CN103218355A - Method and device for generating tags for user - Google Patents
Method and device for generating tags for user Download PDFInfo
- Publication number
- CN103218355A CN103218355A CN2012100157418A CN201210015741A CN103218355A CN 103218355 A CN103218355 A CN 103218355A CN 2012100157418 A CN2012100157418 A CN 2012100157418A CN 201210015741 A CN201210015741 A CN 201210015741A CN 103218355 A CN103218355 A CN 103218355A
- Authority
- CN
- China
- Prior art keywords
- keyword
- user
- label
- information
- operation behavior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a method and a device for generating tags for a user. The method comprises the following steps of aiming at any user X, acquiring operation action information after the user logs in a network in real time; and after acquiring one piece of the operation action information every time, carrying out the following processing once: extracting keywords in the operation action information, and storing; and selecting keywords meeting the requirement from all the stored keywords, and using the keywords as the tags of the user X. The technical scheme provided by the invention is applied, so personalized information of the user can be conveniently and quickly acquired.
Description
Technical field
The present invention relates to network technology, particularly a kind of method and apparatus that generates label for the user.
Background technology
In the prior art, can come for article generates label (Tag) according to the keyword that from article, extracts, thereby make the reader can recognize the content of article etc. quickly and easily.
Correspondingly, also wish and so that get access to user's customized information quickly and easily, thereby, to push possibility information of interest etc. for it for the user generates label as label according to the user better for it provides service.
But also there is not a kind of mode that can generate label in the prior art for the user.
Summary of the invention
In view of this, the invention provides a kind of for the user generates the method and apparatus of label, thereby can get access to user's customized information quickly and easily.
For achieving the above object, technical scheme of the present invention is achieved in that
A kind of method that generates label for the user comprises:
At arbitrary user X, obtain the operation behavior information behind its logging in network in real time, and, then carry out once following the processing after whenever getting access to an operation behavior information:
Extract the keyword in this operation behavior information, and preserve;
From all keywords of being preserved, select satisfactory keyword, as the label of user X.
A kind of device that generates label for the user comprises:
Acquisition module is used at arbitrary user X, obtain the operation behavior information behind its logging in network in real time, and each bar operation behavior information that will get access to sends to processing module;
Described processing module is used for after whenever receiving an operation behavior information, then carries out once following the processing: extract the keyword in this operation behavior information, and preserve; From all keywords of being preserved, select satisfactory keyword, as the label of user X.
As seen, adopt scheme of the present invention, by for the user generates label, can get access to user's customized information quickly and easily, thereby can provide service for the user better; And scheme of the present invention implements simple and convenient, is convenient to popularize and promote.
Description of drawings
Fig. 1 generates the process flow diagram of the method embodiment of label for the user for the present invention.
Fig. 2 subscribes to the synoptic diagram of a certain information for user X.
Fig. 3 shares the synoptic diagram of a certain information for user X.
Fig. 4 generates the composition structural representation of the device embodiment of label for the user for the present invention.
Embodiment
At problems of the prior art, a kind of scheme that generates label for the user is proposed among the present invention.
For make technical scheme of the present invention clearer, understand, below with reference to the accompanying drawing embodiment that develops simultaneously, scheme of the present invention is described in further detail.
Fig. 1 generates the process flow diagram of the method embodiment of label for the user for the present invention.As shown in Figure 1, may further comprise the steps:
Step 11:, obtain the operation behavior information behind its logging in network in real time at arbitrary user X.
For explaining conveniently, represent arbitrary user with user X, at arbitrary user, all can handle according to mode of the present invention.
Behind the user X logging in network, can carry out various operation behaviors, subscribe to a certain information, shared a certain information as click, or paid close attention to a certain information etc., in actual applications, can obtain the operation behavior information of user X in real time.
Fig. 2 subscribes to the synoptic diagram of a certain information for user X; Fig. 3 shares the synoptic diagram of a certain information for user X.Shown in Fig. 2～3, user X can subscribe to " being shared with the good friend " button and shares corresponding information by clicking " subscription this column ".
Step 12: after whenever getting access to an operation behavior information, then carry out once following the processing: extract the keyword in this operation behavior information, and preserve; From all keywords of being preserved, select satisfactory keyword, as the label of user X.
Among the present invention, whenever get access to an operation behavior information, then generate a secondary label, and utilize newly-generated label to come the label that is generated is before upgraded.
Specifically, in this step,, can carry out following processing respectively at every the operation behavior information that gets access to:
1) extracts keyword in this operation behavior information, and preserve.
