CN105763947A - Method for extracting features and interests of smart television users - Google Patents
Method for extracting features and interests of smart television users Download PDFInfo
- Publication number
- CN105763947A CN105763947A CN201610092287.4A CN201610092287A CN105763947A CN 105763947 A CN105763947 A CN 105763947A CN 201610092287 A CN201610092287 A CN 201610092287A CN 105763947 A CN105763947 A CN 105763947A
- Authority
- CN
- China
- Prior art keywords
- intelligent television
- operation behavior
- behavior data
- user
- television user
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/4508—Management of client data or end-user data
- H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Graphics (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a method for extracting features and interests of smart television users. The method includes the following steps: acquiring operation behavior data of a smart television terminal user; based on the acquired data, extracting entity words and presetting the type of operation behavior entity words and an interest threshold value corresponding to the type; based on the extracted key entity words and the preset entity words corresponding to respective type, determining the type of the acquired data; based on attribute information on a dimension in correspondence to the acquired operation behavior data, computing a weighted value of the operation behavior data; based on the weighted value of the operation behavior data, determining attention of the type to which the operation behavior data belong; based on the attention of the type to which the operation behavior data belong and an interest threshold value corresponding to the preset type. Thus, the features and interests of the smart television user are obtained. The method of the invention provides prototype of user features and interests to follow up data mining and recommendation, pushing, and the like that are relevant to the smart television field.
Description
Technical field
The present invention relates to computer technology, intelligent television technology and data mining interest modeling technical field, be specifically related to the feature interest extracting method of a kind of intelligent television user.
Background technology
The fast development of the intellectuality of traditional tv and family the Internet imparts the more intelligentized function of television set, the maximum feature of intelligent television is exactly under the support of hardware, with under the combination of intelligent operating system, it is made to have except traditional TV programme playing function, it is also equipped with the function similar to mobile client to pc client, such as watch Online Video, read online news, play game on line, chat with do shopping, and under intelligent television platform other utilitarian functions extendible.
Under intelligent television platform, user may select the application of use and increases, corresponding operation increases, the resource touched also can get more and more, and user inevitably carrys out positive location by services such as search, recommendation, propelling movements or passively accepts the Internet resources that they want.In this case, it is necessary to the interest characteristics of intelligent television user is collected and excavation, and play the important evidence of respective action in this, as the service such as search, recommendation, propelling movement.But, although the services such as search, recommendation and propelling movement under intelligent television platform resemble in many points with the operating mechanism under pc client or mobile client, but the user interest pattern under intelligent television platform has the aspect of its uniqueness, natural user such as intelligent television client is usually some kinsfolks, feature interest has bigger complexity, need to carry out the user characteristics interest under intelligent television platform reasonably excavating and extracting, with the services such as satisfied search, recommendation and the propelling movement requirement to result accuracy.
Summary of the invention
Instant invention overcomes the deficiencies in the prior art, it is provided that the feature interest extracting method of a kind of intelligent television user.
Consider the problems referred to above of prior art, according to an aspect disclosed by the invention, the present invention by the following technical solutions:
A kind of feature interest extracting method of intelligent television user, described method comprises the following steps:
Step one, from Intelligent television terminal user, gather the operation behavior data of every Intelligent television terminal user；
Step 2, every the intelligent television user gathered from step one operation behavior extracting data go out the critical entities word of respective operations behavior, the user operation behavioral data gathered in training step one, and the classification belonging to predetermined registration operation behavior entity word, and the interest threshold values that classification is corresponding；
Step 3, intelligent television user according to step 2 the critical entities word that extracts of operation behavior data, and the entity word of correspondence of all categories set in advance determines the classification belonging to operation behavior data gathered in step one；
Step 4, calculate the weighted value of the operation behavior data of described intelligent television user according to the attribute information in dimension corresponding to the operation behavior data of described intelligent television user；
Step 5, the described intelligent television user calculated according to step 4 the weighted value of operation behavior data, it is determined that the attention rate of the operation behavior data generic of described intelligent television user；
The classification that interest threshold values identification intelligent television terminal user that step 6, the attention rate respective classes set in advance with in step 2 of the operation behavior data generic of intelligent television user according to step 5 are corresponding is interested, namely obtains the feature interest of intelligent television user.
In order to realize the present invention better, further technical scheme is:
According to one embodiment of the invention, the operation behavior data of the Intelligent television terminal user described in step one include broadcast TV program viewing record, network Online Video viewing browse record, network online news browses record, game operation and record of playing, TV chatting operation record, Intelligent television terminal base attribute information.
Further technical scheme: the critical entities word described in step 2 and classification are based on what the operation behavior data of intelligent television user and the comparative result of the operation behavior data of intelligent television user in network were arranged.
Further technical scheme: the dimension described in step 4 is the statistics dimension of the operation behavior data of intelligent television user, and in each dimension all corresponding corresponding operation behavior data message, the operation behavior of each independent intelligent television user is all the instantiation of respective dimensions.
Further technical scheme: category operation behavior data are arranged by interest threshold values corresponding to classification described in step 6 according to Intelligent television terminal user.
Compared with prior art, one of beneficial effects of the present invention is:
By gathering and analyze the operation behavior data of a large amount of Intelligent television terminal user, determine the classification corresponding to operation behavior data, weighted value, attention rate etc., and identify the feature interest of Intelligent television terminal user on this basis, excavate for the follow-up data that intelligent television field is relevant and the service such as recommendation, propelling movement provides user characteristics interest prototype.
Detailed description of the invention
Below in conjunction with embodiment, the present invention is described in further detail, but embodiments of the present invention are not limited to this.
A kind of feature interest extracting method of intelligent television user, according to one embodiment of present invention, described method comprises the following steps:
Step one, from Intelligent television terminal user, gather the operation behavior data of every Intelligent television terminal user, specifically include following operation behavior data:
(1) broadcast TV program viewing record, the odd-numbered day viewing duration of duration and each television station is always watched including the program source watched, television program type, satellite TV of television station name, television station's type, odd-numbered day, wherein program source is divided into network broadband, satellite program signals, CHINA RFTCOM Co Ltd etc., and television program type is divided into news category, finance and economic, sport category, entertainment class, life kind, talk class, military class, class educational, scientific and technological, juvenile's class etc..
(2) viewing of network Online Video browses record, contents attribute including the video APP name used, video content attribute, wherein video contains the information such as video type, duration, producer, publisher, and wherein video type includes film, TV play, animation, variety, music, information, micro-bat etc..
(3) network online news browses record, including the news client end AP P used, news type, news media's carrier and browse the frequency, stay time etc. in certain type news, wherein news media's carrier includes word, picture, video etc., and news type includes domestic, international etc..
(4) game operation and record of playing, it is divided into local single-play game and online internet game, comprise game name, type of play, operation duration, corresponding game developer, network connection etc., wherein type of play often includes policy class, action class, adventure, simulation class, role playing class, leisure etc., and the qualification of game developer and ability can determine the quality of game to a certain extent.
(5) TV chatting operation record, including the professional chat tool used, the chatting operation frequency etc., the TV chatting operation frequency can reflect the information such as preference that TV user chats for TV and degree of dependence.
(6) the base attribute information of Intelligent television terminal is obtained, including positional information, intelligent television operating system and version, terminal odd-numbered day start duration etc., wherein positional information can reflect some regional preference informations of Intelligent television terminal user intuitively to a certain extent.
Step 2, every the intelligent television user gathered from step one operation behavior extracting data go out the critical entities word of respective operations behavior, the user operation behavioral data gathered in training step one, and the classification belonging to predetermined registration operation behavior entity word, and the interest threshold values that classification is corresponding.
Step 3, intelligent television user according to step 2 the critical entities word that extracts of operation behavior data, and the entity word of correspondence of all categories set in advance determines the classification belonging to operation behavior data gathered in step one.
Wherein, operation behavior data based on intelligent television user arrange user's classification interested and entity word with the comparative result of the operation behavior data of multiple intelligent television users in network, the interest information of the multiple intelligent television users pre-set can be that the service end operation behavior data to multiple users that it collects are analyzed and obtain, and service end storage individual user interest information can based on subsequent acquisition to individual user operation behavioral data by networking or offline mode be updated.
Step 4, calculate the weighted value of the operation behavior data of described intelligent television user according to the attribute information in dimension corresponding to the operation behavior data of described intelligent television user.
Wherein, dimension is the statistics dimension of the operation behavior data of intelligent television user, and in each dimension all corresponding corresponding operation behavior data message, the operation behavior of each independent intelligent television user is all the instantiation of respective dimensions, and the operation behavior data of user, corresponding dimensional information and the weighted value calculated are collectively stored in the feature database of this intelligent television user.
Step 5, the described intelligent television user calculated according to step 4 the weighted value of operation behavior data, it is determined that the attention rate of the operation behavior data generic of described intelligent television user.
