CN104796478A - Resource recommending method and device - Google Patents

Abstract

An embodiment of the invention provides a resource recommending method and device, relates to the technical field of network, and solves the problem that user resource recommendation is low in precision due to untrusted behaviors of users. According to the scheme, on receiving a resource request, confidence degrees of all users in a resource sharing system and matching degrees of keywords of all resources to keywords carried in the resource request are acquired, recommendation values of all resources are acquired according to the confidence levels of the users that the resources belong to, respectively, and the matching degrees, the recommendation values are ranked according their magnitudes, front v of the recommendation values are selected according to a large to small sequence after ranking, and resources corresponding to the front v of the recommendation values are displayed. The resource recommending method and device is applicable to resource recommending.

Description

A kind of resource recommendation method and device

Technical field

The present invention relates to networking technology area, particularly relate to a kind of resource recommendation method and device.

Background technology

In resource sharing system, user provides resource by network, the resource that simultaneously also can be provided by other users of Network Capture.After user logs in, resource request can be sent according to the resource requirement of oneself to resource sharing system, and carry keyword in resource request, to be met the resource of user's request by resource sharing system search.Resource sharing system usually carries out sequence according to the matching degree of the keyword carried in the keyword of resource in resources bank and resource request and sequentially shows in the form of a list, thus the resource of recommendation is returned to user, selects for user.

In prior art, certain customers in order to promote oneself the download of resource and shared rate are provided, often by some with provide resource to have nothing to do popular keyword be appointed as the keyword of this resource to cheat other users, the insincere behavior of certain customers makes resource sharing system not mate with the resource request of user according to the resource of keyword recommendation, thus reduces the accuracy of resource recommendation.Such as, a certain user A has shared a film " a " in resource sharing system, and in order to promote download rate, the keyword " b " of silver screen hits " b " is instantly appointed as the keyword of this film by this user A.When other users want to watch this film " b " and carry out resource searching according to keyword " b ", resource sharing system provides this film assets " a " to be the resource high with the keyword match degree that carries in the resource request of user according to keyword " b " preferential recommendation user A, but this resource is actually and " b " the uncorrelated film of milli " a ", do not meet the resource requirement of other users, reduce the accuracy of resource recommendation.

Summary of the invention

The embodiment of the present invention provides a kind of resource recommendation method and device, the problem that the accuracy recommended of the user resources that the insincere behavior due to user that can solve causes is low.

For achieving the above object, embodiments of the invention adopt following technical scheme:

First aspect, provides a kind of resource recommendation method, comprising:

When receiving resource request, the confidence level that in Gains resources shared system, all users are corresponding respectively, and the matching degree obtaining the keyword carried in all resources keyword corresponding respectively and described resource request;

The keyword corresponding respectively according to described all resources confidence level that owning user is corresponding respectively and described all resources obtains described all resources with the matching degree of the keyword carried in described resource request and distinguishes corresponding recommendation;

Size according to described recommendation sorts to described recommendation, and v described recommendation before choosing according to order from big to small after sequence, and the resource that before display, v described recommendation is corresponding respectively.

In conjunction with first aspect, in the first mode in the cards of first aspect, for arbitrary user in described all users, the confidence level that described in Gains resources shared system, arbitrary user is corresponding comprises:

Determine whether the resource quantity in the resource collection of arbitrary user in described all users is 0;

If not 0, then obtain the confidence level of arbitrary resource in the resource collection of arbitrary user in described all users;

Then, the ratio of resource quantity in the value after the confidence level obtaining each resource in described resource collection adds up and described resource collection, described ratio is the confidence level that in described all users, arbitrary user is corresponding;

Or if 0, then the confidence level that in described all users, arbitrary user is corresponding is the first preset value;

Wherein, the confidence level that in described all users, arbitrary user is corresponding is expressed as:

$T\left(u\right)=\left\{\begin{array}{cc}\underset{r\∈R_u}{\mathrm{\Σ}}\frac{T(u,r)}{\left|R_u\right|},& \left|R_u\right|\≠0\\ q,& \left|R_u\right|\≠0\end{array}\right.;$

T (u) represents the confidence level that in described all users, arbitrary user is corresponding, and T (u, r) represents the confidence level of arbitrary resource in described resource collection, R _urepresent described resource collection, | R _u| represent the quantity of resource in described resource collection, q represents described first preset value.

In conjunction with the first mode in the cards of first aspect, in the second of first aspect mode in the cards, in the described all users of described acquisition arbitrary user resource collection in the confidence level of arbitrary resource comprise:

The quantity of the user of evaluation and the product of the first preset value is provided according to resource arbitrary in described resource collection, with the evaluation of estimate of each described user is added up after value and the second preset value product and, value after being added with described first preset value again, obtain the confidence level of arbitrary resource in described resource collection, wherein, the evaluation of estimate of described user be confidence level corresponding to described user and described user to the product of the evaluation indicated value that resource arbitrary in described resource collection provides, with the ratio of described user to the quantity of the evaluation that described all resources provide;

Wherein, in described all users arbitrary user resource collection in the confidence level of arbitrary resource be expressed as:

T(u,r)＝q+q*s+(1-q)∑ _{j＝1,2,...,s}T(u _j)*k _j/t _j；

T (u, r) represent the confidence level of arbitrary resource in described resource collection, q represents described first preset value, and s represents quantity resource arbitrary in described resource collection being provided to the user of evaluation, (1-q) described second preset value is represented, T (u _j) represent the confidence level that in s user of evaluation, a jth user is corresponding is provided to resource arbitrary in described resource collection, k _jrepresent the evaluation indicated value that a described jth user provides resource arbitrary in described resource collection, t _jrepresent the quantity of a described jth user to the evaluation that described all resources provide.

In conjunction with first aspect, in the third mode in the cards of first aspect, for arbitrary resource in described all resources, the matching degree of the keyword carried in the keyword of arbitrary resource described in Gains resources shared system and described resource request comprises:

Keyword corresponding for arbitrary resource in described all resources is carried out update after Hash operation in Bloom Filter, obtain the mark of arbitrary resource in described all resources, and the keyword carried in described resource request is carried out update after described Hash operation in described Bloom Filter, to obtain the mark of described resource request;

The Hamming distance obtaining the mark of arbitrary resource and the mark of described resource request in described all resources from;

Obtain the ratio of described Hamming distance from the length n with described Bloom Filter, the matching degree of the keyword carried in the keyword of arbitrary resource and described resource request in described all resources be 1 with the difference of described ratio;

Wherein, the matching degree of the keyword carried in the keyword of arbitrary resource and described resource request in described all resources is expressed as:

$S=1-\frac{L}{n};$

S represents the matching degree of the keyword carried in the keyword of arbitrary resource in described all resources and described resource request, L represent described Hamming distance from, n represents the length of described Bloom Filter.

In conjunction with first aspect to the third mode in the cards of first aspect, in the 4th kind of mode in the cards of first aspect, the recommendation that in described all resources, arbitrary resource is corresponding is expressed as:

M _i＝T(u _p)*S _i；

Wherein, M _irepresent the recommendation that in described all resources, arbitrary resource i is corresponding, T (u _p) represent the confidence level of arbitrary resource i owning user p in described all resources, S _irepresent the matching degree of the keyword carried in the keyword of arbitrary resource i in described all resources and described resource request.