The keyword extraction mode of the concrete reverse file word frequency of adopted word frequency (TF, Term Frequency) * (IDF, Inverse Document Frequency).
Wherein, TF is meant in the given file of portion, the number of times that some given words occur in this document, and can carry out normalization according to file size; IDF is used to weigh the general importance of a word, and the IDF of a certain given word can be taken the logarithm divided by the merchant of the number of files that comprises this word by total files again and obtain; In present embodiment, an information can be regarded a file as, extracts the higher word of TF*IDF score value as keyword.
For this reason, need to preserve every the operation behavior information that gets access to, same, need to preserve the keyword of every the operation behavior information that extracts.
In actual applications, also can adopt other keyword extraction mode, such as, based on the keyword extraction mode of the N unit syntax (N-Gram) Information Statistics etc.
2) from all keywords of being preserved, select satisfactory keyword, as the label of user X.
Specifically, can determine the weight of each keyword of being preserved respectively, and sort according to the descending order of weight that the keyword of N position is as the label of user X before being in after will ordering, N is the positive integer greater than 1.
As previously mentioned, at every operation behavior information of being preserved, all can correspondingly preserve its keyword, so, can be at each keyword of being preserved, determine its weight respectively, and sort that the keyword of N position is as the label of user X before being in after will sorting then according to the descending order of weight.The concrete value of N can be decided according to the actual requirements, such as can be 3.
Weight how to determine each keyword can be decided according to the actual requirements equally, such as: the acquisition time of corresponding operation behavior information and between the current time at interval duration long more, corresponding weight is more little; Illustrate: suppose the acquisition time of corresponding operation behavior information and at interval duration is in 5 days between the current time, then its weight is 10, if within 5～10 days, then is 9, and the like; On this basis, also can be further combined with other factors, (from these two operation behavior information, all extracted this keyword such as corresponding two the operation behavior information of a keyword, when ordering, identical keyword can be handled as a keyword), the weight of one of them operation behavior information correspondence is 10, and another is 9, and this keyword final weights can be defined as 19 so; Certainly, also can determine the weight of each keyword, give unnecessary details no longer one by one in conjunction with other factors.
Perhaps, also can adopt other label generating mode, such as: after determining the weight of each keyword of being preserved respectively, greater than the keyword of the predetermined threshold label as user X, the concrete value of described threshold value can be decided according to the actual requirements with weight.
Except comprising selected keyword, also can further comprise one of following information or combination in any in the label of user X: the time (can reflect the active degree of user X etc. to a certain extent) of the classified information that each selected keyword is corresponding respectively, generation label, each selected keyword be the normalized weight value of correspondence respectively.
Wherein, the normalized weight value of can the employing standard dividing the normalization mode to obtain each keyword, specific implementation is a prior art, the realization that can divide with reference to the college entrance examination standard.
In addition, can preestablish the set of classification based training, comprising various classified informations, as ecommerce digital product class, winter cotton dress class, spring and autumn unlined garment class etc.Correspondingly, at each selected keyword Y, can carry out following processing respectively: calculate the similarity of each classified information in the set of keyword Y and predefined classification based training respectively, with the classified information of the result of calculation correspondence of value maximum classified information as keyword Y correspondence.
Can determine mode, determine mode based on the similarity of body by the morphology similarity, or determine that based on the similarity of corpus mode waits to determine the similarity between each keyword and each classified information, specific implementation be similarly prior art.
Illustrate: suppose that a keyword is " Nokia ", through calculate finding itself and the similarity maximum of " ecommerce digital product class " this classified information, classified information that so then will " ecommerce digital product class " this classified information conduct " Nokia " this keyword correspondence.
Obtain after the label of user X, the real-time inquiry service at the label of user X can be provided, and can come according to the label of user X, as push possibility information of interest etc. for user X for user X provides corresponding service.
Illustrate: suppose to comprise " Nokia " this keyword in the label of user X, so after it logins a shopping website, can be it and push the product information relevant with " Nokia ", in addition, because " Nokia " corresponding classified information is an ecommerce digital product class, therefore, can push the relevant information of other ecommerce digital product to it simultaneously.
In addition, also can set up the incidence relation between the different terms in advance, like this, when comprising a certain keyword in the label of user X, can be when user X push the information relevant with this keyword, the relevant information of the word that will be associated with this keyword also is pushed to user X.
Because the label of user X is a real-time update, therefore can in time holds the demand of user X, thereby push current most interested information for it.
In actual applications, following situation may occur: user X often pays close attention to a certain keyword in a certain period time period before, relevant information as Nokia, so, will get access to many relevant operation behavior information, like this, when keyword is sorted, though " Nokia " this keyword does not occur in the operation behavior information that gets access to recently, but in operation behavior information before, often occur, like this, this keyword final weights also may be bigger, thus N position before being in after the ordering, correspondingly, follow-uply will be that user X pushes the information relevant with Nokia, but in fact user X has not needed this category information, thereby it is inaccurate to cause pushing the result.
For overcoming the problems referred to above, can be every through after the scheduled duration, then with the acquisition time preserved and between the current time at interval duration greater than the operation behavior information deletion of scheduled duration, and carry out keyword extraction, preservation and selection again at remaining operation behavior information, with the satisfactory keyword selected label as user X.The concrete value of described scheduled duration can be decided according to the actual requirements, such as can be 1 month.
After having pushed the information relevant, can upgrade the label of user X according to the interest level of user X to the information that pushed with its label for user X.
Such as, pushed after the information for user X according to a keyword in the label, user X does not click this information of reading, so then the normalized weight value of the keyword of this information correspondence can be reduced, even directly delete this keyword, otherwise, if user X clicks this information of having read, then the normalized weight value of the keyword of this information correspondence can be increased, and preferentially carry out information push according to the bigger keyword of normalized weight value.
So far, promptly finished introduction about the inventive method embodiment.
Based on above-mentioned introduction, Fig. 4 generates the composition structural representation of the device embodiment of label for the user for the present invention.As shown in Figure 4, comprising:
Acquisition module is used at arbitrary user X, obtain the operation behavior information behind its logging in network in real time, and each bar operation behavior information that will get access to sends to processing module;
Processing module is used for after whenever receiving an operation behavior information, then carries out once following the processing: extract the keyword in this operation behavior information, and preserve; From all keywords of being preserved, select satisfactory keyword, as the label of user X.
Wherein, can specifically comprise in the processing module:
First processing unit is used for extracting the keyword of the operation behavior information that receives, and preserves;
Second processing unit is used for the weight of definite each keyword of being preserved respectively, and sorts according to the descending order of weight, will be in the label of the keyword of preceding N position as user X after the ordering, and N is the positive integer greater than 1; Perhaps, determine the weight of each keyword preserved respectively, with weight greater than the keyword of predetermined threshold label as user X.
Second processing unit can be further used for, at each selected keyword Y, carry out following processing respectively: calculate the similarity of each classified information in the set of keyword Y and predefined classification based training respectively, with the classified information of the result of calculation correspondence of value maximum classified information as keyword Y correspondence; With each selected keyword and respectively corresponding classified information label as user X.
Can further comprise one of following information or whole in the above-mentioned label: generate the time of label, the selected corresponding respectively normalized weight value of each keyword.
In addition, first processing unit can be further used for, and preserves every the operation behavior information that receives;
Correspondingly, second processing unit can be further used for, after every process scheduled duration, then with the acquisition time preserved and between the current time at interval duration greater than the operation behavior information deletion of scheduled duration, and carry out keyword extraction, preservation and selection again at remaining operation behavior information, with the satisfactory keyword selected label as user X.
Second processing unit also can be further used for, and is that user X pushes the information relevant with its label, and according to the interest level of user X to the information that pushed, the label of renewal user X.
The concrete workflow of device embodiment shown in Figure 4 please refer to the respective description among the method embodiment shown in Figure 1, repeats no more herein.
The above only is preferred embodiment of the present invention, and is in order to restriction the present invention, within the spirit and principles in the present invention not all, any modification of being made, is equal to replacement, improvement etc., all should be included within the scope of protection of the invention.
Claims (12)
1. one kind for the user generates the method for label, it is characterized in that, comprising:
At arbitrary user X, obtain the operation behavior information behind its logging in network in real time, and, then carry out once following the processing after whenever getting access to an operation behavior information:
Extract the keyword in this operation behavior information, and preserve;
From all keywords of being preserved, select satisfactory keyword, as the label of user X.
2. method according to claim 1 is characterized in that, describedly selects satisfactory keyword comprise from all keywords of being preserved:
Determine the weight of each keyword preserved respectively, and sort according to the descending order of weight that the keyword of N position is as the label of user X before being in after will ordering, N is the positive integer greater than 1;
Perhaps, determine the weight of each keyword preserved respectively, with weight greater than the keyword of predetermined threshold label as user X.
3. method according to claim 1 is characterized in that, described selecting after the satisfactory keyword further comprises:
Each keyword Y at selected, carry out following processing respectively:
Calculate the similarity of each classified information in the set of keyword Y and predefined classification based training respectively, with the classified information of the result of calculation correspondence of value maximum classified information as keyword Y correspondence;
With each selected keyword and respectively corresponding classified information label as user X.
4. method according to claim 2 is characterized in that, further comprises one of following information or whole in the described label: generate the time of label, the selected corresponding respectively normalized weight value of each keyword.
5. method according to claim 1 is characterized in that, this method further comprises:
After whenever getting access to an operation behavior information, then preserve this operation behavior information;
And, after every process scheduled duration, then with the acquisition time preserved and between the current time at interval duration greater than the operation behavior information deletion of scheduled duration, and carry out keyword extraction, preservation and selection again at remaining operation behavior information, with the satisfactory keyword selected label as user X.
6. according to claim 1,3 or 5 described methods, it is characterized in that this method further comprises: be that user X pushes the information relevant with its label, and according to the interest level of user X to the information that pushed, the label of renewal user X.
7. one kind for the user generates the device of label, it is characterized in that, comprising:
Acquisition module is used at arbitrary user X, obtain the operation behavior information behind its logging in network in real time, and each bar operation behavior information that will get access to sends to processing module;
Described processing module is used for after whenever receiving an operation behavior information, then carries out once following the processing: extract the keyword in this operation behavior information, and preserve; From all keywords of being preserved, select satisfactory keyword, as the label of user X.
8. device according to claim 7 is characterized in that, comprises in the described processing module:
First processing unit is used for extracting the keyword of the operation behavior information that receives, and preserves;
Second processing unit is used for the weight of definite each keyword of being preserved respectively, and sorts according to the descending order of weight, will be in the label of the keyword of preceding N position as user X after the ordering, and N is the positive integer greater than 1; Perhaps, determine the weight of each keyword preserved respectively, with weight greater than the keyword of predetermined threshold label as user X.
9. device according to claim 8, it is characterized in that, described second processing unit is further used for, at each selected keyword Y, carry out following processing respectively: calculate the similarity of each classified information in the set of keyword Y and predefined classification based training respectively, with the classified information of the result of calculation correspondence of value maximum classified information as keyword Y correspondence; With each selected keyword and respectively corresponding classified information label as user X.
10. device according to claim 8 is characterized in that, further comprises one of following information or whole in the described label: generate the time of label, the selected corresponding respectively normalized weight value of each keyword.
11. device according to claim 8 is characterized in that,
Described first processing unit is further used for, and preserves every the operation behavior information that receives;
Described second processing unit is further used for, after every process scheduled duration, then with the acquisition time preserved and between the current time at interval duration greater than the operation behavior information deletion of scheduled duration, and carry out keyword extraction, preservation and selection again at remaining operation behavior information, with the satisfactory keyword selected label as user X.
12. device according to claim 8 is characterized in that, described second processing unit is further used for, and is that user X pushes the information relevant with its label, and according to the interest level of user X to the information that pushed, the label of renewal user X.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210015741.8A CN103218355B (en) | 2012-01-18 | 2012-01-18 | A kind of method and apparatus generating label for user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210015741.8A CN103218355B (en) | 2012-01-18 | 2012-01-18 | A kind of method and apparatus generating label for user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103218355A true CN103218355A (en) | 2013-07-24 |
| CN103218355B CN103218355B (en) | 2016-08-31 |
Family
ID=48816159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210015741.8A Active CN103218355B (en) | 2012-01-18 | 2012-01-18 | A kind of method and apparatus generating label for user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103218355B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133906A (en) * | 2014-08-06 | 2014-11-05 | 深圳市英威诺科技有限公司 | Technical method for filtering and intelligent sorting of information |
| CN104216881A (en) * | 2013-05-29 | 2014-12-17 | 腾讯科技（深圳）有限公司 | Method and device for recommending individual labels |
| WO2015021937A1 (en) * | 2013-08-14 | 2015-02-19 | 腾讯科技（深圳）有限公司 | Method and device for user recommendation |
| CN104572951A (en) * | 2014-12-29 | 2015-04-29 | 微梦创科网络科技（中国）有限公司 | Ability label determining method |
| CN104572733A (en) * | 2013-10-22 | 2015-04-29 | 腾讯科技（深圳）有限公司 | User interest tag classification method and device |
| CN105005587A (en) * | 2015-06-26 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | User portrait updating method, apparatus and system |
| CN105260877A (en) * | 2015-09-22 | 2016-01-20 | 世纪龙信息网络有限责任公司 | E-mail-based method for acquiring data of user portrait |
| 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 |
| CN106528851A (en) * | 2016-11-24 | 2017-03-22 | 腾讯科技（深圳）有限公司 | Intelligent recommendation method and device |
| WO2017080176A1 (en) * | 2015-11-12 | 2017-05-18 | 乐视控股（北京）有限公司 | Individual user profiling method and system |
| CN107005679A (en) * | 2014-07-11 | 2017-08-01 | 王向恒 | A kind of intelligent Target identifying device based on cloud service, system and method |
| CN107038213A (en) * | 2017-02-28 | 2017-08-11 | 华为技术有限公司 | A kind of method and device of video recommendations |
| CN107180098A (en) * | 2017-05-16 | 2017-09-19 | 武汉斗鱼网络科技有限公司 | Keyword eliminates method and device in a kind of information search |
| CN107451168A (en) * | 2016-05-30 | 2017-12-08 | 中华电信股份有限公司 | File Classification System and Method Based on Vocabulary Statistics |
| CN107526741A (en) * | 2016-06-21 | 2017-12-29 | 华为软件技术有限公司 | user tag generation method and device |
| WO2018023685A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Method for recognizing user's interests and recognition system |
| CN108153752A (en) * | 2016-12-02 | 2018-06-12 | 腾讯科技（北京）有限公司 | A kind of method and device of determining text key word |
| CN108304539A (en) * | 2018-01-30 | 2018-07-20 | 平安科技（深圳）有限公司 | Qualified database method for building up, device and storage medium |
| CN109447717A (en) * | 2018-11-12 | 2019-03-08 | 万惠投资管理有限公司 | A kind of determination method and system of label |
| CN109522467A (en) * | 2018-11-14 | 2019-03-26 | 江苏中威科技软件系统有限公司 | A kind of analysis method and device of the label time based on big data platform |
| CN110097407A (en) * | 2019-05-10 | 2019-08-06 | 宁波奥克斯电气股份有限公司 | A kind of generation method and system of user tag |
| CN111079026A (en) * | 2019-11-28 | 2020-04-28 | 精硕科技（北京）股份有限公司 | Method, storage medium and device for determining character impression data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030101415A1 (en) * | 2001-11-23 | 2003-05-29 | Eun Yeung Chang | Method of summarizing markup-type documents automatically |
| CN101243442A (en) * | 2005-08-18 | 2008-08-13 | 微软公司 | Annotating shared contacts with public descriptors |
| 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 |
-
2012
- 2012-01-18 CN CN201210015741.8A patent/CN103218355B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030101415A1 (en) * | 2001-11-23 | 2003-05-29 | Eun Yeung Chang | Method of summarizing markup-type documents automatically |
| CN101243442A (en) * | 2005-08-18 | 2008-08-13 | 微软公司 | Annotating shared contacts with public descriptors |
| 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 |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216881A (en) * | 2013-05-29 | 2014-12-17 | 腾讯科技（深圳）有限公司 | Method and device for recommending individual labels |
| WO2015021937A1 (en) * | 2013-08-14 | 2015-02-19 | 腾讯科技（深圳）有限公司 | Method and device for user recommendation |
| CN104572733A (en) * | 2013-10-22 | 2015-04-29 | 腾讯科技（深圳）有限公司 | User interest tag classification method and device |
| CN107005679A (en) * | 2014-07-11 | 2017-08-01 | 王向恒 | A kind of intelligent Target identifying device based on cloud service, system and method |
| CN104133906A (en) * | 2014-08-06 | 2014-11-05 | 深圳市英威诺科技有限公司 | Technical method for filtering and intelligent sorting of information |
| CN104133906B (en) * | 2014-08-06 | 2018-07-31 | 深圳市英威诺科技有限公司 | A kind of information filters the technical method of simultaneously intelligent sequencing |
| CN104572951B (en) * | 2014-12-29 | 2018-07-17 | 微梦创科网络科技（中国）有限公司 | A kind of determination method and device of ability label |
| CN104572951A (en) * | 2014-12-29 | 2015-04-29 | 微梦创科网络科技（中国）有限公司 | Ability label determining method |
| CN105005587A (en) * | 2015-06-26 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | User portrait updating method, apparatus and system |
| CN105260877A (en) * | 2015-09-22 | 2016-01-20 | 世纪龙信息网络有限责任公司 | E-mail-based method for acquiring data of user portrait |
| WO2017080176A1 (en) * | 2015-11-12 | 2017-05-18 | 乐视控股（北京）有限公司 | Individual user profiling method and system |
| CN107451168A (en) * | 2016-05-30 | 2017-12-08 | 中华电信股份有限公司 | File Classification System and Method Based on Vocabulary Statistics |
| CN107526741B (en) * | 2016-06-21 | 2021-05-18 | 华为技术有限公司 | User label generation method and device |
| CN107526741A (en) * | 2016-06-21 | 2017-12-29 | 华为软件技术有限公司 | user tag generation method and device |
| WO2018023685A1 (en) * | 2016-08-05 | 2018-02-08 | 吴晓敏 | Method for recognizing user's interests and recognition 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 |
| CN106528851A (en) * | 2016-11-24 | 2017-03-22 | 腾讯科技（深圳）有限公司 | Intelligent recommendation method and device |
| CN108153752A (en) * | 2016-12-02 | 2018-06-12 | 腾讯科技（北京）有限公司 | A kind of method and device of determining text key word |
| CN107038213A (en) * | 2017-02-28 | 2017-08-11 | 华为技术有限公司 | A kind of method and device of video recommendations |
| CN107180098A (en) * | 2017-05-16 | 2017-09-19 | 武汉斗鱼网络科技有限公司 | Keyword eliminates method and device in a kind of information search |
| CN107180098B (en) * | 2017-05-16 | 2019-11-12 | 武汉斗鱼网络科技有限公司 | Keyword eliminates method and device in a kind of information search |
| CN108304539A (en) * | 2018-01-30 | 2018-07-20 | 平安科技（深圳）有限公司 | Qualified database method for building up, device and storage medium |
| CN109447717A (en) * | 2018-11-12 | 2019-03-08 | 万惠投资管理有限公司 | A kind of determination method and system of label |
| CN109522467A (en) * | 2018-11-14 | 2019-03-26 | 江苏中威科技软件系统有限公司 | A kind of analysis method and device of the label time based on big data platform |
| CN110097407A (en) * | 2019-05-10 | 2019-08-06 | 宁波奥克斯电气股份有限公司 | A kind of generation method and system of user tag |
| CN111079026A (en) * | 2019-11-28 | 2020-04-28 | 精硕科技（北京）股份有限公司 | Method, storage medium and device for determining character impression data |
| CN111079026B (en) * | 2019-11-28 | 2023-11-24 | 北京秒针人工智能科技有限公司 | Method, storage medium and device for determining character impression data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103218355B (en) | 2016-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103218355A (en) | Method and device for generating tags for user | |
| CN102279851B (en) | Intelligent navigation method, device and system | |
| CN107295361B (en) | A kind of content delivery method | |
| CN102053983B (en) | Method, system and device for querying vertical search | |
| CN103902697B (en) | Combinatorial search method, client and server | |
| CN105227971A (en) | The information recommendation method of a kind of hotel TV and system | |
| CN104636429B (en) | Trademark class search method and device | |
| CN109388760B (en) | Recommendation label obtaining method, media content recommendation method, device and storage medium | |
| CN105678317B (en) | Information processing method and server | |
| KR20160058896A (en) | System and method for analyzing and transmitting social communication data | |
| CN106445963B (en) | Advertisement index keyword automatic generation method and device of APP platform | |
| EP3306486A1 (en) | Pushed information processing method, apparatus, and device, and non-volatile computer storage medium | |
| JP2013545189A (en) | Determining category information using multistage | |
| CN103778225B (en) | Processing method, identification device and the system of advertisement marketing speech like sound information | |
| CN101547162A (en) | Method and device for tagging user based on user state information | |
| CN109597858B (en) | Merchant classification method and device and merchant recommendation method and device | |
| CN104462096B (en) | Public sentiment method for monitoring and analyzing and device | |
| CN105279206A (en) | Intelligent recommendation method and system | |
| CN107766446A (en) | Method for pushing, device, storage medium and the processor of information | |
| CN103885976A (en) | Method for configuring recommend information in webpage and index service | |
| CN111242709A (en) | Message pushing method and device, equipment and storage medium thereof | |
| CN105447205B (en) | Method and device for sorting search results | |
| CN111447081B (en) | Data link generation method, device, server and storage medium | |
| WO2017107010A1 (en) | Information analysis system and method based on event regression test | |
| CN106844792B (en) | Method and system for realizing advertisement of primary information designated audience of social relationship |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |