CN106021609A - Method and device for intelligently recommending website videos - Google Patents
Method and device for intelligently recommending website videos Download PDFInfo
- Publication number
- CN106021609A CN106021609A CN201610467473.1A CN201610467473A CN106021609A CN 106021609 A CN106021609 A CN 106021609A CN 201610467473 A CN201610467473 A CN 201610467473A CN 106021609 A CN106021609 A CN 106021609A
- Authority
- CN
- China
- Prior art keywords
- video
- user
- data
- behavioral data
- client
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention relates to the field of the internet, in particular to a method and a device for intelligently recommending website videos. The method comprises the following steps: 1, a client acquires behavior data of a user browsing a website in real time and sends the behavior data to a data server; 2, the data server pushes video information in line with behaviors of the user according to the received behavior data and sends the video information to the client; 3, the client calls recommended videos corresponding to the video information in a video database according to the received video information and displays the recommended videos on a website which the user is browsing. Accordingly, the method and the device have the following advantages: the behavior data of the user on the websites are used well, the best and the most accurate content is recommended to the user intelligently through analysis of a website data platform, and the user experience is also improved.
Description
Technical field
The present invention relates to internet arena, especially relate to a kind of method and device realizing web video intelligent recommendation.
Background technology
In the Internet barrage webcast website field, website needs automatically to recommend user's content accurately according to the behavior of user, as: user likes the video seen, user likes the video seen in certain time period, user may like the video seen, user that main broadcaster wishes to etc., the behavioral data of user becomes particularly important for the quality of website and the experience of user, and can only be completed the collection of data by front end.Most of websites waste the behavioral data of user, and do not do intelligent video recommendation for each user, and propelling movement is all the popular video content liked and see or website is promoted mainly.
Summary of the invention
The present invention mainly solves the technical problem existing for prior art;Provide a kind of fabulous behavioral data that make use of user on website, analysis by website data platform, intelligent recommends the optimal content the most accurately of user, also improves a kind of method and device realizing web video intelligent recommendation of the experience of user simultaneously.
The above-mentioned technical problem of the present invention is mainly addressed by following technical proposals:
A kind of method realizing web video intelligent recommendation, it is characterised in that including:
Step 1, the behavioral data that client real-time collecting user browses web sites, and behavioral data is sent to data server;
Step 2, data server, according to the behavioral data received, pushes the video information meeting user behavior, and this video information is issued client;
Step 3, client, according to the video information received, is transferred the interior recommendation video corresponding with video information of video library, and is shown on the website that user is browsing by this recommendation video.
Preferably, in described step 1, the behavioral data that the user of real-time collecting browses web sites includes: behavioral data type and the behavior type data corresponding with behavioral data type;Described behavioral data type includes: user operation action trail, user operation page track, user's browse operation webpage time period, user enters current site source points, user leaves current site jump-point and customer consumption point.
Preferably, in described step 1, after the behavioral data that client real-time collecting user browses web sites, being filtered by behavioral data, the concrete grammar of filtration is:
Step 101, by the granularity equalization of behavioral data, i.e. setting operation interval, when user carries out behavioral data type operations, if actual operating time interval is more than the operating time interval set, then judge that behavioral data is time valid data and performs step 102, otherwise delete behavior data and continue the judgement of this step;
Whether step 102, the time valid data judged in step 101 are malicious data, the most eligible: it is that user's behavior voluntarily triggers that user carries out behavioral data type operations, and time valid data includes page coordinates, if time valid data meets in this step any one or two conditions simultaneously, then judge that time valid data is malicious data, delete this time valid data repeated execution of steps 101 simultaneously;Otherwise time valid data is sent to data server.
Preferably, server is additionally operable to the video information of website operator's active push is sent to client, after client receives the video information of server active push, transfers in video library video and is shown on the website that user is browsing by this recommendation video.
Preferably, in described step 3, this recommendation video is shown that the concrete grammar on the website that user is browsing is by client: carry out scene judgement, and transfers the display effect of coupling according to place scene, and described scene includes: between website homepage, net cast, web video list page;Described display effect includes video recommendations floating layer and planar video;When client judges that current scene is between website homepage and net cast, use video recommendations floating layer display effect;When client judges that current scene is web video list page, use planar video and this planar video is inserted in the middle part of the web video list page that active user is browsing.
A kind of device realizing web video intelligent recommendation, based on a video intelligent recommending module, this video intelligent recommending module includes:
Behavioral data collection module: the behavioral data that client is browsed web sites by behavioral data collection module real-time collecting user, and behavioral data is sent to data server;
Video information pushing module: data server, according to the behavioral data received, is pushed the video information meeting user behavior, and this video information is issued client by video information pushing module;
Video display module: client is according to the video information received, and in transferring video library by video display module, recommendation video corresponding with video information, and shows this recommendation video on the website that user is browsing.
Preferably, the behavioral data that the user of real-time collecting browses web sites includes: behavioral data type and the behavior type data corresponding with behavioral data type;Described behavioral data type includes: user operation action trail, user operation page track, user's browse operation webpage time period, user enters current site source points, user leaves current site jump-point and customer consumption point.
Preferably, after the behavioral data that the behavioral data collection module real-time collecting user of client browses web sites, being filtered by behavioral data, the concrete grammar of filtration is:
Time interval filter element: time interval filter element is by the granularity equalization of behavioral data, i.e. setting operation interval, when user carries out behavioral data type operations, if actual operating time interval is more than the operating time interval set, then judge that behavioral data is time valid data and carries out next step operation, otherwise delete behavior data and continue to be carried out by time interval filter element the judgement of next group behavioral data;
Malicious data filter element: whether the time valid data of judgement is malicious data, the most eligible: it is that user's behavior voluntarily triggers that user carries out behavioral data type operations, and time valid data includes page coordinates, if time valid data meets in this step any one or two conditions simultaneously, then judge that time valid data is malicious data, delete this time valid data simultaneously and repeat to be carried out by time interval filter element the judgement of next group behavioral data;Otherwise time valid data is sent to data server.
Preferably, server is additionally operable to the video information of website operator's active push is sent to client, after client receives the video information of server active push, transfers in video library video and is shown on the website that user is browsing by this recommendation video.
Preferably, this recommendation video is shown that the concrete grammar on the website that user is browsing is by video display module by client: carry out scene judgement, and the display effect of coupling is transferred according to place scene, described scene includes: between website homepage, net cast, web video list page;Described display effect includes video recommendations floating layer and planar video;When client judges that current scene is between website homepage and net cast, use video recommendations floating layer display effect;When client judges that current scene is web video list page, use planar video and this planar video is inserted in the middle part of the web video list page that active user is browsing.
Therefore, present invention have the advantage that the fabulous behavioral data that make use of user on website, by the analysis of website data platform, intelligent recommends the optimal content the most accurately of user, also improves the experience of user simultaneously.
Accompanying drawing explanation
Accompanying drawing 1 is the method flow schematic diagram (in figure, DYS is video intelligent recommending module) of the present invention.
Accompanying drawing 2 is the schematic diagram (in figure, DYS is video intelligent recommending module) of the type collecting user behavior data in the present invention.
Accompanying drawing 3 is the schematic diagram of the user behavior data being collected by filtration in the present invention.
Accompanying drawing 4 is the schematic diagram (in figure, DYS is video intelligent recommending module) that can show different recommendation effect in the present invention below different scenes.
Accompanying drawing 5 is the structured flowchart of the present invention.
Detailed description of the invention
Below by embodiment, and combine accompanying drawing, technical scheme is described in further detail.
A kind of method realizing web video intelligent recommendation, including:
Step 1, the behavioral data that client real-time collecting user browses web sites, and behavioral data is sent to data server;Wherein, the behavioral data that the user of real-time collecting browses web sites includes: behavioral data type and the behavior type data corresponding with behavioral data type;Described behavioral data type includes: user operation action trail, user operation page track, user's browse operation webpage time period, user enters current site source points, user leaves current site jump-point and customer consumption point (behavioral data type such as: user's browse operation webpage time period;The behavioral data corresponding with behavior data type be such as: user 7PM-8PM at night is at operation webpage, and time period 7PM-8PM here is exactly behavioral data);It addition, after the behavioral data that browses web sites of client real-time collecting user, filtered by behavioral data, the concrete grammar of filtration is:
Step 101, by the granularity equalization of behavioral data, i.e. setting operation interval, when user carries out behavioral data type operations, if actual operating time interval is more than the operating time interval set, then judge that behavioral data is time valid data and performs step 102, otherwise delete behavior data and continue the judgement of this step;
Whether step 102, the time valid data judged in step 101 are malicious data, the most eligible: it is that user's behavior voluntarily triggers that user carries out behavioral data type operations, and time valid data includes page coordinates, if time valid data meets in this step any one or two conditions simultaneously, then judge that time valid data is malicious data, delete this time valid data repeated execution of steps 101 simultaneously;Otherwise time valid data is sent to data server.
Step 2, data server, according to the behavioral data received, pushes the video information meeting user behavior, and this video information is issued client;It addition, server can also be according to website operator's active push video information to client, after client receives the video information of server active push, directly transfer in video library video and this recommendation video is shown on the website that user is browsing.
Step 3, client is according to the video information received, recommendation video corresponding with video information in transferring video library, and this recommendation video is shown on the website that user is browsing, concrete grammar is: carry out scene judgement, and the display effect of coupling is transferred according to place scene, described scene includes: between website homepage, net cast, web video list page;Described display effect includes video recommendations floating layer and planar video;When client judges that current scene is between website homepage and net cast, use video recommendations floating layer display effect;When client judges that current scene is web video list page, use planar video and this planar video is inserted in the middle part of the web video list page that active user is browsing.
A kind of device realizing web video intelligent recommendation, including:
Behavioral data collection module: the behavioral data that client is browsed web sites by behavioral data collection module real-time collecting user, and behavioral data is sent to data server;The behavioral data that the user of real-time collecting browses web sites includes: behavioral data type and the behavior type data corresponding with behavioral data type;Described behavioral data type includes: user operation action trail, user operation page track, user's browse operation webpage time period, user enters current site source points, user leaves current site jump-point and customer consumption point (behavioral data type such as: user's browse operation webpage time period;The behavioral data corresponding with behavior data type be such as: user 7PM-8PM at night is at operation webpage, and time period 7PM-8PM here is exactly behavioral data).After the behavioral data that the behavioral data collection module real-time collecting user of client browses web sites, being filtered by behavioral data, the concrete grammar of filtration is:
Time interval filter element: time interval filter element is by the granularity equalization of behavioral data, i.e. setting operation interval, when user carries out behavioral data type operations, if actual operating time interval is more than the operating time interval set, then judge that behavioral data is time valid data and carries out next step operation, otherwise delete behavior data and continue to be carried out by time interval filter element the judgement of next group behavioral data;
Malicious data filter element: whether the time valid data of judgement is malicious data, the most eligible: it is that user's behavior voluntarily triggers that user carries out behavioral data type operations, and time valid data includes page coordinates, if time valid data meets in this step any one or two conditions simultaneously, then judge that time valid data is malicious data, delete this time valid data simultaneously and repeat to be carried out by time interval filter element the judgement of next group behavioral data;Otherwise time valid data is sent to data server.
Video information pushing module: data server, according to the behavioral data received, is pushed the video information meeting user behavior, and this video information is issued client by video information pushing module;Server to client always according to website operator's active push video information, after client receives the video information of server active push, is directly transferred in video library video and is shown on the website that user is browsing by this recommendation video.
Video display module: client is according to the video information received, recommendation video corresponding with video information in transferring video library by video display module, and this recommendation video is shown on the website that user is browsing, concrete grammar is: carry out scene judgement, and the display effect of coupling is transferred according to place scene, described scene includes: between website homepage, net cast, web video list page;Described display effect includes video recommendations floating layer and planar video;When client judges that current scene is between website homepage and net cast, use video recommendations floating layer display effect;When client judges that current scene is web video list page, use planar video and this planar video is inserted in the middle part of the web video list page that active user is browsing.
Embodiment 1:
The present invention provides a kind of method realizing web video intelligent recommendation, including:
Step 1, the behavioral data that client real-time collecting user browses web sites, it is not directly data to be submitted to " data server " after collecting user behavior data, first can be by the granularity equalization (such as: the operating interval of 2 seconds) of behavioral data, then can judge whether behavioral data is malicious data (such as: client carries out malice by plug-in unit and submits to), after all having processed above, just uniform packing submits data to.Wherein
, it may be judged whether the foundation for malicious data is:
1, the premise of valid data is set as " user behavior triggering "
If 2 data do not have page coordinates, regard as " malicious data " (data triggered by user behavior necessarily have page coordinates)
In this step, behavioral data type includes: user operation action trail, user operation page track, user's browse operation webpage time period, user enters current site source points, user leaves current site jump-point and customer consumption point (behavioral data type such as: user's browse operation webpage time period;The behavioral data corresponding with behavior data type be such as: user 7PM-8PM at night is at operation webpage, and time period 7PM-8PM here is exactly behavioral data);
Step 2, data server is according to the behavioral data received, push the video information meeting user behavior, and this video information is issued client (enter website for the first time user, client initiates request to " data server ", obtains the video content data needing to recommend to user under current business).Client run duration, " data server " may propelling data to client.No matter being active request data, or passively receive data, client can be done after receiving data and process as follows:
Different recommendation effect can be shown, such as below different scenes:
1, video recommendations floating layer is shown between website homepage and net cast.
2, recommendation video is jumped the queue by web video list page.
3, etc. (self-defining other types).
In this step, data server is according to the behavioral data received, push the video information meeting user behavior, the method is User Defined, the behavioral data how combining reception pushes the video information reasonably meeting user behavior, use known multi-Fuzzy algorithm i.e. can obtain required result, owing to being known technology, do not repeating at this.
Embodiment 2:
The present invention provides a kind of device realizing web video intelligent recommendation, and based on a video intelligent recommending module, video intelligent recommending module is the JS frame module that front end realizes " video intelligent recommendation ".The Core Feature of this frame module has two: reports, render.Reporting is by collecting user behavior data, and carries out filtering (filtering spam or redundant data retain core data), is then forwarded to data server.Rendering is by active request or passive to obtain data that data server pushed (such as: user likes video that the video seen, user like to see etc. in certain time period), is then rendered to the visual content that user can operate or select.Including:
Behavioral data collection module: the behavioral data that behavioral data collection module real-time collecting user browses web sites, it is not directly data to be submitted to " data server " after collecting user behavior data, first time interval filter element can be by the granularity equalization (such as: the operating interval of 2 seconds) of behavioral data, then malicious data filter element can judge whether behavioral data is malicious data (such as: client carries out malice by plug-in unit and submits to), and after all having processed above, just uniform packing submits data to.Wherein
, it may be judged whether the foundation for malicious data is:
1, the premise of valid data is set as " user behavior triggering "
If 2 data do not have page coordinates, regard as " malicious data " (data triggered by user behavior necessarily have page coordinates)
Wherein, behavioral data type includes: user operation action trail, user operation page track, user's browse operation webpage time period, user enters current site source points, user leaves current site jump-point and customer consumption point (behavioral data type such as: user's browse operation webpage time period;The behavioral data corresponding with behavior data type be such as: user 7PM-8PM at night is at operation webpage, and time period 7PM-8PM here is exactly behavioral data);
Video information pushing module: video information pushing module is according to the behavioral data received, push the video information meeting user behavior, and this video information is issued client (enter website for the first time user, client initiates request to " data server ", obtains the video content data needing to recommend to user under current business).Client run duration, " data server " may propelling data to client.
Video display module: no matter be active request data, or passively receive data, client can do following process after receiving data:
Different recommendation effect can be shown by video display module, such as below different scenes:
1, video recommendations floating layer is shown between website homepage and net cast.
2, recommendation video is jumped the queue by web video list page.
3, etc. (self-defining other types).
Video information pushing module is according to the behavioral data received, push the video information meeting user behavior, the method is User Defined, the behavioral data how combining reception pushes the video information reasonably meeting user behavior, use known multi-Fuzzy algorithm i.e. can obtain required result, owing to being known technology, do not repeating at this.
Specific embodiment described herein is only to present invention spirit explanation for example.Described specific embodiment can be made various amendment or supplements or use similar mode to substitute by those skilled in the art, but without departing from the spirit of the present invention or surmount scope defined in appended claims.
Claims (10)
1. the method realizing web video intelligent recommendation, it is characterised in that including:
Step 1, the behavioral data that client real-time collecting user browses web sites, and behavioral data is sent to data server;
Step 2, data server, according to the behavioral data received, pushes the video information meeting user behavior, and this video information is issued client;
Step 3, client, according to the video information received, is transferred the interior recommendation video corresponding with video information of video library, and is shown on the website that user is browsing by this recommendation video.
A kind of method realizing web video intelligent recommendation the most according to claim 1, it is characterized in that, in described step 1, the behavioral data that the user of real-time collecting browses web sites includes: behavioral data type and the behavior type data corresponding with behavioral data type;Described behavioral data type includes: user operation action trail, user operation page track, user's browse operation webpage time period, user enters current site source points, user leaves current site jump-point and customer consumption point.
A kind of method realizing web video intelligent recommendation the most according to claim 1, it is characterised in that in described step 1, after the behavioral data that client real-time collecting user browses web sites, filters behavioral data, and the concrete grammar of filtration is:
Step 101, by the granularity equalization of behavioral data, i.e. setting operation interval, when user carries out behavioral data type operations, if actual operating time interval is more than the operating time interval set, then judge that behavioral data is time valid data and performs step 102, otherwise delete behavior data and continue the judgement of this step;
Whether step 102, the time valid data judged in step 101 are malicious data, the most eligible: it is that user's behavior voluntarily triggers that user carries out behavioral data type operations, and time valid data includes page coordinates, if time valid data meets in this step any one or two conditions simultaneously, then judge that time valid data is malicious data, delete this time valid data repeated execution of steps 101 simultaneously;Otherwise time valid data is sent to data server.
A kind of method realizing web video intelligent recommendation the most according to claim 1, it is characterized in that, server is additionally operable to the video information of website operator's active push is sent to client, after client receives the video information of server active push, transfer in video library video and this recommendation video is shown on the website that user is browsing.
A kind of method realizing web video intelligent recommendation the most according to claim 1, it is characterized in that, in described step 3, this recommendation video is shown that the concrete grammar on the website that user is browsing is by client: carry out scene judgement, and the display effect of coupling is transferred according to place scene, described scene includes: between website homepage, net cast, web video list page;Described display effect includes video recommendations floating layer and planar video;When client judges that current scene is between website homepage and net cast, use video recommendations floating layer display effect;When client judges that current scene is web video list page, use planar video and this planar video is inserted in the middle part of the web video list page that active user is browsing.
6. the device realizing web video intelligent recommendation, it is characterised in that based on a video intelligent recommending module, this video intelligent recommending module includes:
Behavioral data collection module: the behavioral data that client is browsed web sites by behavioral data collection module real-time collecting user, and behavioral data is sent to data server;
Video information pushing module: data server, according to the behavioral data received, is pushed the video information meeting user behavior, and this video information is issued client by video information pushing module;
Video display module: client is according to the video information received, and in transferring video library by video display module, recommendation video corresponding with video information, and shows this recommendation video on the website that user is browsing.
A kind of device realizing web video intelligent recommendation the most according to claim 6, it is characterised in that the behavioral data that the user of real-time collecting browses web sites includes: behavioral data type and the behavior type data corresponding with behavioral data type;Described behavioral data type includes: user operation action trail, user operation page track, user's browse operation webpage time period, user enters current site source points, user leaves current site jump-point and customer consumption point.
A kind of device realizing web video intelligent recommendation the most according to claim 6, it is characterised in that after the behavioral data that client real-time collecting user browses web sites,
Being filtered by behavioral data, the concrete grammar of filtration is:
Time interval filter element: time interval filter element is by the granularity equalization of behavioral data, i.e. setting operation interval, when user carries out behavioral data type operations, if actual operating time interval is more than the operating time interval set, then judge that behavioral data is time valid data and carries out next step operation, otherwise delete behavior data and continue to be carried out by time interval filter element the judgement of next group behavioral data;
Malicious data filter element: whether the time valid data of judgement is malicious data, the most eligible: it is that user's behavior voluntarily triggers that user carries out behavioral data type operations, and time valid data includes page coordinates, if time valid data meets in this step any one or two conditions simultaneously, then judge that time valid data is malicious data, delete this time valid data simultaneously and repeat to be carried out by time interval filter element the judgement of next group behavioral data;Otherwise time valid data is sent to data server.
A kind of device realizing web video intelligent recommendation the most according to claim 6, it is characterized in that, server is additionally operable to the video information of website operator's active push is sent to client, after client receives the video information of server active push, transfer in video library video and this recommendation video is shown on the website that user is browsing.
A kind of device realizing web video intelligent recommendation the most according to claim 6, it is characterized in that, this recommendation video is shown that the concrete grammar on the website that user is browsing is by video display module by client: carry out scene judgement, and the display effect of coupling is transferred according to place scene, described scene includes: between website homepage, net cast, web video list page;Described display effect includes video recommendations floating layer and planar video;When client judges that current scene is between website homepage and net cast, use video recommendations floating layer display effect;When client judges that current scene is web video list page, use planar video and this planar video is inserted in the middle part of the web video list page that active user is browsing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610467473.1A CN106021609A (en) | 2016-06-24 | 2016-06-24 | Method and device for intelligently recommending website videos |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610467473.1A CN106021609A (en) | 2016-06-24 | 2016-06-24 | Method and device for intelligently recommending website videos |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106021609A true CN106021609A (en) | 2016-10-12 |
Family
ID=57086719
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610467473.1A Pending CN106021609A (en) | 2016-06-24 | 2016-06-24 | Method and device for intelligently recommending website videos |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106021609A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106851418A (en) * | 2017-01-24 | 2017-06-13 | 合网络技术(北京)有限公司 | Video recommendation method and device |
CN106991192A (en) * | 2017-04-13 | 2017-07-28 | 武汉斗鱼网络科技有限公司 | Homepage recommends based reminding method and device |
CN107220383A (en) * | 2017-06-28 | 2017-09-29 | 环球智达科技(北京)有限公司 | Data filtering method |
CN107220382A (en) * | 2017-06-28 | 2017-09-29 | 环球智达科技(北京)有限公司 | Data analysing method |
CN107239573A (en) * | 2017-06-28 | 2017-10-10 | 环球智达科技(北京)有限公司 | Data filtering method |
CN109698975A (en) * | 2019-01-16 | 2019-04-30 | 上海哔哩哔哩科技有限公司 | New content real time playing method, device and storage medium |
CN109783686A (en) * | 2019-01-21 | 2019-05-21 | 广州虎牙信息科技有限公司 | Behavioral data processing method, device, terminal device and storage medium |
CN110297982A (en) * | 2019-07-04 | 2019-10-01 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of recommended method, device, equipment and medium |
CN111262744A (en) * | 2020-01-20 | 2020-06-09 | 北京字节跳动网络技术有限公司 | Multimedia information transmitting method, backup server and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103136275A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术(上海)有限公司 | System and method for recommending personalized video |
CN104333773A (en) * | 2013-12-18 | 2015-02-04 | 乐视网信息技术(北京)股份有限公司 | A Video recommending method and server |
CN104361085A (en) * | 2014-11-14 | 2015-02-18 | 百度在线网络技术(北京)有限公司 | Information recommendation method, device, browser, server and system |
CN105407385A (en) * | 2015-10-29 | 2016-03-16 | 桂林创研科技有限公司 | Video recommendation method and system |
CN105704566A (en) * | 2016-04-25 | 2016-06-22 | 浪潮软件集团有限公司 | Video recommendation system based on television set top box |
-
2016
- 2016-06-24 CN CN201610467473.1A patent/CN106021609A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103136275A (en) * | 2011-12-02 | 2013-06-05 | 盛乐信息技术(上海)有限公司 | System and method for recommending personalized video |
CN104333773A (en) * | 2013-12-18 | 2015-02-04 | 乐视网信息技术(北京)股份有限公司 | A Video recommending method and server |
CN104361085A (en) * | 2014-11-14 | 2015-02-18 | 百度在线网络技术(北京)有限公司 | Information recommendation method, device, browser, server and system |
CN105407385A (en) * | 2015-10-29 | 2016-03-16 | 桂林创研科技有限公司 | Video recommendation method and system |
CN105704566A (en) * | 2016-04-25 | 2016-06-22 | 浪潮软件集团有限公司 | Video recommendation system based on television set top box |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106851418A (en) * | 2017-01-24 | 2017-06-13 | 合网络技术(北京)有限公司 | Video recommendation method and device |
CN106991192A (en) * | 2017-04-13 | 2017-07-28 | 武汉斗鱼网络科技有限公司 | Homepage recommends based reminding method and device |
CN107220383A (en) * | 2017-06-28 | 2017-09-29 | 环球智达科技(北京)有限公司 | Data filtering method |
CN107220382A (en) * | 2017-06-28 | 2017-09-29 | 环球智达科技(北京)有限公司 | Data analysing method |
CN107239573A (en) * | 2017-06-28 | 2017-10-10 | 环球智达科技(北京)有限公司 | Data filtering method |
CN109698975A (en) * | 2019-01-16 | 2019-04-30 | 上海哔哩哔哩科技有限公司 | New content real time playing method, device and storage medium |
CN109783686A (en) * | 2019-01-21 | 2019-05-21 | 广州虎牙信息科技有限公司 | Behavioral data processing method, device, terminal device and storage medium |
CN110297982A (en) * | 2019-07-04 | 2019-10-01 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of recommended method, device, equipment and medium |
CN110297982B (en) * | 2019-07-04 | 2022-08-05 | 武汉斗鱼鱼乐网络科技有限公司 | Recommendation method, device, equipment and medium |
CN111262744A (en) * | 2020-01-20 | 2020-06-09 | 北京字节跳动网络技术有限公司 | Multimedia information transmitting method, backup server and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106021609A (en) | Method and device for intelligently recommending website videos | |
US10089402B1 (en) | Display of videos based on referrers | |
CN106484858B (en) | hot content pushing method and device | |
CN101739427B (en) | Crawler capturing method and device thereof | |
CN102314455A (en) | Method and system for calculating click flow of web page | |
US8972850B2 (en) | Tag aggregator | |
CN103220305B (en) | Network media information share treatment system and processing method | |
CN105451087A (en) | Pushing method, terminals, historical data server and system for barrage information | |
CN104462495B (en) | To the method, equipment and system of user's pushed information on barrage carrier | |
CN104951961A (en) | Method, terminal, server and system for pushing contents | |
CN103400283B (en) | A kind of advertisement push system based on home gateway and method | |
WO2013021391A4 (en) | Automatic website accessibility and compatability | |
CN102004756A (en) | Traffic visualization across web maps | |
WO2006052444A2 (en) | Audience targeting system with profile synchronization | |
CN106709033A (en) | Business multimedia data processing method and device | |
CN102486799B (en) | World wide web (WWW) page processing method and device | |
CN101764661A (en) | Data fusion based video program recommendation system | |
CN103974098A (en) | User-demand-based advertisement push method and system on set top box | |
US20170236170A1 (en) | Visual tag editor | |
CN104268187B (en) | The online content optimum decision system of the many scenes of support based on user feedback | |
CN103744856A (en) | Method, device and system for linkage extended search | |
CN103853757A (en) | Method and system for displaying information of network, terminal and information displaying and processing device | |
CN102004765A (en) | Method and equipment for searching media files based on internet television | |
CN106792172A (en) | A kind of method of internet television personalized recommendation video | |
CN105407385A (en) | Video recommendation method and system |
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: 20161012 |