CN103425678B - The system of selection of the recommendation information of a kind of business object and device - Google Patents

Abstract

This application discloses system of selection and the device of the recommendation information of a kind of business object, including: represent desired value based on set each specified services object specifying user to issue on website of statistics in the time period, determine the comprehensive quality score value of each specified services object；And the size of the comprehensive quality score value according to each specified services object, select to meet the business object setting score value condition, as business object to be recommended from each specified services object；And the recommendation information by business object to be recommended, add in the recommendation unit of this appointment user, it is recommended that the recommendation information in unit is for issuing on website when satisfied setting issue condition.The scheme using the embodiment of the present application to provide, when carrying out the recommendation information issue of business object on website, decreases the consumption processing resource, improves resource utilization.

Description

The system of selection of the recommendation information of a kind of business object and device

Technical field

The application relates to Internet technical field, particularly relates to system of selection and the dress of the recommendation information of a kind of business object Put.

Background technology

In existing Internet technology, website typically can be issued the information of some business objects, for logging in this website User browse, and further for the post-treatment operations of specific transactions object.Such as, with e-commerce website it is Example, business object can be specifically the product that seller user issues, and the information of business object can be specifically the description letter of product Breath, the attribute information of product, and the purchase information etc. of product, the user that browses logging in e-commerce website can be by browsing The various information of release product, understand the details of this product, it is possible to further perform collection, buy or recommend it He users etc. process operation；As a example by community website, business object can be specifically the model that community users is issued, business object Information can be specifically the description information of model, the content information etc. of model, the browsing user and can lead to of website, login community Cross the various information of the model browsing issue, understand the details of this model, it is possible to further perform collection, money order receipt to be signed and returned to the sender or Recommend other users etc. and process operation.

At present, website provides the user of business object, browse its business issued to attract more to browse user The information of object, it will usually recommendation information is set for business object, better simply can be by straight for the description information of business object Connect as recommendation information, and by issuing the recommendation information of this business object on website, browse for browsing user, in order to attract Browse user and further browse the out of Memory of this business object.Such as, when business object is product, it is recommended that information i.e. phase When in advertising message.The issue application of the recommendation information of business object, applies more and more extensive in current internet site, Especially use in e-commerce website is the most universal.

But, owing to the resource-constrained that the recommendation information of business object is issued can be carried out on website, and user on website The quantity of the business object provided is relatively big, and the amount of the recommendation information that request is issued is the biggest, so cannot realize for each use The recommendation information of all business objects at family is all issued.

In order to solve this problem, it is achieved selectively recommendation information is issued, sending out for recommendation information in prior art Cloth is provided with recommendation issue condition, only sets issue condition when the recommendation information of a business object of a user meets Time, just the recommendation information of this business object of this user can be issued.

But, for providing the user of business object, owing to the recommendation information of its issuing service object needs to meet Certain issue condition, so, user needs the issue of the recommendation information of selectable requested part business object, i.e. needs pin To all business objects provided, carry out the management of recommendation information issue.At present, prior art is specifically entered in the following way Line pipe is managed:

User can select part or all of business object, as waiting to push away in its all business objects provided of principal and subordinate Recommend business object, and the recommendation information of the business object to be recommended by selection, join in the recommendation unit of self, it is recommended that unit In recommendation information for when satisfied setting issue condition, website is issued to browsing user.

For the ease of providing the user of business object that the recommendation information of business object is carried out above-mentioned management, at present, website Can all join in the recommendation unit of this user in advance by the recommendation information of all business objects of user, and business pair be provided The user of elephant is so that the recommendation information of business object of self, it is possible to as much as possible be distributed to website browse user, The generally recommendation unit of acquiescence self includes the recommendation information of substantial amounts of business object, thus cause Website server according to When setting issue condition selects recommendation information to issue, need more process resource, and, the most often appearance is issued Business object belonging to recommendation information itself is not browsed user's concern by substantial amounts of, thus causes cannot attracting to browse user to this The further browse operation of the out of Memory of business object, i.e. cannot obtain preferably recommendation effect so that be used for recommending The utilization rate of the resource that information is issued is relatively low.

Summary of the invention

In view of this, the embodiment of the present application provides system of selection and the device of the recommendation information of a kind of business object, is used for When solving the recommendation information issue carrying out business object in prior art on website, process resource consumption relatively big, and resource The problem that utilization rate is relatively low.

