CN114915800A - System and method for predicting age and gender distribution of IPTV (Internet protocol television) family users - Google Patents
System and method for predicting age and gender distribution of IPTV (Internet protocol television) family users Download PDFInfo
- Publication number
- CN114915800A CN114915800A CN202111486192.8A CN202111486192A CN114915800A CN 114915800 A CN114915800 A CN 114915800A CN 202111486192 A CN202111486192 A CN 202111486192A CN 114915800 A CN114915800 A CN 114915800A
- Authority
- CN
- China
- Prior art keywords
- user
- age
- gender
- film
- watching
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 239000013598 vector Substances 0.000 claims description 21
- 239000000523 sample Substances 0.000 claims description 11
- 239000000203 mixture Substances 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims 2
- 238000005406 washing Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 2
- 238000012916 structural analysis Methods 0.000 description 2
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 1
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- 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
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- 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
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
-
- 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
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- 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
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention discloses a system and a method for predicting the distribution of the age and the gender of IPTV family users. According to the invention, a ticket data processing module processes original ticket data to form a user behavior data structure; the program data processing module matches the program data with the user behavior data structure to obtain a user watching record; the media asset data processing module collects the information of the full-network film to form a media asset label; and the user age and gender distribution prediction module calculates the watching degree of the user and attaches a gender-age group label to the user based on the user watching record and the media asset label. According to the IPTV family user age and gender distribution prediction scheme, the media asset information of the whole network, the behavior data of the user watching the IPTV and the program list data are fused, the accuracy of the age and gender distribution prediction analysis of family members is high, and the interest preference of each user in the family is reflected more reasonably.
Description
Technical Field
The invention relates to the field of network information big data, in particular to a system and a method for predicting the distribution of age and gender of a family user based on IPTV live broadcast data.
Background
Today, interactive network television IPTV has gone home. With more and more IPTV programs, users face a selection of a large number of tv programs. It is becoming more and more important how to better recommend television programs to users that meet their needs, thereby improving the user experience.
However, since a current IPTV user generally corresponds to a home, the home user configuration is more complicated than that of a personal user. Since different individuals of a family user have different viewing requirements, in order to provide better tv service experience for each individual of the family user, structural analysis of family members and prediction of age and gender distribution are required for the family user.
In the prior art, when analyzing family members of television users, the adopted scheme is mainly to determine the attributes of the users, such as sex, age and the like, viewing preference and other information by acquiring the registration information of the users and performing questionnaire survey on the users, so as to complete the structural analysis of the family user members.
However, since the registration information includes a lot of user attributes such as age and gender, which are not required to be filled, the registration information is not complete, and thus the analysis of the family members based on the registration information cannot be effectively performed.
For the scheme of analyzing the family members of the television users in the questionnaire survey mode, the user generally fills in the questionnaire survey inactively, and the authenticity of the content is unreliable, so that the analysis of the family members is inaccurate.
Therefore, a problem of low accuracy of information analysis on family members, which is ubiquitous in an existing analysis scheme for IPTV users, is urgently needed to be solved.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter; nor is it intended to be used to determine or limit the scope of the claimed subject matter.
The invention provides a system and a method for predicting the age and gender distribution of home users based on IPTV live broadcast data. Compared with the prior art, the method is more accurate and accords with the characteristics of the family user. Potential customers can also be found for subsequent value added services.
The invention discloses a system for predicting the distribution of the age and the gender of IPTV family users, which comprises:
the call ticket data processing module is used for cleaning, converting, splitting and combining original user playing behavior data (original call tickets) acquired by the probe, and mapping the original user playing behavior data to form a user behavior data structure;
the program list data processing module is used for standardizing the program names and the channel names and matching the program list data with the user behavior data structure to obtain user viewing records;
the system comprises a media resource data processing module, a film playing module and a film playing module, wherein the media resource data processing module is used for collecting film information of the whole network, and the film information comprises a title, a lead actor, a category, a year, a score, an introduction and an existing film watching record information sample so as to form a media resource label, and the film watching record information sample comprises film watching ratios of men and women and film watching ratios of all ages; and
and the user age and gender distribution prediction module is used for calculating the film watching degree of the user according to a formula of film watching degree, namely film watching duration/film duration, and performing cluster analysis and solving on the gender characteristic vector and the age group characteristic vector of the user by adopting a Gaussian mixture model GMM and a maximum expectation EM algorithm, so that the user is labeled with a gender-age group label based on the user watching record and the media asset label.