Second aspect, provides a kind of control device, comprising:

Acquiring unit, for when receiving resource request, the confidence level that in Gains resources shared system, all users are corresponding respectively, and the matching degree obtaining the keyword carried in all resources keyword corresponding respectively and described resource request;

According to the matching degree of the keyword carried in the corresponding respectively keyword of described all resources confidence level that owning user is corresponding respectively and described all resources and described resource request, obtain the recommendation of described all resources correspondence respectively;

Control unit, sorts to described recommendation for the size according to described recommendation, and v described recommendation before choosing according to order from big to small after sequence, and the resource that before display, v described recommendation is corresponding respectively.

In conjunction with second aspect, in the first mode in the cards of second aspect, described acquiring unit specifically for:

Determine whether the resource quantity in the resource collection of arbitrary user in described all users is 0;

If not 0, then obtain the confidence level of arbitrary resource in the resource collection of arbitrary user in described all users;

Then, the ratio of resource quantity in the value after the confidence level obtaining each resource in described resource collection adds up and described resource collection, described ratio is the confidence level that in described all users, arbitrary user is corresponding;

Or if 0, then the confidence level that in described all users, arbitrary user is corresponding is the first preset value;

Wherein, the confidence level that in described all users, arbitrary user is corresponding is expressed as:

$T\left(u\right)=\left\{\begin{array}{cc}\underset{r\∈R_u}{\mathrm{\Σ}}\frac{T(u,r)}{\left|R_u\right|},& \left|R_u\right|\≠0\\ q,& \left|R_u\right|\≠0\end{array}\right.;$

T (u) represents the confidence level that in described all users, arbitrary user is corresponding, T (u, r) represents the confidence level of arbitrary resource in described resource collection, and Ru represents described resource collection, | Ru| represents the quantity of resource in described resource collection, and q represents described first preset value.

In conjunction with the first mode in the cards of second aspect, in the second of second aspect mode in the cards, described acquiring unit specifically for:

The quantity of the user of evaluation and the product of the first preset value is provided according to resource arbitrary in described resource collection, with the evaluation of estimate of each described user is added up after value and the second preset value product and, value after being added with described first preset value again, obtain the confidence level of arbitrary resource in described resource collection, wherein, the evaluation of estimate of described user be confidence level corresponding to described user and described user to the product of the evaluation indicated value that resource arbitrary in described resource collection provides, with the ratio of described user to the quantity of the evaluation that described all resources provide;

Wherein, in described all users arbitrary user resource collection in the confidence level of arbitrary resource be expressed as:

T(u,r)＝q+q*s+(1-q)∑ _{j＝1,2,...,s}T(u _j)*k _j/t _j；

T (u, r) represent the confidence level of arbitrary resource in described resource collection, q represents described first preset value, and s represents quantity resource arbitrary in described resource collection being provided to the user of evaluation, (1-q) described second preset value is represented, T (u _j) represent the confidence level that in s user of evaluation, a jth user is corresponding is provided to resource arbitrary in described resource collection, k _jrepresent the evaluation indicated value that a described jth user provides resource arbitrary in described resource collection, t _jrepresent the quantity of a described jth user to the evaluation that described all resources provide.

In conjunction with second aspect, in the third mode in the cards of second aspect, described acquiring unit specifically for:

Keyword corresponding for arbitrary resource in described all resources is carried out update after Hash operation in Bloom Filter, obtain the mark of arbitrary resource in described all resources, and the keyword carried in described resource request is carried out update after described Hash operation in described Bloom Filter, to obtain the mark of described resource request;

The Hamming distance obtaining the mark of arbitrary resource and the mark of described resource request in described all resources from;

Obtain the ratio of described Hamming distance from the length n with described Bloom Filter, the matching degree of the keyword carried in the keyword of arbitrary resource and described resource request in described all resources be 1 with the difference of described ratio;

Wherein, the matching degree of the keyword carried in the keyword of arbitrary resource and described resource request in described all resources is expressed as:

$S=1-\frac{L}{n};$

S represents the matching degree of the keyword carried in the keyword of arbitrary resource in described all resources and described resource request, L represent described Hamming distance from, n represents the length of described Bloom Filter.

In conjunction with second aspect to the third mode in the cards of second aspect, in the 4th kind of mode in the cards of second aspect, the recommendation that in described all resources, arbitrary resource is corresponding is expressed as:

M _i＝T(u _p)*S _i；

Wherein, M _irepresent the recommendation that in described all resources, arbitrary resource i is corresponding, T (u _p) represent the confidence level of arbitrary resource i owning user p in described all resources, S _irepresent the matching degree of the keyword carried in the keyword of arbitrary resource i in described all resources and described resource request.

The embodiment of the present invention provides a kind of resource recommendation method and device, when control device in resource sharing system receives resource request, the confidence level that in Gains resources shared system, user is corresponding, this confidence level can by the degree of other users to trust in order to characterize this user, and according to the matching degree calculated recommendation value of the keyword in the keyword of resource in the resource sharing system of confidence level corresponding to resource owning user and acquisition and resource request, thus recommend the large resource of recommendation for user priority, the matching degree of the keyword namely in corresponding with a high credibility of owning user and its keyword and resource request is high thus more meet the resource of user resources demand.Because resource sharing system can the preferential recommendation resource that more can be provided by the user of other users to trust, and the User reliability with insincere behavior is low, to be difficult to trust by other users, the resource that this user provides often do not meet yet other users resource requirement thus can not by preferential recommendation, thus can solve the problem that the accuracy of the resource recommendation caused due to the insincere behavior of user in prior art is low.

Accompanying drawing explanation

In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.

A kind of resource recommendation method schematic diagram that Fig. 1 provides for the embodiment of the present invention;

A kind of resource recommendation method schematic diagram that Fig. 2 provides for the embodiment of the present invention;

A kind of process schematic obtaining the confidence level of arbitrary resource that Fig. 3 provides for the embodiment of the present invention;

A kind of process schematic obtaining confidence level corresponding to arbitrary user that Fig. 4 provides for the embodiment of the present invention;

The structural representation of a kind of control device that Fig. 5 provides for the embodiment of the present invention.

Embodiment

Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.

See Fig. 1, the embodiment of the present invention provides a kind of resource recommendation method, and its key step can comprise:

101, control device is when receiving resource request, the confidence level that in Gains resources shared system, all users are corresponding respectively, and obtains the matching degree of the keyword carried in all resources keyword corresponding respectively and resource request.

Wherein, here control device can be the computer equipment being responsible for calculating and resource management in resource sharing system, confidence level corresponding to user can by the degree of other users to trust in order to characterizing consumer, and matching degree is in order to characterize the matching degree of the keyword carried in keyword and resource request that in resource sharing system, all resources are corresponding respectively.