The embodiment of the present application is achieved through the following technical solutions:

The embodiment of the present application provides the system of selection of the recommendation information of a kind of business object, including:

Based on for set time period statistics specify each specified services object of issuing on website of user represent finger Scale value, determines the comprehensive quality score value of described each specified services object；

The size of the comprehensive quality score value according to described each specified services object, selects from described each specified services object Meet the business object setting score value condition, as business object to be recommended；

By the recommendation information of described business object to be recommended, add in the described recommendation unit specifying user, described recommendation Recommendation information in unit is for issuing on website when satisfied setting issue condition.

The embodiment of the present application additionally provides the selection device of the recommendation information of a kind of business object, including:

Score value determines module, for based on for each appointment specifying user to issue on website setting time period statistics Business object represent desired value, determine the comprehensive quality score value of described each specified services object；

Object choice module, for the size according to the comprehensive quality score value of described each specified services object, from described respectively Specified services object selects meet the business object setting score value condition, as business object to be recommended；

Add module, for by the recommendation information of described business object to be recommended, add the described recommendation list specifying user In unit, the recommendation information in described recommendation unit is for issuing on website when satisfied setting issue condition.

In at least one technical scheme above-mentioned that the embodiment of the present application provides, in the choosing of the recommendation information carrying out business object When selecting, be primarily based on the setting time period interior each specified services object specifying user to issue on website added up represents index Value, determines the comprehensive quality score value of each specified services object, and the size of the comprehensive quality score value according to each specified services object, Select to meet the business object setting score value condition, as business object to be recommended, and by the recommendation of this business object to be recommended Information, joins in the recommendation unit of this appointment user.Compared to existing technology, it is no longer all business objects by specifying user Recommendation information, all join in the recommendation unit of this appointment user, but selectively by the recommendation of partial service object Breath joins in recommendation unit, so decreasing process money required when the recommendation information including recommendation unit is issued Source；Further, due to the comprehensive quality score value of each specified services object, characterize after business object issues on website, by website Browse user pay close attention to degree, so, the business object to be recommended that size based on comprehensive quality score value is selected, is by net That stands browses the business object that user's degree of concern is higher, therefore, by the recommendation information of business object higher for the degree that is concerned Website is issued, more can obtain preferably recommendation effect, thus improve the resource carrying out recommendation information issue Utilization rate.

Other features and advantage will illustrate in the following description, and, partly become from description Obtain it is clear that or understand by implementing the application.The purpose of the application and other advantages can be by the explanations write Structure specifically noted in book, claims and accompanying drawing realizes and obtains.

Accompanying drawing explanation

Accompanying drawing is for providing further understanding of the present application, and constitutes a part for description, implements with the application Example is used for explaining the application together, is not intended that the restriction to the application.In the accompanying drawings:

The flow chart of the system of selection of the recommendation information of the business object that Fig. 1 provides for the embodiment of the present application；

The detail flowchart of the system of selection of the recommendation information of the business object that Fig. 2 provides for the embodiment of the present application；

In the system of selection of the recommendation information of the business object that Fig. 3 provides for the embodiment of the present application, information to be recommended is added Enter the detail flowchart in recommendation unit；

The structural representation selecting device of the recommendation information of the business object that Fig. 4 provides for the embodiment of the present application.

Detailed description of the invention

During in order to be given on website the recommendation information issue carrying out business object, minimizing processes the consumption of resource, and Improve resource utilization implementation, the embodiment of the present application provide the recommendation information of a kind of business object system of selection and Device, this technical scheme can apply to the recommendation information of business object provided for user, carries out issuing on website Process, both can be implemented as a kind of method, it is also possible to be embodied as a kind of device.Below in conjunction with excellent to the application of Figure of description Embodiment is selected to illustrate, it will be appreciated that preferred embodiment described herein is merely to illustrate and explains the application, and need not In limiting the application.And in the case of not conflicting, the embodiment in the application and the feature in embodiment can mutual groups Close.

The embodiment of the present application provides the system of selection of the recommendation information of a kind of business object, as it is shown in figure 1, include:

Step 101, based on setting each specified services object specifying user to issue on website of statistics in the time period Represent desired value, determine the comprehensive quality score value of each specified services object.