Wherein, when service end often receives the operation behavior data of a user or is simultaneously received the operation behavior data of a plurality of user, the attention rate of behavioral data can be operated in real time, and utilize the attention rate currently calculated to revise user's attention rate to this operation behavior generic in real time.
The classification that interest threshold values identification intelligent television terminal user that step 6, the attention rate respective classes set in advance with in step 2 of the operation behavior data generic of intelligent television user according to step 5 are corresponding is interested, namely obtains the feature interest of intelligent television user.
Category operation behavior data are arranged by interest threshold values corresponding to described classification according to multiple Intelligent television terminal users, wherein, the operation triggering situation of one classification can be embodied the category difference by different user institute degree of concern by multiple intelligent television users, the interest threshold values that the operation behavior triggering situation of one classification arranges the category hence with multiple terminal uses accurate can embody the actual triggering situation of user interested to the category, thus the present invention is by utilizing such interest threshold values to whether user judges the interesting preference of the category, can be that the result judged is more accurate.
In this specification, each embodiment adopts the mode gone forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, identical similar portion cross-reference between each embodiment.
Than that described above, it can further be stated that, " embodiment ", " another embodiment ", " embodiment " spoken of in this manual etc., refer to the specific features, structure or the feature that describe in conjunction with this embodiment and include at least one embodiment that the application generality describes.Multiple local appearance statement of the same race is not necessarily refer to same embodiment in the description.Furthermore, it is understood that when describing a specific features, structure or feature in conjunction with any embodiment, what advocate is also fall within the scope of the present invention to realize this feature, structure or feature in conjunction with other embodiments.
Although reference be made herein to invention has been described for the multiple explanatory embodiment of the present invention, but, it should be understood that those skilled in the art can be designed that a lot of other amendments and embodiment, these amendments and embodiment will drop within spirit disclosed in the present application and spirit.More specifically, in disclosure and scope of the claims, it is possible to building block and/or layout to theme composite configuration carry out multiple modification and improvement.Except the modification that building block and/or layout are carried out and improvement, to those skilled in the art, other purposes also will be apparent from.
Claims (5)
1. the feature interest extracting method of an intelligent television user, it is characterised in that described method comprises the following steps:
Step one, from Intelligent television terminal user, gather the operation behavior data of every Intelligent television terminal user；
Step 2, every the intelligent television user gathered from step one operation behavior extracting data go out the critical entities word of respective operations behavior, the user operation behavioral data gathered in training step one, and the classification belonging to predetermined registration operation behavior entity word, and the interest threshold values that classification is corresponding；
Step 3, intelligent television user according to step 2 the critical entities word that extracts of operation behavior data, and the entity word of correspondence of all categories set in advance determines the classification belonging to operation behavior data gathered in step one；
Step 4, calculate the weighted value of the operation behavior data of described intelligent television user according to the attribute information in dimension corresponding to the operation behavior data of described intelligent television user；
Step 5, the described intelligent television user calculated according to step 4 the weighted value of operation behavior data, it is determined that the attention rate of the operation behavior data generic of described intelligent television user；
The classification that interest threshold values identification intelligent television terminal user that step 6, the attention rate respective classes set in advance with in step 2 of the operation behavior data generic of intelligent television user according to step 5 are corresponding is interested, namely obtains the feature interest of intelligent television user.
2. the feature interest extracting method of intelligent television user according to claim 1, it is characterised in that: the operation behavior data of the Intelligent television terminal user described in step one include broadcast TV program viewing record, network Online Video viewing browse record, network online news browses record, game operation and record of playing, TV chatting operation record, Intelligent television terminal base attribute information.
3. the feature interest extracting method of intelligent television user according to claim 1, it is characterised in that: the critical entities word described in step 2 and classification are based on what the operation behavior data of intelligent television user and the comparative result of the operation behavior data of intelligent television user in network were arranged.
4. the feature interest extracting method of intelligent television user according to claim 1, it is characterized in that: the dimension described in step 4 is the statistics dimension of the operation behavior data of intelligent television user, and in each dimension all corresponding corresponding operation behavior data message, the operation behavior of each independent intelligent television user is all the instantiation of respective dimensions.
