CN104216881A - Method and device for recommending individual labels - Google Patents
Method and device for recommending individual labels Download PDFInfo
- Publication number
- CN104216881A CN104216881A CN201310206567.XA CN201310206567A CN104216881A CN 104216881 A CN104216881 A CN 104216881A CN 201310206567 A CN201310206567 A CN 201310206567A CN 104216881 A CN104216881 A CN 104216881A
- Authority
- CN
- China
- Prior art keywords
- keyword
- label
- user
- correlation
- degree
- 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
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 invention relates to a method for recommending individual labels. The method comprises the following steps of collecting the historical behavior data of a user visiting a website, storing keywords dug from the historical behavior data, conducting statistics on the relevancy of each keyword and the user, receiving the label recommending request of a client end, extracting at least one keyword from the stored keywords according to the relevancy of easy keyword and the user, generating a keyword label according to the extracted keywords, and returning the generated keywords to the client end to be displayed. The invention further provides a device for recommending the individual labels. According to the method and device, the labels meeting the individual demands can be recommended for the user to allow the user to choose, the activity for the user to set the labels is improved, and the accuracy and the effectiveness for setting the labels are improved.
Description
Technical field
The specific embodiment of the invention relates to technical field of information interaction, particularly a kind of recommend method of personalized labels and device.
Background technology
Along with the development of Internet technology, the application relating to internet gets more and more.In some applications, need user to arrange some labels, for representing the individualized feature of user, the interest, speciality etc. of such as user, so that this application carries out further data analysis or data mining according to set label.Such as, in the answer platform of interaction, usually need user that some are first set and represent that user is good at field (such as IT field, field of textiles), is good at the label of object (such as computer, clothes).The label that answer platform can be arranged according to user is the problem that user recommends some these users and may know the answer, allow user therefrom select permeability answer, thus simplify the complicated processes that user finds problem in answer platform.
But the label General Requirements user of at present application manually inputs and arranges, or select to think that applicable label is arranged from a general label recommendations list.The efficiency of manual input label is obviously lower, and general label recommendations list does not meet the individual demand of user usually, and the enthusiasm that therefore user arranges described label is affected, and the accuracy of set label reflection user individual feature is also lower.And if user is not arranged or arbitrarily arrange label, then cause certain obstacle can to the data analysis in later stage or data mining etc., such as described answer platform is difficult to find according to this label the problem meeting user and require.
Summary of the invention
In view of this, be necessary recommend method and device that a kind of personalized labels is provided, the label meeting individual demand can be recommended to select to arrange for user for user, improve the enthusiasm that user arranges label, and the accuracy of set label and validity.
A recommend method for personalized labels, comprises the following steps: collect step: the historical behavior data of collecting user's access websites, store the keyword excavated from these historical behavior data; Statistic procedure: the degree of correlation of adding up each keyword and the user stored; Receiving step: the label recommendations request receiving client; Extraction step: the degree of correlation according to described each keyword and user extracts at least one keyword from stored keyword; First generation step: generate keyword label according to extracted keyword, generated keyword label is back to client and shows.
A recommendation apparatus for personalized labels, comprising: collection module, for collecting the historical behavior data of user's access websites, stores the keyword excavated from these historical behavior data; Statistical module, for adding up stored each keyword and the degree of correlation of user; Receiver module, for receiving the label recommendations request of client; Extraction module, for extracting at least one keyword according to the degree of correlation of described each keyword and user from stored keyword; First generation module, for generating keyword label according to extracted keyword, being back to client by generated keyword label and showing.
Compared to prior art, the recommend method of personalized labels of the present invention and device, by collecting the historical behavior data of user's access websites, keyword generating labels according to excavating from these historical behavior data returns to client, the label meeting individual demand can be recommended to select to arrange for user for user, improve user and the enthusiasm of label is set, and the accuracy of set label and validity.
For above and other object of the present invention, feature and advantage can be become apparent, preferred embodiment cited below particularly, and coordinate institute's accompanying drawings, be described in detail below.
Accompanying drawing explanation
The environment schematic when recommend method of the personalized labels that Fig. 1 provides for the embodiment of the present invention is applied.
The process flow diagram of the recommend method of the personalized labels that Fig. 2 provides for first embodiment of the invention.
Fig. 3 is the schematic diagram that the label of client arranges the page.
Fig. 4 is the schematic diagram that customized label arranges interface.
The process flow diagram of the recommend method of the personalized labels that Fig. 5 provides for second embodiment of the invention.
Fig. 6 is the schematic diagram of keyword label and the kind label recommended.
The block diagram of the recommendation apparatus of the personalized labels that Fig. 7 provides for third embodiment of the invention.
The block diagram of the recommendation apparatus of the personalized labels that Fig. 8 provides for fourth embodiment of the invention.
Embodiment
For further setting forth the present invention for the technological means that realizes predetermined goal of the invention and take and effect, below in conjunction with accompanying drawing and preferred embodiment, to according to the specific embodiment of the present invention, structure, feature and effect thereof, be described in detail as follows.
Consult shown in Fig. 1, the environment schematic during recommend method application of the personalized labels provided for the embodiment of the present invention.In the present embodiment, the recommend method of this personalized labels is applied in server 1, and this server 1 carries out network service by network 2 and terminal 3.The instantiation of this terminal 3 includes, but are not limited to desk-top computer, portable computer, mobile phone, panel computer, personal digital assistant, self-service network terminal machine or other similar arithmetic units.Network 2 can be arbitrary internetwork connection mode, such as internet (Internet), mobile Internet (as 2G, 3G network that telecom operators provide), LAN (Local Area Network) (wired or wireless) etc.
First embodiment
Consult shown in Fig. 2, first embodiment of the invention provides a kind of recommend method of personalized labels, and the recommend method of this personalized labels comprises the following steps:
Step S1, collects the historical behavior data of user's access websites, stores the keyword excavated from these historical behavior data;
Step S2, adds up the degree of correlation of each keyword and the user stored;
Step S3, the label receiving client arranges request;
Step S4, the degree of correlation according to described each keyword and user extracts at least one keyword from stored keyword;
Step S5, generates keyword label according to extracted keyword, generated keyword label is back to client and shows.
According to the recommend method of above-mentioned personalized labels, by collecting the historical behavior data of user's access websites, keyword generating labels according to excavating from these historical behavior data returns to client, the label meeting individual demand can be recommended to select to arrange for user for user, improve user and the enthusiasm of label is set, and the accuracy of set label and validity.
In some instances, said method each step to realize details as follows:
Website described in step S1 can be such as the service websites such as www.qq.com, Baidu.com, Sina website, comprise the application such as the web page search engine under this service website, answer platform (such as Tengxun asks, Baidu is known, Sina like ask), also the application platform be associated with this service website can be comprised, the QQ space such as associated by QQ login account with www.qq.com and Tengxun's microblogging, the Sina's microblogging etc. associated by login account with Sina website.
Described historical behavior data such as comprise user on the web site the title of browsed webpage, search and webpage input key word, propose on this answer platform or key word etc. that the title of the problem answered, search problem use, even comprise the personal information that user is arranged in the application platform be associated with this website, the data such as the individual label of the representative of consumer individualized feature that such as user is arranged on Tengxun's microblogging.
Collected historical behavior data need to get up with this user-association, and such as, these historical behavior data can log in user the login account that this website uses and associate.After user uses this login account to log in this website, server 1 real-time collecting user accesses the historical behavior data of this website, collected historical behavior data are stored in the storer of server 1, and these stored historical behavior data are associated with the login account of this user, such as, by these collected historical behavior data stored in storage space corresponding to the login account of this user.
In the present embodiment, these historical behavior data can for word, phrase or the sentence etc. be made up of continuous print word, therefore segmentation methods can be first adopted to carry out word segmentation processing to these historical behavior data, then according to the frequency of each word, whether be that the pre-defined rules such as independent word (as "Yes", " ") excavate keyword from these historical behavior data, and excavated keyword to be stored in the storer of server 1.In addition, step S1 can also be normalized excavated keyword, and the keyword after normalized has more versatility.Such as, this normalized can realize based on semantic analysis, by the semantic analysis to keyword, a keyword is merged in the keyword of synonym or nearly justice.Also can be realized by the mode of machine learning the normalized of keyword, a keyword is merged in the keyword of statement same thing.
Keyword described in step S2 and the degree of correlation of user meet the degree of user interest or demand for evaluating keyword.The degree of correlation of keyword and user is higher, and illustrate that user's possibility interested in this keyword or demand is larger, the degree of correlation of keyword and user is lower, illustrates that user's possibility interested in this keyword or demand is lower.
In one example, the frequency that corresponding keyword can be occurred in described historical behavior data calculates the degree of correlation of this keyword and user according to certain function formula.The frequency that keyword occurs in described historical behavior data is higher, this keyword calculated and the degree of correlation of user higher.The frequency that keyword occurs in described historical behavior data is lower, this keyword calculated and the degree of correlation of user lower.In one example, the statistical methods such as Bayes also can be adopted to add up corresponding keyword meet the probability of user interest or demand and obtain the degree of correlation of this keyword and user.In another example, can also by carrying out machine learning to the training set comprising mass data, judge that mode that whether keyword meets user interest or demand obtains the degree of correlation of this keyword and user successively.Each keyword of adding up and the degree of correlation of user are also stored in which memory.
In addition, step S2 can also sort to the degree of correlation order from high to low of stored each keyword according to this and user.Such as, the keyword corresponding with user A stored comprises " computer ", " mobile phone " and " flat board " three, calculating keyword " computer " with the value of the degree of correlation of user according to the frequency of these three keywords and certain function formula is 8, keyword " mobile phone " is 7 with the value of the degree of correlation of user, keyword " flat board " is 9 with the value of the degree of correlation of user, then this three keywords and can sort as { (dull and stereotyped with the form gathered with the degree of correlation of user, 9), (computer, 8), (mobile phone, 7) }.
Client described in step S3 runs in described terminal 3, and user logs in this website by described login account in this client.The label of this client also for showing this website according to the operation of user arranges the page and label setting options.This label for reflecting the individualized feature of this user, the interest, hobby, speciality etc. of such as user.Such as shown in Fig. 3, this client is the answer platform of this website, and the label that this answer platform comprises the problem of being good at of user arranges the page, and " interpolation " option one 0 in Fig. 3 is this label setting options.When the label setting options that user selects this label to arrange on the page, client sends described label recommendations request by server 1.
In step S4, can from stored sort according to the order from high to low of the degree of correlation with user after keyword extract the keyword of the first specified quantity come above, namely extract some keywords higher with the degree of correlation of user.If this first specified quantity of the lazy weight of the keyword stored, then all extract stored keyword.
Step S5 generates keyword label according to extracted keyword, such as generate a corresponding keyword label for each extracted keyword, this keyword label is such as in described answer platform, and the label that user is good at problem arranges in the page label being good at keyword.Then, generated keyword label is back to client and shows by step S5, directly selects the keyword label be applicable to carry out label setting, without the need to the manual input label of user for user from shown keyword label.
In addition, step S5 can also generate a customized label simultaneously and arrange interface, for receiving the customized label that user manually inputs, such as, shown in Fig. 4, then this customized label being arranged interface and being back to client and arranging on the page with the label being presented at client current.If user does not find applicable keyword label in shown keyword label, then the self-defining keyword label of manual input on interface can be set at this shown customized label and arrange.
Second embodiment
In order to the form of expression of abundant recommended label, except described keyword label, also recommend a kind of kind label, second embodiment of the invention provides a kind of recommend method of personalized labels, it is compared to the recommend method of the personalized labels of the first embodiment, consult shown in Fig. 5, described step S2 comprises further:
Step S21, classifies according to the kind preset to stored keyword.Such as in the answer platform of this website, arrange in the page at the label of the problem of being good at, being good at except keyword except arranging, also needing setting to be good at field.This is good at field and namely can be regarded as the classification being good at keyword.Therefore, this kind preset such as comprises clothing, electronic product etc.In the present embodiment, such as linear recurrence method, SVM(Support Vector Machine can be adopted, support vector machine) machine learning method etc., under the keyword this stored is divided into each default kind.Such as, under keyword " mobile phone ", " computer ", " MP3 " etc. can be divided into default electronic product, and under keyword " children's garment ", " down jackets " etc. can be divided into default clothing.
Step S22, each keyword corresponding according to each kind preset and the degree of correlation of user, add up the degree of correlation of default each kind and user.The degree of correlation of this kind and user is used for evaluation type and meets the interest of user and the degree of demand.The degree of correlation of this kind and user is higher, illustrates that user's possibility interested in this kind or demand is larger.The degree of correlation of this kind and user is lower, illustrates that user's possibility interested in this kind or demand is less.Specifically, such as can be weighted the degree of correlation of each keyword under each kind and user or the read group total of not weighting, thus obtain the degree of correlation of each kind and user.Step S22 also can sort according to the order from high to low of the degree of correlation with user to default each kind.
Accordingly, the tag types that needs are recommended will be comprised in the label recommendations request of described client.Described label setting options also can be divided into the setting options (option one 0 as in Fig. 3) of keyword label and the setting options (option 20 as in Fig. 3) of kind label.When user selects the setting options of this keyword label, client sends the label recommendations request of keyword label.When user selects the setting options of this kind label, client sends the label recommendations request of kind label.
Therefore, described step S3 is after the label recommendations request receiving client, the label recommended is needed to be keyword label or kind label by according to this label recommendations requirement analysis, if keyword label, then perform described step S4, if kind label, then perform following step S6 and step S7.
Step S6, the degree of correlation according to described each kind and user obtains at least one kind from default kind.Specifically, can obtain the kind of the second specified quantity come above from the kind preset after sorting according to the order from high to low of the degree of correlation with user, namely extract and kind that the degree of correlation of user is higher.
Step S7, kind label is generated according to obtained kind, then generated kind label is back to client to show, from shown kind label, the kind label be applicable to is selected to carry out label setting for user, such as carry out the label setting that user in answer platform is good at field, without the need to the manual input label of user, as shown in Figure 6.
Certainly, step S7 also can generate a customized label simultaneously and arrange interface, for receiving the customized label that user manually inputs, then this customized label being arranged interface and being back to client and arranging on the page with the label being presented at client current.
In sum, the recommend method of the personalized labels of the present embodiment, can on the basis of the recommend method of the personalized labels of the first embodiment, further abundant the form of expression of recommending label.
3rd embodiment
Consult shown in Fig. 7, third embodiment of the invention provides a kind of recommendation apparatus 100 of personalized labels, and it comprises collection module 101, statistical module 102, receiver module 103, extraction module 104 and the first generation module 105.Be appreciated that above-mentioned each module refers to computer program or program segment, for performing certain one or more specific function.In addition, the differentiation of above-mentioned each module does not represent actual program code and must separate yet.
Collection module 101, for collecting the historical behavior data of user's access websites, stores the keyword excavated from these historical behavior data.Collection module 101 is also normalized excavated keyword.
Statistical module 102, for adding up stored each keyword and the degree of correlation of user.Statistical module 102 is also for sorting according to the order from high in the end of the degree of correlation with user to stored each keyword.
Receiver module 103, for receiving the label recommendations request of client.
Extraction module 104, for extracting at least one keyword according to the degree of correlation of described each keyword and user from stored keyword.Specifically, extraction module 104 can from stored sort according to the order from high to low of the degree of correlation with user after keyword extract the keyword of the first specified quantity come above.If this first specified quantity of the lazy weight of the keyword stored, then all extract stored keyword.
First generation module 105, for generating keyword label according to extracted keyword, being back to client by generated keyword label and showing.First generation module 105 can also generate a customized label simultaneously and arrange interface, for receiving the customized label that user manually inputs, then this customized label being arranged interface and being back to client and arranging on the page with the label being presented at client current.
For the specific works process of above each module, the recommend method of the personalized labels that can provide with further reference to first embodiment of the invention, no longer repeats at this.
In sum, the recommendation apparatus 100 of the personalized labels of the present embodiment, by collecting the historical behavior data of user's access websites, keyword generating labels according to excavating from these historical behavior data returns to client, the label meeting individual demand can be recommended to select to arrange for user for user, improve user and the enthusiasm of label is set, and the accuracy of set label and validity.
4th embodiment
Consult shown in Fig. 8, fourth embodiment of the invention provides a kind of recommendation apparatus 200 of personalized labels, and it is compared to the recommendation apparatus 100 of the personalized labels of the 3rd embodiment, and described statistical module 102 comprises further:
Classification submodule 1021, for classifying according to the kind preset to stored keyword.
Statistics submodule 1022, for the degree of correlation according to each keyword corresponding to each kind preset and user, adds up the degree of correlation of default each kind and user.In addition, add up submodule 1022 also to sort according to the order from high to low of the degree of correlation with user to default each kind.
Accordingly, described receiver module 103 is after the label recommendations request receiving client, the label recommended is needed to be keyword label or kind label by according to this label recommendations requirement analysis, if keyword label, then perform described extraction module 104, if kind label, then perform following acquisition module 201 and the second generation module 202.
Acquisition module 201, for obtaining at least one kind according to the degree of correlation of described each kind and user from default kind.Specifically, the kind of the second specified quantity come above can be obtained from the kind preset after sorting according to the order from high to low of the degree of correlation with user.
Second generation module 202, for generating kind label according to obtained kind, being then back to client by generated kind label and showing.In addition, second generation module 202 also can generate a customized label simultaneously and arrange interface, for receiving the customized label that user manually inputs, then this customized label being arranged interface and being back to client and arranging on the page with the label being presented at client current.
For the specific works process of above each module, the recommend method of the personalized labels that can provide with further reference to second embodiment of the invention, no longer repeats at this.
In sum, the recommendation apparatus 200 of the personalized labels of the present embodiment, can on the basis of the recommendation apparatus 100 of the personalized labels of the 3rd embodiment, further abundant the form of expression of recommending label, except except recommended keywords label, also kind label can be recommended, select to arrange for user.
In addition, the embodiment of the present invention also provides a kind of computer-readable recording medium, is stored with computer executable instructions, and above-mentioned computer-readable recording medium is such as nonvolatile memory such as CD, hard disk or flash memory.Above-mentioned computer executable instructions completes various operations in the recommend method of above-mentioned personalized labels for allowing computing machine or similar arithmetic unit.
The above, it is only preferred embodiment of the present invention, not any pro forma restriction is done to the present invention, although the present invention discloses as above with preferred embodiment, but and be not used to limit the present invention, any those skilled in the art, do not departing within the scope of technical solution of the present invention, make a little change when the technology contents of above-mentioned announcement can be utilized or be modified to the Equivalent embodiments of equivalent variations, in every case be do not depart from technical solution of the present invention content, according to any brief introduction amendment that technical spirit of the present invention is done above embodiment, equivalent variations and modification, all still belong in the scope of technical solution of the present invention.
Claims (18)
1. a recommend method for personalized labels, is characterized in that, the method comprises the following steps:
Collect step: the historical behavior data of collecting user's access websites, store the keyword excavated from these historical behavior data;
Statistic procedure: the degree of correlation of adding up each keyword and the user stored;
Receiving step: the label recommendations request receiving client;
Extraction step: the degree of correlation according to described each keyword and user extracts at least one keyword from stored keyword;
First generation step: generate keyword label according to extracted keyword, generated keyword label is back to client and shows.
2. the recommend method of personalized labels as claimed in claim 1, it is characterized in that, described collection step also comprises:
Excavated keyword is normalized.
3. the recommend method of personalized labels as claimed in claim 1, it is characterized in that, described statistic procedure also comprises:
Stored each keyword is sorted according to the order from high in the end of the degree of correlation with user;
Described extraction step also comprises:
The keyword of the first specified quantity come above is extracted from stored keyword.
4. the recommend method of personalized labels as claimed in claim 1, it is characterized in that, described statistic procedure also comprises:
Stored keyword is classified according to the kind preset;
The each keyword corresponding according to each kind preset and the degree of correlation of user, add up the degree of correlation of default each kind and user.
5. the recommend method of personalized labels as claimed in claim 4, it is characterized in that, described receiving step also comprises:
Need the label recommended to be keyword label or kind label according to this label recommendations requirement analysis, if keyword label, then perform described extraction step.
6. the recommend method of personalized labels as claimed in claim 5, is characterized in that, also comprise:
Obtaining step: the label if desired recommended is kind label, then obtain at least one kind according to the degree of correlation of described each kind and user from default kind.
7. the recommend method of personalized labels as claimed in claim 6, is characterized in that,
Described statistic procedure also comprises:
Default each kind is sorted according to the order from high to low of the degree of correlation with user;
Described obtaining step also comprises:
The kind of the second specified quantity come above is obtained from default kind.
8. the recommend method of personalized labels as claimed in claim 7, is characterized in that, also comprise:
Second generation step: generate kind label according to obtained kind, generated kind label is back to client and shows.
9. the recommend method of the personalized labels as described in claim 1 or 8, is characterized in that, described first generation step or the second generation step also comprise:
Generate customized label and interface is set, this customized label is arranged interface and be back to client and show.
10. a recommendation apparatus for personalized labels, is characterized in that, this device comprises:
Collection module, for collecting the historical behavior data of user's access websites, stores the keyword excavated from these historical behavior data;
Statistical module, for adding up stored each keyword and the degree of correlation of user;
Receiver module, for receiving the label recommendations request of client;
Extraction module, for extracting at least one keyword according to the degree of correlation of described each keyword and user from stored keyword;
First generation module, for generating keyword label according to extracted keyword, being back to client by generated keyword label and showing.
The recommendation apparatus of 11. personalized labels as claimed in claim 10, is characterized in that, described collection module also for:
Excavated keyword is normalized.
The recommendation apparatus of 12. personalized labels as claimed in claim 10, is characterized in that, described statistical module also for:
Stored each keyword is sorted according to the order from high in the end of the degree of correlation with user;
Described extraction module also for:
The keyword of the first specified quantity come above is extracted from stored keyword.
The recommendation apparatus of 13. personalized labels as claimed in claim 10, is characterized in that, described statistical module also for:
Stored keyword is classified according to the kind preset;
The each keyword corresponding according to each kind preset and the degree of correlation of user, add up the degree of correlation of default each kind and user.
The recommendation apparatus of 14. personalized labels as claimed in claim 13, is characterized in that, described receiver module also for:
Need the label recommended to be keyword label or kind label according to this label recommendations requirement analysis, if keyword label, then perform described extraction module.
The recommendation apparatus of 15. personalized labels as claimed in claim 14, is characterized in that, also comprise:
Acquisition module, the label for if desired recommending is kind label, then from default kind, obtain at least one kind according to the degree of correlation of described each kind and user.
The recommendation apparatus of 16. personalized labels as claimed in claim 15, is characterized in that,
Described statistical module also for:
Default each kind is sorted according to the order from high to low of the degree of correlation with user;
Described acquisition module also for:
The kind of the second specified quantity come above is obtained from default kind.
The recommendation apparatus of 17. personalized labels as claimed in claim 16, is characterized in that, also comprise:
Second generation module, for generating kind label according to obtained kind, being back to client by generated kind label and showing.
The recommendation apparatus of 18. personalized labels as described in claim 10 or 17, is characterized in that, described first generation module or the second generation module also for:
Generate customized label and interface is set, this customized label is arranged interface and be back to client and show.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310206567.XA CN104216881A (en) | 2013-05-29 | 2013-05-29 | Method and device for recommending individual labels |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310206567.XA CN104216881A (en) | 2013-05-29 | 2013-05-29 | Method and device for recommending individual labels |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104216881A true CN104216881A (en) | 2014-12-17 |
Family
ID=52098387
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310206567.XA Pending CN104216881A (en) | 2013-05-29 | 2013-05-29 | Method and device for recommending individual labels |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104216881A (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104602042A (en) * | 2014-12-31 | 2015-05-06 | 合一网络技术(北京)有限公司 | User behavior based label setting method |
| CN104750789A (en) * | 2015-03-12 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Label recommendation method and device |
| CN105117449A (en) * | 2015-08-14 | 2015-12-02 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating tags of content items |
| CN105159930A (en) * | 2015-08-05 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Search keyword pushing method and apparatus |
| CN105373531A (en) * | 2015-12-09 | 2016-03-02 | 微梦创科网络科技（中国）有限公司 | Short topic text identification method and device based on social network |
| CN105701139A (en) * | 2015-11-26 | 2016-06-22 | 中国传媒大学 | Holographic video material indexing method |
| CN105912682A (en) * | 2016-04-14 | 2016-08-31 | 乐视控股（北京）有限公司 | Video classification label generating method and device |
| CN105989120A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Personalized content recommendation method and personalized content recommendation system |
| CN106294744A (en) * | 2016-08-11 | 2017-01-04 | 上海动云信息科技有限公司 | Interest recognition methods and system |
| CN106326291A (en) * | 2015-07-01 | 2017-01-11 | 羊剑 | Tag-based demand guidance pairing method and system |
| CN106354861A (en) * | 2016-09-06 | 2017-01-25 | 中国传媒大学 | Automatic film label indexing method and automatic indexing system |
| CN106407239A (en) * | 2015-08-03 | 2017-02-15 | 阿里巴巴集团控股有限公司 | Methods and apparatuses used for recommending information and assisting in recommending information |
| CN107992487A (en) * | 2016-10-26 | 2018-05-04 | 百度国际科技（深圳）有限公司 | Personalized recommendation method and device |
| CN108460104A (en) * | 2018-02-06 | 2018-08-28 | 北京奇虎科技有限公司 | A kind of method and apparatus for realizing content customization |
| CN109242514A (en) * | 2018-08-28 | 2019-01-18 | 腾讯科技（深圳）有限公司 | Client's label recommendation method, device and system |
| CN109271609A (en) * | 2018-09-14 | 2019-01-25 | 广州神马移动信息科技有限公司 | Label generating method, device, terminal device and computer storage medium |
| CN109684579A (en) * | 2017-10-18 | 2019-04-26 | 镇江雅迅软件有限责任公司 | A kind of digital content resource management system based on label |
| CN110110272A (en) * | 2019-04-30 | 2019-08-09 | 贝壳技术有限公司 | A kind of homepage push processing method and device |
| CN110209692A (en) * | 2018-02-14 | 2019-09-06 | 阿里巴巴集团控股有限公司 | Providing method, data processing method, device and the equipment of data label |
| CN110321487A (en) * | 2019-07-01 | 2019-10-11 | 上海硕恩网络科技股份有限公司 | A kind of accurate label recommendations system and its workflow |
| WO2019214245A1 (en) * | 2018-05-09 | 2019-11-14 | 深圳壹账通智能科技有限公司 | Information pushing method and apparatus, and terminal device and storage medium |
| TWI684875B (en) * | 2016-05-12 | 2020-02-11 | 香港商阿里巴巴集團服務有限公司 | Method for determining user behavior preference, method and device for displaying recommended information |
| CN110969222A (en) * | 2018-09-29 | 2020-04-07 | 西门子股份公司 | Information providing method and system |
| CN116779109A (en) * | 2023-05-24 | 2023-09-19 | 纬英(广州)教育科技有限公司 | Self-feature discovery method and device based on exploration scene guidance |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101114295A (en) * | 2007-08-11 | 2008-01-30 | 腾讯科技（深圳）有限公司 | Method for searching on-line advertisement resource and device thereof |
| CN101547162A (en) * | 2008-03-28 | 2009-09-30 | 国际商业机器公司 | Method and device for tagging user based on user state information |
| CN102262653A (en) * | 2011-06-09 | 2011-11-30 | 华中科技大学 | Label recommendation method and system based on user motivation orientation |
| CN102790727A (en) * | 2011-05-19 | 2012-11-21 | 腾讯科技（深圳）有限公司 | Method and system for dynamically pushing personal labels of users |
| CN103218355A (en) * | 2012-01-18 | 2013-07-24 | 腾讯科技（深圳）有限公司 | Method and device for generating tags for user |
-
2013
- 2013-05-29 CN CN201310206567.XA patent/CN104216881A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101114295A (en) * | 2007-08-11 | 2008-01-30 | 腾讯科技（深圳）有限公司 | Method for searching on-line advertisement resource and device thereof |
| CN101547162A (en) * | 2008-03-28 | 2009-09-30 | 国际商业机器公司 | Method and device for tagging user based on user state information |
| CN102790727A (en) * | 2011-05-19 | 2012-11-21 | 腾讯科技（深圳）有限公司 | Method and system for dynamically pushing personal labels of users |
| CN102262653A (en) * | 2011-06-09 | 2011-11-30 | 华中科技大学 | Label recommendation method and system based on user motivation orientation |
| CN103218355A (en) * | 2012-01-18 | 2013-07-24 | 腾讯科技（深圳）有限公司 | Method and device for generating tags for user |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104602042B (en) * | 2014-12-31 | 2017-11-03 | 合一网络技术(北京)有限公司 | Label setting method based on user behavior |
| CN104602042A (en) * | 2014-12-31 | 2015-05-06 | 合一网络技术(北京)有限公司 | User behavior based label setting method |
| CN105989120B (en) * | 2015-02-12 | 2019-08-13 | Oppo广东移动通信有限公司 | A kind of personalization content recommendation method and individualized content recommender system |
| CN105989120A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Personalized content recommendation method and personalized content recommendation system |
| CN104750789B (en) * | 2015-03-12 | 2018-10-16 | 百度在线网络技术（北京）有限公司 | The recommendation method and device of label |
| CN104750789A (en) * | 2015-03-12 | 2015-07-01 | 百度在线网络技术（北京）有限公司 | Label recommendation method and device |
| CN106326291A (en) * | 2015-07-01 | 2017-01-11 | 羊剑 | Tag-based demand guidance pairing method and system |
| CN106407239A (en) * | 2015-08-03 | 2017-02-15 | 阿里巴巴集团控股有限公司 | Methods and apparatuses used for recommending information and assisting in recommending information |
| CN105159930A (en) * | 2015-08-05 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Search keyword pushing method and apparatus |
| CN105117449B (en) * | 2015-08-14 | 2019-08-16 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus for generating the label of content item |
| CN105117449A (en) * | 2015-08-14 | 2015-12-02 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating tags of content items |
| CN105701139A (en) * | 2015-11-26 | 2016-06-22 | 中国传媒大学 | Holographic video material indexing method |
| CN105373531B (en) * | 2015-12-09 | 2018-05-22 | 微梦创科网络科技（中国）有限公司 | A kind of short topic text recognition method and device based on social networks |
| CN105373531A (en) * | 2015-12-09 | 2016-03-02 | 微梦创科网络科技（中国）有限公司 | Short topic text identification method and device based on social network |
| CN105912682A (en) * | 2016-04-14 | 2016-08-31 | 乐视控股（北京）有限公司 | Video classification label generating method and device |
| US11086882B2 (en) | 2016-05-12 | 2021-08-10 | Advanced New Technologies Co., Ltd. | Method for determining user behavior preference, and method and device for presenting recommendation information |
| TWI684875B (en) * | 2016-05-12 | 2020-02-11 | 香港商阿里巴巴集團服務有限公司 | Method for determining user behavior preference, method and device for displaying recommended information |
| US11281675B2 (en) | 2016-05-12 | 2022-03-22 | Advanced New Technologies Co., Ltd. | Method for determining user behavior preference, and method and device for presenting recommendation information |
| CN106294744A (en) * | 2016-08-11 | 2017-01-04 | 上海动云信息科技有限公司 | Interest recognition methods and system |
| CN106354861A (en) * | 2016-09-06 | 2017-01-25 | 中国传媒大学 | Automatic film label indexing method and automatic indexing system |
| CN106354861B (en) * | 2016-09-06 | 2019-09-20 | 中国传媒大学 | Film label automatic indexing method and automatic indexing system |
| CN107992487A (en) * | 2016-10-26 | 2018-05-04 | 百度国际科技（深圳）有限公司 | Personalized recommendation method and device |
| CN109684579A (en) * | 2017-10-18 | 2019-04-26 | 镇江雅迅软件有限责任公司 | A kind of digital content resource management system based on label |
| CN108460104B (en) * | 2018-02-06 | 2021-06-18 | 北京奇虎科技有限公司 | Method and device for customizing content |
| CN108460104A (en) * | 2018-02-06 | 2018-08-28 | 北京奇虎科技有限公司 | A kind of method and apparatus for realizing content customization |
| CN110209692A (en) * | 2018-02-14 | 2019-09-06 | 阿里巴巴集团控股有限公司 | Providing method, data processing method, device and the equipment of data label |
| WO2019214245A1 (en) * | 2018-05-09 | 2019-11-14 | 深圳壹账通智能科技有限公司 | Information pushing method and apparatus, and terminal device and storage medium |
| CN109242514A (en) * | 2018-08-28 | 2019-01-18 | 腾讯科技（深圳）有限公司 | Client's label recommendation method, device and system |
| CN109271609A (en) * | 2018-09-14 | 2019-01-25 | 广州神马移动信息科技有限公司 | Label generating method, device, terminal device and computer storage medium |
| CN110969222A (en) * | 2018-09-29 | 2020-04-07 | 西门子股份公司 | Information providing method and system |
| CN110110272A (en) * | 2019-04-30 | 2019-08-09 | 贝壳技术有限公司 | A kind of homepage push processing method and device |
| CN110321487A (en) * | 2019-07-01 | 2019-10-11 | 上海硕恩网络科技股份有限公司 | A kind of accurate label recommendations system and its workflow |
| CN116779109A (en) * | 2023-05-24 | 2023-09-19 | 纬英(广州)教育科技有限公司 | Self-feature discovery method and device based on exploration scene guidance |
| CN116779109B (en) * | 2023-05-24 | 2024-04-02 | 纬英数字科技(广州)有限公司 | Self-feature discovery method and device based on exploration scene guidance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104216881A (en) | Method and device for recommending individual labels | |
| US10546006B2 (en) | Method and system for hybrid information query | |
| US11765246B2 (en) | Topical activity monitor and identity collector system | |
| CN103339623B (en) | It is related to the method and apparatus of Internet search | |
| CN101551806B (en) | Personalized website navigation method and system | |
| KR101419504B1 (en) | System and method providing a suited shopping information by analyzing the propensity of an user | |
| JP5962926B2 (en) | Recommender system, recommendation method, and program | |
| CN102053983B (en) | Method, system and device for querying vertical search | |
| US7580926B2 (en) | Method and apparatus for representing text using search engine, document collection, and hierarchal taxonomy | |
| CN101216825B (en) | Indexing key words extraction/ prediction method | |
| CN102822815B (en) | For the method and system utilizing browser history to carry out action suggestion | |
| CN102054003B (en) | Methods and systems for recommending network information and creating network resource index | |
| CN109634698B (en) | Menu display method and device, computer equipment and storage medium | |
| CN106251174A (en) | Information recommendation method and device | |
| WO2018040069A1 (en) | Information recommendation system and method | |
| CN105677780A (en) | Scalable user intent mining method and system thereof | |
| CN104933100A (en) | Keyword recommendation method and device | |
| CN104077286A (en) | Commodity information search method and system | |
| CN103577490A (en) | Method and device of showing web browsing history | |
| CN103020128B (en) | With the method and apparatus of data interaction with terminal device | |
| CN107562939A (en) | Vertical field news recommends method, apparatus and readable storage medium | |
| CN108959550B (en) | User focus mining method, device, equipment and computer readable medium | |
| CN104050183A (en) | Content matching result prompting method and device for browser input frame | |
| CN103425767B (en) | A kind of determination method and system pointing out data | |
| Nawazish et al. | Integrating “Random Forest” with Indexing and Query Processing for Personalized Search |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141217 |
|
| RJ01 | Rejection of invention patent application after publication |