Step 102, size according to the comprehensive quality score value of each specified services object, select from each specified services object Meet the business object setting score value condition, as business object to be recommended.

Step 103, by the recommendation information of business object to be recommended, add in the recommendation unit of this appointment user, it is recommended that single Recommendation information in unit is for issuing on website when satisfied setting issue condition.

Further, in above-mentioned steps S101, when determining the comprehensive quality score value of each specified services object, it is also possible to The information quality value of description information based on each specified services object.

Further, in above-mentioned steps 103, it is also possible to specifically the recommendation unit this appointment user includes that multiple recommendation is single During unit, description information based on each recommendation unit respectively with the similarity of the description information of business object to be recommended, by be recommended The recommendation information of business object, joins in the recommendation unit that similarity is big, thus is more convenient for specifying user to business object Recommendation information more effectively manages, be more favorable to follow-up based on set issue condition inquire from each recommendation unit by Recommendation information to be issued, specifically may include that

Determine the description information of business object to be recommended respectively with the similarity score values of the description information of each recommendation unit；Its In, it is recommended that the description information of unit, specifically can be determined based on its recommendation information included；

By the recommendation information of business object to be recommended, join in the recommendation unit that the maximum similarity score values of value is corresponding.

Further, in the embodiment of the present application, when selecting business object to be recommended, can exist from this appointment user in advance In all business objects issued on website, determine that recommendation information does not joins the business pair in the recommendation unit of this appointment user As, as above-mentioned each specified services object such that it is able to reduce the quantity of the follow-up business object determining comprehensive quality score value, enter And reduce and determine the process resource needed for comprehensive quality score value；

But, when, from all business objects, determining in the recommendation unit that recommendation information does not joins this appointment user Process resource required for business object, more than when determining the process resource required for comprehensive quality score value, it is also possible to will be all Business object is as above-mentioned each specified services object, and after the determination completing comprehensive quality score value, from satisfied setting score value bar In the business object of part, then get rid of the business object in the recommendation unit joining this appointment user, and by remaining business Object is as business object to be recommended, and purpose is also for saving process resource required in whole handling process.

Further, it is considered to multiple business objects that user provides may be more similar, and by these similar multiple business The recommendation information of object is all issued, the recommendation of a business object in multiple business objects similar to only issuing this Breath, the recommendation effect reached is more or less the same, so, in the embodiment of the present application, it is also possible to when determining business object to be recommended, From the business object of satisfied setting score value condition, carry out duplicate removal process, will in higher two business objects of similarity degree, Remove the business object that comprehensive quality score value is low, and retain the business object that comprehensive quality score value is high, as business pair to be recommended As selecting recommendation information to issue in order to further saving is follow-up from recommendation unit based on setting issue condition Process resource, and improve resource utilization.

Below in conjunction with the accompanying drawings, the method and device provided the application with specific embodiment is described in detail.

The detail flowchart of the system of selection of the recommendation information of the business object that Fig. 2 provides for the embodiment of the present application, specifically Including processing step as follows:

Step 201, obtain the basic data set in the time period in the historical viewings record of website, the basic data of acquisition Can be used for the follow-up each specified services object added up for this setting time period and specify user to issue on the web site represents finger Scale value.

Such as, specifically can browse user use each search according to the search daily record of website in the setting time period, acquisition When key word scans for, the business object represented, the description information of the generally business object now represented；And represent Business object whether further performed clicking operation, and represent other details of this business object；And by point Whether the business object hit further is performed feedback operation, such as collection, recommends or the feedback operation such as purchase.

Browse record when non-search form can also be used to browse web sites according to browsing user, obtain above-mentioned basis number According to.

Wherein, the setting time period can be arranged the most flexibly, such as, be set to nearest one month.

Wherein, above-mentioned each specified services object can be all business objects that this appointment user issues on website, also Can be in all business objects, it is recommended that information does not currently join the business object in the recommendation unit of this appointment user.

Step 202, according to obtain above-mentioned basic data, add up this appointment user on website for this setting time period Issue each specified services object represent desired value.

Concrete, represent desired value and may include that and represent number of times, after representing, be further executed the number of times of clicking operation, And after clicking on, it is further executed the number of times of feedback operation.

Step 203 is it is also preferred that the left the information quality of the description information of each specified services object can also be determined in this step Value, this information quality value can content the level of detail of description information based on business object, represent form the most various, in this way No include picture, be determined.Various information quality value of the prior art specifically can be used to determine mode, no longer carry out at this Describe in detail.

This step is optional step, does not also have strict sequencing with above-mentioned steps S201 and step S202.

Step 204, each specified services issued on website based on this appointment user added up for this setting time period The above-mentioned of object represents desired value, determines the comprehensive quality score value of each specified services object.

Concrete, when determining comprehensive quality score value, it is also possible to reference to the description information of each specified services object determined Above-mentioned information quality value.Such as, represent desired value and above-mentioned information quality value is weighted summation to above-mentioned, obtain specifying industry The comprehensive quality score value of business object.

Step 205, size according to the comprehensive quality score value of each specified services object, select from each specified services object Meet the business object setting score value condition.

Concrete, set score value condition and specifically can use the following two kinds condition:

The first: set score value condition as comprehensive quality score value reach set point threshold, then this step particularly as follows: according to The size of the comprehensive quality score value of each specified services object, selects comprehensive quality score value to reach to set from each specified services object The business object of point threshold；

The second: set score value condition and set quantity, then before being positioned at according to comprehensive quality score value order from high to low This step, particularly as follows: the size of comprehensive quality score value according to each specified services object, selects to press from each specified services object Business object according to the front setting quantity of comprehensive quality score value order from high to low.

Step 206 is it is also preferred that the left working as each specified services object is all business objects that this appointment user issues on website Time, this step can also select recommendation information not join further from the business object of satisfied setting score value condition Business object in the recommendation unit of this appointment user.

Step 207, similarity degree according to the description information between currently selected business object, to currently selected Business object carry out duplicate removal process, be specifically as follows:

Between similarity degree is higher than two business objects of setting similarity degree threshold value, select comprehensive quality score value high Business object, and by selected business object final in this step, as business object to be recommended.

Wherein, the similarity degree of the description information between business object, various method of the prior art can be used true Fixed, no longer it is described in detail at this.

Step 208, by the recommendation information of selected business object to be recommended, join the recommendation unit of this appointment user In.

By above-mentioned steps 201-step 208, complete the recommendation information of the business object that the embodiment of the present application proposes System of selection, compared to existing technology, is no longer the recommendation information of all business objects by specifying user, all joins this appointment In the recommendation unit of user, but selectively the recommendation information of partial service object is joined in recommendation unit, so subtracting Lack process resource required when the recommendation information including recommendation unit is issued；Further, due to each specified services pair The comprehensive quality score value of elephant, characterizes after business object issues on website, is browsed the degree that user pays close attention to, institute by website With, the business object to be recommended that size based on comprehensive quality score value is selected, is to be browsed user's degree of concern relatively by website High business object, therefore, issues the recommendation information of business object higher for the degree that is concerned on website, more can Obtain preferably recommendation effect, thus improve the utilization rate of the resource carrying out recommendation information issue.

It is also preferred that the left when information to be recommended is joined in recommendation unit, if the recommendation unit of this appointment user includes During multiple recommendation unit, can description information based on each recommendation unit respectively with the phase of the description information of business object to be recommended Like property, by the recommendation information of business object to be recommended, join in the recommendation unit that similarity is big, thus be more convenient for specifying user The recommendation information of business object is more effectively managed, is more favorable to follow-up single from each recommendation based on setting issue condition Unit inquires the recommendation information that will issue, processes step as follows as it is shown on figure 3, specifically include:

Step 301, obtain this appointment user promote unit structural information, specifically may include that

Determine all popularization unit of currently-established this appointment user, and the recommendation that each popularization unit includes Information.

Step 302, determine the description information of each popularization unit of this appointment user, specifically can be based on this popularization unit The recommendation information included is determined, such as:

The all recommendation informations including this popularization unit carry out word segmentation processing, extract core word, and record the every of extraction The number of times that individual core word occurs in all recommendation informations.

Step 303, for selected business object each to be recommended, the description information of this business object to be recommended is entered Row word segmentation processing, extracts core word, and each core word recording extraction goes out in the description information of this business object to be recommended Existing number of times.

This step does not has strict sequencing with above-mentioned steps 301 and step 302.

Step 304, determine the description information of this business object to be recommended, respectively with each recommendation unit of this appointment user The similarity score values of description information.

Similarity score values specifically can use equation below to determine:

$\mathrm{SimScore}=\underset{i=1}{\overset{m}{\mathrm{\Σ}}}\underset{j=1}{\overset{n}{\mathrm{\Σ}}}(y_j\×x_i\×\mathrm{Sim}(w_{\mathrm{yj}},w_{\mathrm{xi}}));$

Wherein, SimScore is that the description information of this business object to be recommended is similar to the description information of this recommendation unit Property score value；w_xiFor the i-th core word extracted after the description information of this business object to be recommended is carried out word segmentation processing；M is right The quantity of the core word that the description information of this business object to be recommended is extracted after carrying out word segmentation processing；x_iFor to this business to be recommended The i-th core word that the description information of object is extracted after carrying out word segmentation processing, in the description information of this business object to be recommended The number of times occurred；w_yjThe jth core word that recommendation information for having included this recommendation unit extracts after carrying out word segmentation processing；n The quantity of the core word that the recommendation information for having included this recommendation unit extracts after carrying out word segmentation processing；y_jFor to this recommendation list The jth core word that the recommendation information that unit has included extracts after carrying out word segmentation processing, at the recommendation that this recommendation unit has included The number of times occurred in breath；Sim(w_yj,w_xi) it is core word w_xiWith core word w_yjSimilarity.

Wherein it is determined that the function Sim of core word and core word similarity, equation below specifically can be used:

$\mathrm{Sim}(w_1,w_2)=\left\{\begin{array}{c}S(w_1,w_2),S(w_1,w_2)\&GreaterEqual;\mathrm{threshold}\\ 0,S(w_1,w_2)<\mathrm{threshold}\end{array}\right.;$

Wherein, S (w₁,w₂) it is core word w₁With core word w₂Similarity scores, the similarity that threshold is default divides Number threshold value, function S can use various similarity scores of the prior art to determine function, no longer be described in detail at this.

Step 305, description information according to this business object to be recommended, respectively with the phase of the description information of each recommendation unit Like property score value, by the recommendation information of this business object to be recommended, join the recommendation unit that the maximum similarity score values of value is corresponding In.

The each similarity score values determined can also be compared by this step with setting similarity score values threshold value, and big from value In the recommendation unit corresponding to the similarity score values of similarity score values threshold value, select the recommendation unit added, when there is not value During more than the similarity score values of similarity score values threshold value, then it represents that the theme the most not phase of this object to be recommended and each recommendation unit Close, can cancel in the recommendation unit that the recommendation information of this object to be recommended is added this appointment user, it is also possible to set up new Recommendation unit, and the recommendation information of this object to be recommended is joined in this recommendation unit newly-established.

The each step in step 201-step 207 in step 301 in above-mentioned Fig. 3 and step 302, with above-mentioned Fig. 2 it Between, there is no strict sequencing.

The system of selection of the recommendation information of the above-mentioned business object provided by the embodiment of the present application, by treating that user provides After the recommendation information recommending business object joins in the recommendation unit of this user, i.e. can be according to setting issue condition, from respectively In the recommendation unit of user, select to meet the recommendation information setting issue condition, website is issued to browsing user.

Wherein, set issue condition to carry out flexibly based on the characteristic of the business object issued on website and recommendation information Arrange, such as, as a example by e-commerce website, website browse user use a certain key word to scan for time, will be from one The recommendation unit of a little users obtains the recommendation information being associated with this key word, and by the recommendation information of acquisition on website Position is specified to issue.

The said method that the embodiment of the present application provides, can be applicable on the website of various application feature, such as, with electronics business As a example by business website, business object can be specifically the product that seller user issues, and the information of business object can be specifically product Description information, the attribute information of product, and the purchase information etc. of product, it is recommended that information is i.e. equivalent to advertising message.

Based on same inventive concept, the selecting party of the recommendation information of the business object provided according to the above embodiments of the present application Method, correspondingly, another embodiment of the application additionally provides the selection device of the recommendation information of a kind of business object, its structural representation Figure as shown in Figure 4, specifically includes:

Score value determines module 401, for each based on issue on website for the appointment user setting time period statistics Specified services object represent desired value, determine the comprehensive quality score value of described each specified services object；

Object choice module 402, for the size of the comprehensive quality score value according to described each specified services object, from described Each specified services object selects meet the business object setting score value condition, as business object to be recommended；

Add module 403, for by the recommendation information of described business object to be recommended, add the described recommendation specifying user In unit, the recommendation information in described recommendation unit is for issuing on website when satisfied setting issue condition.

