CN104391999B - Information recommendation method and device - Google Patents
Information recommendation method and device Download PDFInfo
- Publication number
- CN104391999B CN104391999B CN201410779044.9A CN201410779044A CN104391999B CN 104391999 B CN104391999 B CN 104391999B CN 201410779044 A CN201410779044 A CN 201410779044A CN 104391999 B CN104391999 B CN 104391999B
- Authority
- CN
- China
- Prior art keywords
- information
- click
- classification
- user
- data
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 241001269238 Data Species 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000013515 script Methods 0.000 description 4
- 230000007306 turnover Effects 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of information recommendation method and device.Wherein, the information recommendation method includes：Obtain the current click information of user；Classification according to belonging to current click information searches the association classification associated with classification；Hot information is searched from the other information of association class；And recommend the hot information to user.By the present invention, solve the problems, such as to have reached the effect for accurately recommending customized information to user to user's recommendation information inaccuracy in the prior art.
Description
Technical field
The present invention relates to internet arena, in particular to a kind of information recommendation method and device.
Background technology
Big data with a main trend for being internet development.Currently, website can be collected into the number of users of magnanimity
According to increasing portal website's selection commending system is experienced to improve the access of user.Commending system can be according to user's
History or other users data are accessed, the recommendation of personalization is done for each user.The news portal net of present most domestic
Stand or traditional fixed mode：Homepage is divided into fixed recommendation plate, and each column has different news links, owns
The user page seen be just as.But the actual interest of user is different, the user so to different interest
Recommend identical information method can not accurate match user interest, be not the recommendation done according to the interest of user, can not
Reach and improve the effect that user accesses experience.
For in the prior art to user's recommendation information inaccuracy the problem of, not yet propose effective solution at present.
The content of the invention
It is a primary object of the present invention to provide a kind of information recommendation method and device, to solve in the prior art to user
The problem of recommendation information inaccuracy.
To achieve these goals, a kind of one side according to embodiments of the present invention, there is provided information recommendation method.Root
Information recommendation method according to the present invention includes：Obtain the current click information of user；According to belonging to the current click information
Classification searches the association classification associated with the classification；Hot information is searched from the other information of the association class；And to
The user recommends the hot information.
Further, hot information is searched from the other information of the association class includes：Obtain the other letter of the association class
The time of breath and the click volume of the other information of the association class；Obtain the weight information of the time and the click volume；According to
The time, the click volume and the weight information calculate the score value of the other information of association class；And by the score value
Highest information is as the hot information.
Further, the association class associated with the classification is searched in the classification according to belonging to the current click information
Before not, methods described also includes：Obtain the user click data recorded in website；User's point is identified according to pre-defined rule
Hit the information category of data；The information category that will identify that is added in the user click data, obtains new click data；
The information category identified is associated according to the incidence relation in the new click data, obtains information category pass
Join table.
Further, the classification according to belonging to the current click information searches the association classification associated with the classification
Including：Parse the current click information and determine the information category belonging to the current click information；From described information classification
The information category associated with the information category belonging to the current click information is searched in contingency table.
Further, the user click data with incidence relation is parsed from the user click data includes：Obtain
Take multiple click datas in the user click data；Search the data that adopting consecutive click chemical reaction is recorded in the multiple click data；
And using the data of the adopting consecutive click chemical reaction as the user click data with incidence relation.
To achieve these goals, a kind of another aspect according to embodiments of the present invention, there is provided information recommending apparatus.Root
Information recommending apparatus according to the present invention includes：First acquisition unit, for obtaining the current click information of user；First searches list
Member, the association classification associated with the classification is searched for the classification according to belonging to the current click information；Second searches
Unit, for finding hot information from the other information of the association class；And recommendation unit, for recommending institute to the user
State hot information.
Further, second searching unit includes：First acquisition module, for obtaining the other information of the association class
Time and the other information of the association class click volume；Second acquisition module, for obtaining the time and the click volume
Weight information；Computing module, for calculating the association classification according to the time, the click volume and the weight information
Information score value；And first determining module, for using the score value highest information as the hot information.
Further, described device also includes：Second acquisition unit, for according to belonging to the current click information
Before classification searches the association classification associated with the classification, the user click data recorded in website is obtained；Recognition unit,
For identifying the information category of the user click data according to pre-defined rule；Adding device, for the info class that will identify that
It is not added in the user click data, obtains new click data；Associative cell, for according to the new click data
In incidence relation the information category identified is associated, obtain information category contingency table.
Further, first searching unit includes：Parsing module, for parsing the current click information and determining
Information category belonging to the current click information；First searching modul, for from described information category associations table search with
The information category of information category association belonging to the current click information.
Further, the associative cell includes：3rd acquisition module is more in the new click data for obtaining
Individual click data；Second searching modul, the data of adopting consecutive click chemical reaction are recorded in the multiple click data for searching；And second
Determining module, for using the data of the adopting consecutive click chemical reaction as the user click data with incidence relation.
According to inventive embodiments, user's information interested is gone out according to the click behavioural analysis of user, and searches user's sense
Hot information in one category information of interest, and hot information is recommended into user so that the information for recommending user is user
Information interested, it is the personalized recommendation information for each user, rather than letter is fixed to all users all identicals
Breath, so as to solve the problems, such as to have reached to user's recommendation information inaccuracy in the prior art and accurately recommended personalization to user
The effect of information.
Brief description of the drawings
The accompanying drawing for forming the part of the application is used for providing a further understanding of the present invention, schematic reality of the invention
Apply example and its illustrate to be used to explain the present invention, do not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the flow chart of information recommendation method according to embodiments of the present invention；
Fig. 2 is the flow chart of information recommendation method according to the preferred embodiment of the invention；And
Fig. 3 is the schematic diagram of information recommending apparatus according to embodiments of the present invention.
Embodiment
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the present invention in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, it should all belong to the model that the present invention protects
Enclose.
It should be noted that term " first " in description and claims of this specification and above-mentioned accompanying drawing, "
Two " etc. be for distinguishing similar object, without for describing specific order or precedence.It should be appreciated that so use
Data can exchange in the appropriate case, so as to embodiments of the invention described herein.In addition, term " comprising " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or unit
Process, method, system, product or equipment are not necessarily limited to those steps clearly listed or unit, but may include without clear
It is listing to Chu or for the intrinsic other steps of these processes, method, product or equipment or unit.
The embodiments of the invention provide a kind of information recommendation method.The letter that the information recommendation method can be clicked on according to user
Breath comes for user's pushed information, because the information that user clicks on can embody the interest of the user, therefore the click for passing through user
Information is bonded the interest of user to compare for user's pushed information.In addition, to user push information be hot information, this for
For the faster website of content update, it is possible to increase the speed that new content is pushed, for example, being capable of pushing video website in time
The video of middle renewal or the information of news website.
Fig. 1 is the flow chart of information recommendation method according to embodiments of the present invention.As shown in figure 1, the information recommendation method
It is as follows including step：
Step S102, obtain the current click information of user.
Step S104, the classification according to belonging to current click information search the association classification associated with classification.
Step S106, hot information is found from the other information of association class.
Step S108, recommend hot information to user.
When user clicks on an information of website, the current click information with regard to that can obtain user, the click information belongs to
One category information, the association classification associated with the category is found, and find hot information from this classification and recommend user.
The classification related to the classification belonging to current click information can include click information generic in itself, can also include and point
Hit the related classification of information generic.
The classification of information can need to adjust according to different analyses, for example, the relatively macrotaxonomy that portal website A has has：Newly
News, amusement and finance and economics, there is less classification under each classification.Again including stock, fund and gold etc. under the classification of finance and economics.
When searching association classification, classification can be associated according to the classification searching of current click information, current click information can also be searched
Association classification is searched in affiliated larger classification
For example, the news that user clicks on is " stock market's daily turnover ", then it is stock to determine user classification interested,
Related classification has fund, bank and financing etc., that is, it is fund, bank and financing to associate classification, then the information of recommendation can
To be the hot information in these classifications.In addition, the news that user clicks on is " stock market's daily turnover ", user's classification interested
Finance and economics can also be divided into, then the classification associated with finance and economics there may be the classifications such as science and technology, military affairs, then just big from these
Hot information is searched in class and is recommended.
By above-described embodiment, user's information interested is gone out according to the click behavioural analysis of user, and searches user's sense
Hot information in one category information of interest, and hot information is recommended into user so that the information for recommending user is user
Information interested, it is the personalized recommendation information for each user, rather than letter is fixed to all users all identicals
Breath, so as to solve the problems, such as to have reached to user's recommendation information inaccuracy in the prior art and accurately recommended personalization to user
The effect of information.
Preferably, in order to which newer information is first recommended away, it is determined that during hot information combining information when
Between and click volume judged that to find hot information in the other information of association class include：Obtain the other information of association class
Time and the other information of association class click volume.Obtain the weight information of time and click volume.According to time, click volume and power
Weight information calculates the score value of the other information of association class.Using score value highest information as hot information.
The time of the other information of association class is the time caused by information, and click volume can reflect being concerned for this information
The weight information of degree, time and click volume can do different adjustment according to different news, according to time, click volume and its weight
Information calculates the score value of every information, and score value highest information can serve as hot information and be recommended, can not only be fast
Speed goes out new information recommendation, moreover it is possible to so that the information recommended more is bonded with the interest of user so that new information is pushed away
Recommend to people interested in the information so that the recommendation of information is more targeted.
It is determined that during hot information, different classes of hot information can be counted, for the ease of searching focus letter
Hot information, can be stored in database by breath, and the database can record category IDs belonging to hot information, hot information
ID and click volume.When it is determined that searching the hot information of some classification, can quickly it be looked for according to the ID of information generic
Gone out to the ID of the hot information, and by the information recommendation corresponding to the ID of hot information.
Preferably, before the association classification associated with classification being searched in the classification according to belonging to current click information, build
Vertical information category contingency table, in order to search the information category with currently clicking on information association, i.e. this method also includes：Obtain net
The user click data recorded in standing；According to the information category of pre-defined rule identification user click data；The information that will identify that
Classification is added in user click data, obtains new click data；According to the incidence relation in new click data to identification
The information category gone out is associated, and obtains information category contingency table.
After user click data is obtained, the classification belonging to user click data is identified, the class that will identify that
It is not added in user's hits, obtains new click data.When being associated to information category, according to carrying info class
Incidence relation in other new click data between click data determines the incidence relation between corresponding information category, also
Having obtained record has the information category contingency table of the incidence relation between information category.
The user click data with incidence relation is parsed from user click data to be included：Obtain user click data
In multiple click datas.Search the data that adopting consecutive click chemical reaction is recorded in multiple click datas.And the data of adopting consecutive click chemical reaction are made
For the user click data with incidence relation.
The JS scripts being deployed on website can record the click data of user, and be found out by parsing module with association
The click data of relation.Click data with incidence relation includes a plurality of click data of adopting consecutive click chemical reaction, for example, user is from letter
Breath L jumps to information M, jumps to information N again, then information L and information N is information M association click information, information L, is believed
Breath each self-corresponding classifications of N and information M just have certain incidence relation.This incidence relation is recorded, just can conduct
The information category contingency table corresponding to the incidence relation between information category corresponding to information L, information N and information M.
Specifically, the incidence relation between information category has been stored in information category contingency table, has been closed from information category
With regard to that can find the information category associated by current click information in connection table, i.e., the classification according to belonging to current click information is searched
The association classification associated with classification includes, and parses current click information and determines the information category belonging to current click information.
The information category associated with the information category belonging to current click information is searched from information category contingency table.
The present embodiment is illustrated below in conjunction with Fig. 2.
The front end script being deployed on website can collect user click data, and will click on data and be sent to daily record parsing
System, and obtain correlation rule.
Background server goes out hot information according to the log statistic of front end script collection.
After recommended engine receives user's click, according to user's click information, enter according to correlation rule and hot information
Row is online to be recommended, and carries out recommendation displaying to the information of recommendation, it is achieved thereby that being carried out according to the click behavior of user personalized
Recommendation, solve the problems, such as to have reached the effect of accurate recommendation information to user's recommendation information inaccuracy in the prior art.
The embodiment of the present invention additionally provides a kind of information recommending apparatus.The device can realize its function by computer.
Pushed away it should be noted that the information recommending apparatus of the embodiment of the present invention can be used for the information that the execution embodiment of the present invention is provided
Recommend method, the information recommendation method of the embodiment of the present invention can also by information recommending apparatus that the embodiment of the present invention is provided come
Perform.
Fig. 3 is the schematic diagram of information recommending apparatus according to embodiments of the present invention.As shown in figure 3, the information recommending apparatus
Including：First acquisition unit 10, the first searching unit 30, the second searching unit 50 and recommendation unit 70, wherein：
First acquisition unit 10 is used for the current click information for obtaining user.
The classification that first searching unit 30 is used for according to belonging to current click information searches the association class associated with classification
Not.
Second searching unit 50 is used to find hot information from the other information of association class.And
Recommendation unit 70 is used to recommend hot information to user.
When user clicks on an information of website, the current click information with regard to that can obtain user, the click information belongs to
One category information, the association classification associated with the category is found, and find hot information from this classification and recommend user.
The classification related to the classification belonging to current click information can include click information generic in itself, can also include and point
Hit the related classification of information generic.
The classification of information can need to adjust according to different analyses, for example, the relatively macrotaxonomy that portal website A has has：Newly
News, amusement and finance and economics, there is less classification under each classification.Again including stock, fund and gold etc. under the classification of finance and economics.
When searching association classification, classification can be associated according to the classification searching of current click information, current click information can also be searched
Association classification is searched in affiliated larger classification
For example, the news that user clicks on is " stock market's daily turnover ", then it is stock to determine user classification interested,
Related classification has fund, bank and financing etc., that is, it is fund, bank and financing to associate classification, then the information of recommendation can
To be the hot information in these classifications.In addition, the news that user clicks on is " stock market's daily turnover ", user's classification interested
Finance and economics can also be divided into, then the classification associated with finance and economics there may be the classifications such as science and technology, military affairs, then just big from these
Hot information is searched in class and is recommended.
By above-described embodiment, user's information interested is gone out according to the click behavioural analysis of user, and searches user's sense
Hot information in one category information of interest, and hot information is recommended into user so that the information for recommending user is user
Information interested, it is the personalized recommendation information for each user, rather than letter is fixed to all users all identicals
Breath, so as to solve the problems, such as to have reached to user's recommendation information inaccuracy in the prior art and accurately recommended personalization to user
The effect of information.
Preferably, in order to which newer information is first recommended away, it is determined that during hot information combining information when
Between and click volume judged that is, the second searching unit includes：First acquisition module, for obtaining the other information of association class
Time and the click volume of the other information of association class；Second acquisition module, for obtaining the weight information of time and click volume；Calculate
Module, for calculating the score value of the other information of association class according to time, click volume and weight information；And first determining module,
For using score value highest information as hot information.
The time of the other information of association class is the time caused by information, and click volume can reflect being concerned for this information
The weight information of degree, time and click volume can do different adjustment according to different news, according to time, click volume and its weight
Information calculates the score value of every information, and score value highest information can serve as hot information and be recommended, can not only be fast
Speed goes out new information recommendation, moreover it is possible to so that the information recommended more is bonded with the interest of user so that new information is pushed away
Recommend to people interested in the information so that the recommendation of information is more targeted.
It is determined that during hot information, different classes of hot information can be counted, for the ease of searching focus letter
Hot information, can be stored in database by breath, and the database can record category IDs belonging to hot information, hot information
ID and click volume.When it is determined that searching the hot information of some classification, can quickly it be looked for according to the ID of information generic
Gone out to the ID of the hot information, and by the information recommendation corresponding to the ID of hot information.
Preferably, information category contingency table is established, in order to search the information category with currently clicking on information association, i.e., should
Device also includes：Second acquisition unit, for searching the pass associated with classification in the classification according to belonging to current click information
Before joining classification, the user click data recorded in website is obtained；Recognition unit, for being clicked on according to pre-defined rule identification user
The information category of data；Adding device, the information category for will identify that are added in user click data, obtain new point
Hit data；Associative cell, for being associated according to the incidence relation in new click data to the information category identified, obtain
To information category contingency table.
After user click data is obtained, the classification belonging to user click data is identified, the class that will identify that
It is not added in user's hits, obtains new click data.When being associated to information category, according to carrying info class
Incidence relation in other new click data between click data determines the incidence relation between corresponding information category, also
Having obtained record has the information category contingency table of the incidence relation between information category.
Associative cell includes：3rd acquisition module, for obtaining multiple click datas in user click data；Second looks into
Module is looked for, records the data of adopting consecutive click chemical reaction in multiple click datas for searching；And second determining module, for by continuity point
The data hit are as the user click data with incidence relation.
The JS scripts being deployed on website can record the click data of user, and be found out by parsing module with association
The click data of relation.Click data with incidence relation includes a plurality of click data of adopting consecutive click chemical reaction, for example, user is from letter
Breath L jumps to information M, jumps to information N again, then information L and information N is information M association click information, information L, is believed
Breath each self-corresponding classifications of N and information M just have certain incidence relation.This incidence relation is recorded, just can conduct
The information category contingency table corresponding to the incidence relation between information category corresponding to information L, information N and information M.
Specifically, the incidence relation between information category has been stored in information category contingency table, has been closed from information category
With regard to that can find the information category associated by current click information in connection table, i.e. the first searching unit includes：Parsing module, it is used for
Parse current click information and determine the information category belonging to current click information；First searching modul, for from information category
The information category associated with the information category belonging to current click information is searched in contingency table.
It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the present invention is not limited by described sequence of movement because
According to the present invention, some steps can use other orders or carry out simultaneously.Secondly, those skilled in the art should also know
Know, embodiment described in this description belongs to preferred embodiment, and involved action and module are not necessarily of the invention
It is necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, can be by another way
Realize.For example, device embodiment described above is only schematical, such as the division of the unit, it is only one kind
Division of logic function, can there is an other dividing mode when actually realizing, such as multiple units or component can combine or can
To be integrated into another system, or some features can be ignored, or not perform.Another, shown or discussed is mutual
Coupling direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING or communication connection of device or unit,
Can be electrical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to be contributed in other words to prior art or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are causing a computer
Equipment (can be personal computer, mobile terminal, server or network equipment etc.) performs side described in each embodiment of the present invention
The all or part of step of method.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only Memory),
Random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various to be stored
The medium of program code.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (8)
- A kind of 1. information recommendation method, it is characterised in that including：Obtain the current click information of user；Classification according to belonging to the current click information searches the association classification associated with the classification；Hot information is searched from the other information of the association class；AndRecommend the hot information to the user；Before the classification according to belonging to the current click information searches the association classification associated with the classification, the side Method also includes：Obtain the user click data recorded in website；The information of the user click data is identified according to pre-defined rule Classification；The information category that will identify that is added in the user click data, obtains new click data；According to described new Incidence relation in click data is associated to the information category identified, obtains information category contingency table.
- 2. according to the method for claim 1, it is characterised in that hot information bag is searched from the other information of the association class Include：Obtain the time of the other information of the association class and the click volume of the other information of the association class；Obtain the weight information of the time and the click volume；The score value of the other information of association class is calculated according to the time, the click volume and the weight information；AndUsing the score value highest information as the hot information.
- 3. according to the method for claim 1, it is characterised in that the classification according to belonging to the current click information search with The associated association classification of the classification includes：Parse the current click information and determine the information category belonging to the current click information；The information category associated with the information category belonging to the current click information is searched from described information category associations table.
- 4. according to the method for claim 1, it is characterised in that according to the incidence relation in the new click data to institute State the information category identified to be associated, obtaining information category contingency table includes：Obtain multiple click datas in the new click data；Search the data that adopting consecutive click chemical reaction is recorded in the multiple click data；AndUsing the data of the adopting consecutive click chemical reaction as the user click data with incidence relation.
- A kind of 5. information recommending apparatus, it is characterised in that including：First acquisition unit, for obtaining the current click information of user；First searching unit, the association associated with the classification is searched for the classification according to belonging to the current click information Classification；Second searching unit, for finding hot information from the other information of the association class；AndRecommendation unit, for recommending the hot information to the user；Described device also includes：Second acquisition unit, in the classification lookup according to belonging to the current click information and institute Before stating the associated association classification of classification, the user click data recorded in website is obtained；Recognition unit, for according to predetermined Rule identifies the information category of the user click data；Adding device, the information category for will identify that are added to described In user click data, new click data is obtained；Associative cell, for according to the incidence relation in the new click data The information category identified is associated, obtains information category contingency table.
- 6. device according to claim 5, it is characterised in that second searching unit includes：First acquisition module, for obtaining the time of the other information of the association class and the click of the other information of the association class Amount；Second acquisition module, for obtaining the weight information of the time and the click volume；Computing module, for calculating the other information of association class according to the time, the click volume and the weight information Score value；AndFirst determining module, for using the score value highest information as the hot information.
- 7. device according to claim 5, it is characterised in that first searching unit includes：Parsing module, for parsing the current click information and determining the information category belonging to the current click information；First searching modul, for the lookup from described information category associations table and the info class belonging to the current click information The information category not associated.
- 8. device according to claim 5, it is characterised in that the associative cell includes：3rd acquisition module, for obtaining multiple click datas in the new click data；Second searching modul, the data of adopting consecutive click chemical reaction are recorded in the multiple click data for searching；AndSecond determining module, for using the data of the adopting consecutive click chemical reaction as the user click data with incidence relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410779044.9A CN104391999B (en) | 2014-12-15 | 2014-12-15 | Information recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410779044.9A CN104391999B (en) | 2014-12-15 | 2014-12-15 | Information recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104391999A CN104391999A (en) | 2015-03-04 |
| CN104391999B true CN104391999B (en) | 2018-02-02 |
Family
ID=52609903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410779044.9A Active CN104391999B (en) | 2014-12-15 | 2014-12-15 | Information recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104391999B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104796777A (en) * | 2015-04-26 | 2015-07-22 | 成都创行信息科技有限公司 | Hot video information pushing method |
| CN105005582B (en) * | 2015-06-17 | 2017-09-15 | 深圳市腾讯计算机***有限公司 | The recommendation method and device of multimedia messages |
| CN105068869A (en) * | 2015-09-29 | 2015-11-18 | 北京网诺星云科技有限公司 | Method and device for pushing information in mobile terminal |
| CN105225158A (en) * | 2015-10-22 | 2016-01-06 | 百度在线网络技术（北京）有限公司 | The column recommend method of Web Community and device |
| CN105554088B (en) * | 2015-12-10 | 2019-07-23 | 百度在线网络技术（北京）有限公司 | Information-pushing method and device |
| CN107369091B (en) * | 2016-05-12 | 2021-02-05 | 创新先进技术有限公司 | Product recommendation method and device and financial product recommendation method |
| CN109992331A (en) * | 2017-12-28 | 2019-07-09 | 重庆南华中天信息技术有限公司 | The common function portal assembly dynamic adjusting method and system of Behavior-based control analysis |
| CN108109052A (en) * | 2017-12-29 | 2018-06-01 | 广州优视网络科技有限公司 | Article method for pushing, device and server |
| CN108230101B (en) * | 2017-12-29 | 2022-05-17 | 百度在线网络技术（北京）有限公司 | Information recommendation method and device |
| CN109815368A (en) * | 2018-12-10 | 2019-05-28 | 百度在线网络技术（北京）有限公司 | Resource recommendation method, device, equipment and computer readable storage medium |
| CN110598109A (en) * | 2019-09-16 | 2019-12-20 | 上海喜马拉雅科技有限公司 | Information recommendation method, device, equipment and storage medium |
| CN111581492B (en) * | 2020-04-01 | 2024-02-23 | 车智互联（北京）科技有限公司 | Content recommendation method, computing device and readable storage medium |
| CN112231580B (en) * | 2020-11-10 | 2024-04-02 | 腾讯科技（深圳）有限公司 | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium |
| CN114357140A (en) * | 2022-01-11 | 2022-04-15 | 瀚云科技有限公司 | Question and answer information pushing method and device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768667A (en) * | 2011-05-06 | 2012-11-07 | 腾讯科技（北京）有限公司 | Method and system for releasing pushed information |
| CN102831234A (en) * | 2012-08-31 | 2012-12-19 | 北京邮电大学 | Personalized news recommendation device and method based on news content and theme feature |
| CN103412870A (en) * | 2013-07-09 | 2013-11-27 | 北京深思洛克软件技术股份有限公司 | News pushing method of mobile terminal device news client side software |
| CN103440259A (en) * | 2013-07-31 | 2013-12-11 | 亿赞普(北京)科技有限公司 | Network advertisement push method and device |
| CN103514207A (en) * | 2012-06-26 | 2014-01-15 | 阿里巴巴集团控股有限公司 | Method and device for pushing service objects |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| UA67749C2 (en) * | 1997-08-12 | 2004-07-15 | Егіш Дьйодьсердьяр Рт. | 8-substituted-9h-1,3-dioxolo-[4,5-h][2,3]benzodiazepine being inhibitors of the ampa/kainite receptor |
| US7853485B2 (en) * | 2005-11-22 | 2010-12-14 | Nec Laboratories America, Inc. | Methods and systems for utilizing content, dynamic patterns, and/or relational information for data analysis |
| US9367634B2 (en) * | 2012-01-19 | 2016-06-14 | Brightedge Technologies, Inc. | Optimizing location and mobile search |
-
2014
- 2014-12-15 CN CN201410779044.9A patent/CN104391999B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102768667A (en) * | 2011-05-06 | 2012-11-07 | 腾讯科技（北京）有限公司 | Method and system for releasing pushed information |
| CN103514207A (en) * | 2012-06-26 | 2014-01-15 | 阿里巴巴集团控股有限公司 | Method and device for pushing service objects |
| CN102831234A (en) * | 2012-08-31 | 2012-12-19 | 北京邮电大学 | Personalized news recommendation device and method based on news content and theme feature |
| CN103412870A (en) * | 2013-07-09 | 2013-11-27 | 北京深思洛克软件技术股份有限公司 | News pushing method of mobile terminal device news client side software |
| CN103440259A (en) * | 2013-07-31 | 2013-12-11 | 亿赞普(北京)科技有限公司 | Network advertisement push method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104391999A (en) | 2015-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104391999B (en) | Information recommendation method and device | |
| US8751470B1 (en) | Context sensitive ranking | |
| US9886517B2 (en) | Ranking product information | |
| US9706008B2 (en) | Method and system for efficient matching of user profiles with audience segments | |
| CN107862022B (en) | Culture resource recommendation system | |
| US9317550B2 (en) | Query expansion | |
| US9798806B2 (en) | Information retrieval using dynamic guided navigation | |
| WO2016000555A1 (en) | Methods and systems for recommending social network-based content and news | |
| CN104281718B (en) | A kind of method that intelligent recommendation is excavated based on user group's behavioral data | |
| US9251292B2 (en) | Search result ranking using query clustering | |
| US20160267189A1 (en) | Method for performing network search at a browser side and a browser | |
| CN103365839A (en) | Recommendation search method and device for search engines | |
| CN104537115A (en) | Method and device for exploring user interests | |
| CN106445963B (en) | Advertisement index keyword automatic generation method and device of APP platform | |
| CN107103487B (en) | Advertisement pushing method based on big data | |
| CN106776860A (en) | One kind search abstraction generating method and device | |
| KR102252188B1 (en) | Product recommendation system and method reflecting user purchasing criterion | |
| CN109409928A (en) | A kind of material recommended method, device, storage medium, terminal | |
| CN104462336A (en) | Information pushing method and device | |
| EP2778985A1 (en) | Search result ranking by department | |
| CN110275952A (en) | News recommended method, device and medium based on user's short-term interest | |
| CN108416627A (en) | A kind of brand influence force monitoring method and system based on internet data | |
| CN104361092A (en) | Searching method and device | |
| KR20180075234A (en) | Method and device for recommending contents based on inflow keyword and relevant keyword for contents | |
| CN107688563A (en) | A kind of recognition methods of synonym and identification device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Audio and video file labeling method and device and information recommendation method and device Effective date of registration: 20190531 Granted publication date: 20180202 Pledgee: Shenzhen Black Horse World Investment Consulting Co.,Ltd. Pledgor: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. Registration number: 2019990000503 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| CP02 | Change in the address of a patent holder |
Address after: 100083 No. 401, 4th Floor, Haitai Building, 229 North Fourth Ring Road, Haidian District, Beijing Patentee after: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. Address before: 100086 Beijing city Haidian District Shuangyushu Area No. 76 Zhichun Road cuigongfandian 8 layer A Patentee before: BEIJING GRIDSUM TECHNOLOGY Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20240604 Granted publication date: 20180202 |