CN108415996A - A kind of news information method for pushing, device and electronic equipment - Google Patents

A kind of news information method for pushing, device and electronic equipment Download PDF

Info

Publication number
CN108415996A
CN108415996A CN201810150326.0A CN201810150326A CN108415996A CN 108415996 A CN108415996 A CN 108415996A CN 201810150326 A CN201810150326 A CN 201810150326A CN 108415996 A CN108415996 A CN 108415996A
Authority
CN
China
Prior art keywords
news
user
news type
search
type
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810150326.0A
Other languages
Chinese (zh)
Inventor
彭睿棋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Qihoo Technology Co Ltd
Original Assignee
Beijing Qihoo Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Qihoo Technology Co Ltd filed Critical Beijing Qihoo Technology Co Ltd
Priority to CN201810150326.0A priority Critical patent/CN108415996A/en
Publication of CN108415996A publication Critical patent/CN108415996A/en
Pending legal-status Critical Current

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

The present invention discloses a kind of news information method for pushing, device and electronic equipment, pass through the search need of preposition user's news type in the search of user's initiation news type, the search efficiency and user experience of significant increase search engine, personalized search recommendation results are provided, the realization efficiency and user's viscosity of search engine are increased.This method includes：In the search content for detecting target user's search news type, the web-based history behavior record of the news type of the whole network user is extracted；The web-based history behavior record of news type based on the whole network user determines the recommendation information of news type corresponding with the target user；The recommendation information of the news type is illustrated in result of page searching corresponding with the search content of the news type.

Description

A kind of news information method for pushing, device and electronic equipment
Technical field
The present invention relates to a kind of electronic technology field more particularly to news information method for pushing, device and electronic equipments.
Background technology
As the information processing technology develops, more and more electronic equipments appear in the work and life of people, convenient Daily life.These electronic equipments are provided to the user by internet easily to be serviced.The development institute band of internet The information content come increases so that user is increasingly fixed against search engine when filter information.Search engine refers to basis Certain strategy collects information with specific computer program from internet, after carrying out tissue and processing to information, is User provides retrieval service, will search for the system that the relevant information of content shows user with user.Currently, being used in user During search engine, traditional search engine only provides official website addressing service, such as：User searches for the name of news website Claim, the search result that search engine is determined is the network address of news website.Therefore, prior art search engine is only capable of meeting user Web site query demand, the search service provided is single, and user's viscosity is poor.
Invention content
In view of the above problems, it is proposed that the present invention overcoming the above problem in order to provide one kind or solves at least partly State shopping information method for pushing, device and the electronic equipment of problem.
In a first aspect, the application provides a kind of news information method for pushing, including：
In the search content for detecting target user's search news type, the news type of the whole network user is extracted Web-based history behavior record；
The web-based history behavior record of news type based on the whole network user, determination are corresponding with the target user The recommendation information of news type；
The recommendation information of the news type is illustrated in search result corresponding with the search content of the news type In the page.
Optionally, the web-based history behavior record of the news type based on the whole network user determines and the mesh The recommendation information of the corresponding news type of user is marked, including：
The web-based history behavior record of news type based on the whole network user, determines candidate items；
It determines each scoring of the user to candidate items in the whole network user, establishes user's rating matrix；
Based on the rating matrix, neighbor user collection similar with the target user in the whole network user is determined；
Based on the neighbor user collection, recommended project is determined from the candidate items；
Determine recommendation of the recommendation information corresponding with the recommended project for news type corresponding with the target user Information.
Optionally, the web-based history behavior record for obtaining the whole network user, including：
Obtain the search record of the news type of the whole network user in preset time range, the click record of news type It is combined with any one or more in the browsing record of news type.
Optionally, the web-based history behavior record of the news type based on the whole network user, determines candidate item Mesh, including：
Determine that searching times are more than in the search record of the news type of the whole network user in the preset time range The search content of first preset times is candidate items；And/or
Determine that the click record midpoint machine number of the news type of the whole network user in the preset time range is more than The click on content of second preset times is candidate items；And/or
Determine that number of visits is more than in the browsing record of the news type of the whole network user in the preset time range The browsing content of third preset times is candidate items.
Optionally, described to be based on the rating matrix, determine neighbour similar with the target user in the whole network user User's collection is occupied, including：
Based on the rating matrix, the similitude of the target user and other users in the whole network user are calculated；
Based on the similitude of other users in the target user and the whole network user, determine and target user's phase As neighbor user collection.
Optionally, the similitude based on other users in the target user and the whole network user, determining and institute The similar neighbor user collection of target user is stated, including：
Determine similar with target user neighbor user collection include in the whole network user with the target user Similitude is more than the user of the first predetermined threshold value.
Optionally, the similitude based on other users in the target user and the whole network user, determining and institute The similar neighbor user collection of target user is stated, including：
Determine similar with target user neighbor user collection include in the whole network user with the target user Similitude arrange from large to small after preceding first preset number user.
Optionally, described to be based on the neighbor user collection, recommended project is determined from the candidate items, including：
Based on the neighbor user collection, determine that the target user is pre- to the interest-degree of each project in the candidate items Measured value；
Determine that the project that interest-degree predicted value is more than the second predetermined threshold value in the candidate items is recommended project or determination The project of preceding second preset number after interest-degree predicted value arranges from large to small in the candidate items is recommended project.
Optionally, described to be based on the neighbor user collection, recommended project is determined from the candidate items, including：
Determine weighted average of all neighbor users to each project in the candidate items of the neighbor user concentration Interest-degree；
Determine that project that weighted average interest-degree in the candidate items is more than third predetermined threshold value is recommended project or really The project of preceding third preset number after weighted average interest-degree arranges from large to small in the fixed candidate items is recommended project.
Optionally, the recommendation information by the news type is illustrated in corresponding with the search content of the news type Result of page searching in, including：
The recommendation information of the news type is illustrated under the corresponding search result of search content of the news type Side, the recommendation information of the news type includes candidate search word corresponding with the recommended project and/or web page interlinkage.
Optionally, the search content of the news type includes：News website title, news website link and news content Any one or more in mark combines.
Optionally, the recommendation information by the news type is illustrated in corresponding with the search content of the news type Result of page searching, including：
Searching for the news type searched for the target user is determined from the recommendation information of the news type The relevant recommendation information of rope content；
The relevant recommendation information of search content for the news type searched for the target user is illustrated in and institute State the corresponding result of page searching of search content of news type.
Optionally, the recommendation information of the news type specifically includes the news object that user can directly browse, the side Method further includes：
User is responded to the trigger action of the news object, loads the corresponding browsing webpage of the news object.
Second aspect, the application provide a kind of news information method for pushing, including：
In the search content for detecting target user's search news type, the news type of the whole network user is extracted Web-based history behavior record；
The web-based history behavior record of news type based on the whole network user, determination are similar with the target user Similar users collection；
The information of the interested news type of each similar users is concentrated based on the similar users, is determined and the target The recommendation information of the corresponding news type of user；
The recommendation information of the news type is illustrated in search result corresponding with the search content of the news type In the page.
The third aspect, the application provide a kind of news information pusher, including：
Acquiring unit, in the search content for detecting target user's search news type, extraction the whole network to be used The web-based history behavior record of the news type at family；
Determination unit, be used for the news type based on the whole network user web-based history behavior record, determine with it is described The recommendation information of the corresponding news type of target user；
Display unit, for the recommendation information of the news type to be illustrated in the search content pair with the news type In the result of page searching answered.
Optionally, the determination unit includes：
First determining module is used for the web-based history behavior record of the news type based on the whole network user, determines Candidate items；
Second determining module establishes user for determining each scoring of the user to candidate items in the whole network user Rating matrix；
Third determining module, for be based on the rating matrix, determine in the whole network user with target user's phase As neighbor user collection；
4th determining module determines recommended project for being based on the neighbor user collection from the candidate items；
5th determining module, for determining that recommendation information corresponding with the recommended project is corresponding with the target user News type recommendation information.
Optionally, the acquiring unit is used for：
Obtain the search record of the news type of the whole network user in preset time range, the click record of news type It is combined with any one or more in the browsing record of news type.
Optionally, first determining module is used for：
Determine that searching times are more than in the search record of the news type of the whole network user in the preset time range The search content of first preset times is candidate items；And/or
Determine that the click record midpoint machine number of the news type of the whole network user in the preset time range is more than The click on content of second preset times is candidate items；And/or
Determine that number of visits is more than in the browsing record of the news type of the whole network user in the preset time range The browsing content of third preset times is candidate items.
Optionally, the third determining module is used for：
Based on the rating matrix, the similitude of the target user and other users in the whole network user are calculated；
Based on the similitude of other users in the target user and the whole network user, determine and target user's phase As neighbor user collection.
Optionally, the third determining module is used for：
Determine similar with target user neighbor user collection include in the whole network user with the target user Similitude is more than the user of the first predetermined threshold value.
Optionally, the third determining module is used for：
Determine similar with target user neighbor user collection include in the whole network user with the target user Similitude arrange from large to small after preceding first preset number user.
Optionally, the 4th determining module is used for：
Based on the neighbor user collection, determine that the target user is pre- to the interest-degree of each project in the candidate items Measured value；
Determine that the project that interest-degree predicted value is more than the second predetermined threshold value in the candidate items is recommended project or determination The project of preceding second preset number after interest-degree predicted value arranges from large to small in the candidate items is recommended project.
Optionally, the 4th determining module is used for：
Determine weighted average of all neighbor users to each project in the candidate items of the neighbor user concentration Interest-degree；
Determine that project that weighted average interest-degree in the candidate items is more than third predetermined threshold value is recommended project or really The project of preceding third preset number after weighted average interest-degree arranges from large to small in the fixed candidate items is recommended project.
Optionally, the display unit is used for：
The recommendation information of the news type is illustrated under the corresponding search result of search content of the news type Side, the recommendation information of the news type includes candidate search word corresponding with the recommended project and/or web page interlinkage.
Optionally, the search content of the news type includes：News website title, news website link and news content Any one or more in mark combines.
Optionally, the display unit is used for：
Searching for the news type searched for the target user is determined from the recommendation information of the news type The relevant recommendation information of rope content；
The relevant recommendation information of search content for the news type searched for the target user is illustrated in and institute State the corresponding result of page searching of search content of news type.
Optionally, the recommendation information of the news type specifically includes the news object that user can directly browse, the dress It sets and further includes：
Response unit, the trigger action for responding user to the news object, it is corresponding to load the news object Browse webpage.
Fourth aspect, the application provide a kind of news information pusher, including：
Acquiring unit, in the search content for detecting target user's search news type, extraction the whole network to be used The web-based history behavior record of the news type at family；
First determination unit, be used for the news type based on the whole network user web-based history behavior record, determine with The similar similar users collection of the target user；
Second determination unit, the letter for concentrating the interested news type of each similar users based on the similar users Breath determines the recommendation information of news type corresponding with the target user；
Display unit, for the recommendation information of the news type to be illustrated in the search content pair with the news type In the result of page searching answered.
5th aspect, the application provide a kind of electronic equipment, and the electronic equipment includes processor and memory：It is described to deposit Reservoir is used to store the program for the news information method for pushing for executing aforementioned first aspect and second aspect；The processor It is configurable for executing the program stored in the memory.
6th aspect, the application provides a kind of computer storage media, for being stored as above-mentioned news information pusher Computer software instructions used, it includes be the program designed by news information pusher for executing above-mentioned aspect.
Said one in the embodiment of the present application or multiple technical solutions at least have following one or more technology effects Fruit：
In the technical solution of the embodiment of the present invention, in the search content situation for detecting target user's search news type Under, extract the web-based history behavior record of the news type of the whole network user；News type again based on the whole network user is gone through History network behavior determines the recommendation information of news type corresponding with the target user；Finally pushing away the news type Recommend the corresponding result of page searching of information is illustrated in the target user searches for search content.In this way, in user by searching It, can be by the web-based history behavior record model of the news type of the whole network user, in advance in the case of index holds up initiation news category search Survey the search need of the potential news category of user.The recommendation information for further determining that out the relevant news type of user is carrying out It, can be by the recommendation information of the relevant news type of user together with displaying when search result is shown.In this way, new by being initiated in user Hear the information browse demand of preposition user's news category when the search of type, the search efficiency of significant increase search engine and user Experience provides personalized search recommendation results, increases the realization efficiency and user's viscosity of search engine.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit are common for this field Technical staff will become clear.Attached drawing only for the purpose of illustrating preferred embodiments, and is not considered as to the present invention Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings：
Fig. 1 is a kind of flow chart of news information method for pushing in first embodiment of the invention；
Fig. 2 is a kind of flow chart of news information method for pushing in second embodiment of the invention；
Fig. 3 is a kind of schematic diagram of news information pusher in third embodiment of the invention；
Fig. 4 is a kind of schematic diagram of news information pusher in fourth embodiment of the invention；
Fig. 5 is the schematic diagram of the electronic equipment in fifth embodiment of the invention.
Specific implementation mode
The present embodiment discloses a kind of news information method for pushing, device and electronic equipment, by initiating news category in user The search need of preposition user's news type when the search of type, the search efficiency and user experience of significant increase search engine, Personalized search recommendation results are provided, the realization efficiency and user's viscosity of search engine are increased.This method includes：It is detecting Target user searches in the case of the search content of news type, extracts the web-based history behavior note of the news type of the whole network user Record；The web-based history behavior record of news type based on the whole network user determines news corresponding with the target user The recommendation information of type；The recommendation information of the news type is illustrated in search corresponding with the search content of the news type In rope results page.
Technical solution of the present invention is described in detail below by attached drawing and specific embodiment, it should be understood that the application Specific features in embodiment and embodiment are the detailed description to technical scheme, rather than to present techniques The restriction of scheme, in the absence of conflict, the technical characteristic in the embodiment of the present application and embodiment can be combined with each other.
The terms "and/or", only a kind of incidence relation of description affiliated partner, indicates that there may be three kinds of passes System, for example, A and/or B, can indicate：Individualism A exists simultaneously A and B, these three situations of individualism B.In addition, herein Middle character "/", it is a kind of relationship of "or" to typically represent forward-backward correlation object.
Embodiment
Referring to FIG. 1, first embodiment of the invention provides a kind of news information method for pushing, the news information method for pushing Include the following steps：
S101：In the search content for detecting target user's search news type, the news of the whole network user is extracted The web-based history behavior record of type；
S102：The web-based history behavior record of news type based on the whole network user determines and the target user The recommendation information of corresponding news type；
S103：The recommendation information of the news type is illustrated in search corresponding with the search content of the news type In results page.
Specifically, in the present embodiment, news information method for pushing is mainly used in the server end of search engine, when So, client can also be applied to.User when client inputs the search content of news type by search engine, draw by search It holds up the server of the search content transmission of the news type to search engine, when server receives the search of the news type After content, corresponding search result is retrieved.On this basis, server can also obtain the history of the news type of the whole network user Network behavior is noted down, and is predicted the search need of the potential news type of user, is further determined that out the relevant news type of user Recommendation information, scan for result displaying when, can be by the recommendation information of the relevant news type of user together with displaying.This Sample passes through the search need of preposition user's news type in the search of user's initiation news type, significant increase search engine Search efficiency and user experience, personalized search recommendation results are provided, realization efficiency and the user of search engine are increased Viscosity.
Further, in the present embodiment, the search content of above-mentioned steps S101, the news type include News Network's station name Claim, any one or more in news website link and news content mark combines.
Specifically, in the present embodiment, initiating the search content of search news type in target user, triggering is held News information method for pushing in row the present embodiment, such as：Title, new of the target user in search site search news website A In the case of hearing network address or the news content mark A of website B, the news information method for pushing executed in the present embodiment can be triggered, The recommendation information of personalized news type is pushed for user.In specific implementation process, the search content of news type may be used also To be other content, here, the application does not limit.
Method in the present embodiment can just be triggered in the search content for initiating search news type, can be effective Avoid to search for non-news type and carry out related push, cause the interference to user, can further reduce equipment Data transmission is born, and the Experience Degree of user is improved.
Further, after the news information method for pushing in the present embodiment is triggered, step S101 is in specific implementation process In, it can be achieved by the steps of：
Obtain the search record of the news type of the whole network user in preset time range, the click record of news type It is combined with any one or more in the browsing record of news type.
Specifically, in the present embodiment, need to obtain preset time range (such as：1 hour, 5 hours, 24 hours etc.) in The whole network user news type search record, news type click record and news type browsing record in it is any one Kind or multiple combinations.Such as：The search record of news type can be that the whole network user searches for News Network in preset time range The record that any one or more in station name, news website link and news content mark combines.Such as：In user A away from working as It was searched in the case of the title of site search news website A before 20 minutes preceding moment, determines that this is recorded as the news category of the whole network user The search of type records.
For another example：The click record of news type can be the news website chain that the whole network user clicks in preset time range Connect and click the record of news.Such as：In user B in the case where clicking news website B before away from 30 minutes current times, determine This is recorded as the click record of the news type of the whole network user.
For another example：The browsing record of news type can be the news network address that the whole network user browses in preset time range And/or the record of news links.Such as：The news A of news website B is browsed before away from 30 minutes current times in user C, Determine that this is recorded as the browsing of the news type of the whole network user record, in the browsing record of the news type of record the whole network user When, in order to ensure the validity of record, it is also contemplated that browsing duration is more than preset duration (such as by browsing duration：1 minute, 5 minutes etc.) news content mark browsing be denoted as the whole network user news type browsing record.
In this way, the web-based history behavior record of the news type of the whole network user can effectively be counted.
Further, it after getting the web-based history behavior record of the news type of the whole network user, executes in the present embodiment When step S102, it can be achieved by the steps of：
The web-based history behavior record of news type based on the whole network user, determines candidate items；
It determines each scoring of the user to candidate items in the whole network user, establishes user's rating matrix；
Based on the rating matrix, neighbor user collection similar with the target user in the whole network user is determined；
Based on the neighbor user collection, recommended project is determined from the candidate items；
Determine recommendation of the recommendation information corresponding with the recommended project for news type corresponding with the target user Information.
Specifically, in the present embodiment, collaborative filtering model may be used to filter out corresponding news category in step S102 The recommendation information of type, it is, of course, also possible to be realized using other modes, here, the application is not limited.In step s 102, first First, the web-based history behavior record of the news type of the whole network user based on acquisition is needed, determines candidate items, waited determining When option, it can be achieved by the steps of：
Determine that searching times are more than in the search record of the news type of the whole network user in the preset time range The search content of first preset times is candidate items；And/or
Determine that number of clicks is more than in the click record of the news type of the whole network user in the preset time range The click on content of second preset times is candidate items；And/or
Determine that number of visits is more than in the browsing record of the news type of the whole network user in the preset time range The browsing content of third preset times is candidate items.
Specifically, since the web-based history behavior record of the whole network user includes the whole network user in preset time range The browsing record etc. of the search record of news type, the click record of news type, news type.So determining candidate item When mesh, searching times can be filtered out from the search of the news type of the whole network user in preset time range record and be more than The search content of first preset times is candidate items.Such as：It is pre- to be more than first for the searching times of the whole network user in 24 hours If number is (such as：1000 times, it is 5000 inferior) news type search content include news content mark A, it is news network address B, new Content identification B etc. is heard, then news content mark A, news network address B, news content mark B can screen as candidate items, in this reality It applies in example, news content is identified as the news keyword searched for when search news.
It similarly, can be from the point of the news type of the whole network user in preset time range when determining candidate items It is candidate items to hit in record and filter out number of clicks more than the click on content of the second preset times.Such as：It is complete in 24 hours The number of clicks of network users is more than the second preset times (such as：1000 times, it is 5000 inferior) the click on content of news type include News content identifies C, news network address A, news content mark D etc., then news content mark C, news network address A, news content mark Knowing D can also screen as candidate items.
It similarly, can be from the clear of the news type of the whole network user in preset time range when determining candidate items It is candidate items to look at and filter out number of visits in recording more than the browsing content of third preset times.Such as：It is complete in 24 hours The number of visits of network users is more than third preset times (such as：1000 times, it is 5000 inferior) the browsing content of news type include News content identifies E, news network address C, news content mark F etc., then news content mark E, news network address C, news content mark Knowing F can also screen as candidate items.The candidate items determined in this way more meet the actual interest of the whole network user Variation tendency, and then the recommendation information for the news type determined according to candidate items more meets user demand.
In conjunction with above-mentioned three kinds of situations, the whole network user in preset time range can also be considered, a certain content is searched The number summation of rope, click and browsing is more than predetermined threshold value in the number summation, also can be using the content as candidate Project.
In specific implementation process, determine that the mode of candidate items is not limited to aforesaid way, it can also be according to practical need It is set, such as：The web-based history behavior record for only considering the news type of target user, determines that target user searches Rope, click and the more content of number of visits are as candidate items, here, the application is not limited.
Determining candidate items, you can establish user's rating matrix that the whole network user is directed to candidate items, use Family rating matrix can indicate as follows：
In above formula, UiIndicate the user i, I in the whole network userjIt is that user i comments candidate items j for candidate items j, Rij Point.In the present embodiment, user can indicate the scorings of candidate items with Binary Zero and 1, and 0 indicates user to candidate item Mesh is lost interest in, and 1 indicates that user is interested in candidate items.Scoring of the user to candidate items is being determined in this way When, the web-based history behavior record for the news type for calling the user is needed, such as：Search record, when the user searches for the candidate The number of project is more than preset search number, determines that the user is 1 to the scoring of the candidate items.Conversely, when the user searches for The number of the candidate items is less than or equal to preset search number, determines that the user is 0 to the scoring of the candidate items.
Alternatively, the number that the user searches for all candidate items can also be obtained, when the user searches for the candidate items The percentage that number accounts for the number that the user searches for all candidate items is more than preset percentage, determines the user to the candidate item Purpose scoring is 1.Conversely, when the number that the user searches for the candidate items accounts for the number that the user searches for all candidate items Percentage is less than or equal to preset percentage, determines that the user is 0 to the scoring of the candidate items.
It is, of course, also possible to which the number that user is directly searched for certain candidate items accounts for time that the user searches for all candidate items Several percentage is as the user to the score value of the candidate items.In specific implementation process, other modes can also be used Scoring of the user to candidate items is determined, here, the application is not limited.
Further, after establishing user's rating matrix, the method in the present embodiment can be determined according to rating matrix Neighbor user collection similar with target user.It, can be as follows when determining the corresponding neighbor user collection of target user It realizes：
