CN108415992A - Resource recommendation method, device and computer equipment - Google Patents
Resource recommendation method, device and computer equipment Download PDFInfo
- Publication number
- CN108415992A CN108415992A CN201810145643.3A CN201810145643A CN108415992A CN 108415992 A CN108415992 A CN 108415992A CN 201810145643 A CN201810145643 A CN 201810145643A CN 108415992 A CN108415992 A CN 108415992A
- Authority
- CN
- China
- Prior art keywords
- resource
- user
- recommended
- quality
- mentioned
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
A kind of resource recommendation method of the application proposition, device and computer equipment, above-mentioned resource recommendation method include：Obtain resource to be recommended；The user model of user is obtained, and determines user's classification belonging to the user；According to the matching degree of the user model and resource to be recommended, the correlation of the user and the resource to be recommended are determined；User's classification and the user and the correlation of the resource to be recommended belonging to the user recommend resource to the user.The application may be implemented to be directed to different types of user, carries out resource recommendation in different ways, improves the overall experience of user, under the premise of the resource and the correlation of user for ensureing to recommend, improve the quality of resource recommended to the user.
Description
Technical field
This application involves a kind of Internet technical field more particularly to resource recommendation method, device and computer equipments.
Background technology
It is existing in the related technology, atlas commending system is by three big portion of personalized queue, Collaborative Recommendation queue and Xin Re queues
It is grouped as.Wherein, personalized queue is point of interest completely according to user model and classification come the point of interest and classification with article
To be matched；Collaborative Recommendation queue is that the reading histories of similar users are recommended active user；New hot queue be then by
It is clicked on line and shows rate is high and timeliness is new atlas resource recommendation to all users.Only personalization for from the strict sense
Queue belongs to personalized recommendation, although Collaborative Recommendation queue and Xin Re queues are to dissipate interest as user to use, this two
Person has no bearing on personalization, and the expectation for the atlas and user that whole system recommends out can be caused to differ greatly.
In addition, existing atlas commending system does not control atlas quality, i.e., the resource that the system is recommended
Quality is unable to get guarantee.Since the source of new hot queue is to click to show the high resource of rate on line, and existing atlas pushes away
It recommends system not to be controlled the quality of atlas resource, so the atlas resource for recommending out by new hot queue is easy to go out
Existing low-quality resource, if current user is high-end user, it is clear that can be experienced for the content currently recommended bad.In addition,
Due to more or less may all carry some resources inferior in the reading histories of user, so being also easy in Collaborative Recommendation queue
Resource inferior is brought out, to influence user experience.
Invention content
The application is intended to solve at least some of the technical problems in related technologies.
For this purpose, first purpose of the application is to propose a kind of resource recommendation method, to realize for different types of
User carries out resource recommendation in different ways, improves the overall experience of user, in the phase for the resource and user for ensureing to recommend
Under the premise of closing property, the quality of resource recommended to the user is improved.
Second purpose of the application is to propose a kind of resource recommendation device.
The third purpose of the application is to propose a kind of computer equipment.
The 4th purpose of the application is to propose a kind of non-transitorycomputer readable storage medium.
In order to achieve the above object, the application first aspect embodiment proposes a kind of resource recommendation method, including：It obtains and waits pushing away
Recommend resource；The user model of user is obtained, and determines user's classification belonging to the user；According to the user model with wait pushing away
The matching degree for recommending resource determines the correlation of the user and the resource to be recommended；According to the user belonging to the user
Classification and the user and the correlation of the resource to be recommended recommend resource to the user.
In the resource recommendation method of the embodiment of the present application, after obtaining resource to be recommended, the user model of user is obtained, and
User's classification belonging to above-mentioned user is determined, and according to the matching degree of above-mentioned user model and resource to be recommended, in determination
State the correlation of user and above-mentioned resource to be recommended, then belonging to above-mentioned user user classification and above-mentioned user with it is above-mentioned
The correlation of resource to be recommended, recommends resource to above-mentioned user, different types of user is directed to so as to realize, using difference
Mode carry out resource recommendation, improve the overall experience of user, and can be in the resource and the correlation of user for ensureing to recommend
Under the premise of, improve the quality of resource recommended to the user.
In order to achieve the above object, the application second aspect embodiment proposes a kind of resource recommendation device, including：Obtain mould
Block, for obtaining resource to be recommended；And the user model of user is obtained, and determine user's classification belonging to the user；Really
Cover half block determines the user and the money to be recommended for the matching degree according to the user model and resource to be recommended
The correlation in source；Recommending module, the user's classification being used for belonging to the user and the user and the resource to be recommended
Correlation to the user recommend resource.
In the resource recommendation device of the embodiment of the present application, after acquisition module obtains resource to be recommended, the use of user is obtained
Family model, and determine user's classification belonging to above-mentioned user, determining module is according to of above-mentioned user model and resource to be recommended
With degree, the correlation of above-mentioned user and above-mentioned resource to be recommended are determined, then use of the recommending module belonging to above-mentioned user
Family is classified and the correlation of above-mentioned user and above-mentioned resource to be recommended, recommends resource to above-mentioned user, is directed to so as to realize
Different types of user carries out resource recommendation in different ways, improves the overall experience of user, and can ensure to recommend
Resource and user correlation under the premise of, improve the quality of resource recommended to the user.
In order to achieve the above object, the application third aspect embodiment proposes a kind of computer equipment, including memory, processor
And it is stored in the computer program that can be run on the memory and on the processor, the processor executes the calculating
When machine program, method as described above is realized.
To achieve the goals above, the application fourth aspect embodiment proposes a kind of computer-readable storage of non-transitory
Medium, is stored thereon with computer program, and the computer program realizes method as described above when being executed by processor.
The additional aspect of the application and advantage will be set forth in part in the description, and will partly become from the following description
It obtains obviously, or recognized by the practice of the application.
Description of the drawings
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, wherein：
Fig. 1 is the flow chart of the application resource recommendation method one embodiment；
Fig. 2 is the flow chart of another embodiment of the application resource recommendation method；
Fig. 3 is the flow chart of the application resource recommendation method further embodiment；
Fig. 4 is the flow chart of the application resource recommendation method further embodiment；
Fig. 5 is the flow chart of the application resource recommendation method further embodiment；
Fig. 6 is the structural schematic diagram of the application resource recommendation device one embodiment；
Fig. 7 is the structural schematic diagram of another embodiment of the application resource recommendation device；
Fig. 8 is the structural schematic diagram of the application computer equipment one embodiment.
Specific implementation mode
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and should not be understood as the limitation to the application.
It is analyzed from user behavior, either which type of user, will not all generate repulsion to interested resource, and it is right
In correlation is less strong or even incoherent resource, as long as high-quality, user can also tolerate.It is not fine for quality
Resource, system can also be recommended to the interested user of this kind of resource, but need to prevent by such resource spread to
Other users.Therefore, it sees on the whole, high-quality resource can recommend all users, and resource relatively inferior then needs root
User is recommended according to the correlation of user's classification and resource and user.
Fig. 1 is the flow chart of the application resource recommendation method one embodiment, as shown in Figure 1, above-mentioned resource recommendation method
May include：
Step 101, resource to be recommended is obtained.
Specifically, server can obtain resource to be recommended after receiving the operation requests that user sends.Aforesaid operations
Request can be drop-down page operation of the above-mentioned user in browsing pages, or the click page operation of above-mentioned user,
Or the long-press page operation of above-mentioned user, the operation requests that the present embodiment sends above-mentioned user are not construed as limiting, as long as above-mentioned
Operation requests can be used for request server and recommend resource to above-mentioned user.
Wherein, obtaining resource to be recommended can be：By personalized queue, Collaborative Recommendation queue and Xin Re queues, to money
Resource in the library of source is screened, and resource to be recommended is obtained.
Step 102, the user model of user is obtained, and determines user's classification belonging to above-mentioned user.
Wherein, the user model for obtaining user determines that the classification of the user belonging to above-mentioned user can be：According to above-mentioned user
User model, determine that above-mentioned user belongs to high-end user or ordinary user.In the present embodiment, high-end user includes to pushing away
The higher user of quality and correlation requirement for the resource recommended, ordinary user includes will not be special to the quality requirement of the resource of recommendation
It is not high, there is certain tolerance to the lower resource of quality, often more focus on the relevant user of interest.
In specific implementation, can according to the user model of above-mentioned user, in conjunction with above-mentioned user historical behavior (such as：
The historical viewings of above-mentioned user and click behavior) determine that the user belonging to above-mentioned user classifies.
Step 103, according to the matching degree of above-mentioned user model and resource to be recommended, determine that above-mentioned user waits pushing away with above-mentioned
Recommend the correlation of resource.
Step 104, the correlation of the user classification and above-mentioned user and above-mentioned resource to be recommended belonging to above-mentioned user,
Recommend resource to above-mentioned user.
In the present embodiment, resource to be recommended may include picture resource, textual resources and/or voice resource, the present embodiment
The concrete form of above-mentioned resource to be recommended is not construed as limiting.
In above-mentioned resource recommendation method, after obtaining resource to be recommended, the user model of user is obtained, and determine above-mentioned use
User's classification belonging to family, and according to the matching degree of above-mentioned user model and resource to be recommended, determine above-mentioned user with it is upper
The correlation of resource to be recommended is stated, then user's classification belonging to above-mentioned user and above-mentioned user and above-mentioned resource to be recommended
Correlation, to above-mentioned user recommend resource, so as to realize be directed to different types of user, carry out in different ways
Resource recommendation improves the overall experience of user, and can be improved under the premise of the resource and the correlation of user for ensureing to recommend
The quality of resource recommended to the user.
Fig. 2 is the flow chart of another embodiment of the application resource recommendation method, as shown in Fig. 2, real shown in the application Fig. 1
It applies in example, step 103 may include：
Step 201, the point of interest for obtaining above-mentioned resource to be recommended and/or the classification belonging to above-mentioned resource to be recommended.
Step 202, if the interest points matching of the point of interest and above-mentioned user model of above-mentioned resource to be recommended, and/or on
State the classification belonging to resource to be recommended and the interest classification and matching of above-mentioned user model, it is determined that above-mentioned user with it is above-mentioned to be recommended
Resource is related；If the point of interest of the point of interest of above-mentioned resource to be recommended and above-mentioned user model mismatches, and above-mentioned waits pushing away
It recommends classification and the interest classification of above-mentioned user model belonging to resource to mismatch, it is determined that above-mentioned user and above-mentioned resource to be recommended
It is uncorrelated.
Specifically, in the present embodiment, according to the power of degree of correlation, correlation can be divided into strong correlation to it is weak related：
1) strong correlation：When the interest points matching of the point of interest and above-mentioned user model of resource to be recommended, and it is matched emerging
Interest point is when clicking to show rate height and have the point of interest of enough confidence levels in above-mentioned user model, to determine above-mentioned resource to be recommended
With above-mentioned user there is strong correlation, this matched point of interest to be properly termed as strong point of interest.When the strong interest matched
Point is more, it is believed that the resource to be recommended and the correlation of user are stronger.
2) weak correlation：When the point of interest of resource to be recommended and the interest points matching of above-mentioned user model or above-mentioned wait pushing away
The interest classification and matching of the classification and above-mentioned user model belonging to resource is recommended, but matched point of interest is in above-mentioned user model
When the confidence level that click shows rate not and be especially high or matched point of interest is not especially high, it is believed that matched point of interest is
The weak point of interest of user determines that the resource to be recommended has weak dependence with user in this case.
Fig. 3 is the flow chart of the application resource recommendation method further embodiment, as shown in figure 3, real shown in the application Fig. 1
It applies in example, step 104 may include：
Step 301, the quality of resource to be recommended is determined.
Step 302, it when above-mentioned user belongs to high-end user, is searched in above-mentioned resource to be recommended related to above-mentioned user
And quality is higher than the resource of predetermined threshold, after the resource found is carried out fusion sequence, recommends above-mentioned user.
Wherein, above-mentioned predetermined threshold can in specific implementation according to the sets itselfs such as system performance and/or realization demand,
The present embodiment is not construed as limiting the size of above-mentioned predetermined threshold.
Specifically, requirement of the high-end user to resource quality is very high, therefore for the recommendation of this kind of user, not only to ensure
The resource of recommendation and the correlation of high-end user, will also ensure the quality of resource, for high-end user, need to excavate with it is upper
It states user's correlation and quality is recommended higher than the resource of predetermined threshold.
When specific implementation, for high-end user, related and quality is searched in above-mentioned resource to be recommended to above-mentioned user
After the resource of predetermined threshold, to the resource found carry out fusion sequence when, can improve in the resource found with
The weight of the resource of above-mentioned user's strong correlation, to ensure that the resource for being higher than predetermined threshold with high-end user strong correlation and quality can
Preferentially to show.
Fig. 4 is the flow chart of the application resource recommendation method further embodiment, as shown in figure 4, real shown in the application Fig. 1
It applies in example, step 104 may include：
Step 401, the quality of resource to be recommended is determined.
Step 402, it when above-mentioned user belongs to ordinary user, is searched in above-mentioned resource to be recommended related to above-mentioned user
Resource, and in above-mentioned resource to be recommended search to the user uncorrelated but quality higher than predetermined threshold resource.
Step 403, fusion sequence is carried out to the resource found, when carrying out fusion sequence to the resource found, carried
Weight of the and quality related to above-mentioned user higher than the resource of predetermined threshold in the high above-mentioned resource found.
In the present embodiment, ordinary user generally will not be especially high to the quality requirement of the resource of recommendation, often more focuses on emerging
It is interesting related, therefore to the recommendation of this kind of user, it should determine the way of recommendation according to the degree of correlation of user and resource to be recommended.When
When judging that resource to be recommended and user have correlation, user generally can be interested in click, as long as being not belonging to illegal interior
Hold, can be used as recommended candidate collection, can be suitably weighted when this resource to be recommended belongs to high-quality resource to ensure preferential exhibition
It is existing；And when there is content incoherent with user, then the quality for ensureing resource to be recommended is needed, makes user will not be to the resource
Dislike is generated, so as to more objectively carry out interest digging and diffusion to user to the behavior of such resource by user.
In specific implementation, when carrying out fusion sequence to the resource found, the above-mentioned resource found can be improved
In and quality related to above-mentioned user higher than predetermined threshold resource weight, it is possible to further be arranged and above-mentioned user
Strong correlation and quality are higher than the weight of the resource of predetermined threshold, are more than the weak related and quality to above-mentioned user and are higher than predetermined threshold
The weight of the resource of value, to ensure preferentially to show the resource for being higher than predetermined threshold with above-mentioned user's strong correlation and quality.
Step 404, the resource recommendation after sequence is given to above-mentioned user.
In the application Fig. 3 and embodiment illustrated in fig. 4, determine that the quality of resource to be recommended can be：According to above-mentioned to be recommended
The vulgar degree of the mass fraction of resource itself, the plagiarism degree of above-mentioned resource to be recommended and/or above-mentioned resource to be recommended determines
The quality of above-mentioned resource to be recommended.
Specifically, according to the mass fraction of above-mentioned resource to be recommended itself, above-mentioned resource to be recommended plagiarism degree and/or
The vulgar degree of above-mentioned resource to be recommended determines that the quality of above-mentioned resource to be recommended can be：When above-mentioned resource to be recommended itself
Mass fraction be less than second threshold higher than the score of first threshold, the plagiarisms degree of above-mentioned resource to be recommended and/or above-mentioned wait for
When the score of the vulgar degree of resource being recommended to be less than third threshold value, determine that the quality of above-mentioned resource to be recommended is higher than predetermined threshold.
Wherein, the size of above-mentioned first threshold, second threshold and third threshold value can be in specific implementation according to systematicness
Sets itselfs, the present embodiment such as energy and/or realization demand do not make the size of above-mentioned first threshold, second threshold and third threshold value
It limits.
In the present embodiment, the judgement for resource quality to be recommended can be carried out from following several dimensions：
A) mass fraction of resource itself：Resource can pass through an audit marking mechanism on the data streams, obtain a phase
The mass fraction answered, score is higher to indicate that the quality of resource is better, this is the fundamental prerequisite for identifying resource quality, once it is discontented
The score of sufficient resource is less than passing score, which can be filtered；
B) the plagiarism degree of resource：The plagiarism degree of resource can be judged on the data streams, and score is lower to represent its plagiarism journey
Degree is lower, i.e., resource is more novel；
C) the vulgar degree of resource：The vulgar degree of resource can be judged on the data streams, and the higher expression resource of score is more
Vulgar, the resource can be filtered when higher than some threshold value.
Due to having strobe utility in data flow, so being in contrast resource inferior for the inferior and high-quality of resource
It is not meant to be underproof resource, these resources should not be abandoned, otherwise be easy to cause waste.For high-quality money
The excavation in source combines three above dimension, when resource meet certain mass fraction, novelty degree and it is not vulgar when, the money
Source is judged as high-quality resource, i.e. quality is higher than the resource of predetermined threshold, opposite, remaining resource is then resource inferior.
Fig. 5 is the schematic diagram of the application resource recommendation method further embodiment, as shown in figure 5, commending system is often
Wish to see good resource recommendation to user.Wish the interested content of user as far as possible as personalized recommendation system
It is presented to user, while also being intended to that the interest of user can be spread and be excavated.Based on quality and the two related dimensions, from
It is analyzed in the behavior of user, interest is the principal element for influencing user and clicking, it is believed that for most of ordinary user
Speech has the quality of the resource certain tolerance when they are very interested to certain type of resource, and for
Their less interested resources, then can have higher requirements to quality；In addition, for a small amount of high-end user, they are then
To no matter the resource under the conditions of which kind of quality requirement it is very high.Therefore, it sees on the whole, it is useful that high-quality resource can recommend institute
Family, and resource relatively inferior then needs the correlation according to user's classification and resource and user to recommend user.
Resource recommendation method provided by the embodiments of the present application can improve the quality of the resource of recommendation, according to different types of
User differently recommends, and can improve the overall experience of user, and the exhibition of the resource high with End-user relevance
Existing weight is high, can be from the correlation of the whole resource and user for being promoted and being recommended.In addition, resource provided by the embodiments of the present application pushes away
It recommends method and still remains the part impersonal theory way of recommendation, make the data that recommendation comes out that there is certain diversity and diffusion
Property.
Fig. 6 is the structural schematic diagram of the application resource recommendation device one embodiment, and the resource in the embodiment of the present application pushes away
It recommends device and resource recommendation method provided by the embodiments of the present application may be implemented.As shown in fig. 6, above-mentioned resource recommendation device can wrap
It includes：Acquisition module 61, determining module 62 and recommending module 63；
Wherein, acquisition module 61, for obtaining resource to be recommended；And the user model of user is obtained, and determination is above-mentioned
User's classification belonging to user；
Specifically, acquisition module 61 can obtain resource to be recommended after receiving the operation requests that user sends；Its
In, aforesaid operations request can be drop-down page operation of the above-mentioned user in browsing pages, or the point of above-mentioned user
Page operation or the long-press page operation of above-mentioned user are hit, the present embodiment does not limit the operation requests that above-mentioned user sends
It is fixed, as long as aforesaid operations request can be used for request server recommends resource to above-mentioned user.
Wherein, acquisition module 61 specifically can be by personalized queue, Collaborative Recommendation queue and Xin Re queues, to resources bank
In resource screened, obtain resource to be recommended.
Wherein, acquisition module 61 obtains the user model of user, determines that the classification of the user belonging to above-mentioned user can be：Root
According to the user model of above-mentioned user, determine that above-mentioned user belongs to high-end user or ordinary user.In the present embodiment, high-end use
Family includes the higher user of quality and correlation requirement to the resource of recommendation, and ordinary user includes the quality to the resource of recommendation
It is required that will not be especially high, there is certain tolerance to the lower resource of quality, often more focus on the relevant user of interest.
In specific implementation, acquisition module 61 can be according to the user model of above-mentioned user, in conjunction with the history of above-mentioned user
Behavior (such as：The historical viewings of above-mentioned user and click behavior) determine that the user belonging to above-mentioned user classifies.
Determining module 62, for according to the matching degree of above-mentioned user model and resource to be recommended, determine above-mentioned user and
The correlation of above-mentioned resource to be recommended.
Recommending module 63, the user's classification being used for belonging to above-mentioned user and above-mentioned user and above-mentioned resource to be recommended
Correlation recommends resource to above-mentioned user.
In the present embodiment, resource to be recommended may include picture resource, textual resources and/or voice resource, the present embodiment
The concrete form of above-mentioned resource to be recommended is not construed as limiting.
In above-mentioned resource recommendation device, after acquisition module 61 obtains resource to be recommended, the user model of user is obtained, and
Determine user's classification belonging to above-mentioned user, determining module 62 according to the matching degree of above-mentioned user model and resource to be recommended,
Determine the correlation of above-mentioned user and above-mentioned resource to be recommended, then user classification of the recommending module 63 belonging to above-mentioned user
With the correlation of above-mentioned user and above-mentioned resource to be recommended, recommend resource to above-mentioned user, inhomogeneity is directed to so as to realize
The user of type carries out resource recommendation in different ways, improves the overall experience of user, and can be in the resource for ensureing to recommend
Under the premise of the correlation of user, the quality of resource recommended to the user is improved.
Fig. 7 is the structural schematic diagram of the application resource recommendation device another embodiment, in the present embodiment, determining module
62, it is specifically used for the point of interest for obtaining above-mentioned resource to be recommended and/or the classification belonging to above-mentioned resource to be recommended, waits pushing away when above-mentioned
Recommend classification belonging to the point of interest of resource and the interest points matching of above-mentioned user model and/or above-mentioned resource to be recommended with it is above-mentioned
When the interest classification and matching of user model, determine that above-mentioned user is related to above-mentioned resource to be recommended；When above-mentioned resource to be recommended
Point of interest and the point of interest of above-mentioned user model mismatch, and the classification belonging to above-mentioned resource to be recommended and above-mentioned user model
Interest classification mismatch when, determine that above-mentioned user is uncorrelated to above-mentioned resource to be recommended.
Specifically, in the present embodiment, according to the power of degree of correlation, correlation can be divided into strong correlation to it is weak related：
1) strong correlation：When the interest points matching of the point of interest and above-mentioned user model of resource to be recommended, and it is matched emerging
Interest point is when clicking to show rate height and have the point of interest of enough confidence levels in above-mentioned user model, to determine above-mentioned resource to be recommended
With above-mentioned user there is strong correlation, this matched point of interest to be properly termed as strong point of interest.When the strong interest matched
Point is more, it is believed that the resource to be recommended and the correlation of user are stronger.
2) weak correlation：When the point of interest of resource to be recommended and the interest points matching of above-mentioned user model or above-mentioned wait pushing away
The interest classification and matching of the classification and above-mentioned user model belonging to resource is recommended, but matched point of interest is in above-mentioned user model
When the confidence level that click shows rate not and be especially high or matched point of interest is not especially high, it is believed that matched point of interest is
The weak point of interest of user determines that the resource to be recommended has weak dependence with user in this case.
Compared with resource recommendation device shown in fig. 6, the difference is that, in resource recommendation device shown in Fig. 7, recommend
Module 63 may include：Quality determination sub-module 631 searches submodule 632, sorting sub-module 633 and resource recommendation submodule
634；
In a kind of realization method of the present embodiment, quality determination sub-module 631, the quality for determining resource to be recommended；
Search submodule 632, for when above-mentioned user belongs to high-end user, searched in above-mentioned resource to be recommended with it is upper
It states user's correlation and quality is higher than the resource of predetermined threshold；
Sorting sub-module 633 carries out fusion sequence for will search the resource that submodule 632 is found；
Resource recommendation submodule 634, for by the resource after the fusion sequence of sorting sub-module 633, recommending above-mentioned user.
Wherein, above-mentioned predetermined threshold can in specific implementation according to the sets itselfs such as system performance and/or realization demand,
The present embodiment is not construed as limiting the size of above-mentioned predetermined threshold.
Specifically, requirement of the high-end user to resource quality is very high, therefore for the recommendation of this kind of user, not only to ensure
The resource of recommendation and the correlation of high-end user, will also ensure the quality of resource, for high-end user, need to excavate with it is upper
It states user's correlation and quality is recommended higher than the resource of predetermined threshold.
When specific implementation, for high-end user, searches submodule 632 and searched in above-mentioned resource to be recommended and above-mentioned user
After related and quality is higher than the resource of predetermined threshold, when sorting sub-module 633 carries out fusion sequence to the resource found,
The weight with the resource of above-mentioned user's strong correlation in the resource found can be improved, with ensure with high-end user strong correlation and
Quality can preferentially show higher than the resource of predetermined threshold.
In another realization method of the present embodiment, quality determination sub-module 631, the matter for determining resource to be recommended
Amount；
Search submodule 632, for when above-mentioned user belongs to ordinary user, searched in above-mentioned resource to be recommended with it is upper
The relevant resource of user is stated, and searches the uncorrelated but quality to above-mentioned user in above-mentioned resource to be recommended and is higher than predetermined threshold
Resource；
Sorting sub-module 633, for carrying out fusion sequence to searching the resource that submodule 632 is found, to finding
Resource when carrying out fusion sequence, improve the money of and quality related to above-mentioned user in the resource found higher than predetermined threshold
The weight in source；
Resource recommendation submodule 634, for the resource recommendation after sorting sub-module 633 sorts to above-mentioned user.
In the present embodiment, ordinary user generally will not be especially high to the quality requirement of the resource of recommendation, often more focuses on emerging
It is interesting related, therefore to the recommendation of this kind of user, it should determine the way of recommendation according to the degree of correlation of user and resource to be recommended.When
When judging that resource to be recommended and user have correlation, user generally can be interested in click, as long as being not belonging to illegal interior
Hold, can be used as recommended candidate collection, can be suitably weighted when this resource to be recommended belongs to high-quality resource to ensure preferential exhibition
It is existing；And when there is content incoherent with user, then the quality for ensureing resource to be recommended is needed, makes user will not be to the resource
Dislike is generated, so as to more objectively carry out interest digging and diffusion to user to the behavior of such resource by user.
In specific implementation, sorting sub-module 633 can improve above-mentioned when carrying out fusion sequence to the resource found
And quality related to above-mentioned user is higher than the weight of the resource of predetermined threshold in the resource found, it is possible to further set
It sets with above-mentioned user's strong correlation and quality is higher than the weight of the resource of predetermined threshold, be more than to above-mentioned user weak related and matter
Amount is preferentially showed with above-mentioned user's strong correlation with guarantee higher than the weight of the resource of predetermined threshold and quality is higher than predetermined threshold
Resource.
Wherein, quality determination sub-module 631 is specifically used for according to the mass fraction of above-mentioned resource to be recommended itself, above-mentioned
The vulgar degree of the plagiarism degree of resource to be recommended and/or above-mentioned resource to be recommended determines the quality of above-mentioned resource to be recommended.
Wherein, quality determination sub-module 631 is specifically used for being higher than first when the mass fraction of above-mentioned resource to be recommended itself
Threshold value, the plagiarism degree of above-mentioned resource to be recommended score less than second threshold and/or above-mentioned resource to be recommended vulgar degree
Score be less than third threshold value when, determine above-mentioned resource to be recommended quality be higher than predetermined threshold.
Wherein, the size of above-mentioned first threshold, second threshold and third threshold value can be in specific implementation according to systematicness
Sets itselfs, the present embodiment such as energy and/or realization demand do not make the size of above-mentioned first threshold, second threshold and third threshold value
It limits.
In the present embodiment, the judgement for resource quality to be recommended can be carried out from following several dimensions：
A) mass fraction of resource itself：Resource can pass through an audit marking mechanism on the data streams, obtain a phase
The mass fraction answered, score is higher to indicate that the quality of resource is better, this is the fundamental prerequisite for identifying resource quality, once it is discontented
The score of sufficient resource is less than passing score, which can be filtered；
B) the plagiarism degree of resource：The plagiarism degree of resource can be judged on the data streams, and score is lower to represent its plagiarism journey
Degree is lower, i.e., resource is more novel；
C) the vulgar degree of resource：The vulgar degree of resource can be judged on the data streams, and the higher expression resource of score is more
Vulgar, the resource can be filtered when higher than some threshold value.
Due to having strobe utility in data flow, so being in contrast resource inferior for the inferior and high-quality of resource
It is not meant to be underproof resource, these resources should not be abandoned, otherwise be easy to cause waste.For high-quality money
The excavation in source combines three above dimension, when resource meet certain mass fraction, novelty degree and it is not vulgar when, quality
Determination sub-module 631 can determine that the resource is high-quality resource, i.e., quality is higher than the resource of predetermined threshold, opposite, remaining money
Source is then resource inferior.
Fig. 8 is the structural schematic diagram of the application computer equipment one embodiment, and above computer equipment may include depositing
Reservoir, processor and it is stored in the computer program that can be run on above-mentioned memory and on above-mentioned processor, above-mentioned processor
When executing above computer program, resource recommendation method provided by the embodiments of the present application may be implemented.
Wherein, above computer equipment can be server, or terminal device, the present embodiment is to above computer
The specific form of equipment is not construed as limiting.
Fig. 8 shows the block diagram of the exemplary computer device 12 suitable for being used for realizing the application embodiment.Fig. 8 is shown
Computer equipment 12 be only an example, any restrictions should not be brought to the function and use scope of the embodiment of the present application.
As shown in figure 8, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can be with
Including but not limited to：One or more processor or processing unit 16, system storage 28 connect different system component
The bus 18 of (including system storage 28 and processing unit 16).
Bus 18 indicates one or more in a few class bus structures, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using the arbitrary bus structures in a variety of bus structures.It lifts
For example, these architectures include but not limited to industry standard architecture (Industry Standard
Architecture；Hereinafter referred to as：ISA) bus, microchannel architecture (Micro Channel Architecture；Below
Referred to as：MAC) bus, enhanced isa bus, Video Electronics Standards Association (Video Electronics Standards
Association；Hereinafter referred to as：VESA) local bus and peripheral component interconnection (Peripheral Component
Interconnection；Hereinafter referred to as：PCI) bus.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (Random Access Memory；Hereinafter referred to as：RAM) 30 and/or cache memory 32.Computer equipment 12
It may further include other removable/nonremovable, volatile/non-volatile computer system storage mediums.Only conduct
Citing, storage system 34 can be used for reading and writing immovable, non-volatile magnetic media, and (Fig. 8 do not show, commonly referred to as " hard disk
Driver ").Although being not shown in Fig. 8, can provide for the magnetic to moving non-volatile magnetic disk (such as " floppy disk ") read-write
Disk drive, and to removable anonvolatile optical disk (such as：Compact disc read-only memory (Compact Disc Read Only
Memory；Hereinafter referred to as：CD-ROM), digital multi CD-ROM (Digital Video Disc Read Only
Memory；Hereinafter referred to as：DVD-ROM) or other optical mediums) read-write CD drive.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program production
Product, the program product have one group of (for example, at least one) program module, and it is each that these program modules are configured to perform the application
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can be stored in such as memory 28
In, such program module 42 includes --- but being not limited to --- operating system, one or more application program, other programs
Module and program data may include the realization of network environment in each or certain combination in these examples.Program mould
Block 42 usually executes function and/or method in embodiments described herein.
Computer equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24
Deng) communication, can also be enabled a user to one or more equipment interact with the computer equipment 12 communicate, and/or with make
The computer equipment 12 any equipment (such as network interface card, the modulatedemodulate that can be communicated with one or more of the other computing device
Adjust device etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, computer equipment 12 may be used also
To pass through network adapter 20 and one or more network (such as LAN (Local Area Network；Hereinafter referred to as：
LAN), wide area network (Wide Area Network；Hereinafter referred to as：WAN) and/or public network, for example, internet) communication.Such as figure
Shown in 8, network adapter 20 is communicated by bus 18 with other modules of computer equipment 12.Although should be understood that in Fig. 8 not
It shows, other hardware and/or software module can be used in conjunction with computer equipment 12, including but not limited to：Microcode, equipment are driven
Dynamic device, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 is stored in program in system storage 28 by operation, to perform various functions application and
Data processing, such as realize resource recommendation method provided by the embodiments of the present application.
The embodiment of the present application also provides a kind of non-transitorycomputer readable storage medium, is stored thereon with computer journey
Resource recommendation method provided by the embodiments of the present application may be implemented in sequence, above computer program when being executed by processor.
Appointing for one or more computer-readable media may be used in above-mentioned non-transitorycomputer readable storage medium
Meaning combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.Computer can
It reads storage medium and for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device
Or device, or the arbitrary above combination.The more specific example (non exhaustive list) of computer readable storage medium includes：
Electrical connection, portable computer diskette, hard disk, random access memory (RAM), read-only storage with one or more conducting wires
Device (Read Only Memory；Hereinafter referred to as：ROM), erasable programmable read only memory (Erasable
Programmable Read Only Memory；Hereinafter referred to as：EPROM) or flash memory, optical fiber, portable compact disc are read-only deposits
Reservoir (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer
Readable storage medium storing program for executing, which can be any, includes or the tangible medium of storage program, which can be commanded execution system, device
Either device use or in connection.
Computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission for by instruction execution system, device either device use or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with one or more programming languages or combinations thereof come write for execute the application operation computer
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partly executes or executed on a remote computer or server completely on the remote computer on the user computer.
It is related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (Local
Area Network；Hereinafter referred to as：) or wide area network (Wide Area Network LAN；Hereinafter referred to as：WAN) it is connected to user
Computer, or, it may be connected to outer computer (such as being connected by internet using ISP).
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiments or example.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present application, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing custom logic function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discuss suitable
Sequence, include according to involved function by it is basic simultaneously in the way of or in the opposite order, to execute function, this should be by the application
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (system of such as computer based system including processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicating, propagating or passing
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium includes following：Electricity with one or more wiring
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (Random Access
Memory；Hereinafter referred to as：RAM), read-only memory (Read Only Memory；Hereinafter referred to as：ROM), erasable editable
Read memory (Erasable Programmable Read Only Memory；Hereinafter referred to as：EPROM) or flash memory,
Fiber device and portable optic disk read-only storage (Compact Disc Read Only Memory；Hereinafter referred to as：CD-
ROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other suitable media, because
For can be then suitable with other into edlin, interpretation or when necessary for example by carrying out optical scanner to paper or other media
Mode is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or combination thereof.Above-mentioned
In embodiment, software that multiple steps or method can in memory and by suitable instruction execution system be executed with storage
Or firmware is realized.Such as, if realized in another embodiment with hardware, following skill well known in the art can be used
Any one of art or their combination are realized：With for data-signal realize logic function logic gates from
Logic circuit is dissipated, the application-specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (Programmable
Gate Array；Hereinafter referred to as：PGA), field programmable gate array (Field Programmable Gate Array；Below
Referred to as：FPGA) etc..
Those skilled in the art are appreciated that realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, which includes the steps that one or a combination set of embodiment of the method when being executed.
In addition, each functional unit in each embodiment of the application can be integrated in a processing module, it can also
That each unit physically exists alone, can also two or more units be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and when sold or used as an independent product, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
Embodiments herein is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as the limit to the application
System, those skilled in the art can be changed above-described embodiment, change, replace and become within the scope of application
Type.
Claims (15)
1. a kind of resource recommendation method, which is characterized in that including：
Obtain resource to be recommended；
The user model of user is obtained, and determines user's classification belonging to the user；
According to the matching degree of the user model and resource to be recommended, determine that the user is related to the resource to be recommended
Property；
User's classification and the user and the correlation of the resource to be recommended belonging to the user are pushed away to the user
Recommend resource.
2. according to the method described in claim 1, it is characterized in that, according to the user model and resource to be recommended
With degree, determine that the user and the correlation of the resource to be recommended include：
The point of interest for obtaining the resource to be recommended and/or the classification belonging to the resource to be recommended；
If interest points matching and/or the to be recommended resource of the point of interest of the resource to be recommended with the user model
The interest classification and matching of affiliated classification and the user model, it is determined that the user is related to the resource to be recommended；
If the point of interest of the resource to be recommended and the point of interest of the user model mismatch, and the resource to be recommended
Affiliated classification and the interest classification of the user model mismatch, it is determined that the user and the resource to be recommended not phase
It closes.
3. according to the method described in claim 1, it is characterized in that, it is described belonging to the user user classification and it is described
The correlation of user and the resource to be recommended recommends the resource to include to the user：
Determine the quality of the resource to be recommended；
When the user belongs to high-end user, related and quality is higher than to the user for lookup in the resource to be recommended
The resource of predetermined threshold after the resource found is carried out fusion sequence, recommends the user.
4. according to the method described in claim 1, it is characterized in that, it is described belonging to the user user classification and it is described
The correlation of user and the resource to be recommended recommends the resource to include to the user：
Determine the quality of the resource to be recommended；
When the user belongs to ordinary user, lookup and the relevant resource of the user in the resource to be recommended, and
The resource that the uncorrelated but quality to the user is higher than predetermined threshold is searched in the resource to be recommended；
Fusion sequence is carried out to the resource found, when carrying out fusion sequence to the resource found, is found described in raising
Resource in and quality related to the user higher than predetermined threshold resource weight；
Give the resource recommendation after sequence to the user.
5. method according to claim 3 or 4, which is characterized in that the quality of the determination resource to be recommended includes：
According to the mass fraction of the resource to be recommended itself, the plagiarism degree of the resource to be recommended and/or described to be recommended
The vulgar degree of resource determines the quality of the resource to be recommended.
6. according to the method described in claim 5, it is characterized in that, the quality according to the resource to be recommended itself point
The vulgar degree of the plagiarism degree of several, the described resource to be recommended and/or the resource to be recommended determines the resource to be recommended
Quality includes：
When the mass fraction of the resource to be recommended itself is higher than the score of first threshold, the plagiarism degree of the resource to be recommended
When being less than third threshold value less than second threshold and/or the score of the vulgar degree of the resource to be recommended, determine described to be recommended
The quality of resource is higher than predetermined threshold.
7. according to the method described in any of claim 1 to 4, which is characterized in that described to obtain resource to be recommended and include：
By personalized queue, Collaborative Recommendation queue and Xin Re queues, the resource in resources bank is screened, is obtained to be recommended
Resource.
8. a kind of resource recommendation device, which is characterized in that including：
Acquisition module, for obtaining resource to be recommended；And the user model of user is obtained, and determine the use belonging to the user
Classify at family；
Determining module determines that the user waits for described for the matching degree according to the user model and resource to be recommended
Recommend the correlation of resource；
Recommending module, the correlation for user classification and the user and the resource to be recommended belonging to the user
Recommend resource to the user.
9. device according to claim 8, which is characterized in that
The determining module is specifically used for obtaining belonging to point of interest and/or the resource to be recommended of the resource to be recommended
Classification；Belonging to the point of interest of the resource in the resources bank and the interest points matching of the user model and/or the resource
Classification with the interest classification and matching of the user model when, determine that the user is related to the resource；When the resources bank
In the point of interest of point of interest and the user model of resource mismatch, and the classification belonging to the resource and the user
When the interest classification of model mismatches, determine that the user is uncorrelated to the resource.
10. device according to claim 8, which is characterized in that the recommending module includes：
Quality determination sub-module, the quality for determining the resource to be recommended；
Submodule is searched, for when the user belongs to high-end user, being searched and the user in the resource to be recommended
Related and quality is higher than the resource of predetermined threshold；
Sorting sub-module, the resource for finding the lookup submodule carry out fusion sequence；
Resource recommendation submodule, for by the resource after sorting sub-module fusion sequence, recommending the user.
11. device according to claim 8, which is characterized in that the recommending module includes：
Quality determination sub-module, the quality for determining the resource to be recommended；
Submodule is searched, for when the user belongs to ordinary user, being searched and the user in the resource to be recommended
Relevant resource, and in the resource to be recommended search to the user uncorrelated but quality higher than predetermined threshold money
Source；
Sorting sub-module, the resource for being found to the lookup submodule carries out fusion sequence, in the resource to finding
When carrying out fusion sequence, and quality related to the user is higher than the resource of predetermined threshold in the resource found described in raising
Weight；
Resource recommendation submodule, for the resource recommendation after the sorting sub-module sorts to the user.
12. the device according to claim 10 or 11, which is characterized in that
The quality determination sub-module, specifically for the mass fraction according to the resource to be recommended itself, the money to be recommended
The vulgar degree of the plagiarism degree in source and/or the resource to be recommended determines the quality of the resource to be recommended.
13. device according to claim 12, which is characterized in that
The quality determination sub-module is specifically used for the mass fraction when the resource to be recommended itself higher than first threshold, institute
The score for stating the plagiarism degree of resource to be recommended is low less than the score of second threshold and/or the vulgar degree of the resource to be recommended
When third threshold value, determine that the quality of the resource to be recommended is higher than predetermined threshold.
14. a kind of computer equipment, which is characterized in that including memory, processor and be stored on the memory and can be
The computer program run on the processor when the processor executes the computer program, realizes such as claim 1-7
In any method.
15. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the meter
The method as described in any in claim 1-7 is realized when calculation machine program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810145643.3A CN108415992B (en) | 2018-02-12 | 2018-02-12 | Resource recommendation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810145643.3A CN108415992B (en) | 2018-02-12 | 2018-02-12 | Resource recommendation method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108415992A true CN108415992A (en) | 2018-08-17 |
| CN108415992B CN108415992B (en) | 2022-03-04 |
Family
ID=63128509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810145643.3A Active CN108415992B (en) | 2018-02-12 | 2018-02-12 | Resource recommendation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108415992B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711875A (en) * | 2018-12-19 | 2019-05-03 | 口碑(上海)信息技术有限公司 | Content recommendation method and device |
| CN112784142A (en) * | 2019-10-24 | 2021-05-11 | 北京搜狗科技发展有限公司 | Information recommendation method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004094384A (en) * | 2002-08-29 | 2004-03-25 | Ntt Comware Corp | Recommendation device and method for setting taste information |
| CN102651033A (en) * | 2012-04-09 | 2012-08-29 | 百度在线网络技术（北京）有限公司 | Method and device for recommending online resource |
| CN103108049A (en) * | 2013-02-20 | 2013-05-15 | 杭州东信北邮信息技术有限公司 | Method for providing personalized page for mobile terminal user |
| CN106802915A (en) * | 2016-12-09 | 2017-06-06 | 宁波大学 | A kind of academic resources based on user behavior recommend method |
| CN106815216A (en) * | 2015-11-30 | 2017-06-09 | 北京云莱坞文化传媒有限公司 | A kind of story screening and the method and apparatus for precisely representing |
| CN107609060A (en) * | 2017-08-28 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device |
-
2018
- 2018-02-12 CN CN201810145643.3A patent/CN108415992B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004094384A (en) * | 2002-08-29 | 2004-03-25 | Ntt Comware Corp | Recommendation device and method for setting taste information |
| CN102651033A (en) * | 2012-04-09 | 2012-08-29 | 百度在线网络技术（北京）有限公司 | Method and device for recommending online resource |
| CN103108049A (en) * | 2013-02-20 | 2013-05-15 | 杭州东信北邮信息技术有限公司 | Method for providing personalized page for mobile terminal user |
| CN106815216A (en) * | 2015-11-30 | 2017-06-09 | 北京云莱坞文化传媒有限公司 | A kind of story screening and the method and apparatus for precisely representing |
| CN106802915A (en) * | 2016-12-09 | 2017-06-06 | 宁波大学 | A kind of academic resources based on user behavior recommend method |
| CN107609060A (en) * | 2017-08-28 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711875A (en) * | 2018-12-19 | 2019-05-03 | 口碑(上海)信息技术有限公司 | Content recommendation method and device |
| CN112784142A (en) * | 2019-10-24 | 2021-05-11 | 北京搜狗科技发展有限公司 | Information recommendation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108415992B (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9449271B2 (en) | Classifying resources using a deep network | |
| US11455465B2 (en) | Book analysis and recommendation | |
| US10324591B2 (en) | System for creating and retrieving contextual links between user interface objects | |
| US10902077B2 (en) | Search result aggregation method and apparatus based on artificial intelligence and search engine | |
| US20170034107A1 (en) | Annotating content with contextually relevant comments | |
| CN104735468B (en) | A kind of method and system that image is synthesized to new video based on semantic analysis | |
| US9483462B2 (en) | Generating training data for disambiguation | |
| WO2023005339A1 (en) | Search result display method, apparatus and device, and medium | |
| US20150169710A1 (en) | Method and apparatus for providing search results | |
| CN102982124A (en) | Microblog summarizing | |
| US9710437B2 (en) | Group tagging of documents | |
| CN107590216A (en) | Answer preparation method, device and computer equipment | |
| Chen | RETRACTED ARTICLE: Research on personalized recommendation algorithm based on user preference in mobile e-commerce | |
| US20190121905A1 (en) | Identifying categories within textual data | |
| US20180053235A1 (en) | Unbiased search and user feedback analytics | |
| US20220121668A1 (en) | Method for recommending document, electronic device and storage medium | |
| WO2020151548A1 (en) | Method and device for sorting followed pages | |
| CN108108419A (en) | A kind of information recommendation method, device, equipment and medium | |
| US20190317648A1 (en) | System enabling audio-based navigation and presentation of a website | |
| CN108334626A (en) | Generation method, device and the computer equipment of news program | |
| CN108415992A (en) | Resource recommendation method, device and computer equipment | |
| JP5430960B2 (en) | Content classification apparatus, method, and program | |
| CN107944026A (en) | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation | |
| US11836197B2 (en) | Search processing method and apparatus based on clipboard data | |
| US20200264746A1 (en) | Cognitive computing to identify key events in a set of data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |