, the third correction value, and the fourth correction value, and the target recommendation score may be represented by the following formula:
W＝w0×ht
wherein h istI.e. a fourth correction value determined for the heat value.
The device may perform a combined operation based on the above mentioned second correction values and the first correction values to obtain target correction values, and then correct the initial recommended score by the target correction values to obtain a target recommended score. For example, the target recommendation score may be characterized by the following formula:
in the technical scheme provided by this embodiment, the device determines the heat value of the service theme according to the operation information of all users, so as to determine a fourth correction value of the service theme according to the heat value, and finally, the fourth correction value of the service theme accurately corrects the initial recommendation score to obtain a target recommendation score of the service theme.
In one embodiment, step S10 includes:
acquiring operation information of a first user, and determining each financial product purchased or browsed by the first user according to the operation information of the first user
Generating each business theme according to the attribute characteristics of each financial product, and determining the attribute characteristics matched with each business theme in each attribute characteristic;
respectively generating a business theme, an attribute characteristic and an icon corresponding to the financial product;
and connecting the icon corresponding to the attribute characteristic with the icon of the business theme matched with the attribute characteristic, and connecting the icon corresponding to the attribute characteristic with the icon of the financial product to which the attribute characteristic belongs to obtain the knowledge graph.
In this embodiment, the apparatus may generate a knowledge graph. Specifically, the device acquires operation information of the first user, and then determines the financial product purchased or browsed by the first user according to the operation information of the first user. The apparatus generates respective business topics from respective first financial products. The device then determines the attribute characteristics matched to each business topic. For example, referring to fig. 1, "robust profit" matches the "T +1 tie-out", "net value", "R2 risk", "R1 risk", "monetary type", "real-time tie-out" six attribute features.
The device respectively generates an icon of a business theme, an attribute feature and an icon of a financial product, then the icon corresponding to the attribute feature is connected with the icon of the business theme matched with the attribute feature, and the icon corresponding to the attribute feature is connected with the icon of the financial product to which the attribute feature belongs, so that a knowledge graph is obtained.
In the technical scheme provided by this embodiment, the apparatus can accurately generate the knowledge graph of the first user based on the operation information of the first user.
The present invention also provides a recommendation apparatus for financial products, and referring to fig. 7, the recommendation apparatus 700 for financial products includes:
the acquiring module 710 is configured to acquire a knowledge graph corresponding to a first user to be recommended, where the product knowledge graph includes a connection relationship between a plurality of business topics and financial products, each business topic is connected to one or more financial products, the business topics are connected to the financial products through common attribute features, and the financial products are financial products purchased or browsed by the first user;
a determining module 720, configured to determine, according to the knowledge graph, a target parameter corresponding to each business topic, where the target parameter includes at least one of a first number of attribute features, a second number of paths, and operation information of the first user, and the paths are connection paths of the financial product and the business topics;
a determining module 720, configured to determine, according to the initial recommendation score and the target parameter corresponding to each service topic, a target recommendation score corresponding to each service topic;
the determining module 720 is configured to determine a target business topic in each business topic according to the target recommendation score, and push product information of the financial product associated with the target business topic to a terminal associated with the first user, where the target recommendation score of the target business topic is greater than a preset score.
In one embodiment, the recommendation apparatus 700 for financial products includes:
a determining module 720 for determining a maximum number among the respective first numbers;
the determining module 720 is configured to determine a first correction value corresponding to each service topic according to the maximum number and a first number corresponding to each service topic, where the first number and the first correction value are in a positive correlation;
and the correction module is used for correcting the initial recommendation score corresponding to the service theme according to the first correction value corresponding to the service theme to obtain the target recommendation score corresponding to the service theme.
In one embodiment, the recommendation apparatus 700 for financial products includes:
a determining module 720, configured to determine, according to the second quantity corresponding to the service theme, a path weight of each path corresponding to the service theme, where the path weight and the second quantity are in a negative correlation relationship;
a determining module 720, configured to determine the length of each path, and determine a product between the length of the path and the path weight to obtain a numerical value corresponding to the path;
a determining module 720, configured to determine a second modification value corresponding to the service theme according to a sum of numerical values corresponding to each path corresponding to the service theme;
and the correction module is used for correcting the initial recommendation score corresponding to the service theme according to the second correction value corresponding to the service theme to obtain the target recommendation score corresponding to the service theme.
In one embodiment, the recommendation apparatus 700 for financial products includes:
an obtaining module 710, configured to obtain, according to the operation information, an operation behavior of the first user on each path;
a determining module 720, configured to determine, according to the type of the operation behavior corresponding to the path, a behavior weight corresponding to the path;
a determining module 720, configured to determine a third modification value corresponding to the business topic according to a sum of behavior weights corresponding to each path of the business topic;
and the correction module is used for correcting the initial recommendation score corresponding to the service theme according to the third correction value corresponding to the service theme to obtain the target recommendation score corresponding to the service theme.
In one embodiment, the recommendation apparatus 700 for financial products includes:
an obtaining module 710, configured to obtain operation information of each second user, where a first user is any one of the second users;
a determining module 720, configured to determine, according to the operation information corresponding to each second user, the number of user operations of each attribute feature corresponding to the service theme;
a determining module 720, configured to determine a heat value of the service theme according to the number of user operations of each attribute feature corresponding to the service theme;
the determining module 720 is configured to determine a fourth correction value corresponding to the service theme according to the heat value corresponding to the theme service, where the heat value and the fourth correction value are in a positive correlation;
and the correction module is used for correcting the initial recommendation score corresponding to the service theme according to the fourth correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
In one embodiment, the recommendation apparatus 700 for financial products includes:
an obtaining module 710, configured to obtain operation information of a first user, and determine, according to the operation information of the first user, each financial product purchased or browsed by the first user;
the generating module is used for generating each business theme according to the attribute characteristics of each financial product and determining the attribute characteristics matched with each business theme in each attribute characteristic;
the generating module is used for respectively generating a business theme, an attribute characteristic and an icon corresponding to the financial product;
and the connecting module is used for connecting the icon corresponding to the attribute characteristic with the icon of the business theme matched with the attribute characteristic, and connecting the icon corresponding to the attribute characteristic with the icon of the financial product to which the attribute characteristic belongs to obtain the knowledge graph.
Fig. 8 is a hardware configuration diagram illustrating a recommendation apparatus for a financial product according to an exemplary embodiment.
The recommendation device 800 for financial products may include: a process 801, such as a CPU, a memory 802, and a transceiver 803. Those skilled in the art will appreciate that the configuration shown in FIG. 8 does not constitute a limitation of the recommendation device for financial products and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components. The memory 802 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The processor 801 may call a computer program stored in the memory 802 to perform all or part of the steps of the above-described recommendation method for financial products.
The transceiver 803 is used for receiving and transmitting information from and to an external device.
A non-transitory computer readable storage medium, wherein instructions of the storage medium, when executed by a processor of a recommendation device for a financial product, enable the recommendation device for a financial product to perform the recommendation method for a financial product.
A computer program product comprising a computer program which, when executed by a processor of a recommendation device for a financial product, enables the recommendation device for a financial product to carry out the above-mentioned recommendation method for a financial product.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A method for recommending financial products, comprising:
acquiring a knowledge graph corresponding to a first user to be recommended, wherein the product knowledge graph comprises a plurality of connection relations between business topics and financial products, each business topic is connected with one or more financial products, the business topics are connected with the financial products through common attribute features, and the financial products are financial products purchased or browsed by the first user;
determining a target parameter corresponding to each business topic according to the knowledge graph, wherein the target parameter comprises at least one of a first number of attribute features, a second number of paths and operation information of a first user, and the paths are connection paths of the financial products and the business topics;
determining a target recommendation score corresponding to each service theme according to the initial recommendation score corresponding to each service theme and the target parameters;
and determining a target business theme in each business theme according to the target recommendation score, and pushing product information of the financial product associated with the target business theme to a terminal associated with the first user, wherein the target recommendation score of the target business theme is larger than a preset score.
2. The method of claim 1, wherein the objective parameters include the first quantity, and wherein the step of determining the objective recommendation score for each of the business topics based on the initial recommendation score for each of the business topics and the objective parameters includes:
determining a maximum number among the respective first numbers;
determining a first correction value corresponding to each business topic according to the maximum number and a first number corresponding to each business topic, wherein the first number and the first correction value are in a positive correlation;
and correcting the initial recommendation score corresponding to the service theme according to the first correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
3. The method of claim 1, wherein the objective parameters include the second quantity, and wherein the step of determining the objective recommendation score for each of the business topics based on the initial recommendation score for each of the business topics and the objective parameters includes:
determining the path weight of each path corresponding to the business theme according to the second quantity corresponding to the business theme, wherein the path weight and the second quantity are in a negative correlation relationship;
determining the length of each path, and determining the product of the length of the path and the path weight to obtain a numerical value corresponding to the path;
determining a second correction value corresponding to the business theme according to the sum of the numerical values corresponding to the paths corresponding to the business theme;
and correcting the initial recommendation score corresponding to the service theme according to the second correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
4. The method of claim 1, wherein the objective parameters include operation information of a first user, and the step of determining the objective recommendation score for each of the business topics according to the initial recommendation score for each of the business topics and the objective parameters includes:
acquiring the operation behavior of the first user on each path according to the operation information;
determining the behavior weight corresponding to the path according to the type of the operation behavior corresponding to the path;
determining a third correction value corresponding to the business theme according to the sum of the behavior weights corresponding to each path of the business theme;
and correcting the initial recommendation score corresponding to the service theme according to the third correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
5. The method of claim 1, wherein the objective parameters include operation information of a first user, and the step of determining the objective recommendation score for each of the business topics according to the initial recommendation score for each of the business topics and the objective parameters includes:
acquiring operation information of each second user, wherein the first user is any one of the second users;
determining the user operation times of each attribute feature corresponding to the service theme according to the operation information corresponding to each second user;
determining the heat value of the service theme according to the user operation times of each attribute feature corresponding to the service theme;
determining a fourth correction value corresponding to the service theme according to the heat value corresponding to the theme service, wherein the heat value and the fourth correction value are in a positive correlation;
and correcting the initial recommendation score corresponding to the service theme according to the fourth correction value corresponding to the service theme to obtain a target recommendation score corresponding to the service theme.
6. The method for recommending financial products according to any of claims 1-5, wherein said step of obtaining a knowledge-graph corresponding to the first user to be recommended comprises:
acquiring operation information of the first user, and determining each financial product purchased or browsed by the first user according to the operation information of the first user;
generating each business theme according to the attribute characteristics of each financial product, and determining the attribute characteristics matched with each business theme in each attribute characteristic;
generating the business theme, the attribute characteristics and the icons corresponding to the financial products respectively;
and connecting the icon corresponding to the attribute characteristic with the icon of the business theme matched with the attribute characteristic, and connecting the icon corresponding to the attribute characteristic with the icon of the financial product to which the attribute characteristic belongs to obtain the knowledge graph.
7. An apparatus for recommending financial products, comprising:
the system comprises an acquisition module, a recommendation module and a recommendation module, wherein the acquisition module is used for acquiring a knowledge graph corresponding to a first user to be recommended, the product knowledge graph comprises a connection relation between a plurality of business topics and financial products, each business topic is connected with one or more financial products, the business topics are connected with the financial products through common attribute features, and the financial products are financial products purchased or browsed by the first user;
a determining module, configured to determine, according to the knowledge graph, a target parameter corresponding to each business topic, where the target parameter includes at least one of a first number of attribute features, a second number of paths, and operation information of a first user, and the paths are connection paths between the financial product and the business topic;
the determining module is further configured to determine a target recommendation score corresponding to each service topic according to the initial recommendation score corresponding to each service topic and the target parameter;
the determining module is further configured to determine a target business topic in each business topic according to the target recommendation score, and push product information of a financial product associated with the target business topic to a terminal associated with the first user, where the target recommendation score of the target business topic is greater than a preset score.
8. An apparatus for recommending financial products, comprising: a memory and a processor;
the memory stores computer-executable instructions;
the processor executes the computer-executable instructions stored in the memory to cause the processor to perform the method of recommending financial products as claimed in any one of claims 1 to 6.
9. A computer-readable storage medium having stored therein computer-executable instructions for implementing the method of recommending financial products according to any one of claims 1 to 6 when executed by a processor.
10. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method of recommending financial products of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111572374.7A CN114417007A (en) | 2021-12-21 | 2021-12-21 | Recommendation method and related equipment for financial products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111572374.7A CN114417007A (en) | 2021-12-21 | 2021-12-21 | Recommendation method and related equipment for financial products |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114417007A true CN114417007A (en) | 2022-04-29 |
Family
ID=81266897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111572374.7A Pending CN114417007A (en) | 2021-12-21 | 2021-12-21 | Recommendation method and related equipment for financial products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114417007A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782150A (en) * | 2022-06-21 | 2022-07-22 | 北京梦幻天下科技有限公司 | Financial product recommendation method and system based on financial product directional screening |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033101A (en) * | 2017-06-08 | 2018-12-18 | 华为软件技术有限公司 | Label recommendation method and device |
| CN111966916A (en) * | 2020-06-20 | 2020-11-20 | 中国建设银行股份有限公司 | Recommendation method and device, electronic equipment and computer readable storage medium |
| US20210027146A1 (en) * | 2018-10-23 | 2021-01-28 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for determining interest of user for information item |
| KR20210040891A (en) * | 2020-06-22 | 2021-04-14 | 베이징 바이두 넷컴 사이언스 테크놀로지 컴퍼니 리미티드 | Method and Apparatus of Recommending Information, Electronic Device, Computer-Readable Recording Medium, and Computer Program |
| CN112767144A (en) * | 2021-03-18 | 2021-05-07 | 中国工商银行股份有限公司 | Bank financial marketing recommendation method and device |
| CN112927050A (en) * | 2021-03-26 | 2021-06-08 | 中国建设银行股份有限公司 | Method and device for determining financial product to be recommended, electronic equipment and storage medium |
| CN113139748A (en) * | 2021-05-12 | 2021-07-20 | 腾讯科技（深圳）有限公司 | Service information recommendation method and device, electronic equipment and storage medium |
-
2021
- 2021-12-21 CN CN202111572374.7A patent/CN114417007A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109033101A (en) * | 2017-06-08 | 2018-12-18 | 华为软件技术有限公司 | Label recommendation method and device |
| US20210027146A1 (en) * | 2018-10-23 | 2021-01-28 | Tencent Technology (Shenzhen) Company Limited | Method and apparatus for determining interest of user for information item |
| CN111966916A (en) * | 2020-06-20 | 2020-11-20 | 中国建设银行股份有限公司 | Recommendation method and device, electronic equipment and computer readable storage medium |
| KR20210040891A (en) * | 2020-06-22 | 2021-04-14 | 베이징 바이두 넷컴 사이언스 테크놀로지 컴퍼니 리미티드 | Method and Apparatus of Recommending Information, Electronic Device, Computer-Readable Recording Medium, and Computer Program |
| CN112767144A (en) * | 2021-03-18 | 2021-05-07 | 中国工商银行股份有限公司 | Bank financial marketing recommendation method and device |
| CN112927050A (en) * | 2021-03-26 | 2021-06-08 | 中国建设银行股份有限公司 | Method and device for determining financial product to be recommended, electronic equipment and storage medium |
| CN113139748A (en) * | 2021-05-12 | 2021-07-20 | 腾讯科技（深圳）有限公司 | Service information recommendation method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 韩慧: "基于知识图谱的商品推荐系统", 《信息通信》, no. 6, 15 June 2020 (2020-06-15), pages 200 - 201 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782150A (en) * | 2022-06-21 | 2022-07-22 | 北京梦幻天下科技有限公司 | Financial product recommendation method and system based on financial product directional screening |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8660925B2 (en) | Algorithmic trading system and method | |
| US20200090268A1 (en) | Method and apparatus for determining level of risk of user, and computer device | |
| US20020174056A1 (en) | System and method for providing user-specific options trading data | |
| CN110766541A (en) | Loan risk assessment method, loan risk assessment device, loan risk assessment equipment and computer-readable storage medium | |
| CN108460627A (en) | Marketing activity scheme method for pushing, device, computer equipment and storage medium | |
| CN104965844A (en) | Information processing method and apparatus | |
| CN109948882B (en) | Task processing method based on block data structure and related equipment | |
| CN110942393B (en) | Transaction processing method and device based on main account and sub account, and electronic equipment | |
| CN112101691B (en) | Dynamic risk level adjustment method, device and server | |
| CN114417007A (en) | Recommendation method and related equipment for financial products | |
| CN111369345A (en) | Big data credit user credit assessment method and system of cloud computing block chain | |
| CN109636581A (en) | Processing method and processing device, storage medium, the computer equipment of loan application information | |
| CN113191887A (en) | Abnormal account early warning method and device | |
| CN111445326A (en) | Loan amount assessment method and device | |
| CN111199453A (en) | Product information pushing method, electronic equipment and storage medium | |
| CN116362895A (en) | Financial product recommendation method, device and storage medium | |
| CN112884591A (en) | Investment suggestion method, device, equipment and storage medium for trading products | |
| CN113935827A (en) | Credit risk assessment method and device, storage medium and electronic equipment | |
| CN112182502A (en) | Compliance auditing method, device and equipment | |
| KR20170099321A (en) | Method for peer to peer secured loan finalcial technology service with condition matching and apparatus thereof | |
| KR20190032305A (en) | Lending Meditation Platform System and Credit Estimating Apparatus | |
| CN117873906B (en) | Method and device for testing prize amount distribution in transaction system | |
| CN116629975A (en) | Recommendation method, device, equipment and storage medium of financial products | |
| Chen et al. | Does the Prohibition of Trade-Through Hurt Liquidity Demanders? | |
| CN112116459B (en) | Data processing method and device based on lending |
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 |