Based on the rating matrix, the similitude of the target user and other users in the whole network user are calculated；Base The similitude of other users in the target user and the whole network user determines that neighbours similar with the target user use Family collection.
Specifically, in the present embodiment, it can be based on the rating matrix of above-mentioned foundation, using Euclidean distance formula meter Calculate target user and the whole network other users Euclidean distance, the Euclidean distance can be used to indicate that the target user and The similitude of other users.Euclidean distance formula isFormula surface user X and user y's Euclidean distance, Rxj are scorings of the user x to candidate items j, and Ryj is scorings of the user y to candidate items j.It is used with target The Euclidean distance at family is bigger, shows that the similitude of the user and target user are higher, the news of the user and target user The hobby of class is more similar.Certainly, in the present embodiment, can also using cosine similarity formula come calculate target user with The similitude of the whole network other users, cosine similarity formula areWherein, VxIt is user x to all candidate items Purpose scoring vector, VyIt is user y vectorial to the scoring of all candidate items.Bigger, the table with the cosine similarity of target user The bright user is more similar to the hobby of the news category of target user.In specific implementation process, target user and its are determined The mode of the similitude of his user can be set according to actual needs, here, the application is not limited.
Further, after determining similitude of the target user with the whole network other users, it may be used but be not limited to following Two ways determines neighbor user collection similar with target user：
First way：Determine similar with target user neighbor user collection include in the whole network user with it is described The similitude of target user is more than the user of the first predetermined threshold value.
Specifically, in the present embodiment, the first predetermined threshold value can be preset, when in the whole network user with target user's When similitude is more than first predetermined threshold value, neighbor user similar with target user can be added into and concentrated, i.e., from the whole network User filters out user of the similarity more than the first predetermined threshold value as neighbor user collection similar with target user.
The second way：Determine similar with target user neighbor user collection include in the whole network user with it is described The similitude of target user arrange from large to small after preceding first preset number user.
Specifically, in the present embodiment, after determining similitude of the target user with the whole network other users, can incite somebody to action It is ranked up from large to small by similitude, then, will come the user of the first preset number of front as with target user Similar neighbor user collection.Such as：The whole network user after being ranked up from large to small by the similitude with target user includes using Family 1, user 3, user 4, user 5, user 2 are determined as neighbor user similar with target user when first preset number is 2 Collection includes user 1, user 3.
In specific implementation process, first in the first predetermined threshold value and the second way in above-mentioned first way Preset number can be set according to actual needs, here, the application is not limited.It is, of course, also possible to using other modes Neighbor user collection is determined, here, the application is not limited.
Further, it after determining neighbor user collection, can be generated to target user's according to the preference of the news category of neighbours Recommended project.Specifically, determining that recommended project can be realized by the following two kinds mode according to neighbor user collection：
First way：Based on the neighbor user collection, determine the target user to each item in the candidate items Purpose interest-degree predicted value；Determine that the project that interest-degree predicted value is more than the second predetermined threshold value in the candidate items is recommendation items The project of preceding second preset number after interest-degree predicted value arranges from large to small in mesh or the determining candidate items is to recommend Project.
Specifically, in the present embodiment, neighbor user collection can be based on, determine target user to each item in candidate items Formula may be used when calculating interest-degree predicted value of the target user to candidate items in purpose interest-degree predicted valueWherein,It is average scores of the target user u to all candidate items, i is neighbor user collection User, ciIt is the similarity between target family u and neighbor user i, rijIt is scorings of the neighbor user i to candidate items j,It is adjacent Occupy average scores of the user i to all candidate items.
In this way, the second predetermined threshold value can be preset, by that can determine target user to institute by above-mentioned formula There is the interest-degree predicted value of candidate items, and then filters out interest-degree predicted value of the target user to it from all candidate items Project more than the second predetermined threshold value is recommended project.
Alternatively, after determining target user to the interest-degree predicted value of each candidate items, candidate items can be pressed Interest-degree predicted value is ranked up from large to small, then, will come the candidate items of the second preset number of front as recommendation Project.Such as：Candidate items after being ranked up from large to small by interest-degree predicted value include project 1, project 3, project 4, item Mesh 5, project 2 determine that recommended project includes project 1, project 3, project 4 when second preset number is 3.
The second way：Determine all neighbor users of the neighbor user concentration to each project in the candidate items Weighted average interest-degree；Determine that the project that weighted average interest-degree is more than third predetermined threshold value in the candidate items is to recommend Project determines that the project of the preceding third preset number after weighted average interest-degree arranges from large to small in the candidate items is Recommended project.
Specifically, in the present embodiment, each candidate items can be directed to, determine that all neighbours that neighbor user is concentrated use To the weighted average interest-degree of the candidate items, weighting coefficient can be set according to actual needs at family, here, the application is not It is limited.In turn, third predetermined threshold value can be preset, since all neighbor users can be determined to each candidate items Weighted average interest-degree, and then filter out from all candidate items the item that weighted average interest-degree is more than third predetermined threshold value Mesh is recommended project.
Alternatively, after determining the weighted average interest-degree of each candidate items, candidate items can be pressed weighted average Interest-degree is ranked up from large to small, then, will come the candidate items of the third preset number of front as recommended project.Than Such as：Candidate items after being ranked up from large to small by weighted average interest-degree include project 1, project 3, project 4, project 5, item Mesh 2 determines that recommended project includes project 1, project 3, project 4 when third preset number is 3.
After determining recommended project, it is also necessary to determine pushing away for news type corresponding with target user based on recommended project Recommend information.Specifically, the recommendation information of the news type includes candidate search word corresponding with the recommended project and/or net Page link.
Specifically, in the present embodiment, the recommended project determined may be the search term or news of some news types Type website, so, the recommendation information for recommending the news type of target user includes candidate search corresponding with recommended project Word and/or web page interlinkage.Such as：Recommended project includes the title of news website A, news content mark B, recommends target user News type recommendation information be news website A network address and news content identify the corresponding candidate search words of B, Huo Zhewei The news report link etc. of the corresponding candidate search word of title and news content the mark B of news website A, target user can be with Candidate search word is clicked directly on, and then obtains the search result of the candidate search word.Target user can click directly on recommendation Web page interlinkage, into the corresponding website of the web page interlinkage.In specific implementation process, according to the recommendation information of recommended project determination It can be set according to actual needs, here, the application is not limited.
Further, in the present embodiment, the recommendation information of the news type specifically include user can directly browse it is new Object is heard, the method further includes：User is responded to the trigger action of the news object, it is corresponding to load the news object Browse webpage.
Specifically, in the present embodiment, the recommended project determined is also possible to be some news objects, so, it recommends The recommendation information of the news type of target user includes that the browsing of news object corresponding with recommended project links.Such as：News News browsing link of content identification B etc., target user can go to its browsing net by clicking directly on the news object of recommendation Page link, and then can the interested news of fast browsing.
Further, in step s 103, the recommendation information by the news type is needed to be illustrated in and the news type The corresponding result of page searching of search content in.When showing the recommendation information of news type, news category can be illustrated in Below the corresponding search result of search content of type, further, the recommendation information for the news type determined in the present embodiment can To be illustrated in the lower section of the first item result in search result.Such as：Target user initiates the search of search news website A titles When, search result includes the official website network address and other continuous item search results of news website A, through this embodiment in side The recommendation information for the news type that method is determined can be illustrated in the lower section of the official website network address item of news website A, be convenient for user It checks.
Further, in the present embodiment, it is illustrated in and the news type by the recommendation information of the news type The corresponding result of page searching of content is searched for, can also be achieved by the steps of：
Searching for the news type searched for the target user is determined from the recommendation information of the news type The relevant recommendation information of rope content；By the relevant recommendation of search content for the news type searched for the target user Breath is illustrated in result of page searching corresponding with the search content of the news type.
Specifically, in the present embodiment, in order to enable the news type information of push is anticipated closer to the news browsing of user Figure, more meets the news browsing demand of user, when showing the recommendation information of news type, can be determined from based on recommended project Recommendation information in determine that the relevant recommendation information of search content searched for target user pushes.Such as：Target is used After the search of news website A is initiated at family, news type that the web-based history behavior of the news type based on the whole network user is determined Recommendation information include news website B, news content mark A, news content mark B and news content mark C when, if newly The news network address that website A is finance and economic is heard, and news website B is the news network address for entertaining class, it is political class that news content, which identifies A, News content mark, news content mark B and news content mark C are finance and economic news content mark, then can will be new It hears content identification B and the corresponding recommendation informations of news content mark C is illustrated in the page of search result, specifically, can be with It is illustrated in the lower section of the official website search result of news website A, prediction user may books news content mark interested.
For another example：After target user initiates the search of news content mark D, the history net of the news type based on the whole network user The recommendation information for the news type that network behavior is determined include news website B, news content mark A, news content mark B and When news content identifies C, if news content mark D is the content identification for entertaining class, news website B is the News Network of finance and economic Location, news content identify the news content mark that A is political class, and news content mark B and news content mark C are amusement Class news content identifies, then news content can be identified to B and the corresponding recommendation informations of news content mark C are illustrated in search knot In the page of fruit, specifically, the lower section of the official website search result of news website A can be illustrated in, prediction user may be interested News.In this way, can will search for the relevant recommendation information of content with target user is pushed to target user so that target user's energy It is enough that interested news content is quickly located by the information recommended, promote user experience.
Further, the method in the present embodiment can also will search for the higher recommendation of the content degree of correlation with target user Breath is illustrated in front, will search for the lower recommendation information of the content degree of correlation with target user and be illustrated in below, such as：Target user After the search for initiating news content mark D, news category that the web-based history behavior of the news type based on the whole network user is determined When the recommendation information of type includes news website B, news content mark A, news content mark B and news content mark C, if News content mark D is the content identification for entertaining class, and news website B is the news network address of finance and economic, and it is political affairs that news content, which identifies A, The news content mark of class is controlled, news content mark B and news content mark C are amusement class news content mark.It is opening up When showing recommendation information, news content can be identified to B and the corresponding recommendation informations of news content mark C show forefront, rear Show that news website B, news content identify A.It is shown in this way, the higher recommendation information of the content degree of correlation will be searched for target user In most eye-catching location push to target user, the target user that enables is quickly located interested by the information of recommendation News content, promoted user experience.
News information method for pushing in the present embodiment can initiate news website, news content mark etc. in target user After relevant inquiry, the search need of the news category of preposition user predicts the next interested news content of user, energy The search efficiency and user experience of significant increase search engine.
Fig. 2 is referred to, the second embodiment of the present invention provides a kind of news information method for pushing, including：
S201：In the search content for detecting target user's search news type, the news of the whole network user is extracted The web-based history behavior record of type；
S202：The web-based history behavior record of news type based on the whole network user determines and the target user Similar similar users collection；
S203：The information of the interested news type of each similar users, determining and institute are concentrated based on the similar users State the recommendation information of the corresponding news type of target user；
S204：The recommendation information of the news type is illustrated in search corresponding with the search content of the news type In results page.
Specifically, in the present embodiment, news information method for pushing is mainly used in the server end of search engine, when So, client can also be applied to.User when client inputs the search content of news type by search engine, draw by search It holds up the server of the search content transmission of the news type to search engine, when server receives the search of the news type After content, corresponding search result is retrieved.On this basis, server can also obtain the history of the news type of the whole network user Network behavior is noted down, and determines similar users collection similar with target user, the similar users concentrated further according to similar users The web-based history behavior record of news type predicts the search need of the potential news type of user, further determines that out user The recommendation information of relevant news type can be by the recommendation of the relevant news type of user when scanning for result displaying Breath is together with displaying.In this way, by the search need of preposition user's news type in the search of user's initiation news type, greatly The search efficiency and user experience for promoting search engine provide personalized search recommendation results, increase the change of search engine Existing efficiency and user's viscosity.
Further, in the present embodiment, the search content of above-mentioned steps S201, the news type include News Network's station name Claim, any one or more in news website link and news content mark combines.
Specifically, in the present embodiment, initiating the search content of search news type in target user, triggering is held News information method for pushing in row the present embodiment, such as：Title, new of the target user in search site search news website A In the case of hearing network address or the news content mark A of website B, the news information method for pushing executed in the present embodiment can be triggered, The recommendation information of personalized news type is pushed for user.In specific implementation process, the search content of news type includes Any one or more in news network address title news website links and news content mark title combines, it is, of course, also possible to be Other content, here, the application does not limit.
Method in the present embodiment can just be triggered in the search content for initiating search news type, can be effective Avoid to search for non-news type and carry out related push, cause the interference to user, can further reduce equipment Data transmission is born, and the Experience Degree of user is improved.
Further, after the news information method for pushing in the present embodiment is triggered, step S201 is in specific implementation process In, it can be achieved by the steps of：
Obtain the search record of the news type of the whole network user in preset time range, the click record of news type It is combined with any one or more in the browsing record of news type.
Specifically, in the present embodiment, need to obtain preset time range (such as：1 hour, 5 hours, 24 hours etc.) in The whole network user news type search record, news type click record and news type browsing record in it is any one Kind or multiple combinations.Such as：The search record of news type can be that the whole network user searches for News Network in preset time range The record that any one or more in station name, news website link and news content mark combines.Such as：In user A away from working as It was searched in the case of the title of site search news website A before 20 minutes preceding moment, determines that this is recorded as the news category of the whole network user The search of type records.
For another example：News type click record can be the whole network user click in preset time range news network address, The record that any one or more in news website links and news links combines.Such as：In user B at 30 minutes away from current time In the case of preceding click news website B, determine that this is recorded as the click of the news type of the whole network user record.
For another example：The browsing record of news type can be the news network address that the whole network user browses in preset time range And/or the record of news links.Such as：The news content mark of news website B is browsed before away from 30 minutes current times in user C In the case of A, determines that this is recorded as the browsing of the news type of the whole network user record, recording the clear of the news type of the whole network user Look at record when, in order to ensure record validity, it is also contemplated that browsing duration, i.e., will browsing duration be more than preset duration (such as： 1 minute, 5 minutes etc.) news content mark browsing be denoted as the whole network user news type browsing record.
In this way, the web-based history behavior record of the news type of the whole network user can effectively be counted.
Further, it after getting the web-based history behavior record of the news type of the whole network user, executes in the present embodiment Step S202 needs the web-based history behavior record of the news type based on the whole network user, determines phase similar with target user Collect like user.
Specifically, in the present embodiment, the historical search with target user in the whole network user, history can be clicked and/ Or the similar user of content of historical viewings is as similar users.Such as：The historical search of the news type of target user, history Click and/or historical impressions are most four be A news contents mark, B news contents mark, C news contents mark, D News content identifies.If the search of the whole network user's history, history are clicked and/or what historical impressions were most includes in A news Hold in mark, B news contents mark, C news contents mark, D news contents mark arbitrary three, you can determine that the user is Similar users can form similar users collection in this way.Again alternatively, can also use in aforementioned first embodiment The method referred to determines similar users collection, specifically repeats no more, referring to previous embodiment.
In turn, after determining similar users collection, step S203 is executed, each similar users are concentrated based on similar users The information of interested news type determines the recommendation information of news type corresponding with the target user.
Specifically, in the present embodiment, each interested news type of similar users can be concentrated according to similar users Information, determine the information of the news type of common interest, the information of the news type of common interest be pushed to mesh Mark user.Such as：Similar users collection includes user 1, user 2, user 3 and user 4, the letter of 1 interested news type of user Breath includes A news network address, B news contents mark and C news contents mark, and the information of 2 interested news type of user includes A News network address, B news contents mark and D news contents mark, the information of 3 interested news type of user includes A News Networks Location, B news contents mark and E news contents mark, the information of 4 interested news type of user include B news network address, C new Content identification and E news contents mark are heard, when there are predetermined number similar users interested in same information, determines the information To recommend the information of target user.When predetermined number is set as 2, then A news network address, B news contents mark, C news contents Mark and E news contents identify the recommendation information that corresponding information is news type.
Certainly, in specific implementation process, determine that the recommendation information of similar users collection and news type can be according to reality It needs to be configured, here, the application is not limited.
It, can be by the recommendation information of the news type and search result together with exhibition after determining the recommendation information of news type Show, the mode of displaying can refer to the mode in first embodiment, here, the application does not repeat.
Fig. 3 is please referred to, third embodiment of the invention additionally provides a kind of news information pusher, including：
Acquiring unit 301, in the search content for detecting target user's search news type, extracting the whole network The web-based history behavior record of the news type of user；
Determination unit 302 is used for the web-based history behavior record of the news type based on the whole network user, determining and institute State the recommendation information of the corresponding news type of target user；
Display unit 303, for by the recommendation information of the news type be illustrated in in the search of the news type Hold in corresponding result of page searching.
Specifically, in the present embodiment, news information pusher can be arranged in the server, can also be arranged and move Dynamic terminal device, such as mobile phone, tablet computer, laptop equipment, can also be the equipment such as desktop computer, certainly can be with It is other electronic equipments, here, the application is not limited.The mode that news information pusher carries out news information push exists It is described in detail in aforementioned first embodiment, here, this embodiment is not repeated.
As a kind of optional embodiment, the determination unit 302 includes：
First determining module is used for the web-based history behavior record of the news type based on the whole network user, determines Candidate items；
Second determining module establishes user for determining each scoring of the user to candidate items in the whole network user Rating matrix；
Third determining module, for be based on the rating matrix, determine in the whole network user with target user's phase As neighbor user collection；
4th determining module determines recommended project for being based on the neighbor user collection from the candidate items；
5th determining module, for determining that recommendation information corresponding with the recommended project is corresponding with the target user News type recommendation information.
As a kind of optional embodiment, the acquiring unit 301 is used for：
Obtain the search record of the news type of the whole network user in preset time range, the click record of news type It is combined with any one or more in the browsing record of news type.
As a kind of optional embodiment, first determining module is used for：
Determine that searching times are more than in the search record of the news type of the whole network user in the preset time range The search content of first preset times is candidate items；And/or
Determine that number of clicks is more than in the click record of the news type of the whole network user in the preset time range The click on content of second preset times is candidate items；And/or
Determine that number of visits is more than in the browsing record of the news type of the whole network user in the preset time range The browsing content of third preset times is candidate items.
As a kind of optional embodiment, the third determining module is used for：
Based on the rating matrix, the similitude of the target user and other users in the whole network user are calculated；
Based on the similitude of other users in the target user and the whole network user, determine and target user's phase As neighbor user collection.
As a kind of optional embodiment, the third determining module is used for：
Determine similar with target user neighbor user collection include in the whole network user with the target user Similitude is more than the user of the first predetermined threshold value.
As a kind of optional embodiment, the third determining module is used for：
Determine similar with target user neighbor user collection include in the whole network user with the target user Similitude arrange from large to small after preceding first preset number user.
As a kind of optional embodiment, the 4th determining module is used for：
Based on the neighbor user collection, determine that the target user is pre- to the interest-degree of each project in the candidate items Measured value；
Determine that the project that interest-degree predicted value is more than the second predetermined threshold value in the candidate items is recommended project or determination The project of preceding second preset number after interest-degree predicted value arranges from large to small in the candidate items is recommended project.
As a kind of optional embodiment, the 4th determining module is used for：
Determine weighted average of all neighbor users to each project in the candidate items of the neighbor user concentration Interest-degree；
Determine that project that weighted average interest-degree in the candidate items is more than third predetermined threshold value is recommended project or really The project of preceding third preset number after weighted average interest-degree arranges from large to small in the fixed candidate items is recommended project.
As a kind of optional embodiment, the display unit is used for：
The recommendation information of the news type is illustrated under the corresponding search result of search content of the news type Side, the recommendation information of the news type includes candidate search word corresponding with the recommended project and/or web page interlinkage.
As a kind of optional embodiment, the search content of the news type includes：News website title, news website Any one or more in link and news content mark combines.
As a kind of optional embodiment, the display unit is used for：
Searching for the news type searched for the target user is determined from the recommendation information of the news type The relevant recommendation information of rope content；
The relevant recommendation information of search content for the news type searched for the target user is illustrated in and institute State the corresponding result of page searching of search content of news type.
As a kind of optional embodiment, the recommendation information of the news type specifically include user can directly browse it is new Object is heard, described device further includes：
Response unit, the trigger action for responding user to the news object, it is corresponding to load the news object Browse webpage.
Fig. 4 is please referred to, third embodiment of the invention additionally provides a kind of news information pusher, including：
Acquiring unit 401 is used to, in the search content for detecting target user's search news type, extract the whole network The web-based history behavior record of the news type of user；
First determination unit 402 is used for the web-based history behavior record of the news type based on the whole network user, determines Similar users collection similar with the target user；
Second determination unit 402, for concentrating each interested news type of similar users based on the similar users Information, determine the recommendation information of corresponding with target user news type；
Display unit 403, for by the recommendation information of the news type be illustrated in in the search of the news type Hold in corresponding result of page searching.
Specifically, in the present embodiment, news information pusher can be arranged in the server, can also be arranged and move Dynamic terminal device, such as mobile phone, tablet computer, laptop equipment, can also be the equipment such as desktop computer, certainly can be with It is other electronic equipments, here, the application is not limited.The mode that news information pusher carries out news information push exists It is described in detail in aforementioned second embodiment, here, this embodiment is not repeated.
Fifth embodiment of the invention additionally provides a kind of electronic equipment, for convenience of description, illustrates only and present invention reality The relevant part of example is applied, particular technique details does not disclose, please refers to present invention method part.The electronic equipment can be with Can also be that (Personal Digital Assistant, individual digital help including mobile phone, tablet computer, PDA for server Reason), POS (Point of Sales, point-of-sale terminal), the arbitrary electronic equipment such as vehicle-mounted computer, by taking electronic equipment is mobile phone as an example：
Fig. 5 shows the block diagram with the part-structure of the relevant mobile phone of electronic equipment provided in an embodiment of the present invention.Ginseng Fig. 5 is examined, mobile phone includes：Radio frequency (Radio Frequency, RF) circuit 510, memory 520, input unit 530, display unit 540, sensor 550, voicefrequency circuit 560, Wireless Fidelity (wireless-fidelity, Wi-Fi) module 570, processor 580, And the equal components of power supply 590.It will be understood by those skilled in the art that handset structure shown in Fig. 5 is not constituted to mobile phone It limits, may include either combining certain components or different components arrangement than illustrating more or fewer components.
Each component parts of mobile phone is specifically introduced with reference to Fig. 5：
RF circuits 510 can be used for receiving and sending messages or communication process in, signal sends and receivees, particularly, by base station After downlink information receives, handled to processor 580；In addition, the data for designing uplink are sent to base station.In general, RF circuits 510 Including but not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier (Low Noise Amplifier, LNA), duplexer etc..In addition, RF circuits 510 can also be communicated with network and other equipment by radio communication. Above-mentioned wireless communication can use any communication standard or agreement, including but not limited to global system for mobile communications (Global System of Mobile communication, GSM), general packet radio service (General Packet Radio Service, GPRS), CDMA (Code Division Multiple Access, CDMA), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA), long term evolution (Long Term Evolution, LTE), Email, short message service (Short Messaging Service, SMS) etc..
Memory 520 can be used for storing software program and module, and processor 580 is stored in memory 520 by operation Software program and module, to execute various function application and the data processing of mobile phone.Memory 520 can include mainly Storing program area and storage data field, wherein storing program area can storage program area, the application journey needed at least one function Sequence (such as sound-playing function, image player function etc.) etc.；Storage data field can be stored to be created according to using for mobile phone Data (such as audio data, phone directory etc.) etc..It, can be in addition, memory 520 may include high-speed random access memory Including nonvolatile memory, for example, at least a disk memory, flush memory device or other volatile solid-states Part.
Input unit 530 can be used for receiving the number or character information of input, and generate with the user setting of mobile phone with And the related key signals input of function control.Specifically, input unit 530 may include that touch panel 531 and other inputs are set Standby 532.Touch panel 531, also referred to as touch screen, collect user on it or neighbouring touch operation (such as user use The operation of any suitable object or attachment such as finger, stylus on touch panel 531 or near touch panel 531), and root Corresponding attachment device is driven according to preset formula.Optionally, touch panel 531 may include touch detecting apparatus and touch Two parts of controller.Wherein, the touch orientation of touch detecting apparatus detection user, and the signal that touch operation is brought is detected, Transmit a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and is converted into touching Point coordinates, then give processor 580, and order that processor 580 is sent can be received and executed.Furthermore, it is possible to using electricity The multiple types such as resistive, condenser type, infrared ray and surface acoustic wave realize touch panel 531.In addition to touch panel 531, input Unit 530 can also include other input equipments 532.Specifically, other input equipments 532 can include but is not limited to secondary or physical bond It is one or more in disk, function key (such as volume control button, switch key etc.), trace ball, mouse, operating lever etc..
Display unit 540 can be used for showing information input by user or be supplied to user information and mobile phone it is various Menu.Display unit 540 may include display panel 541, optionally, liquid crystal display (Liquid Crystal may be used Display, LCD), the forms such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) it is aobvious to configure Show panel 541.Further, touch panel 531 can cover display panel 541, when touch panel 531 detect it is on it or attached After close touch operation, processor 580 is sent to determine the type of touch event, is followed by subsequent processing device 580 according to touch event Type corresponding visual output is provided on display panel 541.Although in Figure 5, touch panel 531 and display panel 541 It is that input and the input function of mobile phone are realized as two independent components, but in some embodiments it is possible to by touch-control Panel 531 and display panel 541 are integrated and that realizes mobile phone output and input function.
Mobile phone may also include at least one sensor 550, such as optical sensor, motion sensor and other sensors. Specifically, optical sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can be according to ambient light Light and shade adjust the brightness of display panel 541, proximity sensor can close display panel 541 when mobile phone is moved in one's ear And/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (generally three axis) acceleration Size, size and the direction of gravity are can detect that when static, can be used to identify the application of mobile phone posture, (for example horizontal/vertical screen is cut Change, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；May be used also as mobile phone The other sensors such as gyroscope, barometer, hygrometer, thermometer, the infrared sensor of configuration, details are not described herein.
Voicefrequency circuit 560, loud speaker 561, microphone 562 can provide the audio interface between user and mobile phone.Audio-frequency electric The transformed electric signal of the audio data received can be transferred to loud speaker 561 by road 560, and sound is converted to by loud speaker 561 Signal exports；On the other hand, the voice signal of collection is converted to electric signal by microphone 562, is turned after being received by voicefrequency circuit 560 It is changed to audio data, then by after the processing of audio data output processor 580, through RF circuits 510 to be sent to such as another mobile phone, Or audio data is exported to memory 520 to be further processed.
WiFi belongs to short range wireless transmission technology, and mobile phone can help user's transceiver electronics postal by WiFi module 570 Part, browsing webpage and access streaming video etc., it has provided wireless broadband internet to the user and has accessed.Although Fig. 5 is shown WiFi module 570, but it is understood that, and it is not belonging to must be configured into for mobile phone, it can not change as needed completely Become in the range of the essence of invention and omits.
Processor 580 is the control centre of mobile phone, using the various pieces of various interfaces and connection whole mobile phone, is led to It crosses operation or executes the software program and/or module being stored in memory 520, and call and be stored in memory 520 Data execute the various functions and processing data of mobile phone, to carry out integral monitoring to mobile phone.Optionally, processor 580 can wrap Include one or more processing units；Preferably, processor 580 can integrate application processor and modem processor, wherein answer With the main processing operation system of processor, user interface and application program etc., modem processor mainly handles wireless communication. It is understood that above-mentioned modem processor can not also be integrated into processor 580.
Mobile phone further includes the power supply 590 (such as battery) powered to all parts, it is preferred that power supply can pass through power supply pipe Reason system and processor 580 are logically contiguous, to realize management charging, electric discharge and power managed by power-supply management system Etc. functions.
Although being not shown, mobile phone can also include camera, bluetooth module etc., and details are not described herein.
In embodiments of the present invention, the processor 580 is also with the following functions：
The web-based history behavior record of news type based on the whole network user, determines candidate items；
It determines each scoring of the user to candidate items in the whole network user, establishes user's rating matrix；
Based on the rating matrix, neighbor user collection similar with the target user in the whole network user is determined；
Based on the neighbor user collection, recommended project is determined from the candidate items；
Determine recommendation of the recommendation information corresponding with the recommended project for news type corresponding with the target user Information.
In embodiments of the present invention, the processor 580 is also with the following functions：
Obtain the search record of the news type of the whole network user in preset time range, the click record of news type It is combined with any one or more in the browsing record of news type.
In embodiments of the present invention, the processor 580 is also with the following functions：
Determine that searching times are more than in the search record of the news type of the whole network user in the preset time range The search content of first preset times is candidate items；And/or
Determine that number of clicks is more than in the click record of the news type of the whole network user in the preset time range The click on content of second preset times is candidate items；And/or
Determine that number of visits is more than in the browsing record of the news type of the whole network user in the preset time range The browsing content of third preset times is candidate items.
In embodiments of the present invention, the processor 580 is also with the following functions：
Based on the rating matrix, the similitude of the target user and other users in the whole network user are calculated；
Based on the similitude of other users in the target user and the whole network user, determine and target user's phase As neighbor user collection.
In embodiments of the present invention, the processor 580 is also with the following functions：
Determine similar with target user neighbor user collection include in the whole network user with the target user Similitude is more than the user of the first predetermined threshold value.
In embodiments of the present invention, the processor 580 is also with the following functions：
Determine similar with target user neighbor user collection include in the whole network user with the target user Similitude arrange from large to small after preceding first preset number user.
In embodiments of the present invention, the processor 580 is also with the following functions：
Based on the neighbor user collection, determine that the target user is pre- to the interest-degree of each project in the candidate items Measured value；
Determine that the project that interest-degree predicted value is more than the second predetermined threshold value in the candidate items is recommended project or determination The project of preceding second preset number after interest-degree predicted value arranges from large to small in the candidate items is recommended project.
In embodiments of the present invention, the processor 580 is also with the following functions：
Determine weighted average of all neighbor users to each project in the candidate items of the neighbor user concentration Interest-degree；
Determine that project that weighted average interest-degree in the candidate items is more than third predetermined threshold value is recommended project or really The project of preceding third preset number after weighted average interest-degree arranges from large to small in the fixed candidate items is recommended project.
In embodiments of the present invention, the processor 580 is also with the following functions：
The recommendation information of the news type is illustrated under the corresponding search result of search content of the news type Side, the recommendation information of the news type includes candidate search word corresponding with the recommended project and/or web page interlinkage.
In embodiments of the present invention, the search content of the news type includes：News website title, news website link Any one or more in being identified with news content combines.
In embodiments of the present invention, the processor 580 is also with the following functions：
Searching for the news type searched for the target user is determined from the recommendation information of the news type The relevant recommendation information of rope content；
The relevant recommendation information of search content for the news type searched for the target user is illustrated in and institute State the corresponding result of page searching of search content of news type.
In embodiments of the present invention, the recommendation information of the news type specifically includes the news pair that user can directly browse As the processor 580 is also with the following functions：
User is responded to the trigger action of the news object, loads the corresponding browsing webpage of the news object.
Sixth embodiment of the invention provides a kind of computer readable storage medium, is stored thereon with computer program, this If inventing the integrated functional unit of the news information pusher in the third and fourth embodiment with SFU software functional unit Form realize and when sold or used as an independent product, can be stored in a computer read/write memory medium. Based on this understanding, the present invention realizes all or part in the news information method for pushing of above-mentioned the first and second embodiments Flow can also instruct relevant hardware to complete by computer program, and the computer program can be stored in a meter In calculation machine readable storage medium storing program for executing, the computer program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method Suddenly.Wherein, the computer program includes computer program code, the computer program code can be source code form, Object identification code form, executable file or certain intermediate forms etc..The computer-readable medium may include：Institute can be carried State computer program code any entity or device, medium, USB flash disk, mobile hard disk, magnetic disc, CD, computer storage, only Memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electricity is read to carry Wave signal, telecommunication signal and software distribution medium etc..It should be noted that the content that the computer-readable medium includes can To carry out increase and decrease appropriate according to legislation in jurisdiction and the requirement of patent practice, such as in certain jurisdictions, root According to legislation and patent practice, computer-readable medium does not include electric carrier signal and telecommunication signal.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies Within, then the present invention is also intended to include these modifications and variations.

Claims (10)

1. a kind of news information method for pushing, which is characterized in that including：
In the search content for detecting target user's search news type, the history of the news type of the whole network user is extracted Network behavior records；
The web-based history behavior record of news type based on the whole network user determines news corresponding with the target user The recommendation information of type；
The recommendation information of the news type is illustrated in result of page searching corresponding with the search content of the news type In.
2. the method as described in claim 1, which is characterized in that the history net of the news type based on the whole network user Network behavior record determines the recommendation information of news type corresponding with the target user, including：
The web-based history behavior record of news type based on the whole network user, determines candidate items；
It determines each scoring of the user to candidate items in the whole network user, establishes user's rating matrix；
Based on the rating matrix, neighbor user collection similar with the target user in the whole network user is determined；
Based on the neighbor user collection, recommended project is determined from the candidate items；
Determine recommendation information corresponding with the recommended project for the recommendation information of news type corresponding with the target user.
3. method as claimed in claim 1 or 2, which is characterized in that the web-based history behavior record for obtaining the whole network user, Including：
The search of the news type of the whole network user of acquisition in preset time range records, the click of news type records and new Any one or more in the browsing record of type is heard to combine.
4. method as described in any one of claims 1-3, which is characterized in that the news type based on the whole network user Web-based history behavior record determines candidate items, including：
Determine that searching times are more than first in the search record of the news type of the whole network user in the preset time range The search content of preset times is candidate items；And/or
Determine that number of clicks is more than second in the click record of the news type of the whole network user in the preset time range The click on content of preset times is candidate items；And/or
Determine that number of visits is more than third in the browsing record of the news type of the whole network user in the preset time range The browsing content of preset times is candidate items.
5. the method as described in claim 1-4 is any, which is characterized in that it is described to be based on the rating matrix, it determines described complete Neighbor user collection similar with the target user in network users, including：
Based on the rating matrix, the similitude of the target user and other users in the whole network user are calculated；
Based on the similitude of other users in the target user and the whole network user, determination is similar with the target user Neighbor user collection.
6. a kind of news information method for pushing, which is characterized in that including：
In the search content for detecting target user's search news type, the history of the news type of the whole network user is extracted Network behavior records；
The web-based history behavior record of news type based on the whole network user, determination are similar similar to the target user User collects；
The information of the interested news type of each similar users is concentrated based on the similar users, is determined and the target user The recommendation information of corresponding news type；
The recommendation information of the news type is illustrated in result of page searching corresponding with the search content of the news type In.
7. a kind of news information pusher, which is characterized in that including：
Acquiring unit, in the search content for detecting target user's search news type, extracting the whole network user's The web-based history behavior record of news type；
Determination unit is used for the web-based history behavior record of the news type based on the whole network user, determines and the target The recommendation information of the corresponding news type of user；
Display unit, it is corresponding with the search content of the news type for being illustrated in the recommendation information of the news type In result of page searching.
8. a kind of news information pusher, which is characterized in that including：
Acquiring unit, in the search content for detecting target user's search news type, extracting the whole network user's The web-based history behavior record of news type；
First determination unit, be used for the news type based on the whole network user web-based history behavior record, determine with it is described The similar similar users collection of target user；
Second determination unit, the information for concentrating the interested news type of each similar users based on the similar users, Determine the recommendation information of news type corresponding with the target user；
Display unit, it is corresponding with the search content of the news type for being illustrated in the recommendation information of the news type In result of page searching.
9. a kind of electronic equipment, which is characterized in that including processor and memory：
The memory is used to store the program that perform claim requires any one of 1 to 6 the method；
The processor is configurable for executing the program stored in the memory.
10. a kind of computer storage media, which is characterized in that the calculating for being stored as used in above-mentioned news information pusher Machine software instruction, it includes be the program designed by news information pusher for executing above-mentioned aspect.
CN201810150326.0A 2018-02-13 2018-02-13 A kind of news information method for pushing, device and electronic equipment Pending CN108415996A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810150326.0A CN108415996A (en) 2018-02-13 2018-02-13 A kind of news information method for pushing, device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810150326.0A CN108415996A (en) 2018-02-13 2018-02-13 A kind of news information method for pushing, device and electronic equipment

Publications (1)

Publication Number Publication Date
CN108415996A true CN108415996A (en) 2018-08-17

Family

ID=63128696

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810150326.0A Pending CN108415996A (en) 2018-02-13 2018-02-13 A kind of news information method for pushing, device and electronic equipment

Country Status (1)

Country Link
CN (1) CN108415996A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112417302A (en) * 2020-12-08 2021-02-26 六晟信息科技(杭州)有限公司 Big data-based information content intelligent analysis recommendation processing system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101828393A (en) * 2007-08-24 2010-09-08 谷歌公司 Recommendation based on medium
CN102780920A (en) * 2011-07-05 2012-11-14 上海奂讯通信安装工程有限公司 Television program recommending method and system
CN104572825A (en) * 2014-12-04 2015-04-29 百度在线网络技术（北京）有限公司 Method and device for recommending information
CN106651546A (en) * 2017-01-03 2017-05-10 重庆邮电大学 Intelligent community oriented electronic commerce information recommendation method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101828393A (en) * 2007-08-24 2010-09-08 谷歌公司 Recommendation based on medium
CN102780920A (en) * 2011-07-05 2012-11-14 上海奂讯通信安装工程有限公司 Television program recommending method and system
CN104572825A (en) * 2014-12-04 2015-04-29 百度在线网络技术（北京）有限公司 Method and device for recommending information
CN106651546A (en) * 2017-01-03 2017-05-10 重庆邮电大学 Intelligent community oriented electronic commerce information recommendation method

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112417302A (en) * 2020-12-08 2021-02-26 六晟信息科技(杭州)有限公司 Big data-based information content intelligent analysis recommendation processing system
CN112417302B (en) * 2020-12-08 2021-06-04 六晟信息科技(杭州)有限公司 Big data-based information content intelligent analysis recommendation processing system

Similar Documents

Publication Publication Date Title
CN108388630A (en) A kind of shopping information method for pushing, device and electronic equipment
CN106528745B (en) Method and device for recommending resources on mobile terminal and mobile terminal
CN104239535B (en) A kind of method, server, terminal and system for word figure
CN108073605B (en) Method and device for loading and pushing service data and generating interactive information
CN104244032B (en) Push the method and apparatus of multi-medium data
CN108399232A (en) A kind of information-pushing method, device and electronic equipment
CN107948748B (en) Method, device, mobile terminal and computer storage medium for recommending videos
CN103605656B (en) A kind of method, apparatus for recommending music and a kind of mobile terminal
CN108388629A (en) A kind of multimedia information push method, device and electronic equipment
CN103914502B (en) The method and its terminal of the intelligent search service of use situation identification
CN108156508B (en) Barrage information processing method and device, mobile terminal, server and system
CN103501485B (en) Push the method, apparatus and terminal device of application
CN108038192A (en) Application searches method and apparatus, electronic equipment, computer-readable recording medium
WO2021003673A1 (en) Content pushing method and related product
CN106131627A (en) A kind of method for processing video frequency, Apparatus and system
CN103313139A (en) History display method and device and electronic device
CN110321474A (en) Recommended method, device, terminal device and storage medium based on search term
CN107977431A (en) Image processing method, device, computer equipment and computer-readable recording medium
CN108492836A (en) A kind of voice-based searching method, mobile terminal and storage medium
CN108573064A (en) Information recommendation method, mobile terminal, server and computer readable storage medium
CN106033467A (en) Image file sharing method and device
CN104965831B (en) A kind of network address error correction method, server, terminal and system
CN104281610B (en) The method and apparatus for filtering microblogging
CN106791185A (en) Method for managing contact person information, device and mobile terminal
CN108897846A (en) Information search method, equipment and computer readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20180817

RJ01 Rejection of invention patent application after publication