The invention discloses a method for predicting the distribution of the age and the gender of IPTV family users, which comprises the following steps:
collecting user playing behavior data;
processing the collected user playing behavior data, including cleaning, converting, splitting and combining to generate a user behavior data structure;
processing the data of the program list, and standardizing the program name and the channel name;
matching the obtained program data after standardization with the generated user behavior data structure to obtain user viewing record data;
calculating the film watching degree of the user based on the watching record of the user, wherein the film watching degree is film watching duration/film duration;
collecting the film information of the whole network and the sample information to form a media asset label; and
and (3) performing cluster analysis and solving on the gender characteristic vector and the age group characteristic vector of the user by adopting a Gaussian mixture model GMM and a maximum expectation EM algorithm, and attaching a gender-age group label to the user.
These and other features and advantages will become apparent upon reading the following detailed description and upon reference to the accompanying drawings. It is to be understood that both the foregoing general description and the following detailed description are explanatory only and are not restrictive of aspects as claimed.
Drawings
The present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which specific embodiments of the invention are shown.
Fig. 1 is a schematic block diagram of a system for predicting the distribution of age and gender of home users based on IPTV live broadcast data according to the present invention;
FIG. 2 is a schematic diagram of a gender index neural network architecture;
FIG. 3 is a schematic diagram of an exponential neural network structure for each age group;
fig. 4 is a flowchart illustrating a method for predicting the distribution of the age and gender of home users based on IPTV live broadcast data according to the present invention.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).
Detailed Description
The present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which specific embodiments of the invention are shown. Various advantages and benefits of the present invention will become apparent to those of ordinary skill in the art upon reading the following detailed description of the specific embodiments. It should be understood, however, that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. The following embodiments are provided so that the invention may be more fully understood. Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by those of skill in the art to which this application belongs.
Fig. 1 shows a system 100 for predicting the age and gender distribution of a home user based on IPTV live broadcast data according to the present invention, which includes a ticket data processing module 110, a program data processing module 120, a media data processing module 130, and a user age and gender distribution predicting module 140, and the following modules are described in detail:
■ a ticket data processing module 110, configured to clean, convert, split, combine, etc., the user playing behavior data acquired by the probe. Cleaning comprises removing abnormal values, repeated values, useless data and the like, and converting, splitting and combining comprise format standardization of original data. For example, the user ID is null, the channel name is null, non-live data (url not like 'http%' and url not like 'rtsp%') and the like are checked, and the original call tickets are split, merged and mapped into a system internal user behavior data structure based on user dimensions.
For example, the original call ticket data with 2 million rows and 108 columns is cleaned, converted and combined to form the following data structure expressing the behavior of the user 1 as shown in table 1 below.
Table 1:
| user ID | Time of sampling | Channel ID | Channel name |
| User 1 | 20210314152431 | 1 | CCTV1 |
| User 1 | 20210314152942 | 1 | CCTV1 |
| User 1 | 20210314153524 | 1 | CCTV1 |
| User 1 | 20210314154044 | 1 | CCTV1 |
| User 1 | 20210314154553 | 1 | CCTV1 |
Here, 20210314152431 means, for example, 15 o' clock, 24 min 31 sec on 14 th day on 03 th month in 2021.
■ program data processing module 120, configured to process the program, standardize the program name and the channel name, and then match the program data with the user behavior data structure obtained from the IPTV user ticket data to obtain the viewing record of the user.
The program data mainly includes: channel name, time, program name. For example, the program listings in the left four columns of Table 2 below are normalized to the right column.
Table 2:
and matching the program list data with the behavior data structure of the IPTV user obtained by the ticket data processing module to obtain the conclusion that the watching record of the user in the table 1 is watched news live broadcasting room.
■ media asset data processing module 130 processes the film information collected in the whole network into media asset labels in the media asset library, and part of the media asset labels are obtained by complementing the collected existing film watching record information as samples.
The whole network comprises various large video websites such as bean, love singularity and the like, the film information comprises but is not limited to title, leading actor, category, year, score and brief introduction, and the collected existing film watching record information samples comprise but is not limited to film watching ratios of men and women, and film watching ratios of various age groups such as film watching ratios of 1-17 years old, 18-24 years old, 25-30 years old, 31-35 years old, 36-40 years old and more than 40 years old.
■ the user age and gender distribution prediction module 140, by performing statistical analysis on the user viewing records, uses the viewing list of the user in a period of time, the viewing degree of each movie, and the gender-age group index (the term "gender-age group index" refers to the viewing ratio of male and female of a certain movie, the viewing ratio of each age group), and applies a gender-age group label to the user by using a gaussian mixture model.
The concept of degree of viewing is introduced here to measure the user's preference for movies. The method comprises the following steps of carrying out statistical analysis on viewing records of a user to obtain the name of a film watched by the user within a period of time and the duration of watching each film, and calculating the viewing degree by the following formula:
film watching duration/film duration
I.e. how proportional to the total duration the user sees, and thus measures the user's preference for the film.
According to general intuition, it is assumed that the gender index of the entire user is gaussian distributed (normal distribution). And (3) adopting a Gaussian Mixture Model (GMM) and a maximum Expectation (EM) algorithm to perform cluster analysis and solution on the gender eigenvectors of the viewing users. As shown in figure 2 for gender index neural network architecture and figure 3 for age group index neural network architecture. The probability that each user belongs to a certain category is calculated. The probability that each user belongs to a male or a female is exemplified below by table 3.
Table 3:
| film name | Degree of film viewing | Gender direction | Sex index | Gender feature vector |
| Wave earth | 1 | For male | Male: 0.6882 female: 0.3118 | 1 |
| Four-month-one-day-different event book | 0.85 | Female | Male: 0.2388A woman: 0.7612 | -0.85 |
| And the final person: fortune of darkness | 0.92 | For male | Male: 0.8479 female: 0.1512 | 0.92 |
| Oriented life | 0.84 | Woman | Male: 0.4579 female: 0.5421 | -0.84 |
| Brother of running bar | 0.75 | Female | Male: 0.4595 female: 0.5405 | -0.75 |
| Young song line | 0.78 | For male | Male: 0.7327 female: 0.2673 | 0.78 |
| Am of great origin | 1 | For male | Male: 0.6329A woman: 0.3671 | 1 |
The gender feature vector (gender feature) of the last column is calculated by:
sex characteristic vector is sight shadow degree x sex direction value
Wherein the gender pointing values are set as: male ═ 1, female ═ 1
Similarly, age group feature vectors may also be calculated.
Age group feature vector is observation degree multiplied by age group pointing value
There are only two values of 1 and-1, as distinguished from the gender-assigned value, and the age-assigned value is, for example, 6 to correspond to, for example, 6 age groups of 1-17, 18-24, 25-30, 31-35, 36-40, and 40 years old, respectively. Of course, the distribution of these 6 age groups is not absolute, and any other way of dividing the age groups and their corresponding age group pointing to numerical settings may be contemplated.
Fig. 4 is a flowchart illustrating a method for predicting the age and gender distribution of home users based on IPTV live broadcast data according to the present invention. The method comprises the following steps:
s10: collecting user playing behavior data;
s20: and processing the collected user playing behavior data to generate a user behavior data structure. The processing includes operations such as cleaning, converting, splitting, merging and the like, for example, cleaning data with a null user ID and a null channel name, checking non-live data and the like;
s30: processing the data of the program list, and standardizing the program name, the channel name and the like;
s40: matching the program data obtained after standardization in the S30 with the user behavior data structure generated in the S20 to obtain user viewing records;
s50: calculating the watching degree of the user based on the watching records of the user: the film watching degree is the film watching duration/film duration;
s60: collecting all-network film information and sample information to form a media asset label, wherein the film information comprises but is not limited to title, lead actor, category, year, score and brief introduction, and the film watching record sample information comprises but is not limited to film watching ratio of male and female and film watching ratio of each age group;
s70: and (3) attaching a gender-age group label to the user by using the viewing degree of the user in a period of time and combining the gender-age group index and a Gaussian mixture model.
The method and the system of the invention fuse the internet media asset information, the behavior data of the user watching the IPTV live broadcast and the program data, and can obtain the age and gender distribution prediction of the user with higher accuracy.