102, control device is according to the matching degree of the keyword carried in the corresponding respectively keyword of all resources confidence level that owning user is corresponding respectively and all resources and resource request, obtains the recommendation of all resources correspondence respectively.

103, control device sorts to recommendation according to the size of recommendation, and v recommendation before choosing according to order from big to small after sequence, and the resource that before display, v recommendation is corresponding respectively.

Wherein, the corresponding respectively resource of a front v recommendation is the resource that resource sharing system is recommended, and the concrete numerical value of certain v can set as required, does not limit here.Wherein, what be specifically shown to user here can be the resource name recommending resource, mark (the such as resource number that this resource name can be able to identify with system, the memory location etc. of resource) be associated, recommend the page of resource so that user by selecting recommends resource name corresponding to resource to navigate to thus share this recommendation resource.

Alternatively, for user arbitrary in all users, the confidence level that in control device Gains resources shared system, arbitrary user is corresponding can comprise:

Control device determines whether the resource quantity in the resource collection of arbitrary user in all users is 0;

If not 0, then control device obtains the confidence level of arbitrary resource in the resource collection of arbitrary user in all users;

Then, in the set of control device Gains resources the confidence level of each resource add up after value and resource collection in the ratio of resource quantity, ratio is the confidence level that in all users, arbitrary user is corresponding;

Or if 0, then the confidence level that in all users of control device, arbitrary user is corresponding is the first preset value;

Wherein, the confidence level that in all users, arbitrary user is corresponding is expressed as:

$T\left(u\right)=\left\{\begin{array}{cc}\underset{r\∈R_u}{\mathrm{\Σ}}\frac{T(u,r)}{\left|R_u\right|},& \left|R_u\right|\≠0\\ q,& \left|R_u\right|\≠0\end{array}\right.;$

T (u) represents the confidence level that in all users, arbitrary user is corresponding, and T (u, r) represents the confidence level of arbitrary resource in resource collection, R _urepresent resource collection, | R _u| represent the quantity of resource in resource collection, q represents the first preset value.

Alternatively, the confidence level that control device obtains arbitrary resource in the resource collection of arbitrary user in all users can comprise:

Control device provides the quantity of the user of evaluation and the product of the first preset value according to resource arbitrary in resource collection, with the evaluation of estimate of each user is added up after value and the second preset value product and, value after being added with the first preset value again, the confidence level of arbitrary resource in Gains resources set, wherein, the evaluation of estimate of user be confidence level corresponding to user and user to the product of the evaluation indicated value that resource arbitrary in resource collection provides, with the ratio of user to the quantity of the evaluation that all resources provide;

Wherein, in all users arbitrary user resource collection in the confidence level of arbitrary resource be expressed as:

T(u,r)＝q+q*s+(1-q)∑ _{j＝1,2,...,s}T(u _j)*k _j/t _j；

T (u, r) represents the confidence level of arbitrary resource in resource collection, and q represents the first preset value, and s represents quantity resource arbitrary in resource collection being provided to the user of evaluation, and (1-q) represents the second preset value, T (u _j) represent the confidence level that in s user of evaluation, a jth user is corresponding is provided to resource arbitrary in resource collection, k _jrepresent the evaluation indicated value that a jth user provides resource arbitrary in resource collection, t _jrepresent that a jth user is to the quantity of the evaluation that all resources provide.

Alternatively, for resource arbitrary in all resources, the matching degree of the keyword carried in the keyword of arbitrary resource and resource request in control device Gains resources shared system can comprise:

Keyword corresponding for resource arbitrary in all resources is carried out update by control device after Hash operation in Bloom Filter, obtain the mark of arbitrary resource in all resources, and the keyword carried in resource request is carried out update after Hash operation in Bloom Filter, to obtain the mark of resource request;

The Hamming distance that control device obtains the mark of arbitrary resource and the mark of resource request in all resources from;

Control device obtains Hamming distance from the ratio of the length n with Bloom Filter, in all resources arbitrary resource keyword and resource request in the matching degree of keyword of carrying be the difference of 1 and ratio;

Wherein, the matching degree of the keyword carried in the keyword of arbitrary resource and resource request in all resources is expressed as:

$S=1-\frac{L}{n};$

S represents the matching degree of the keyword carried in the keyword of arbitrary resource in all resources and resource request, L represent Hamming distance from, n represents the length of Bloom Filter.

Alternatively, the recommendation that in all resources, arbitrary resource is corresponding can be expressed as:

M _i＝T(u _p)*S _i；

Wherein, M _irepresent the recommendation that in all resources, arbitrary resource i is corresponding, T (u _p) represent the confidence level of arbitrary resource i owning user p in all resources, S _irepresent the matching degree of the keyword carried in the keyword of arbitrary resource i in all resources and resource request.

The embodiment of the present invention provides a kind of resource recommendation method, when control device in resource sharing system receives resource request, the confidence level that in Gains resources shared system, user is corresponding, this confidence level can by the degree of other users to trust in order to characterize this user, and according to the matching degree calculated recommendation value of the keyword in the keyword of resource in the resource sharing system of confidence level corresponding to resource owning user and acquisition and resource request, thus recommend the large resource of recommendation for user priority, the matching degree of the keyword namely in corresponding with a high credibility of owning user and its keyword and resource request is high thus more meet the resource of user resources demand.Because resource sharing system can the preferential recommendation resource that more can be provided by the user of other users to trust, and the User reliability with insincere behavior is low, to be difficult to trust by other users, the resource that this user provides often do not meet yet other users resource requirement thus can not by preferential recommendation, thus can solve the problem that the accuracy of the resource recommendation caused due to the insincere behavior of user in prior art is low.

See Fig. 2, the embodiment of the present invention provides a kind of resource recommendation method, mainly can comprise the following steps:

201, for user arbitrary in all users, control device, when receiving resource request, is determined whether the resource quantity in the resource collection of arbitrary user in all users is 0, is then entered step 202 or step 204.

Here control device can be the computer being responsible for calculating and resource management in resource sharing system, and the resource collection of arbitrary resource owning user refers to the set of all resources that arbitrary resource owning user provides.User, when needs carry out resource searching, can send resource request according to the resource requirement of self to control device, and carry keyword in resource request, to search for the resource meeting own resource demand.

Control device is when receiving resource request, can by determining whether the resource quantity in the resource collection of arbitrary user in all users is 0, thus can obtain according to step 202,203 confidence level that in all users, arbitrary user is corresponding when resource quantity is not 0, or obtain according to step 204 confidence level that in all users, arbitrary user is corresponding when resource quantity is 0.Wherein, the confidence level that in all users, arbitrary user is corresponding can characterize this user can by the degree of other users to trust.

202, if not 0, then control device provides the quantity of the user of evaluation and the product of the first preset value according to arbitrary resource in the resource collection to user arbitrary in all users, with the evaluation of estimate of each user is added up after value and the second preset value product and, value after being added with the first preset value again, the confidence level of arbitrary resource in Gains resources set, wherein, the evaluation of estimate of user is that confidence level corresponding to user and user are to the product of the evaluation indicated value that resource arbitrary in resource collection provides, with the ratio of user to the quantity of the evaluation that all resources provide, then enter step 203.

Wherein, in all users arbitrary user resource collection in the confidence level of arbitrary resource can characterize this arbitrary resource can by the degree of other users to trust.The higher resource of quality more can trust by other users, wherein, the resource quality of arbitrary resource can comprise the accuracy that Resource Key describes, the influence power of list of references class resource, the many aspects such as video class resource resolution.Exemplary, if the keyword of this arbitrary resource conforms to the particular content of resource, then this arbitrary resource more can by other users to trust.If in all users of control device determination resource sharing system arbitrary user resource collection in resource quantity be not 0, then can obtain the confidence level of arbitrary resource in the resource collection of arbitrary user in all users according to formula 1.Wherein, formula 1 can be expressed as:

T(u,r)＝q+q*s+(1-q)∑ _{j＝1,2,...,s}T(u _j)*k _j/t _j；

In formula 1, T (u, r) represents the confidence level of arbitrary resource in resource collection, and q represents the first preset value, and s represents quantity resource arbitrary in resource collection being provided to the user of evaluation, and (1-q) represents the second preset value, T (u _j) represent the confidence level that in s user of evaluation, a jth user is corresponding is provided to resource arbitrary in resource collection, k _jrepresent the evaluation indicated value that a jth user provides resource arbitrary in resource collection, t _jrepresent that a jth user is to the quantity of the evaluation that all resources provide.Wherein, the process schematic obtaining the confidence level of arbitrary resource can see Fig. 3.

According to the formula 1 of the confidence level of arbitrary resource in the resource collection of arbitrary user in all users of acquisition, at least can the following aspects be known:

1, it is more obvious that the comment that the user that confidence level is higher provides promotes effect to the confidence level of this arbitrary resource, is presented as the T (uj) in formula 1;

2, more to the quantity of the evaluation that all resources provide users, its contribution degree evaluated for other User reliability will reduce, and can be presented as the T (u in formula 1 _j) * k _j/ t _j;

3, the user that the evaluation quantity obtained is more, its trust value can obtain lifting to a certain extent.Be presented as the q*s in formula 1;

4, the arbitrary resource not obtaining evaluating has acquiescence confidence level, is presented as the q in formula 1.

As from the foregoing, obtain in the embodiment of the present invention in the formula 1 of the confidence level of arbitrary resource in the resource collection of arbitrary user in all users and introduce confidence level corresponding to evaluation is provided to this arbitrary resource user, thus inventive embodiments considers the Different Effects produced when different user that confidence level there are differences is evaluated other users, calculate formula 1 that arbitrary resource confidence level adopts and algorithm more reasonable, thus make the confidence level calculating the arbitrary resource obtained more credible.

In addition, the q in formula 1 represents the acquiescence confidence level of the first weight and arbitrary resource, and its concrete numerical value can set as required, does not limit here.K in formula 1 _jrepresent the evaluation indicated value that a jth user provides resource arbitrary in resource collection, k _jthe difference of the evaluation type that can provide according to user j and different, other user can provide dissimilar evaluation according to the height of the quality of this arbitrary resource.For example, the evaluation type that a jth user provides can be commented for favorable comment or difference, corresponding k _jcan be 1 ,-1 respectively, exemplary, when user thinks that the keyword of this arbitrary resource conforms to particular content, or other reason is when making the quality of this arbitrary resource lower, favorable comment can be provided, when the insincere behavior of this arbitrary resource owning user is (such as using the keyword of current popular keyword as provided resource, and provide the content of resource and this popular keyword to have nothing to do) keyword of this arbitrary resource and particular content are not inconsistent, or other reason is when making the quality of this arbitrary resource lower, user can comment to going on business this arbitrary resource.Or, the evaluation type that a jth user provides also can for favorable comment, in comment or difference is commented, corresponding k _jcan be 1,0.5 ,-1 respectively, the embodiment of the present invention limit for the concrete size evaluating type and corresponding evaluation indicated value.

203, in the set of control device Gains resources the confidence level of each resource add up after value and resource collection in the ratio of resource quantity, ratio is the confidence level that in all users, arbitrary user is corresponding, then enters step 208.

After getting the confidence level of arbitrary resource in the resource collection of arbitrary user in step 202., the ratio of resource quantity in value after the confidence level that can obtain each resource in the resource collection of this arbitrary user according to formula 2 adds up and resource collection, this ratio is the confidence level that in all users, arbitrary user is corresponding.Wherein, formula 2 can be expressed as:

$T\left(u\right)=\underset{r\∈R_u}{\mathrm{\Σ}}\frac{T(u,r)}{\left|R_u\right|},\left|R_u\right|\≠0$

In formula 2, T (u) represents the confidence level that in all users, arbitrary user is corresponding, and T (u, r) represents the confidence level of arbitrary resource in resource collection, R _urepresent resource collection, | R _u| represent resource in resource collection quantity and | R _u| be not that 0, q represents the first preset value.

From formula 2, in the resource collection of arbitrary user, the quality of arbitrary resource is higher when making the confidence level of this arbitrary resource higher, in this arbitrary user resources set, the average of resource is higher, in the resource collection of i.e. this arbitrary user the confidence level of each resource add up after value and resource collection in the ratio of resource quantity comparatively large, confidence level corresponding to this arbitrary user is higher.And the keyword of the resource that the insincere behavior of working as this arbitrary user makes it provide and resource content are not inconsistent, or due to other reason cause the quality of this resource lower time, the resource provided in the resource collection of this arbitrary user with a low credibility, thus make corresponding with a low credibility of this arbitrary user.

If 204 0, then the confidence level that in all users, arbitrary user is corresponding is the first preset value, then enters step 208.

If in all users of control device determination resource sharing system arbitrary user resource collection in resource quantity be 0, then the confidence level that this arbitrary user is corresponding is the first preset value.In this step, the confidence level that in all users, arbitrary user is corresponding can be expressed as formula 3:

T (u)=q, wherein, T (u) represents the confidence level that in all users, arbitrary user is corresponding, R _urepresent resource collection, | R _u| represent resource in resource collection quantity and | R _u| be that 0, q represents the first preset value.

In equation 3, resource quantity is worked as | R _u| when being 0, the acquiescence confidence level of this arbitrary user is the first weight q.That is, if this arbitrary user does not provide any resource, then this user has acquiescence confidence level q.

In conjunction with formula 2 and formula 3, the confidence level that in all users, arbitrary user is corresponding can be expressed as formula 4:

$T\left(u\right)=\left\{\begin{array}{cc}\underset{r\∈R_u}{\mathrm{\Σ}}\frac{T(u,r)}{\left|R_u\right|},& \left|R_u\right|\≠0\\ q,& \left|R_u\right|\≠0\end{array}\right.;$

T (u) represents the confidence level that in all users, arbitrary user is corresponding, and T (u, r) represents the confidence level of arbitrary resource in resource collection, R _urepresent resource collection, | R _u| represent the quantity of resource in resource collection, q represents the first preset value.

Integrating step 201 to 204, the process schematic obtaining confidence level corresponding to arbitrary user can see Fig. 4.

In addition, control device is when receiving resource request, and the matching degree of the keyword that can also carry in all resources are corresponding respectively in Gains resources shared system keyword and resource request, specifically can see the description of following steps 205 to 207.

205, for resource arbitrary in all resources, keyword corresponding for resource arbitrary in all resources is carried out update by control device after Hash operation in Bloom Filter, obtain the mark of arbitrary resource in all resources, and the keyword carried in resource request is carried out update after Hash operation in Bloom Filter, to obtain the mark of resource request.

Wherein, the binary value that Hash operation obtains be one piece of data uniquely and extremely compact numeric representation form, keyword can be converted to binary Hash after Hash operation.The binary Hash of keyword corresponding for resource arbitrary in all resources is carried out update in Bloom Filter, the mark of arbitrary resource in all resources can be obtained.The binary Hash of the keyword carried in resource request is carried out update in Bloom Filter, the mark of resource request can be obtained.

Exemplary, if the keyword that in all resources, arbitrary resource is corresponding is the set K={k of c keyword ₁, k ₂..., k _i..., k _c, then: 1 keyword carries out the result F (k after update after Hash operation in Bloom Filter ₁) formula 5 can be expressed as:

F(k ₁)＝V ₀∪h{k ₁}＝<v ₀|d ₁₀,v ₁|d ₁₁,…,v _n-1|d _1(n-1)>；

I keyword carries out the result F (k after update after Hash operation in Bloom Filter _i) formula 6 can be expressed as:

F(k _i)＝V ₀∪h{k ₁}∪h{k ₂}∪…∪h{k _i}＝F(k _i-1)∪h{k _i}；

C keyword carries out the result F (k after update after Hash operation in Bloom Filter _c) formula 7 can be expressed as:

F(k _c)＝V ₀∪h{k ₁}∪h{k _i}∪…∪h{k _c}＝F(k _c-1)∪h{k _c}

Thus, the mark id of arbitrary resource can be expressed as formula:

id＝F(k _c)＝V ₀∪h{k ₁}∪h{k ₂}∪…∪h{k _c}

Wherein, V ₀represent the initial condition of Bloom Filter, the Binary Zero vector of to be length be n, v ₀..., v _n-1represent the binary number 0, h{k of in the Bloom Filter of initial condition the 0th to (n-1)th _irepresent the cryptographic Hash of keyword ki after Hash operation, the binary vector of to be length be n, <d _i0, d _i1..., d _{i (n-1)}, > represents keyword k _icryptographic Hash h{k _iin the binary numeral of the 0th to (n-1)th, " ∪ " represents the update defined in Bloom Filter, and " | " represents step-by-step or computing.

After an above-mentioned c keyword carries out c update, the length of Bloom Filter is still n, and now, this length is the mark that the binary vector of n is arbitrary resource in all resources obtained according to the keyword of resource arbitrary in all resources.

Wherein, similar with the process obtaining the mark of arbitrary resource according to the keyword of resource arbitrary in all resources according to the process of the mark of the resource request of the keyword acquisition of carrying in resource request, repeat no more here.

206, the control device Hamming distance that obtains the mark of arbitrary resource and the mark of resource request in all resources from.

After obtaining in all resources the mark of arbitrary resource and the mark of resource request in step 205 respectively, the Hamming distance that control device can obtain the mark of arbitrary resource and the mark of resource request in all resources respectively from.Wherein, mark and the resource request of arbitrary resource obtain after identifying and carrying out step-by-step or computing 1 quantity be corresponding Hamming distance from, namely Hamming distance is from the different figure place of the numerical value that can represent in two marks in identical bits, thus Hamming distance is from less, in two marks, isotopic number is not fewer, two marks are more similar, and this arbitrary resource more meets the resource requirement of user.

207, control device obtains Hamming distance from the ratio of the length n with Bloom Filter, in all resources arbitrary resource keyword and resource request in the matching degree of keyword of carrying be the difference of 1 and ratio.

Obtain Hamming distance in step 206 from rear, control device can obtain the ratio of Hamming distance from the length n of L and Bloom Filter, the matching degree of the keyword carried in the keyword of arbitrary resource and resource request in all resources be 1 with the difference of this ratio, namely matching degree can be expressed as formula 8:

$S=1-\frac{L}{n};$

Wherein, S represents the matching degree of the keyword carried in the keyword of arbitrary resource in all resources and resource request, L represent the Hamming distance of the mark of this arbitrary resource and the mark of resource request from, n represents the length of Bloom Filter.

From formula 8, the Hamming distance of the mark of arbitrary resource and the mark of resource request is from less, and namely in two marks, isotopic number is not fewer, then the ratio of L and n is less, value larger, the matching degree of the keyword namely carried in the keyword of this arbitrary resource and resource request is higher, and this arbitrary resource more meets the resource requirement of user.

It should be noted that, after carrying out the mark of arbitrary resource that bit arithmetic obtains n-dimensional vector form and the mark of resource request by Hash operation and Bloom Filter, obtain the matching degree of the keyword carried in the keyword of arbitrary resource and resource request again, its calculate magnitude be O (| R|) namely to | R| is directly proportional, wherein, | R| is the quantity of all resources in resource sharing system.And in prior art, if the set of keywords of the w carried in resource request keyword be combined into k1, k2 ..., kw}, in resource sharing system all resources resource collection R in arbitrary resource r _ithe set of keywords of f keyword be combined into { k _i1, k _i2..., k _f, calculate the quantity of keyword identical with the keyword carried in resource request in the set of keywords of arbitrary resource in all resources respectively, namely | k1, k2 ..., kw} ∩ k _i1, k _i2..., k _if| value, also namely obtain the matching degree of the keyword carried in the keyword of arbitrary resource in all resources and resource request respectively, wherein, the quantity of identical keyword is more, and matching degree is higher.Because the quantity of keyword in resource request different in prior art is different, in resource sharing system, the quantity of the keyword of different resource is also different, namely in resource request and resource sharing system, the quantity of the keyword of resource is dynamic change, thus prior art obtains the calculating magnitude of the process of matching degree is that O (m*|R|) is namely directly proportional to the value of m*|R|, wherein | R| represents the resource quantity of all resources in resource sharing system, and m represents the quantity of the keyword of dynamic change.Visible, compared with prior art, the account form that the embodiment of the present invention obtains the matching degree of the keyword carried in the keyword of arbitrary resource in all resources and resource request respectively reduces calculating magnitude, optimizes the matching way of resource recommendation.

Wherein, in the embodiment of the present invention, the concrete value of s, n, f, w is not limited.

208, control device is according to the matching degree of the keyword carried in the corresponding respectively keyword of all resources confidence level that owning user is corresponding respectively and all resources and resource request, obtains the recommendation of all resources correspondence respectively.

After step 203 or 204 obtain the confidence level that in all users, arbitrary user is corresponding, control device can according to the matching degree of the keyword of arbitrary resource in all resources obtained in confidence level corresponding to resource owning user arbitrary in all resources and step 207 with the keyword of resource request, obtains the recommendation of all resources correspondence respectively.Wherein, the recommendation that in all resources, arbitrary resource is corresponding can be expressed as formula 9:

M _i＝T(u _p)*S _i；

In formula 9, M _irepresent the recommendation that in all resources, arbitrary resource i is corresponding, T (u _p) represent the confidence level of arbitrary resource i owning user p in all resources, S _irepresent the matching degree of the keyword carried in the keyword of arbitrary resource i in all resources and resource request.

From formula 9, if the matching degree S of the keyword carried in the keyword of arbitrary resource i and resource request in all resources _ilarger, namely in all resources, arbitrary resource more meets the resource requirement of user, then the recommendation M that in all resources, arbitrary resource i is corresponding _ilarger; Meanwhile, in all resources, the confidence level of arbitrary resource i owning user p is higher, then the recommendation M that in all resources, arbitrary resource i is corresponding _ilarger.

209, control device sorts to recommendation according to the size of recommendation, and v recommendation before choosing according to order from big to small after sequence, and the resource that before display, v recommendation is corresponding respectively.

Control device after to recommendation sequence, chooses a front v recommendation according to order from big to small, and the resource of front v recommendation correspondence is respectively the resource of resource sharing system recommendation, and the resource of recommendation is shown to user, so that user selects.The concrete numerical value of certain v can set as required, does not limit here.Exemplary, what be specifically shown to user can be the resource name of the recommendation resource of tabular form or other form, mark (the such as resource number that this resource name can be able to identify with system, the memory location etc. of resource) be associated, recommend the page of resource so that user by selecting recommends resource name corresponding to resource to navigate to thus share this recommendation resource.

The confidence level corresponding due to arbitrary resource owning user is higher, and the matching degree of the keyword of its keyword and resource request is higher, the recommendation that then this resource is corresponding is larger, thus the resource that resource sharing system can recommend user with a high credibility to provide for user priority can be made, and in embodiments of the present invention, the higher resource of quality more can trust by other users, namely the confidence level of resource is higher, the confidence level that its owning user is corresponding is also higher, this resource is more easily by preferential recommendation, that is the resource that quality is higher is more easily by preferentially recommended, thus the confidence level of resource is introduced and confidence level corresponding to user can improve the resource quality recommending resource, and corresponding with a low credibility of the user with insincere behavior, to be difficult to trust by other users, the quality of the resource that this user provides is also often poor, does not meet the resource requirement of other users, thus can not by preferential recommendation.Meanwhile, resource sharing system can be made the keyword match degree height carried in its keyword and user resources request can be recommended namely more to meet the resource of user resources demand for user priority.

It should be noted that, in embodiments of the present invention, obtain the process of confidence level corresponding to all resources difference owning user (wherein, the process obtaining confidence level corresponding to arbitrary user is step 201-204), with obtain the keyword carried in the corresponding respectively keyword of all resources and resource request matching degree process (wherein, the process obtaining the matching degree of the keyword carried in keyword corresponding to arbitrary resource and resource request is step 205-207) there is no clear and definite precedence relationship, the embodiment of the present invention does not limit.

In addition, all resources confidence level that owning user is corresponding respectively and all resources are corresponding respectively in Gains resources shared system keyword in the embodiment of the present invention with the matching degree of keyword of carrying in resource request after, obtain all resources respectively correspondence recommendation thus carry out resource recommendation.Certainly, also can confidence level that first user is corresponding in Gains resources shared system, then corresponding to user confidence level sorts, then obtain the matching degree of the keyword carried in the keyword and resource request that in the resource collection of front g user with a high credibility, all resources are corresponding respectively, and then front v the resource choosing matching degree high carries out resource recommendation; Or, also the matching degree of the keyword carried in all resources keyword corresponding respectively and resource request can first be obtained, then obtain front x the resource confidence level that owning user is corresponding respectively that matching degree is high, and then front v the resource with a high credibility choosing owning user corresponding carries out resource recommendation, the embodiment of the present invention does not limit.Wherein, the value for g, x, v can set as required, does not limit here.

In addition, recommendation corresponding to arbitrary resource i also can calculate according to the matching degree of the keyword carried in the keyword of the confidence level of arbitrary resource i and arbitrary resource i and resource request, and the recommendation that such as arbitrary resource i is corresponding can be expressed as M _i=T (u, r _i) * S _i.Wherein, M _irepresent the recommendation that in all resources, arbitrary resource i is corresponding, T (u, r _i) represent the confidence level of arbitrary resource i, T (u, r _i) acquisition can be calculated according to the algorithm in step 201, S _irepresent the matching degree of the keyword carried in the keyword of arbitrary resource i in all resources and resource request, the present invention does not limit.

The embodiment of the present invention provides a kind of resource recommendation method, when control device in resource sharing system receives resource request, the confidence level that in Gains resources shared system, user is corresponding, this confidence level can by the degree of other users to trust in order to characterize this user, and according to the matching degree calculated recommendation value of the keyword in the keyword of resource in the resource sharing system of confidence level corresponding to resource owning user and acquisition and resource request, thus recommend the large resource of recommendation for user priority, the matching degree of the keyword namely in corresponding with a high credibility of owning user and its keyword and resource request is high thus more meet the resource of user resources demand.Because resource sharing system can the preferential recommendation resource that more can be provided by the user of other users to trust, and the User reliability with insincere behavior is low, to be difficult to trust by other users, the resource that this user provides often do not meet yet other users resource requirement thus can not by preferential recommendation, thus can solve the problem that the accuracy of the resource recommendation caused due to the insincere behavior of user in prior art is low.

See Fig. 5, the embodiment of the present invention provides a kind of control device 300, and this control device 300 can comprise:

Acquiring unit 301, may be used for when receiving resource request, the matching degree of the keyword carried in the corresponding respectively keyword of the confidence level that in Gains resources shared system, all users are corresponding respectively and all resources and resource request, obtains the recommendation of all resources correspondence respectively according to all resources confidence level that owning user is corresponding respectively and matching degree.

Control unit 302, may be used for sorting to all resources according to the size of recommendation, and v recommendation before choosing according to order from big to small after sequence, and the resource that before display, v recommendation is corresponding respectively.

Wherein, control device 300 can be the computer equipment being responsible for calculating and resource management in resource sharing system.

Alternatively, acquiring unit 301 can be specifically for:

Determine whether the resource quantity in the resource collection of arbitrary user in all users is 0;

If not 0, then obtain the confidence level of arbitrary resource in the resource collection of arbitrary user in all users;

Then, in Gains resources set the confidence level of each resource add up after value and resource collection in the ratio of resource quantity, ratio is the confidence level that in all users, arbitrary user is corresponding;

Or if 0, then the confidence level that in all users, arbitrary user is corresponding is the first preset value;

Wherein, the confidence level that in all users, arbitrary user is corresponding is expressed as:

$T\left(u\right)=\left\{\begin{array}{cc}\underset{r\&Element;R_u}{\mathrm{\&Sigma;}}\frac{T(u,r)}{\left|R_u\right|},& \left|R_u\right|\&NotEqual;0\\ q,& \left|R_u\right|\&NotEqual;0\end{array}\right.;$

T (u) represents the confidence level that in all users, arbitrary user is corresponding, and T (u, r) represents the confidence level of arbitrary resource in resource collection, R _urepresent resource collection, | R _u| represent the quantity of resource in resource collection, q represents the first preset value.

Alternatively, acquiring unit 301 can be specifically for:

The quantity of the user of evaluation and the product of the first preset value is provided according to resource arbitrary in resource collection, with the evaluation of estimate of each user is added up after value and the second preset value product and, value after being added with the first preset value again, the confidence level of arbitrary resource in Gains resources set, wherein, the evaluation of estimate of user be confidence level corresponding to user and user to the product of the evaluation indicated value that resource arbitrary in resource collection provides, with the ratio of user to the quantity of the evaluation that all resources provide;

Wherein, in all users arbitrary user resource collection in the confidence level of arbitrary resource be expressed as:

T(u,r)＝q+q*s+(1-q)∑ _{j＝1,2,...,s}T(u _j)*k _j/t _j；

T (u, r) represents the confidence level of arbitrary resource in resource collection, and q represents the first preset value, and s represents quantity resource arbitrary in resource collection being provided to the user of evaluation, and (1-q) represents the second preset value, T (u _j) represent the confidence level that in s user of evaluation, a jth user is corresponding is provided to resource arbitrary in resource collection, k _jrepresent the evaluation indicated value that a jth user provides resource arbitrary in resource collection, t _jrepresent that a jth user is to the quantity of the evaluation that all resources provide.

Alternatively, acquiring unit 301 can also be specifically for:

Keyword corresponding for resource arbitrary in all resources is carried out update after Hash operation in Bloom Filter, obtain the mark of arbitrary resource in all resources, and the keyword carried in resource request is carried out update after Hash operation in Bloom Filter, to obtain the mark of resource request;

The Hamming distance obtaining the mark of arbitrary resource and the mark of resource request in all resources from;

Obtain Hamming distance from the ratio of the length n with Bloom Filter, in all resources arbitrary resource keyword and resource request in the matching degree of keyword of carrying be the difference of 1 and ratio;

Wherein, the matching degree of the keyword carried in the keyword of arbitrary resource and resource request in all resources is expressed as:

$S=1-\frac{L}{n};$

S represents the matching degree of the keyword carried in the keyword of arbitrary resource in all resources and resource request, L represent Hamming distance from, n represents the length of Bloom Filter.

Alternatively, the recommendation that in all resources, arbitrary resource is corresponding is expressed as:

M _i＝T(u _p)*S _i；

Wherein, M _irepresent the recommendation that in all resources, arbitrary resource i is corresponding, T (u _p) represent the confidence level of arbitrary resource i owning user p in all resources, S _irepresent the matching degree of the keyword carried in the keyword of arbitrary resource i in all resources and resource request.

The embodiment of the present invention provides a kind of control device 300, when control device 300 in resource sharing system receives resource request, the confidence level that in Gains resources shared system, user is corresponding, this confidence level can by the degree of other users to trust in order to characterize this user, and according to the matching degree calculated recommendation value of the keyword in the keyword of resource in the resource sharing system of confidence level corresponding to resource owning user and acquisition and resource request, thus recommend the large resource of recommendation for user priority, the matching degree of the keyword namely in corresponding with a high credibility of owning user and its keyword and resource request is high thus more meet the resource of user resources demand.Because resource sharing system can the preferential recommendation resource that more can be provided by the user of other users to trust, and the User reliability with insincere behavior is low, to be difficult to trust by other users, the resource that this user provides often do not meet yet other users resource requirement thus can not by preferential recommendation, thus can solve the problem that the accuracy of the resource recommendation caused due to the insincere behavior of user in prior art is low.

In several embodiments that the application provides, should be understood that disclosed apparatus and method can realize by another way.Such as, apparatus embodiments described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, such as multiple unit or assembly can in conjunction with or another system can be integrated into, or some features can be ignored, or do not perform.Another point, shown or discussed coupling each other or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of device or unit or communication connection can be electrical, machinery or other form.

In addition, in the equipment in each embodiment of the present invention and system, each functional unit can be integrated in a processing unit, also can be that the independent physics of unit comprises, also can two or more unit in a unit integrated.And above-mentioned each unit both can adopt the form of hardware to realize, the form that hardware also can be adopted to add SFU software functional unit had realized.

The all or part of step realizing said method embodiment can have been come by the hardware that program command is relevant, and aforesaid program can be stored in a computer read/write memory medium, and this program, when performing, performs the step comprising said method embodiment; And aforesaid storage medium comprises: USB flash disk, portable hard drive, read-only memory (Read Only Memory, be called for short ROM), random access memory (Random Access Memory, be called for short RAM), magnetic disc or CD etc. various can be program code stored medium.

The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should described be as the criterion with the protection range of claim.

Claims (10)

1. a resource recommendation method, is characterized in that, comprising:

When receiving resource request, the confidence level that in Gains resources shared system, all users are corresponding respectively, and the matching degree obtaining the keyword carried in all resources keyword corresponding respectively and described resource request;

According to the matching degree of the keyword carried in the corresponding respectively keyword of described all resources confidence level that owning user is corresponding respectively and described all resources and described resource request, obtain the recommendation of described all resources correspondence respectively;

Size according to described recommendation sorts to described recommendation, and v described recommendation before choosing according to order from big to small after sequence, and the resource that before display, v described recommendation is corresponding respectively.

2. method according to claim 1, is characterized in that, for arbitrary user in described all users, the confidence level that described in Gains resources shared system, arbitrary user is corresponding comprises:

Determine whether the resource quantity in the resource collection of arbitrary user in described all users is 0;

If not 0, then obtain the confidence level of arbitrary resource in the resource collection of arbitrary user in described all users;

Then, the ratio of resource quantity in the value after the confidence level obtaining each resource in described resource collection adds up and described resource collection, described ratio is the confidence level that in described all users, arbitrary user is corresponding;

Or if 0, then the confidence level that in described all users, arbitrary user is corresponding is the first preset value;

Wherein, the confidence level that in described all users, arbitrary user is corresponding is expressed as:

$T\left(u\right)=\left\{\begin{array}{cc}\underset{r\&Element;R_u}{\mathrm{\&Sigma;}}\frac{T(u,r)}{\left|R_u\right|},& \left|R_u\right|\&NotEqual;0\\ q,& \left|R_u\right|\&NotEqual;0\end{array}\right.;$

T (u) represents the confidence level that in described all users, arbitrary user is corresponding, and T (u, r) represents the confidence level of arbitrary resource in described resource collection, R _urepresent described resource collection, | R _u| represent the quantity of resource in described resource collection, q represents described first preset value.

3. method according to claim 2, is characterized in that, in the described all users of described acquisition arbitrary user resource collection in the confidence level of arbitrary resource comprise:

The quantity of the user of evaluation and the product of the first preset value is provided according to resource arbitrary in described resource collection, with the evaluation of estimate of each described user is added up after value and the second preset value product and, value after being added with described first preset value again, obtain the confidence level of arbitrary resource in described resource collection, wherein, the evaluation of estimate of described user be confidence level corresponding to described user and described user to the product of the evaluation indicated value that resource arbitrary in described resource collection provides, with the ratio of described user to the quantity of the evaluation that described all resources provide;

Wherein, in described all users arbitrary user resource collection in the confidence level of arbitrary resource be expressed as:

T(u,r)＝q+q*s+(1-q)∑ _{j＝1,2,...,s}T(u _j)*k _j/t _j；

T (u, r) represent the confidence level of arbitrary resource in described resource collection, q represents described first preset value, and s represents quantity resource arbitrary in described resource collection being provided to the user of evaluation, (1-q) described second preset value is represented, T (u _j) represent the confidence level that in s user of evaluation, a jth user is corresponding is provided to resource arbitrary in described resource collection, k _jrepresent the evaluation indicated value that a described jth user provides resource arbitrary in described resource collection, t _jrepresent the quantity of a described jth user to the evaluation that described all resources provide.

4. method according to claim 1, is characterized in that, for arbitrary resource in described all resources, the matching degree of the keyword carried in the keyword of arbitrary resource described in Gains resources shared system and described resource request comprises:

Keyword corresponding for arbitrary resource in described all resources is carried out update after Hash operation in Bloom Filter, obtain the mark of arbitrary resource in described all resources, and the keyword carried in described resource request is carried out update after described Hash operation in described Bloom Filter, to obtain the mark of described resource request;

The Hamming distance obtaining the mark of arbitrary resource and the mark of described resource request in described all resources from;

Obtain the ratio of described Hamming distance from the length n with described Bloom Filter, the matching degree of the keyword carried in the keyword of arbitrary resource and described resource request in described all resources be 1 with the difference of described ratio;

Wherein, the matching degree of the keyword carried in the keyword of arbitrary resource and described resource request in described all resources is expressed as:

$S=1-\frac{L}{n};$

S represents the matching degree of the keyword carried in the keyword of arbitrary resource in described all resources and described resource request, L represent described Hamming distance from, n represents the length of described Bloom Filter.

5. the method according to any one of claim 1-4, is characterized in that, the recommendation that in described all resources, arbitrary resource is corresponding is expressed as:

M _i＝T(u _p)*S _i；

Wherein, M _irepresent the recommendation that in described all resources, arbitrary resource i is corresponding, T (u _p) represent the confidence level of arbitrary resource i owning user p in described all resources, S _irepresent the matching degree of the keyword carried in the keyword of arbitrary resource i in described all resources and described resource request.

6. a control device, is characterized in that, comprising:

Acquiring unit, for when receiving resource request, the confidence level that in Gains resources shared system, all users are corresponding respectively, and the matching degree obtaining the keyword carried in all resources keyword corresponding respectively and described resource request;

According to the matching degree of the keyword carried in the corresponding respectively keyword of described all resources confidence level that owning user is corresponding respectively and described all resources and described resource request, obtain the recommendation of described all resources correspondence respectively;

Control unit, sorts to described recommendation for the size according to described recommendation, and v described recommendation before choosing according to order from big to small after sequence, and the resource that before display, v described recommendation is corresponding respectively.

7. control device according to claim 6, is characterized in that, described acquiring unit specifically for:

Determine whether the resource quantity in the resource collection of arbitrary user in described all users is 0;

If not 0, then obtain the confidence level of arbitrary resource in the resource collection of arbitrary user in described all users;

Then, the ratio of resource quantity in the value after the confidence level obtaining each resource in described resource collection adds up and described resource collection, described ratio is the confidence level that in described all users, arbitrary user is corresponding;

Or if 0, then the confidence level that in described all users, arbitrary user is corresponding is the first preset value;

Wherein, the confidence level that in described all users, arbitrary user is corresponding is expressed as:

$T\left(u\right)=\left\{\begin{array}{cc}\underset{r\&Element;R_u}{\mathrm{\&Sigma;}}\frac{T(u,r)}{\left|R_u\right|},& \left|R_u\right|\&NotEqual;0\\ q,& \left|R_u\right|\&NotEqual;0\end{array}\right.;$

T (u) represents the confidence level that in described all users, arbitrary user is corresponding, and T (u, r) represents the confidence level of arbitrary resource in described resource collection, R _urepresent described resource collection, | R _u| represent the quantity of resource in described resource collection, q represents described first preset value.

8. control device according to claim 7, is characterized in that, described acquiring unit specifically for:

The quantity of the user of evaluation and the product of the first preset value is provided according to resource arbitrary in described resource collection, with the evaluation of estimate of each described user is added up after value and the second preset value product and, value after being added with described first preset value again, obtain the confidence level of arbitrary resource in described resource collection, wherein, the evaluation of estimate of described user be confidence level corresponding to described user and described user to the product of the evaluation indicated value that resource arbitrary in described resource collection provides, with the ratio of described user to the quantity of the evaluation that described all resources provide;

Wherein, in described all users arbitrary user resource collection in the confidence level of arbitrary resource be expressed as:

T(u,r)＝q+q*s+(1-q)∑ _{j＝1,2,...,s}T(u _j)*k _j/t _j；

T (u, r) represent the confidence level of arbitrary resource in described resource collection, q represents described first preset value, and s represents quantity resource arbitrary in described resource collection being provided to the user of evaluation, (1-q) described second preset value is represented, T (u _j) represent the confidence level that in s user of evaluation, a jth user is corresponding is provided to resource arbitrary in described resource collection, k _jrepresent the evaluation indicated value that a described jth user provides resource arbitrary in described resource collection, t _jrepresent the quantity of a described jth user to the evaluation that described all resources provide.

9. control device according to claim 6, is characterized in that, described acquiring unit specifically for:

Keyword corresponding for arbitrary resource in described all resources is carried out update after Hash operation in Bloom Filter, obtain the mark of arbitrary resource in described all resources, and the keyword carried in described resource request is carried out update after described Hash operation in described Bloom Filter, to obtain the mark of described resource request;

The Hamming distance obtaining the mark of arbitrary resource and the mark of described resource request in described all resources from;

Obtain the ratio of described Hamming distance from the length n with described Bloom Filter, the matching degree of the keyword carried in the keyword of arbitrary resource and described resource request in described all resources be 1 with the difference of described ratio;

Wherein, the matching degree of the keyword carried in the keyword of arbitrary resource and described resource request in described all resources is expressed as:

$S=1-\frac{L}{n};$

S represents the matching degree of the keyword carried in the keyword of arbitrary resource in described all resources and described resource request, L represent described Hamming distance from, n represents the length of described Bloom Filter.

10. the control device according to any one of claim 6-9, is characterized in that, the recommendation that in described all resources, arbitrary resource is corresponding is expressed as:

M _i＝T(u _p)*S _i；

Wherein, M _irepresent the recommendation that in described all resources, arbitrary resource i is corresponding, T (u _p) represent the confidence level of arbitrary resource i owning user p in described all resources, S _irepresent the matching degree of the keyword carried in the keyword of arbitrary resource i in described all resources and described resource request.