CN109005431A - A kind of video evaluations recommender system - Google Patents
A kind of video evaluations recommender system Download PDFInfo
- Publication number
- CN109005431A CN109005431A CN201811090258.XA CN201811090258A CN109005431A CN 109005431 A CN109005431 A CN 109005431A CN 201811090258 A CN201811090258 A CN 201811090258A CN 109005431 A CN109005431 A CN 109005431A
- Authority
- CN
- China
- Prior art keywords
- dimension
- self
- video
- assessment
- age
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- H04N21/25—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
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- 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
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/252—Processing of multiple end-users' preferences to derive collaborative 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]
- H04N21/20—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
-
- 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
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
-
- 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
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- 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
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Computer Graphics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention proposes a kind of video evaluations recommender systems, comprising: mode selection module, video evaluations module, video recommendations module, self-control content evaluation recommending data library, self-control content utilization database;Wherein, mode selection module, for obtaining the evaluation profile instruction or recommendation pattern instruction of user terminal sending;Video evaluations module carries out the assessment of assessment object, and assessment result is sent to user terminal for instructing according to evaluation profile, calling the data in self-control content evaluation recommending data library and making the normal data of content utilization database by oneself;Video recommendations module calculates the self-control content for obtaining and meeting screening conditions, and screening recommendation results are sent to user terminal for instructing according to recommendation pattern, calling the data in self-control content evaluation recommending data library and making the normal data of content utilization database by oneself.
Description
Technical field
The present invention relates to big data processing field, espespecially a kind of video evaluations recommender system.
Background technique
It is shown according to the 41st China Internet network state of development statistical report of CNNIC2017, China Internet netizen
In 7.72 hundred million netizens, 5.78 hundred million netizens be using internet video application, video class using rate up to 75%, in all kinds of interconnections
Ranking the 4th in the utilization rate of net application.Video content has become indispensable in China Internet netizen's network recreation
Content.
As Video Applications utilization rate is constantly promoted, the copyright purchasing model that video website is faced with competition increasingly miserable is also opened
Beginning actively seeks to break through.Therefore, self-control content in internet is operated and is given birth to, and internet self-control content can be in content in video media
The selected topic, shooting, broadcast occupy leading position.The self-control content of China Internet in 2017 is set up the project 686 altogether, and internet makes content by oneself
Into the increment epoch.
At the same time, for advertiser, internet makes content by oneself as a kind of emerging media resource, gives advertiser
Provide more choices space and marketing opportunities in marketing activity.The marketing resource and advertisement form of innovation and different
Internet is all allowed to make the favor that content receives advertiser by oneself in traditional modality for co-operation.But can achieve phenomenon grade standard from
The self-control content that perhaps single collection playback volume crosses hundred million in system but only has 10 remaining parts.Although the quantity for making content by oneself is promoted but is propagating matter
Still have huge uncontrollable factor in the control of amount, in the past advertiser make by oneself content launch decision on only by virtue of experience and
Media data is referred to.Although so that have in Marketing Cooperation Erie's grain mostly with " wonderful work is said " cooperation successful case,
Also the negative public praise after having red ox implantation " grave-robbery notes ".
Therefore, brand advertising master can have a variety of puzzlements in video content dispensing, such as: 1, industry missing is directed to network video
The unified standard of frequency assessment, it is difficult to carry out targetedly quantitative evaluation;2, phenomenon grade network video content is difficult to screen, Wu Fabao
Barrier launches quality and effect;3, it can not judge whether network video content meets the marketing objectives demand of advertiser itself.
To sum up, a kind of big data system that forecast assessment recommendation is carried out for network video content is needed.
Summary of the invention
It is right at present temporarily without the big data system for carrying out forecast assessment for the network video content in video website in industry
This, the present invention proposes a kind of video evaluations recommender system based on big data;Using integrated data quantitative evaluation as means into
The forecast assessment of row video content is commented for network video play and variety by big data automated analysis for advertiser's quantization
Estimate network video content marketing value, recommends good video content, help advertiser to lock high-quality resource in advance, and pass through
Big data operation will be that advertiser's output customizes internet video content in future.
Specifically, the video evaluations recommender system, comprising: mode selection module, video evaluations module, video recommendations mould
Block, self-control content evaluation recommending data library, self-control content utilization database;Wherein, mode selection module, for obtaining user terminal
The evaluation profile of sending instructs or recommendation pattern instruction;Video evaluations module is called in self-control for being instructed according to evaluation profile
Hold the data in assessment recommending data library and make the normal data of content utilization database by oneself, carries out the assessment of assessment object, and will
Assessment result is sent to user terminal;Video recommendations module calls self-control content evaluation to recommend number for being instructed according to recommendation pattern
According to the data in library and the normal data of self-control content utilization database, the self-control content for obtaining and meeting screening conditions is calculated, and will
Screening recommendation results are sent to user terminal.
Further, video evaluations mode includes: the assessment object that video evaluations module is selected according to user terminal, to self-control
Transfer corresponding data in content evaluation recommending data library;And judge whether feedback data is available dimension, unavailable dimension is preset
Weight distribution feeds back to user terminal to available dimension;Video evaluations recommender system receives the available dimension choosing that user terminal is sent
Call instruction is selected, and assessment dimension, weight are adjusted according to instruction;According to assessment dimension adjusted, weight and self-control content
Historical data base calculates second level dimension, level-one dimension and assessment object total score, and assessment result is sent to user terminal.
Further, video recommendations mode includes: the screening conditions that video recommendations module receives user terminal input, wherein sieving
Selecting condition includes essential restrictive condition and optional condition;According to optional condition, transferred pair to self-control content evaluation recommending data library
Reply as and corresponding data, and according to essential restrictive condition calculate matching degree level-one dimension scores;According to matching degree score descending
Arrangement generates and recommends self-control content;According to the assessment content that user selects, correspondence is transferred to self-control content evaluation recommending data library
Data;And judge whether feedback data is available dimension, by the default weight distribution of unavailable dimension to available dimension, and feed back to
User terminal;Video evaluations recommender system receives the available dimension Selection and call instruction that user terminal is sent, and is commented according to instruction adjustment
Estimate dimension, weight;According to assessment dimension adjusted, weight and self-control content utilization database, second level dimension, level-one are calculated
Dimension and recommended total score, and screening recommendation results are sent to user terminal.
Further, the system further include: contrastive pattern, by the way that assessment result and screening recommendation results are carried out dimension knot
Fruit comparison, obtains and makes content deltas data under different demands by oneself.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, not
Constitute limitation of the invention.In the accompanying drawings:
Fig. 1 is the video evaluations recommender system configuration diagram of one embodiment of the invention.
Fig. 2 is the video evaluations recommender system configuration diagram with comparing function of one embodiment of the invention.
Fig. 3 is the assessment dimension schematic diagram of one embodiment of the invention.
Fig. 4 is the scoring schematic diagram of a specific embodiment of the invention.
Specific embodiment
Cooperate schema and presently preferred embodiments of the present invention below, the present invention is further explained to reach predetermined goal of the invention institute
The technological means taken.
Fig. 1 is the video evaluations recommender system configuration diagram of one embodiment of the invention.As shown in connection with fig. 1, this system is
To assess and recommend both of which respectively to " network is made by oneself acute " in video website, " copyright is acute " " self-control variety " " copyright is comprehensive
Four class of skill " carries out goal-based assessment in video content and condition is recommended;By the above four classes video content press respectively " rising star " with " repeatedly
Two class of generation " carries out the delimitation of assessment dimension and the calculating of relevant criterion.
It can be by commenting when video content (not online or will be online video content) that advertiser has target to launch
Estimate mode.Prediction quantitative evaluation is carried out to object content, before target video content is not online to its following broadcast prospect into
The scoring of row data, and Intelligent generation topological diagram and assessment official documents and correspondence, refer to for advertiser.
Specifically, the system includes: video evaluations mode, video recommendations mode and comparing function;Wherein,
1, evaluation profile:
From the point of view of Fig. 1, evaluation profile is the assessment object selected according to user terminal, to self-control content evaluation recommending data
Transfer corresponding data in library;And judge whether feedback data is available dimension, unavailable dimension is preset into weight distribution to available dimension
Degree, and feed back to user terminal;
Video evaluations recommender system receives the available dimension Selection and call instruction that user terminal is sent, and is commented according to instruction adjustment
Estimate dimension, weight;
According to assessment dimension adjusted, weight and self-control content utilization database, second level dimension, level-one dimension are calculated
And assessment object total score, and assessment result is sent to user terminal.
2, recommendation pattern:
Refering to what is shown in Fig. 1, recommendation pattern is to carry out video recommendations according to the screening conditions of user terminal input, wherein screening item
Part includes essential restrictive condition and optional condition;
Firstly, transferring corresponding objects and corresponding data, and root to self-control content evaluation recommending data library according to optional condition
Matching degree level-one dimension scores are calculated according to essential restrictive condition;
It is arranged according to matching degree score descending, generates and recommend self-control content;
According to the assessment content that user selects, corresponding data is transferred to self-control content evaluation recommending data library;And judge anti-
Whether feedback data are available dimension, by the default weight distribution of unavailable dimension to available dimension, and feed back to user terminal;
Video evaluations recommender system receives the available dimension Selection and call instruction that user terminal is sent, and is commented according to instruction adjustment
Estimate dimension, weight;
According to assessment dimension adjusted, weight and self-control content utilization database, second level dimension, level-one dimension are calculated
And recommended total score, and screening recommendation results are sent to user terminal.
3, contrastive pattern:
Refering to what is shown in Fig. 2, after above two Pattern completion, by the way that assessment result and screening recommendation results are carried out dimension
Comparative result obtains and makes content deltas data under different demands by oneself.
Fig. 3 is the assessment dimension schematic diagram of one embodiment of the invention.Assessment dimension contains internal factor and external factor,
Specific dimension, which can according to need, to be adjusted, it should be noted that assessment dimension and revocable, similar assessment dimension body
System should all be within the scope of protection of this application.
From the point of view of Fig. 3, level-one dimension may include: playback volume, production ability, resource value, IP value, matching degree,
Playing platform, channel, attention rate, star, topic divergence.
Wherein, second level dimension calculation method are as follows: recommended will be assessed, the second level dimension that user chooses level-one dimension is corresponding
Data are brought into the dimension standards of grading, obtain corresponding second level dimension scores;
Level-one dimension calculation method in addition to matching degree are as follows:
A1=B1×W1+B2×W2+…+Bn×Wn;
A1For level-one dimension scores;B1、B2、…、BnFor every second level dimension scores;W1、W2、…、WnIt is every corresponding
Evaluation criterion is obtained according to self-control content utilization database.
Matching degree calculation method are as follows:
A2=C1×W1+C2×W2+C3×W3+C4×W4+…+Cn×Wn;
A2For matching degree score;C1For age score;C2For gender score;C3For region score;C4、…、CnIt is other each
Item score;W1、W2、W3、W4、…、WnFor every corresponding evaluation criterion, obtained according to self-control content utilization database.
The calculation method of second level dimension age score are as follows:
Age range range are as follows: 0 < X < 100;
Age range is divided into the age range of " assessment object " and the age range of " client's selection ";
The age range of " assessment object ": lower age limit X1, lower age limit Y1;Expression-form are as follows: X1≤age≤Y1;
The age range of " user's selection ": lower age limit X2, lower age limit Y2;Expression-form are as follows: X2≤age≤Y2;
As Y2 > Y1 and X2 >=X1, age-matched degree=Y1-X2/Y2-X2;
As Y2 > Y1 and X2 < X1, age-matched degree=Y1-X1/Y2-X2;
As Y2=Y1 and X1≤X2, age-matched degree=100%;
As Y2=Y1 and X1 > X2, age-matched degree=Y1-X1/Y2-X2;
As Y2 < Y1 and X1 > X2, age-matched degree=Y2-X1/Y2-X2;
As Y2 < Y1 and X1≤X2, age-matched degree=100%.
The calculation method of second level dimension gender score are as follows:
The initial appearance form of gender data are as follows: male 60: female 40;
The sex ratio of " assessment object ": male X1: female Y1;
The sex ratio of " client's selection ": male X2: female Y2;
As X2 >=Y2 and X1 >=X2, gender matching degree=100%;
As X2 >=Y2 and X1 < X2, gender matching degree=100- (X2-X1);
As X2 < Y2 and Y1 >=Y2, gender matching degree=100%;
As X2 < Y2 and Y1 < Y2, gender matching degree=100- (Y2-Y1).
In order to carry out apparent explanation to above-mentioned video evaluations recommender system, below with reference to a specific embodiment
It is illustrated, however, it should be noted that the embodiment merely to the present invention is better described, is not constituted to the present invention
Improperly limit.
As shown in connection with fig. 4, for acute by the self-control of, in 2016 in 2017, self-control variety, before those programs are shown, benefit
A series of scorings are carried out with this system, X is score;
Phenomenon grade is A grades, keypoint recommendation, 3 X≤4 < of scoring, such as: self-control acute " fellow No.9's door ", " there is cry of surprise in China to self-control variety
It breathes out ";
Outstanding grade is B grades, it is proposed that is recommended, 2 X≤3 < of scoring, such as: self-control acute " legal medical expert Qin Ming ", " small hand is led self-control variety
Doggie ";
Generally grade is C grades, considers to recommend, 1 X≤2 < of scoring, such as: self-control acute " assassin's biographies ", " face value is big for self-control variety
War ";
Secondary grade is D grades, prudent to recommend, X≤1 of scoring, such as: self-control acute " style vollyball ", self-control variety " chat by new three taste
Vegetarian ";
After program is shown, tracking follow-up program effect and score reexamine, with preliminary assessment score, rank substantially close to;Phenomenon
" there is hip-hop in China " playback volume, public praise, the clicking rate etc. of grade are in the top in the network platform;And the program for being located at secondary grade is broadcast
It is high-volume bad, it is almost the same with preliminary assessment score.
From the point of view of to sum up, the beneficial effects of the present invention are:
1, this system realizes the integrated and application of multidimensional big data.The video content rankings system is by the big number of video media
It is organically incorporated into a set of big data system according to, enterprise innovation big data and industry third party big data and carries out comprehensive answer
With.
Video media big data: each video media is grasped not by the collection to major video media data and information in time
Carry out video content playing plan and each video content estimates playback volume, production, resource value, star, matching degree, playing platform etc.
Content information.
Enterprise innovation big data automatically grabbing and acquiring: system can carry out mesh according to the condition of setting on the internet
Mark content automatically grabbing and collecting.
Industry third party's big data: the acquisition by industry third party data disclosed in the platforms such as Baidu, microblogging is for this
System provides necessary data supplement and verification.
2, video content rankings system is first to i.e. by online self-control content progress various dimensions comprehensive quantification in industry
The big data system of forecast assessment.
In numerous data and information about internet self-control content, this system is summarized as 10 level-one dimensions
Degree level-one dimension is made of 104 second level dimensions (second level dimension is specific data entry).But when practical application, number of dimensions can
To adjust as needed.Meanwhile each level-one dimension has the second level dimension more refined progress COMPREHENSIVE CALCULATING to help client more quasi-
True quantitative prediction directory index.
3, this system realizes various dimensions comprehensive quantification forecast assessment.Its customized assessment dimension and weight are to meet difference
The customization evaluation requirement of client, the different demands (pursue playback volume, pursue public praise, celebrity-driven etc.) for client are visitor
Family provides assessment dimension and the customization function of weight can customize assessment dimension and weight accounting.In different dimensions or different weights
Under, same portion's self-control content will generate different as a result, to meet client under different situations to the comprehensive consideration of self-control content.
4, this system is that video content is given a mark, and intelligently generates result topological diagram and comment more by data standard
It is intuitive that video content commercial value is presented and plays prospect.This video evaluations system devises several hundred standard words arts, system
By comprehensive assessment as a result, carrying out the matching of intelligence, the most reasonable describing mode of selection carries out the presentation of assessment report
5, this system can complete the self-renewing and verification for data assessment standard by the machine learning system of AI,
Using big data as the basis of study, data are obtained by internet, by neural network algorithm, deep learning, intensified learning
Deng constantly self upgrading evolution.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail it is bright, it should be understood that the above is only a specific embodiment of the present invention, the guarantor being not intended to limit the present invention
Range is protected, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in this
Within the protection scope of invention.
Claims (9)
1. a kind of video evaluations recommender system characterized by comprising mode selection module, video evaluations module, video recommendations
Module, self-control content evaluation recommending data library, self-control content utilization database;Wherein,
Mode selection module, for obtaining the evaluation profile instruction or recommendation pattern instruction of user terminal sending;
Video evaluations module calls the data and self-control in self-control content evaluation recommending data library for instructing according to evaluation profile
The normal data of content utilization database, carries out the assessment of assessment object, and assessment result is sent to user terminal;
Video recommendations module calls the data and self-control in self-control content evaluation recommending data library for instructing according to recommendation pattern
The normal data of content utilization database calculates the self-control content for obtaining and meeting screening conditions, and screening recommendation results is sent
To user terminal.
2. video evaluations recommender system according to claim 1, which is characterized in that video evaluations mode includes:
The assessment object that video evaluations module is selected according to user terminal transfers corresponding number to self-control content evaluation recommending data library
According to;And judge whether feedback data is available dimension, by the default weight distribution of unavailable dimension to available dimension, and feed back to use
Family end;
Video evaluations recommender system receives the available dimension Selection and call instruction that user terminal is sent, and adjusts assessment dimension according to instruction
Degree, weight;
According to assessment dimension adjusted, weight and self-control content utilization database, calculate second level dimension, level-one dimension and
Object total score is assessed, and assessment result is sent to user terminal.
3. video evaluations recommender system according to claim 1, which is characterized in that video recommendations mode includes:
Video recommendations module receives the screening conditions of user terminal input, and wherein screening conditions include essential restrictive condition and optional item
Part;
According to optional condition, corresponding objects and corresponding data are transferred to self-control content evaluation recommending data library, and according to essential limit
Condition processed calculates matching degree level-one dimension scores;
It is arranged according to matching degree score descending, generates and recommend self-control content;
According to the assessment content that user selects, corresponding data is transferred to self-control content evaluation recommending data library;And judge feedback coefficient
According to whether being available dimension, by the default weight distribution of unavailable dimension to available dimension, and user terminal is fed back to;
Video evaluations recommender system receives the available dimension Selection and call instruction that user terminal is sent, and adjusts assessment dimension according to instruction
Degree, weight;
According to assessment dimension adjusted, weight and self-control content utilization database, calculate second level dimension, level-one dimension and
Recommended total score, and screening recommendation results are sent to user terminal.
4. video evaluations recommender system according to claim 1, which is characterized in that the system further include: contrastive pattern is led to
It crosses and assessment result and screening recommendation results is subjected to dimension Comparative result, obtain and make content deltas data under different demands by oneself.
5. video evaluations recommender system according to claim 2 or 3, which is characterized in that second level dimension calculation method are as follows: will
Recommended is assessed, the second level dimension corresponding data that user chooses level-one dimension is brought into the dimension standards of grading, obtains correspondence
Second level dimension scores;
Level-one dimension calculation method in addition to matching degree are as follows:
A1=B1×W1+B2×W2+…+Bn×Wn;
A1For level-one dimension scores;B1、B2、…、BnFor every second level dimension scores;W1、W2、…、WnIt is marked for every corresponding evaluation
Standard is obtained according to self-control content utilization database.
6. video evaluations recommender system according to claim 5, which is characterized in that matching degree calculation method are as follows:
A2=C1×W1+C2×W2+C3×W3+C4×W4+…+Cn×Wn;
A2For matching degree score;C1For age score;C2For gender score;C3For region score;C4、…、CnIt is obtained for all other
Point;W1、W2、W3、W4、…、WnFor every corresponding evaluation criterion, obtained according to self-control content utilization database.
7. video evaluations recommender system according to claim 6, which is characterized in that the calculating side of second level dimension age score
Method are as follows:
Age range range are as follows: 0 < X < 100;
Age range is divided into the age range of " assessment object " and the age range of " client's selection ";
The age range of " assessment object ": lower age limit X1, lower age limit Y1;Expression-form are as follows: X1≤age≤Y1;
The age range of " user's selection ": lower age limit X2, lower age limit Y2;Expression-form are as follows: X2≤age≤Y2;
As Y2 > Y1 and X2 >=X1, age-matched degree=Y1-X2/Y2-X2;
As Y2 > Y1 and X2 < X1, age-matched degree=Y1-X1/Y2-X2;
As Y2=Y1 and X1≤X2, age-matched degree=100%;
As Y2=Y1 and X1 > X2, age-matched degree=Y1-X1/Y2-X2;
As Y2 < Y1 and X1 > X2, age-matched degree=Y2-X1/Y2-X2;
As Y2 < Y1 and X1≤X2, age-matched degree=100%.
8. video evaluations recommender system according to claim 6, which is characterized in that the calculating side of second level dimension gender score
Method are as follows:
The initial appearance form of gender data are as follows: male 60: female 40;
The sex ratio of " assessment object ": male X1: female Y1;
The sex ratio of " client's selection ": male X2: female Y2;
As X2 >=Y2 and X1 >=X2, gender matching degree=100%;
As X2 >=Y2 and X1 < X2, gender matching degree=100- (X2-X1);
As X2 < Y2 and Y1 >=Y2, gender matching degree=100%;
As X2 < Y2 and Y1 < Y2, gender matching degree=100- (Y2-Y1).
9. video evaluations recommender system according to claim 2 or 3, which is characterized in that level-one dimension include: playback volume,
Or production ability or resource value or IP value or matching degree or playing platform or channel or attention rate or star or
Topic divergence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811090258.XA CN109005431B (en) | 2018-09-18 | 2018-09-18 | A kind of video evaluations recommender system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811090258.XA CN109005431B (en) | 2018-09-18 | 2018-09-18 | A kind of video evaluations recommender system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109005431A true CN109005431A (en) | 2018-12-14 |
CN109005431B CN109005431B (en) | 2019-11-12 |
Family
ID=64592304
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811090258.XA Expired - Fee Related CN109005431B (en) | 2018-09-18 | 2018-09-18 | A kind of video evaluations recommender system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109005431B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008369A (en) * | 2018-12-26 | 2019-07-12 | 阿里巴巴集团控股有限公司 | Information processing method and its device, electronic equipment, computer-readable medium |
CN110688629A (en) * | 2019-12-11 | 2020-01-14 | 浙江过塘行网络科技有限公司 | Copyright protection method and device based on medical animation ecology, electronic equipment and storage medium |
WO2022267720A1 (en) * | 2021-06-23 | 2022-12-29 | 华为技术有限公司 | Data transmission method and communication apparatus |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120033194A1 (en) * | 2010-08-06 | 2012-02-09 | Canon Kabushiki Kaisha | Decision method and storage medium |
CN104516983A (en) * | 2015-01-08 | 2015-04-15 | 龙思薇 | Data display method |
CN105718467A (en) * | 2014-12-03 | 2016-06-29 | 苏宁云商集团股份有限公司 | Method and system for evaluating and recommending retrieval algorithms |
CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股(北京)有限公司 | Video recommendation method and device |
CN106557516A (en) * | 2015-09-29 | 2017-04-05 | 北京国双科技有限公司 | Data push method and device |
CN107705005A (en) * | 2017-09-27 | 2018-02-16 | 吴殿义 | A kind of movie and television contents Valuation Method |
CN107729519A (en) * | 2017-10-27 | 2018-02-23 | 上海数据交易中心有限公司 | Appraisal procedure and device, terminal based on multi-source multidimensional data |
-
2018
- 2018-09-18 CN CN201811090258.XA patent/CN109005431B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120033194A1 (en) * | 2010-08-06 | 2012-02-09 | Canon Kabushiki Kaisha | Decision method and storage medium |
CN105718467A (en) * | 2014-12-03 | 2016-06-29 | 苏宁云商集团股份有限公司 | Method and system for evaluating and recommending retrieval algorithms |
CN104516983A (en) * | 2015-01-08 | 2015-04-15 | 龙思薇 | Data display method |
CN106557516A (en) * | 2015-09-29 | 2017-04-05 | 北京国双科技有限公司 | Data push method and device |
CN105847985A (en) * | 2016-03-30 | 2016-08-10 | 乐视控股(北京)有限公司 | Video recommendation method and device |
CN107705005A (en) * | 2017-09-27 | 2018-02-16 | 吴殿义 | A kind of movie and television contents Valuation Method |
CN107729519A (en) * | 2017-10-27 | 2018-02-23 | 上海数据交易中心有限公司 | Appraisal procedure and device, terminal based on multi-source multidimensional data |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008369A (en) * | 2018-12-26 | 2019-07-12 | 阿里巴巴集团控股有限公司 | Information processing method and its device, electronic equipment, computer-readable medium |
CN110688629A (en) * | 2019-12-11 | 2020-01-14 | 浙江过塘行网络科技有限公司 | Copyright protection method and device based on medical animation ecology, electronic equipment and storage medium |
CN110688629B (en) * | 2019-12-11 | 2020-11-27 | 浙江过塘行网络科技有限公司 | Copyright protection method and device based on medical animation ecology, electronic equipment and storage medium |
WO2022267720A1 (en) * | 2021-06-23 | 2022-12-29 | 华为技术有限公司 | Data transmission method and communication apparatus |
Also Published As
Publication number | Publication date |
---|---|
CN109005431B (en) | 2019-11-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109005431A (en) | A kind of video evaluations recommender system | |
CN108681970A (en) | Finance product method for pushing, system and computer storage media based on big data | |
CN103377250A (en) | Top-k recommendation method based on neighborhood | |
CN101874255A (en) | Method and apparatus for estimating total interest of a group of users directing to a content | |
CN103649981A (en) | Method and apparatus for delivering targeted content | |
CN107483982A (en) | A kind of main broadcaster recommends method and apparatus | |
CN108322317A (en) | A kind of account identification correlating method and server | |
CN106951471A (en) | A kind of construction method of the label prediction of the development trend model based on SVM | |
Graeber et al. | Stories, statistics, and memory | |
WO2020135642A1 (en) | Model training method and apparatus employing generative adversarial network | |
CN106997383A (en) | The problem of based on PageRank algorithms, recommends method and system | |
CN111581516A (en) | Investment product recommendation method and related device | |
Werner et al. | Prospects for New England agriculture: farm to fork | |
CN116911962A (en) | Article selecting device and method based on data model | |
CN115311048A (en) | Information processing method and device and storage medium | |
CN109391829A (en) | Video gets position analysis system, analysis method and storage media ready | |
CN109034101B (en) | One-to-many dynamic and static advertisement playing method | |
Musayeva et al. | Assessment of the competitiveness of food products of Ukraine in the domestic and foreign markets | |
CN110634051B (en) | Fresh agricultural product recommendation method based on multi-granularity fuzzy data | |
KR102643159B1 (en) | A matching method that finds empty space in lcl containers in real time during container import and export | |
CN115222461B (en) | Intelligent marketing accurate recommendation method | |
Amadou | Food and income diversification decisions as climate change adaptation strategies: Evidence from Kalfou and Tabalak local governments, Tahoua State, Niger Republic | |
Qu et al. | The effects of online video on consumers’ attitudes toward local food | |
Janssen et al. | Trends in the organization and financing of agricultural research in developed countries: implications for developing countries | |
CN114387041B (en) | Multimedia data acquisition method and system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CB03 | Change of inventor or designer information |
Inventor after: Liu Guangxu Inventor before: Liu Guangxu |
|
CB03 | Change of inventor or designer information | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191112 |
|
CF01 | Termination of patent right due to non-payment of annual fee |