By calculating the film watching degree, the invention avoids errors caused by actions such as short watching time and the like, such as error points, trial watching and the like of the user, and more reasonably reflects the interest preference of the user in watching the film.
According to the invention, the age and gender distribution of the user can be better predicted by adopting the Gaussian mixture model.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present disclosure, and the present disclosure should be construed as being covered by the claims and the specification.
Claims (10)
1. An IPTV family user age and gender distribution prediction system comprises:
the call ticket data processing module is used for forming a user behavior data structure based on the original call ticket;
the program data processing module is used for matching the program data with the user behavior data structure to obtain a user viewing record;
the media asset data processing module is used for collecting the information of the whole-network film to form a media asset label; and
and the user age and gender distribution prediction module is used for calculating the watching degree of the user and labeling the gender-age group label on the user based on the user watching record and the media asset label.
2. The system of claim 1, wherein:
the call ticket data processing module is used for cleaning, converting, splitting and combining the original user playing behavior data acquired by the probe, and mapping to form the user behavior data structure.
3. The system of claim 1, wherein:
the program data processing module is further used for standardizing program names and channel names.
4. The system of claim 1, wherein:
the film information collected by the media asset data processing module comprises a title, a lead actor, a category, a year, a score, an introduction and an existing film watching record information sample.
5. The system of claim 4, wherein:
the film watching record information sample comprises film watching ratios of men and women and film watching ratios of all age groups.
6. The system of claim 1, wherein the degree of viewing is used to express a user's preference for movies and is calculated by the following formula:
the film watching degree is the film watching duration/film duration.
7. The system of claim 1, wherein the user age and gender distribution prediction module employs a Gaussian mixture model GMM and maximum expected EM algorithm to perform cluster analysis and solution on the gender feature vector and the age group feature vector of the user, wherein
The gender feature vector is calculated by the following formula:
the sex characteristic vector is the observation degree multiplied by the sex direction numerical value;
the age group feature vector is calculated by the following formula:
age group feature vector is observation degree × age group index value.
8. An IPTV family user age and gender distribution prediction method comprises the following steps:
collecting user playing behavior data;
processing the collected user playing behavior data to generate a user behavior data structure;
processing the data of the program list, and standardizing the program name and the channel name;
matching the obtained program data after standardization with the generated user behavior data structure to obtain a user viewing record;
calculating the film watching degree of the user based on the user watching record, wherein the film watching degree is film watching duration/film duration;
collecting the film information of the whole network and the sample information to form a media asset label; and
the user is tagged with a gender-age group tag.
9. The method of claim 8, wherein processing the collected user playback behavior data comprises washing, converting, splitting, merging operations, including washing out data with a null user ID and a null channel name, and checking for non-live data and the like.
10. The method of claim 8, wherein labeling the user with a gender-age tag comprises clustering and solving a gender feature vector and an age feature vector of the user using a Gaussian mixture model GMM and a maximum expectation-EM algorithm, wherein the gender feature vector and the age feature vector are calculated by the following formulas, respectively:
the sex characteristic vector is the film watching degree multiplied by the sex pointing numerical value; and
age group feature vector is observation degree × age group index value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111486192.8A CN114915800A (en) | 2021-12-07 | 2021-12-07 | System and method for predicting age and gender distribution of IPTV (Internet protocol television) family users |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111486192.8A CN114915800A (en) | 2021-12-07 | 2021-12-07 | System and method for predicting age and gender distribution of IPTV (Internet protocol television) family users |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114915800A true CN114915800A (en) | 2022-08-16 |
Family
ID=82763398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111486192.8A Pending CN114915800A (en) | 2021-12-07 | 2021-12-07 | System and method for predicting age and gender distribution of IPTV (Internet protocol television) family users |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114915800A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700843A (en) * | 2015-02-05 | 2015-06-10 | 海信集团有限公司 | Method and device for identifying ages |
| CN106454529A (en) * | 2016-10-21 | 2017-02-22 | 乐视控股（北京）有限公司 | Family member analyzing method and device based on television |
| CN106529569A (en) * | 2016-10-11 | 2017-03-22 | 北京航空航天大学 | Three-dimensional model triangular facet feature learning classification method and device based on deep learning |
| CN108694954A (en) * | 2018-06-13 | 2018-10-23 | 广州势必可赢网络科技有限公司 | A kind of Sex, Age recognition methods, device, equipment and readable storage medium storing program for executing |
| CN109118284A (en) * | 2018-08-15 | 2019-01-01 | 深圳快购科技有限公司 | The management method and system of movie ticket sale |
| CN110430471A (en) * | 2019-07-24 | 2019-11-08 | 山东海看新媒体研究院有限公司 | It is a kind of based on the television recommendations method and system instantaneously calculated |
| CN111739516A (en) * | 2020-06-19 | 2020-10-02 | 中国—东盟信息港股份有限公司 | Speech recognition system for intelligent customer service call |
| CN112653908A (en) * | 2020-12-21 | 2021-04-13 | 四川长虹电器股份有限公司 | Intelligent television media asset real-time recommendation method |
-
2021
- 2021-12-07 CN CN202111486192.8A patent/CN114915800A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700843A (en) * | 2015-02-05 | 2015-06-10 | 海信集团有限公司 | Method and device for identifying ages |
| CN106529569A (en) * | 2016-10-11 | 2017-03-22 | 北京航空航天大学 | Three-dimensional model triangular facet feature learning classification method and device based on deep learning |
| CN106454529A (en) * | 2016-10-21 | 2017-02-22 | 乐视控股（北京）有限公司 | Family member analyzing method and device based on television |
| CN108694954A (en) * | 2018-06-13 | 2018-10-23 | 广州势必可赢网络科技有限公司 | A kind of Sex, Age recognition methods, device, equipment and readable storage medium storing program for executing |
| CN109118284A (en) * | 2018-08-15 | 2019-01-01 | 深圳快购科技有限公司 | The management method and system of movie ticket sale |
| CN110430471A (en) * | 2019-07-24 | 2019-11-08 | 山东海看新媒体研究院有限公司 | It is a kind of based on the television recommendations method and system instantaneously calculated |
| CN111739516A (en) * | 2020-06-19 | 2020-10-02 | 中国—东盟信息港股份有限公司 | Speech recognition system for intelligent customer service call |
| CN112653908A (en) * | 2020-12-21 | 2021-04-13 | 四川长虹电器股份有限公司 | Intelligent television media asset real-time recommendation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11574321B2 (en) | Generating audience response metrics and ratings from social interest in time-based media | |
| CN108875022B (en) | Video recommendation method and device | |
| CN106331778B (en) | Video recommendation method and device | |
| US8069076B2 (en) | Generating audience analytics | |
| KR102068790B1 (en) | Estimating and displaying social interest in time-based media | |
| CN108108491B (en) | Multimedia data recommendation method and device | |
| CN112417207B (en) | Video recommendation method, device, equipment and storage medium | |
| CN104798346A (en) | Enriching broadcast media related electronic messaging | |
| CN104933135A (en) | Method and device for clustering multimedia data | |
| CN115134668A (en) | OTT-based family member age group and family structure dividing method and device | |
| CN105956061A (en) | Method and device for determining similarity between users | |
| CN114915800A (en) | System and method for predicting age and gender distribution of IPTV (Internet protocol television) family users | |
| Jan et al. | Interest‐Based Content Clustering for Enhancing Searching and Recommendations on Smart TV | |
| CN113852864A (en) | User customized service recommendation method and system for IPTV terminal application | |
| WO2024014327A1 (en) | Information processing device, information processing method, and information processing program | |
| CN114417890B (en) | Comment content reply method and device, electronic equipment and storage medium | |
| CN109819243B (en) | Method and device for evaluating television station channel column performance | |
| CN112929753B (en) | Set top box data acquisition system | |
| US20240187695A1 (en) | Affinity profile system and method | |
| Chen et al. | [Retracted] Correlation Analysis of Population Educational Structure and Program Audience Share Based on Multisample Regression for Correction | |
| CN116137677A (en) | Theme recommendation method of intelligent television, computer equipment and readable storage medium | |
| Batara et al. | Exploring the Influence of Viewers Engagement in Live Shopping: A Study on the Impact of Skepticism and Perceived Emotional Value on Purchase Intention | |
| Erglis et al. | Prototype Proposal for Profiling and Identification of TV Viewers using Watching Patterns. | |
| Jan et al. | Research Article Interest-Based Content Clustering for Enhancing Searching and Recommendations on Smart TV | |
| CN117648488A (en) | Model training method, content sorting method, device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |