CN103455485A - Method and device for automatically updating user interest model - Google Patents
Method and device for automatically updating user interest model Download PDFInfo
- Publication number
- CN103455485A CN103455485A CN2012101688700A CN201210168870A CN103455485A CN 103455485 A CN103455485 A CN 103455485A CN 2012101688700 A CN2012101688700 A CN 2012101688700A CN 201210168870 A CN201210168870 A CN 201210168870A CN 103455485 A CN103455485 A CN 103455485A
- Authority
- CN
- China
- Prior art keywords
- user
- feedback
- user interest
- interest model
- interest
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to a method and a device for automatically updating a user interest model. The method particularly includes the steps: filtering push messages according to a current user interest model, and displaying the push messages to a user; acquiring feedback data after the user browses the push messages, and automatically updating the user interest model after analyzing the feedback data. According to the method and the device for automatically updating the user interest model, messages not interesting the user are filtered by the user interest model, the user interest model is automatically updated according to feedback of the user, so that better personalized service is provided for the user, and search efficiency is improved.
Description
Technical field
The present invention relates to field of computer technology, specifically a kind of automatic renewal user interest model method and device thereof.
Background technology
At present, people usually utilize the mode of search information after search engine input key word to obtain the network information.But, this mode hit rate based on keyword query is low, and it is difficult to meet the inquiry request of different purposes, different background and different times, can't automatically adjust to cater to browsing interest and automatically recommending in real time the page for the user of each user, thereby can not promptly for the user, provide its needed service.On the other hand; birth along with pushed information; the user often can receive unwanted rubbish PUSH message, this message push severe jamming of not distinguishing user interest user's life, cause providing the businessman of Push Service also can't reach the purpose that it uses extension service.
Personalized Service Technology can address the above problem effectively, and its core is the demand of match user, therefore how to solve the foundation of user interest model and the key that renewal technology becomes personalized service.
Summary of the invention
Fundamental purpose of the present invention is to provide a kind of automatic renewal user interest model method and device, thinks that the user provides the personalized service that meets its interest.
The present invention proposes a kind of automatic renewal user interest model method, comprising:
Filter PUSH message and be shown to the user according to current user interest model;
Obtain the feedback data after the user browses PUSH message, analyze after described feedback data and automatically upgrade user interest model.
Preferably, describedly also comprise before filtering PUSH message and be shown to user's step according to current user interest model:
Receive the interest keyword of user's input and the weight of each described interest keyword;
Utilize the vector space model method that user interest is expressed as to vector, set up the initial interest model of user.
Preferably, described user's feedback comprises positive feedback and negative feedback, when user feedback is interesting to PUSH message, is described positive feedback, when user feedback is not interested to PUSH message, is described negative feedback.
Preferably, after described analysis feedback data, the automatic step of upgrading user interest model specifically comprises:
When the user be fed back to described positive feedback the time, adopt formula
upgrade user interest model;
When the user be fed back to described negative feedback the time, adopt formula
upgrade user interest model;
Wherein,
for new user interest vector,
for old user interest vector,
for the vector representation of feedback document, α is old user interest vector weight, and β is the positive feedback weight, and γ is the negative feedback weight, and alpha+beta=1, α+γ=1.
Preferably, the feedback of described analysis user also comprises after automatically upgrading afterwards the step of user interest model:
When user's off-line, utilize all feedbacks that get, utilize default formula to upgrade described user interest model.
The present invention also proposes a kind of for automatically upgrading the device of user interest model, comprising:
Filtering module, filter PUSH message and be shown to the user for the user interest model according to current;
Update module, for accepting the feedback after the user browses PUSH message, upgrade user interest model automatically according to user's feedback.
Preferably, described device also comprises:
Load module, for the interest keyword that receives user input and the weight of each described interest keyword;
Build module, for utilizing the vector space model method, user interest is expressed as to vector, set up the initial interest model of user.
Preferably, described user's feedback comprises positive feedback and negative feedback, when user feedback is interesting to PUSH message, is described positive feedback, when user feedback is not interested to PUSH message, is described negative feedback.
Preferably, described update module specifically for:
When the user be fed back to described positive feedback the time, adopt formula
upgrade user interest model;
When the user be fed back to described negative feedback the time, adopt formula
upgrade user interest model;
Wherein,
for new user interest vector,
for old user interest vector,
for the vector representation of feedback document, α is old user interest vector weight, and β is the positive feedback weight, and γ is the negative feedback weight, and alpha+beta=1, α+γ=1.
Preferably, described device also comprises the off-line update module, for:
When user's off-line, utilize all feedbacks that get, utilize default formula to upgrade described user interest model.
Automatic renewal user interest model method provided by the invention and device, filter out the message of non-user interest by user interest model, and automatically upgrade user interest model according to user's feedback, thereby, for the user provides better personalized service, improve search efficiency.
The accompanying drawing explanation
The schematic flow sheet that Fig. 1 is automatic renewal user interest model one embodiment provided by the invention;
The schematic flow sheet that Fig. 2 is automatic another embodiment of renewal user interest model provided by the invention;
Fig. 3 is provided by the invention for automatically upgrading the structural representation of device one embodiment of user interest model;
Fig. 4 is provided by the invention for automatically upgrading the structural representation of another embodiment of device of user interest model;
Fig. 5 is provided by the invention for automatically upgrading the structural representation of the another embodiment of device of user interest model.
The realization of the object of the invention, functional characteristics and advantage, in connection with embodiment, are described further with reference to accompanying drawing.
Embodiment
In order to make purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
The automatic renewal user model method that the present invention proposes and the range of application of device comprise the PUSH message filtration, in the personalized services such as the commercial product recommending of various e-commerce websites, forum's service recommendation and the filtration of RSS subscribed content.Adopt the drift of default formula track user interest, proposed a kind of method of adaptive updates user interest model, thereby can provide personalized service better to the user, farthest meet user's demand.In the embodiment that the present invention proposes, be filtered into example with PUSH message and be described further, those skilled in the art can know, the implementation in other similar personalized services similarly, does not repeat them here.
Please refer to Fig. 1, the schematic flow sheet of the automatic renewal user interest model method that Fig. 1 provides for the embodiment of the present invention, as shown in Figure 1, in the present embodiment, the method specifically comprises the following steps:
S10: according to current user interest model, filter PUSH message and be shown to the user;
According to current user interest model, system is filtered PUSH message, and PUSH message that simultaneously will be irrelevant with active user's interest is stored separately, to facilitate the user, checks later.After completing filtration, system is shown to the user by PUSH message after filtering.In other embodiment, system can also will be deleted with the irrelevant PUSH message of active user's interest, to save system memory space.
S20: obtain the feedback data after the user browses PUSH message, automatically upgrade user interest model after the analysis feedback data;
In the present embodiment, whether system points out the user to select when to the user, showing PUSH message interested in this PUSH message, for example, eject problem " whether interested in this PUSH message " and accept user's selection to the user, perhaps in ending place of PUSH message to the user, point out problem and accept user's selection, according to user's feedback data, automatically upgrade user interest model.
Further, user's feedback message is divided into positive feedback and negative feedback, when user feedback is interesting to PUSH message, be positive feedback, be negative feedback when user feedback is not interested to PUSH message, to distinguish positive feedback and negative feedback, user interest model upgraded more targetedly.In other embodiment, the key word of the PUSH message that system can also counting user have been read, according to the keyword analyses user's who counts on interest, and according to the automatically updating data user interest model got.After the feedback data according to the user is upgraded user interest model, when having new PUSH message to enter system, interest that can track user, filter out the part pushed information, thereby provide more personalized service for the user.
More specifically, in the present embodiment, when the user reads certain PUSH message and feeds back the evaluation to this PUSH message, when interested in this message, be the single positive feedback, according to Rocchio single positive feedback algorithmic formula
upgrade user interest model; When the user loses interest in to this message, be the single negative feedback, according to Rocchio single negative feedback algorithmic formula
upgrade user interest model.Wherein,
for new user interest vector,
for old user interest vector,
for the vector representation of feedback document, α is old user interest vector weight, and β is the positive feedback weight, and γ is the negative feedback weight, and alpha+beta=1, α+γ=1.
After the renewal completed user interest model, judge whether the user logs off, if so, online updating finishes, otherwise proceeds the renewal of user interest model.
Please refer to Fig. 2, the schematic flow sheet of the automatic renewal user interest model method that Fig. 2 is another embodiment of the present invention proposition as shown in Figure 2, also comprised before step S10:
Step S30: accept the interest keyword of user's input and the weight of each interest keyword;
When the user logins first, now user interest model is not also set up, and owing to there is no Visitor Logs, need to be inputted by the user weight of its interest keyword and each interest keyword, system is accepted the information of user's input so that the initialized user interest model of system made.In other embodiment, the user can also be registered when login system first, at first input essential information (comprising the personal information such as user name, password) when registration, so that the user is associated with corresponding user interest model, makes and set up a plurality of user interest models in same system.
Step S40: utilize vectorial control modelling that user interest is expressed as to vector, set up the initial interest model of user;
More specifically, utilize interest keyword vector representation user interest model, be about to user interest and be expressed as the set { word that the interest keyword forms
1, word
2..., word
n, word wherein
j(j=1,2 ..., n) expression user's item of interest j.Each item of interest word
jgive certain weights ω according to the height of user interest
j, and
user interest model can be expressed as to 1 two tuple set, Profile={word
1, ω
1), (word
2, ω
2) ..., (word
n, ω
n), i.e. initial user interest model vector.After the initial user interest model is set up, read the feedback of pushed information according to subsequent user, user interest model is upgraded, so that it is more suitable for user's individual demand.
On the basis of previous embodiment, in another embodiment, the step that the feedback of analysis user is upgraded user interest model afterwards automatically also comprises afterwards:
When user's off-line, utilize all feedbacks that get, utilize formula after differentiation positive feedback and negative feedback
Upgrade described user interest model;
After user log off, native system also, according to the repeatedly feedback data got, utilizes the Rocchio algorithm, and off-line upgrades user interest model, and concrete steps comprise:
All feedback informations when the collection user is online;
Distinguish positive feedback information and negative-feedback information from all feedback informations of collecting;
According to
Upgrade corresponding user interest model.
The repeatedly feedback algorithm used during by off-line, the deviation occurred in the time of can correcting online use single feedback, the stability of raising whole system, the interest that user interest model more is close to the users.
Automatic renewal user interest model method provided by the invention, filter out the message of non-user interest by user interest model, and automatically upgrade user interest model according to user's feedback, thereby, for the user provides better personalized service, improve search efficiency.
Please refer to Fig. 3, further embodiment of this invention also proposes a kind of for automatically upgrading the device of user interest model, and as shown in Figure 3, this device specifically comprises:
According to current user interest model, 100 pairs of PUSH message of filtering module are filtered, and PUSH message that simultaneously will be irrelevant with active user's interest is stored separately, to facilitate the user, checks later.After completing filtration, filtering module 100 is shown to the user by PUSH message after filtering.In other embodiment, filtering module 100 can also will be deleted with the irrelevant PUSH message of active user's interest, to save system memory space.
In the present embodiment, whether update module 200 points out the user to select when to the user, showing PUSH message interested in this PUSH message, for example, update module 200 ejects problem " whether interested in this PUSH message " and accepts user's selection to the user, perhaps in ending place of PUSH message to the user, point out problem and accept user's selection, according to user's feedback data, automatically upgrade user interest model.Further, user's feedback message is divided into positive feedback and negative feedback, when user feedback is interesting to PUSH message, be positive feedback, be negative feedback when user feedback is not interested to PUSH message, to distinguish positive feedback and negative feedback, user interest model upgraded more targetedly.In other embodiment, the key word of the PUSH message that update module 200 can also counting user have been read, according to the keyword analyses user's who counts on interest, and according to the automatically updating data user interest model got.After update module 200 is upgraded user interest model according to user's feedback data, when having new PUSH message to enter system, interest that can track user, filter out the part pushed information, thereby provide more personalized service for the user.
More specifically, in the present embodiment, when the user reads certain PUSH message and feeds back the evaluation to this PUSH message, when interested in this message, be the single positive feedback, according to Rocchio single positive feedback algorithmic formula
upgrade user interest model; When the user loses interest in to this message, be the single negative feedback, according to Rocchio single negative feedback algorithmic formula
upgrade user interest model.Wherein,
for new user interest vector,
for old user interest vector,
for the vector representation of feedback document, α is old user interest vector weight, and β is the positive feedback weight, and γ is the negative feedback weight, and alpha+beta=1, α+γ=1.
After the renewal completed user interest model, judge whether the user logs off, if so, online updating finishes, otherwise proceeds the renewal of user interest model.
Please refer to Fig. 4, the structural representation of the device for automatic renewal user interest model that Fig. 4 is further embodiment of this invention proposition, as shown in Figure 4, this device also comprises:
When the user logins first, now user interest model is not also set up, and owing to there is no Visitor Logs, need to be inputted the weight of its interest keyword and each interest keyword by the user, build module 400 and accept the information of user's input so that the initialized user interest model of system made.In other embodiment, the user can also be registered when login system first, at first input essential information (comprising the personal information such as user name, password) when registration, so that the user is associated with corresponding user interest model, makes and set up a plurality of user interest models in same system.
More specifically, build module 400 and utilize interest keyword vector representation user interest model, be about to user interest and be expressed as the set { word that the interest keyword forms
1, word
2..., word
n, word wherein
j(j=1,2 ..., n) expression user's item of interest j.Each item of interest word
jgive certain weights ω according to the height of user interest
j, and
user interest model can be expressed as to 1 two tuple set, Profile={ (word
1, ω
1), (word
2, ω
2) ..., (word
n, ω
n), i.e. initial user interest model vector.After the initial user interest model is set up, read the feedback of pushed information according to subsequent user, user interest model is upgraded, so that it is more suitable for user's individual demand.
On the basis of previous embodiment, with reference to Fig. 5, in another embodiment, also comprise off-line update module 500 for the device that automatically upgrades user interest model, for when user's off-line, utilize all feedbacks that get, utilize formula after differentiation positive feedback and negative feedback
Upgrade described user interest model;
After user log off, this device is also according to the repeatedly feedback data got, and off-line upgrades user interest model, and the concrete steps that off-line update module 500 is upgraded user interest model comprise:
All feedback informations when the collection user is online;
Distinguish positive feedback information and negative-feedback information from all feedback informations of collecting;
According to
Upgrade corresponding user interest model.
The repeatedly feedback algorithm used during by off-line, the deviation occurred in the time of can correcting online use single feedback, the stability of raising whole system, the interest that user interest model more is close to the users.
Provided by the invention for automatically upgrading the device of user interest model, filter out the message of non-user interest by user interest model, and automatically upgrade user interest model according to user's feedback, thereby, for the user provides better personalized service, improve search efficiency.
These are only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. one kind is upgraded the user interest model method automatically, it is characterized in that, comprising:
Filter PUSH message and be shown to the user according to current user interest model;
Obtain the feedback data after the user browses PUSH message, analyze after described feedback data and automatically upgrade user interest model.
2. method according to claim 1, is characterized in that, describedly also comprises before filtering PUSH message and be shown to user's step according to current user interest model:
Receive the interest keyword of user's input and the weight of each described interest keyword;
Utilize the vector space model method that user interest is expressed as to vector, set up the initial interest model of user.
3. method according to claim 1, is characterized in that, described user's feedback comprises positive feedback and negative feedback, when user feedback is interesting to PUSH message, is described positive feedback, when user feedback is not interested to PUSH message, is described negative feedback.
4. method according to claim 1, is characterized in that, the step of automatically upgrading user interest model after described analysis feedback data specifically comprises:
When the user be fed back to described positive feedback the time, adopt formula
upgrade user interest model;
When the user be fed back to described negative feedback the time, adopt formula
upgrade user interest model;
Wherein,
for new user interest vector,
for old user interest vector,
for the vector representation of feedback document, α is old user interest vector weight, and β is the positive feedback weight, and γ is the negative feedback weight, and alpha+beta=1, α+γ=1.
5. according to the described method of claim 1 to 4 any one, it is characterized in that, the step of automatically upgrading user interest model after the feedback data of described analysis user also comprises afterwards:
When user's off-line, utilize all feedbacks that get, utilize default formula to upgrade described user interest model.
6. the device for automatic renewal user interest model, is characterized in that, comprising:
Filtering module, filter PUSH message and be shown to the user for the user interest model according to current;
Update module, for accepting the feedback after the user browses PUSH message, upgrade user interest model automatically according to user's feedback.
7. device according to claim 6, is characterized in that, described device also comprises:
Load module, for the interest keyword that receives user input and the weight of each described interest keyword;
Build module, for utilizing the vector space model method, user interest is expressed as to vector, set up the initial interest model of user.
8. device according to claim 6, is characterized in that, described user's feedback comprises positive feedback and negative feedback, when user feedback is interesting to PUSH message, is described positive feedback, when user feedback is not interested to PUSH message, is described negative feedback.
9. device according to claim 6, is characterized in that, described update module specifically for:
When the user be fed back to described positive feedback the time, adopt formula
upgrade user interest model;
When the user be fed back to described negative feedback the time, adopt formula
upgrade user interest model;
Wherein,
for new user interest vector,
for old user interest vector,
for the vector representation of feedback document, α is old user interest vector weight, and β is the positive feedback weight, and γ is the negative feedback weight, and alpha+beta=1, α+γ=1.
10. according to the described device of claim 6 to 9 any one, it is characterized in that, described device also comprises the off-line update module, for:
When user's off-line, utilize all feedbacks that get, utilize default formula to upgrade described user interest model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101688700A CN103455485A (en) | 2012-05-28 | 2012-05-28 | Method and device for automatically updating user interest model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101688700A CN103455485A (en) | 2012-05-28 | 2012-05-28 | Method and device for automatically updating user interest model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103455485A true CN103455485A (en) | 2013-12-18 |
Family
ID=49737867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101688700A Pending CN103455485A (en) | 2012-05-28 | 2012-05-28 | Method and device for automatically updating user interest model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103455485A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933163A (en) * | 2015-06-26 | 2015-09-23 | 广西中烟工业有限责任公司 | Product customization system based on social group and product customization method based on social group |
| CN105407152A (en) * | 2015-11-03 | 2016-03-16 | 竞技世界（杭州）网络技术有限公司 | Message pushing method |
| CN105677316A (en) * | 2015-12-24 | 2016-06-15 | 小米科技有限责任公司 | Message notification filtering method and apparatus |
| CN105874457A (en) * | 2016-03-30 | 2016-08-17 | 马岩 | Network information push method and system |
| CN106647645A (en) * | 2015-11-02 | 2017-05-10 | 中兴通讯股份有限公司 | Method and system for home control adjustment |
| CN107391511A (en) * | 2016-05-16 | 2017-11-24 | ***通信集团内蒙古有限公司 | A kind of information-pushing method and device |
| CN107562912A (en) * | 2017-09-12 | 2018-01-09 | 电子科技大学 | Sina weibo event recommendation method |
| CN107612966A (en) * | 2017-08-11 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Feed information feedback processing methods and system |
| CN107861674A (en) * | 2017-06-27 | 2018-03-30 | 陆金所（上海）科技服务有限公司 | Financial Information method for pushing, display device and computer-readable recording medium |
| CN108476259A (en) * | 2015-12-29 | 2018-08-31 | 华为技术有限公司 | The system and method for commending contents based on user behavior |
| CN108616444A (en) * | 2018-03-30 | 2018-10-02 | 平安科技（深圳）有限公司 | A kind of PUSH message processing method, computer readable storage medium and terminal device |
| CN108846062A (en) * | 2018-06-04 | 2018-11-20 | 上海市疾病预防控制中心 | Method for pushing based on users ' individualized requirement |
| CN109063157A (en) * | 2018-08-10 | 2018-12-21 | 优视科技新加坡有限公司 | Resource recommendation method and its device, equipment/terminal/server, computer-readable medium |
| CN109165315A (en) * | 2018-08-24 | 2019-01-08 | 大陆汽车投资（上海）有限公司 | In-vehicle information/entertainment service method is pushed based on machine learning |
| CN112634881A (en) * | 2020-12-30 | 2021-04-09 | 广州博士信息技术研究院有限公司 | Intelligent voice recognition method and system based on scientific and technological achievement database |
| CN115037791A (en) * | 2022-04-13 | 2022-09-09 | 中国电信股份有限公司 | Event pushing method, device and system, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090138326A1 (en) * | 2004-11-18 | 2009-05-28 | Koninklijke Philips Electronics, N.V. | Apparatus and method for updating user profile |
| CN101520784A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Information issuing system and information issuing method |
| CN101551806A (en) * | 2008-04-03 | 2009-10-07 | 北京搜狗科技发展有限公司 | Personalized website navigation method and system |
-
2012
- 2012-05-28 CN CN2012101688700A patent/CN103455485A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090138326A1 (en) * | 2004-11-18 | 2009-05-28 | Koninklijke Philips Electronics, N.V. | Apparatus and method for updating user profile |
| CN101520784A (en) * | 2008-02-29 | 2009-09-02 | 富士通株式会社 | Information issuing system and information issuing method |
| CN101551806A (en) * | 2008-04-03 | 2009-10-07 | 北京搜狗科技发展有限公司 | Personalized website navigation method and system |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104933163A (en) * | 2015-06-26 | 2015-09-23 | 广西中烟工业有限责任公司 | Product customization system based on social group and product customization method based on social group |
| CN104933163B (en) * | 2015-06-26 | 2018-03-06 | 广西中烟工业有限责任公司 | A kind of product ordering system and method based on community |
| CN106647645A (en) * | 2015-11-02 | 2017-05-10 | 中兴通讯股份有限公司 | Method and system for home control adjustment |
| CN105407152A (en) * | 2015-11-03 | 2016-03-16 | 竞技世界（杭州）网络技术有限公司 | Message pushing method |
| CN105677316A (en) * | 2015-12-24 | 2016-06-15 | 小米科技有限责任公司 | Message notification filtering method and apparatus |
| CN108476259A (en) * | 2015-12-29 | 2018-08-31 | 华为技术有限公司 | The system and method for commending contents based on user behavior |
| US10664500B2 (en) | 2015-12-29 | 2020-05-26 | Futurewei Technologies, Inc. | System and method for user-behavior based content recommendations |
| CN108476259B (en) * | 2015-12-29 | 2021-10-01 | 华为技术有限公司 | System and method for content recommendation based on user behavior |
| US11500907B2 (en) | 2015-12-29 | 2022-11-15 | Futurewei Technologies, Inc. | System and method for user-behavior based content recommendations |
| CN114138993A (en) * | 2015-12-29 | 2022-03-04 | 华为技术有限公司 | System and method for content recommendation based on user behavior |
| CN105874457A (en) * | 2016-03-30 | 2016-08-17 | 马岩 | Network information push method and system |
| WO2017166132A1 (en) * | 2016-03-30 | 2017-10-05 | 马岩 | Network information pushing method and system |
| CN107391511A (en) * | 2016-05-16 | 2017-11-24 | ***通信集团内蒙古有限公司 | A kind of information-pushing method and device |
| CN107861674A (en) * | 2017-06-27 | 2018-03-30 | 陆金所（上海）科技服务有限公司 | Financial Information method for pushing, display device and computer-readable recording medium |
| CN107612966B (en) * | 2017-08-11 | 2021-01-26 | 百度在线网络技术（北京）有限公司 | Feed information feedback processing method and system |
| CN107612966A (en) * | 2017-08-11 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Feed information feedback processing methods and system |
| CN107562912A (en) * | 2017-09-12 | 2018-01-09 | 电子科技大学 | Sina weibo event recommendation method |
| CN108616444B (en) * | 2018-03-30 | 2019-10-25 | 平安科技（深圳）有限公司 | A kind of PUSH message processing method, computer readable storage medium and terminal device |
| CN108616444A (en) * | 2018-03-30 | 2018-10-02 | 平安科技（深圳）有限公司 | A kind of PUSH message processing method, computer readable storage medium and terminal device |
| CN108846062A (en) * | 2018-06-04 | 2018-11-20 | 上海市疾病预防控制中心 | Method for pushing based on users ' individualized requirement |
| CN109063157A (en) * | 2018-08-10 | 2018-12-21 | 优视科技新加坡有限公司 | Resource recommendation method and its device, equipment/terminal/server, computer-readable medium |
| CN109165315A (en) * | 2018-08-24 | 2019-01-08 | 大陆汽车投资（上海）有限公司 | In-vehicle information/entertainment service method is pushed based on machine learning |
| CN112634881A (en) * | 2020-12-30 | 2021-04-09 | 广州博士信息技术研究院有限公司 | Intelligent voice recognition method and system based on scientific and technological achievement database |
| CN112634881B (en) * | 2020-12-30 | 2023-08-11 | 广州博士信息技术研究院有限公司 | Speech intelligent recognition method and system based on scientific and technological achievement database |
| CN115037791A (en) * | 2022-04-13 | 2022-09-09 | 中国电信股份有限公司 | Event pushing method, device and system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103455485A (en) | Method and device for automatically updating user interest model | |
| US11580104B2 (en) | Method, apparatus, device, and storage medium for intention recommendation | |
| CN101071424B (en) | Personalized information push system and method | |
| CN102130933B (en) | Recommending method, system and equipment based on mobile Internet | |
| CN104361063B (en) | user interest discovery method and device | |
| CN103428076A (en) | Method and device for transmitting information to multi-type terminals or applications | |
| CN103186600B (en) | The specific analysis method and apparatus of internet public feelings | |
| CN102624756B (en) | Data download terminal and data download method | |
| CN103020845A (en) | Mobile application pushing method and system | |
| CN104899220A (en) | Application program recommendation method and system | |
| CN103810162A (en) | Method and system for recommending network information | |
| CN102811207A (en) | Network information pushing method and system | |
| KR102615244B1 (en) | Apparatus and method for recommending user's privacy control | |
| CN102207967B (en) | Method and system for automatically providing new browser plugin | |
| CN102622372A (en) | Method and device for recommending short message receiving person | |
| CN104156356A (en) | Personalized navigation page generating method and device | |
| CN105740481A (en) | Search recommending method and device | |
| CN102375847A (en) | Method and device for forming merge tree for generating document template | |
| CN105408894A (en) | Method and device for determining user identity category | |
| CN103544150A (en) | Method and system for providing recommendation information for mobile terminal browser | |
| CN107395695B (en) | Business pushing method and device | |
| DE202013000058U1 (en) | Device and computer readable medium for recognizing locations | |
| US10217455B2 (en) | Linguistic model database for linguistic recognition, linguistic recognition device and linguistic recognition method, and linguistic recognition system | |
| CN103714120A (en) | System for extracting interesting topics from url (uniform resource locator) access records of users | |
| CN109241031B (en) | Model generation method, model using method, device, system and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20131218 |