5. the feature interest extracting method of intelligent television user according to claim 1, it is characterised in that: category operation behavior data are arranged by interest threshold values corresponding to classification described in step 6 according to Intelligent television terminal user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610092287.4A CN105763947A (en) | 2016-02-19 | 2016-02-19 | Method for extracting features and interests of smart television users |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610092287.4A CN105763947A (en) | 2016-02-19 | 2016-02-19 | Method for extracting features and interests of smart television users |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105763947A true CN105763947A (en) | 2016-07-13 |
Family
ID=56330059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610092287.4A Pending CN105763947A (en) | 2016-02-19 | 2016-02-19 | Method for extracting features and interests of smart television users |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105763947A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106851344A (en) * | 2017-02-07 | 2017-06-13 | 广州视源电子科技股份有限公司 | The message of intelligent television recommends method and device |
| CN109309875A (en) * | 2018-09-03 | 2019-02-05 | 四川长虹电器股份有限公司 | A method of showing user behavior characteristics model on smart television |
| CN111949776A (en) * | 2020-07-17 | 2020-11-17 | 上海淇馥信息技术有限公司 | Method and device for evaluating user tag and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6169570B1 (en) * | 1996-04-19 | 2001-01-02 | Sony Corporation | Two-way information transmission system, two-way information method, and subscriber terminal device |
| CN101739402A (en) * | 2008-11-07 | 2010-06-16 | 华为技术有限公司 | Method and device for interest analysis |
| CN103888466A (en) * | 2014-03-28 | 2014-06-25 | 北京搜狗科技发展有限公司 | User interest discovering method and device |
-
2016
- 2016-02-19 CN CN201610092287.4A patent/CN105763947A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6169570B1 (en) * | 1996-04-19 | 2001-01-02 | Sony Corporation | Two-way information transmission system, two-way information method, and subscriber terminal device |
| CN101739402A (en) * | 2008-11-07 | 2010-06-16 | 华为技术有限公司 | Method and device for interest analysis |
| CN103888466A (en) * | 2014-03-28 | 2014-06-25 | 北京搜狗科技发展有限公司 | User interest discovering method and device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106851344A (en) * | 2017-02-07 | 2017-06-13 | 广州视源电子科技股份有限公司 | The message of intelligent television recommends method and device |
| CN109309875A (en) * | 2018-09-03 | 2019-02-05 | 四川长虹电器股份有限公司 | A method of showing user behavior characteristics model on smart television |
| CN109309875B (en) * | 2018-09-03 | 2020-12-15 | 四川长虹电器股份有限公司 | Method for displaying user behavior characteristic model on smart television |
| CN111949776A (en) * | 2020-07-17 | 2020-11-17 | 上海淇馥信息技术有限公司 | Method and device for evaluating user tag and electronic equipment |
| CN111949776B (en) * | 2020-07-17 | 2023-09-22 | 上海淇馥信息技术有限公司 | User tag evaluation method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108184144B (en) | Live broadcast method and device, storage medium and electronic equipment | |
| US9230352B2 (en) | Information processing apparatus, information processing method, and computer program product | |
| CN108650558B (en) | Method and device for generating video precondition based on interactive video | |
| CN105095431A (en) | Method and device for pushing videos based on behavior information of user | |
| CN103781522A (en) | Methods and systems for generating and joining shared experience | |
| CN106331779A (en) | Method and system for pushing anchor based on user preferences during video playing process | |
| CN105095480A (en) | Providing link to portion of media object in real time in social networking update | |
| CN103686237A (en) | Method and system for recommending video resource | |
| CN103596020A (en) | Method and system for mixed arrangement and playing of television programs | |
| CN110248246B (en) | Data analysis method and device, computer equipment and computer readable storage medium | |
| Jiang et al. | Live: an integrated production and feedback system for intelligent and interactive tv broadcasting | |
| CN113569037A (en) | Message processing method and device and readable storage medium | |
| CN101854346A (en) | System and method for fusing mobile multimedia broadcast and Internet service | |
| CN104837034A (en) | Information processing method, client and server | |
| CN111444415A (en) | Barrage processing method, server, client, electronic device and storage medium | |
| CN103873945A (en) | System and method for socializing with object in video program | |
| CN113573090A (en) | Content display method, device and system in game live broadcast and storage medium | |
| CN114938459A (en) | Virtual live broadcast interaction method and device based on barrage, storage medium and equipment | |
| CN105763947A (en) | Method for extracting features and interests of smart television users | |
| CN114339399A (en) | Multimedia file editing method and device and computing equipment | |
| CN103530301A (en) | Virtual community establishing system and method | |
| CN106713973A (en) | Program searching method and device | |
| CN112328895A (en) | User portrait generation method, device, server and storage medium | |
| CN112533032B (en) | Video data processing method and device and storage medium | |
| CN109309875B (en) | Method for displaying user behavior characteristic model on smart television |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160713 |
|
| RJ01 | Rejection of invention patent application after publication |