Further, score value determines module 401, specifically for based on setting in the time period appointment user of statistics in website Each specified services object of upper issue represent desired value, and the information quality of the description information of described each specified services object Value, determines the comprehensive quality score value of described each specified services object.

Further, add module 403, specifically for determining the description information of described business object to be recommended, respectively with The similarity score values of the description information of the described each recommendation unit specifying user；And by the recommendation of described business object to be recommended Breath, joins in the recommendation unit that the maximum similarity score values of value is corresponding.

Further, add module 403, specifically use equation below, determine the description information of business object to be recommended with The similarity score values of the description information of recommendation unit:

$\mathrm{SimScore}=\underset{i=1}{\overset{m}{\mathrm{\&Sigma;}}}\underset{j=1}{\overset{n}{\mathrm{\&Sigma;}}}(y_j\&times;x_i\&times;\mathrm{Sim}(w_{\mathrm{yj}},w_{\mathrm{xi}}));$

Wherein, SimScore is that the description information of this business object to be recommended is similar to the description information of this recommendation unit Property score value；w_xiFor the i-th core word extracted after the description information of this business object to be recommended is carried out word segmentation processing；M is right The quantity of the core word that the description information of this business object to be recommended is extracted after carrying out word segmentation processing；x_iFor to this business to be recommended The i-th core word that the description information of object is extracted after carrying out word segmentation processing, in the description information of this business object to be recommended The number of times occurred；w_yjThe jth core word that recommendation information for having included this recommendation unit extracts after carrying out word segmentation processing；n The quantity of the core word that the recommendation information for having included this recommendation unit extracts after carrying out word segmentation processing；y_jFor to this recommendation list The jth core word that the recommendation information that unit has included extracts after carrying out word segmentation processing, at the recommendation that this recommendation unit has included The number of times occurred in breath；Sim(w_yj,w_xi) it is core word w_xiWith core word w_yjSimilarity.

Further, also include:

Object determines module 404, specifically for determining the described institute specifying user to issue on website in the following way State each specified services object: and from the described all business objects specifying user to issue on website, determine that recommendation information is not Join the business object in the described recommendation unit specifying user, as described each specified services object.

Further, object choice module 402, specifically for from described each specified services object, select comprehensive quality Score value reaches to set point threshold, and recommendation information does not joins the business object in the described recommendation unit specifying user, As business object to be recommended；Or

From described each specified services object, select the front setting quantity according to comprehensive quality score value order from high to low , and recommendation information do not join described specify user recommendation unit in business object, as business object to be recommended.

Further, object choice module 402, specifically for the comprehensive quality score value according to described each specified services object Size, from described each specified services object select meet set score value condition business object；

According to the similarity degree of the description information between selected business object, from similarity degree higher than setting similar journey Between two business objects of degree threshold value, select the business object that comprehensive quality score value is high, as business object to be recommended.

The function of above-mentioned each module may correspond to the respective handling step in flow process shown in Fig. 1 to Fig. 3, the most superfluous at this State.

In sum, the scheme that the embodiment of the present application provides, including: exist based on the appointment user added up in setting the time period On website issue each specified services object represent desired value, determine the comprehensive quality score value of each specified services object；And root According to the size of the comprehensive quality score value of each specified services object, select to meet from each specified services object to set score value condition Business object, as business object to be recommended；And the recommendation information by business object to be recommended, add pushing away of this appointment user Recommend in unit, it is recommended that the recommendation information in unit is for issuing on website when satisfied setting issue condition.Use this The scheme that application embodiment provides, when carrying out the recommendation information issue of business object on website, decreases and processes disappearing of resource Consumption, improves resource utilization.

The selection device that embodiments herein is provided can be realized by computer program.Those skilled in the art should It is understood that above-mentioned Module Division mode is only the one in numerous Module Division mode, if be divided into other modules or Do not divide module, as long as selecting device to have above-mentioned functions, all should be within the protection domain of the application.

The application is with reference to method, equipment (system) and the flow process of computer program according to the embodiment of the present application Figure and/or block diagram describe.It should be understood that can the most first-class by computer program instructions flowchart and/or block diagram Flow process in journey and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided Instruction arrives the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce A raw machine so that the instruction performed by the processor of computer or other programmable data processing device is produced for real The device of the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame now.

These computer program instructions may be alternatively stored in and computer or other programmable data processing device can be guided with spy Determine in the computer-readable memory that mode works so that the instruction being stored in this computer-readable memory produces and includes referring to Make the manufacture of device, this command device realize at one flow process of flow chart or multiple flow process and/or one square frame of block diagram or The function specified in multiple square frames.

These computer program instructions also can be loaded in computer or other programmable data processing device so that at meter Perform sequence of operations step on calculation machine or other programmable devices to produce computer implemented process, thus at computer or The instruction performed on other programmable devices provides for realizing at one flow process of flow chart or multiple flow process and/or block diagram one The step of the function specified in individual square frame or multiple square frame.

Obviously, those skilled in the art can carry out various change and the modification essence without deviating from the application to the application God and scope.So, if these amendments of the application and modification belong to the scope of the application claim and equivalent technologies thereof Within, then the application is also intended to comprise these change and modification.

Claims (12)

1. the system of selection of the recommendation information of a business object, it is characterised in that including:

Based on for set time period statistics specify each specified services object of issuing on website of user represent desired value, Determine the comprehensive quality score value of described each specified services object；

The size of the comprehensive quality score value according to described each specified services object, selects to meet from described each specified services object Set the business object of score value condition, as business object to be recommended；

By the recommendation information of described business object to be recommended, add in the described recommendation unit specifying user, described recommendation unit In recommendation information for issuing on website when satisfied setting issue condition；

By the recommendation information of described business object to be recommended, add in the described recommendation unit specifying user, specifically include: determine The description information of described business object to be recommended, respectively with the similarity of description information of the described each recommendation unit specifying user Score value；By the recommendation information of described business object to be recommended, join in the recommendation unit that the maximum similarity score values of value is corresponding.

2. the method for claim 1, it is characterised in that based on the appointment user added up in setting the time period on website Issue each specified services object represent desired value, determine the comprehensive quality score value of described each specified services object, particularly as follows:

Desired value is represented based on set each specified services object specifying user to issue on website of statistics in the time period, with And the information quality value of the description information of described each specified services object, determine that the comprehensive quality of described each specified services object divides Value.

3. the method for claim 1, it is characterised in that specifically use equation below, determines business object to be recommended The similarity score values of the description information of description information and recommendation unit:

$SimScore=\underset{i=1}{\overset{m}{\&Sigma;}}\underset{j=1}{\overset{n}{\&Sigma;}}(y_j\&times;x_i\&times;Sim(w_{yj},w_{xi}\left)\right);$

Wherein, SimScore is that the description information of this business object to be recommended is divided with the similarity of the description information of this recommendation unit Value；w_xiFor the i-th core word extracted after the description information of this business object to be recommended is carried out word segmentation processing；M is for treat this The quantity of the core word that the description information recommending business object is extracted after carrying out word segmentation processing；x_iFor to this business object to be recommended Description information carry out the i-th core word that extracts after word segmentation processing, occur in the description information of this business object to be recommended Number of times；w_yjThe jth core word that recommendation information for having included this recommendation unit extracts after carrying out word segmentation processing；N is right The quantity of the core word that the recommendation information that this recommendation unit has included extracts after carrying out word segmentation processing；y_jFor to this recommendation unit Including recommendation information carry out the jth core word that extracts after word segmentation processing, in the recommendation information that this recommendation unit has been included The number of times occurred；Sim(w_yj,w_xi) it is core word w_xiWith core word w_yjSimilarity.

4. the method as described in claim 1-3 is arbitrary, it is characterised in that specifically determine described appointment user in the following way The described each specified services object issued on website:

From the described all business objects specifying user to issue on website, determine that recommendation information does not joins described appointment and uses Business object in the recommendation unit at family, as described each specified services object.

5. the method as described in claim 1-3 is arbitrary, it is characterised in that according to the comprehensive quality of described each specified services object The size of score value, selects to meet the business object setting score value condition, as industry to be recommended from described each specified services object Business object, specifically includes:

From described each specified services object, select comprehensive quality score value to reach to set point threshold, and recommendation information does not adds Enter the business object in the described recommendation unit specifying user, as business object to be recommended；Or

From described each specified services object, select front setting quantity according to comprehensive quality score value order from high to low, And recommendation information does not joins the business object in the described recommendation unit specifying user, as business object to be recommended.

6. the method as described in claim 1-3 is arbitrary, it is characterised in that according to the comprehensive quality of described each specified services object The size of score value, selects to meet the business object setting score value condition, as industry to be recommended from described each specified services object Business object, specifically includes:

The size of the comprehensive quality score value according to described each specified services object, selects to meet from described each specified services object Set the business object of score value condition；

According to the similarity degree of the description information between selected business object, from similarity degree higher than setting similarity degree threshold Between two business objects of value, select the business object that comprehensive quality score value is high, as business object to be recommended.

7. the selection device of the recommendation information of a business object, it is characterised in that including:

Score value determines module, for based on for each specified services specifying user to issue on website setting time period statistics Object represent desired value, determine the comprehensive quality score value of described each specified services object；

Object choice module, for the size of the comprehensive quality score value according to described each specified services object, from described each appointment Business object selects meet the business object setting score value condition, as business object to be recommended；

Add module, for by the recommendation information of described business object to be recommended, add in the described recommendation unit specifying user, Recommendation information in described recommendation unit is for issuing on website when satisfied setting issue condition；

Described addition module, specifically for determining the description information of described business object to be recommended, respectively with described appointment user The similarity score values of description information of each recommendation unit；And by the recommendation information of described business object to be recommended, join value In the recommendation unit that maximum similarity score values is corresponding.

8. device as claimed in claim 7, it is characterised in that described score value determines module, specifically for based on the time of setting In section statistics specify each specified services object of issuing on website of user represent desired value, and described each specified services The information quality value of the description information of object, determines the comprehensive quality score value of described each specified services object.

9. device as claimed in claim 7, it is characterised in that described addition module, specifically uses equation below, determines and wait to push away Recommend the similarity score values of the description information of business object and the description information of recommendation unit:

$SimScore=\underset{i=1}{\overset{m}{\&Sigma;}}\underset{j=1}{\overset{n}{\&Sigma;}}(y_j\&times;x_i\&times;Sim(w_{yj},w_{xi}\left)\right);$

Wherein, SimScore is that the description information of this business object to be recommended is divided with the similarity of the description information of this recommendation unit Value；w_xiFor the i-th core word extracted after the description information of this business object to be recommended is carried out word segmentation processing；M is for treat this The quantity of the core word that the description information recommending business object is extracted after carrying out word segmentation processing；x_iFor to this business object to be recommended Description information carry out the i-th core word that extracts after word segmentation processing, occur in the description information of this business object to be recommended Number of times；w_yjThe jth core word that recommendation information for having included this recommendation unit extracts after carrying out word segmentation processing；N is right The quantity of the core word that the recommendation information that this recommendation unit has included extracts after carrying out word segmentation processing；y_jFor to this recommendation unit Including recommendation information carry out the jth core word that extracts after word segmentation processing, in the recommendation information that this recommendation unit has been included The number of times occurred；Sim(w_yj,w_xi) it is core word w_xiWith core word w_yjSimilarity.

10. the device as described in claim 7-9 is arbitrary, it is characterised in that also include:

Object determines module, specifically for determining the described described each appointment specifying user to issue on website in the following way Business object: and from the described all business objects specifying user to issue on website, determine that recommendation information does not joins institute State the business object in the recommendation unit specifying user, as described each specified services object.

11. devices as described in claim 7-9 is arbitrary, it is characterised in that described object choice module, specifically for from described In each specified services object, select comprehensive quality score value to reach to set point threshold, and recommendation information does not joins described finger Determine the business object in the recommendation unit of user, as business object to be recommended；Or

From described each specified services object, select front setting quantity according to comprehensive quality score value order from high to low, And recommendation information does not joins the business object in the described recommendation unit specifying user, as business object to be recommended.

12. devices as described in claim 7-9 is arbitrary, it is characterised in that described object choice module, specifically for according to institute State the size of the comprehensive quality score value of each specified services object, select to meet setting score value bar from described each specified services object The business object of part；

According to the similarity degree of the description information between selected business object, from similarity degree higher than setting similarity degree threshold Between two business objects of value, select the business object that comprehensive quality score value is high, as business object to be recommended.