CN103714130A - Video recommendation system and method thereof - Google Patents
Video recommendation system and method thereof Download PDFInfo
- Publication number
- CN103714130A CN103714130A CN201310684807.7A CN201310684807A CN103714130A CN 103714130 A CN103714130 A CN 103714130A CN 201310684807 A CN201310684807 A CN 201310684807A CN 103714130 A CN103714130 A CN 103714130A
- Authority
- CN
- China
- Prior art keywords
- user
- video
- friend
- data
- information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a video recommendation system and a method thereof. The video recommendation system and the method thereof comprises: acquiring multi-source data including personal information, social network information and video classification information of users by a information acquisition module; presetting the multi-source data by a data pre-processing module; storing the multi-source data after preprocessing by a user database which is established by a data storage module; enabling an analytical module of the characteristics of users to acquire feature and mood information of the users according to microblog data sent by the users and enabling an analytical module of the social network information to analyze friend groups of the users to acquire friend circles; enabling a video recommendation module to select favorable videos of the users according to the feature, mood and friend circles; enabling a front-end display module to display the selected videos for the users.
Description
Technical field
The present invention relates to areas of information technology, relate in particular to a kind of video commending system and method.
Background technology
Current existing video recommendation method and system mainly contain two kinds.Be that user initiatively selects a video classification of liking, then system selects to recommend the video of identical category according to user; Another kind of be the historical record of watching according to user, recommend other videos of the video identical category of watching with user.
The common trait of these two kinds of methods is all to utilize user's personal information and lay particular emphasis on only to utilize its viewing information to carry out video recommendation, and other portray the important information of user characteristics to have ignored user's sex, age, occupation, nationality, area etc.The a certain class film that this has caused its recommendation results concentrations to be watched in user, cannot reflect user's true interest, the accuracy of recommendation, comprehensively spend on the low side.
And the member of the social networks such as user's relatives, friend can directly affect user's the custom of watching, for example user's good friend has recommended a certain film to it, or this user's multidigit good friend watched same portion film, it is very big that this user likes the possibility of this film so.These information recommend to have very big reference value for video, and the above-mentioned method of mentioning is not but used these social informations completely.This has caused its recommendation results cannot react user's social feature completely, and the potential video classification that unpredictable user may like, does not have adaptability, and dirigibility is poor.
Therefore also there is defect in prior art, needs to be improved and develop.
Summary of the invention
The invention provides a kind of video commending system, this video commending system can offer that user recommends accurately, comprehensive video.
A video commending system, comprising:
Acquisition of information module, for obtaining the multi-source data that comprises userspersonal information, the user social contact network information and video classification information;
Data preprocessing module, for carrying out pre-service to described multi-source data;
Data memory module, builds customer data base, and multi-source data after pretreatment is stored in described database;
User's characteristic analysis module, for the microblogging data acquisition user's that sends according to user personality and mood;
Social networks analysis module, for the good friend's cluster analysis to user, obtains described user's friend circle;
Video recommending module, for according to described user's personality, mood and friend circle, chooses the video of described user preferences;
Front end display module, for showing the video of choosing to described user.
Further, described acquisition of information module comprises:
Userspersonal information obtains submodule, by the user registration module of webpage version, obtains user's personal information, and described personal information comprises age, sex, occupation, nationality, location, the video type of liking, the list of videos of watching;
Social network information obtains submodule, by intercommunion platform, obtain the user social contact network information, the described user social contact network information comprises user's friend information, the microblogging content that user pushes and the when and where that sends microblogging, the list of videos that user watched, user's video marking information; And
Video classification acquisition of information submodule, obtains video classification information by video website, and described video classification packets of information is drawn together title, director, age, type etc., video scoring, video tab.
Further, described data preprocessing module comprises:
Data cleansing submodule, for rejecting the incomplete data of described multi-source data;
Data stipulations submodule, for unifying the form of the multi-source data from different platform; And
Data integration submodule, for by the data integration from disparate databases after stipulations to identical database.
Further, described data memory module is for storing described userspersonal information the relevant database of Sqlserver or Mysql into and by the figure relational database of user social contact network information store M ongoDB.
Further, described user's characteristic analysis module comprises:
User's character analysis submodule, for the microblogging data analysis user's that sent according to user personality in the past; And
User emotion is analyzed submodule, for the microblogging data analysis user's that sent according to user mood in the past.
Further, described video recommending module comprises:
Userspersonal information's recommending module, for choosing the video film of user preferences according to user's personality and mood; And
Social network information recommending module, for choosing the video film of user preferences according to user's friend circle.
Further, also comprise the real-time capture module of user profile, for Real-time Obtaining user's social network information, and deposit in described database.
Further, also comprise result optimizing module, for the video that described video recommending module is chosen according to friend circle, give weights, and according to the generating recommendations list of sorting of described weights.
Further, described front end display module comprises form web page, television terminal or mobile phone terminal.
In addition, the present invention also provides a kind of video recommendation method, comprises the steps:
Obtain the multi-source data that comprises userspersonal information, the user social contact network information and video classification information;
Described multi-source data is carried out to pre-service;
Build customer data base, and multi-source data after pretreatment is stored in described database;
The microblogging data acquisition user's who sends according to user personality and mood;
Good friend's cluster analysis to user, obtains described user's friend circle, and described friend circle comprises close friend's circle, good friend's circle and maximum propagation influence power good friend;
According to described user's personality, mood and friend circle, choose the video of described user preferences; And
For show the video of choosing to described user.
Further, the microblogging data acquisition user's who sends according to user personality and mood, comprise the steps:
Mathematical abstractions is the vector space of a N dimension, and each vectorial corresponding personality/mood fundamental, wherein personality fundamental is: introversion, flare, stable, unstable, mood fundamental is: happy, angry, sad, frightened, detest, surprised, the vector space that described N ties up is P=[x
1, x
2... ];
Described microblogging data are carried out to participle, obtain semantic feature, be defined as C=[c
1, c
2... ];
Set up Function Mapping relation, P=f(C), wherein, P is the set of personality/mood fundamental sum key element, and C is the semantic feature set obtaining after microblogging data participle, and f is corresponding mapping function;
From described microblogging, collect microblogging data C, judge the score of every fundamental, thereby obtain personality/mood fundamental P, composing training data set;
Utilize neural network algorithm to learn to obtain model of fit for training dataset, then according to the model prediction user personality/mood obtaining.
Further, the good friend's cluster analysis to user, obtains described user's friend circle, comprises the steps:
User's good friend is expressed as to the set of series of features vector, described set comprises region, age, sex, occupation, the video type of liking and the list of videos of watching;
The distance of calculating between good friend's vector characterizes the similarity between good friend and good friend, and by good friend's automatic cluster of user, is some types according to similarity employing clustering algorithm KMeans;
Choose front 20 good friends that similarity is higher and form its close friend's circle;
The propagation effect power of calculating user good friend according to user good friend's microblogging quantity forwarded and forwarding quantity, described computing formula is p=0.2S+0.8F, and wherein P is good friend's propagation effect power, and S is microblogging quantity forwarded, and F is the number of times that microblogging is forwarded.
Further, according to described user's personality, mood and friend circle, choose the video of described user preferences, comprise the steps:
According to user's personality and mood, choose the video film of user preferences; And
According to user's friend circle, choose the video film of user preferences.
Further, according to user's personality and mood, choose the video film of user preferences, comprise the steps:
Every film is described with region, age, protagonist, four attributes of type;
According to user's personality and mood, obtain this user for the preference degree with the film of certain attribute, and give weights;
For any film, described user sums up corresponding to the preference degree of described film attribute, obtains the fancy grade of described user to described film;
All films are calculated, and 10 films choosing fancy grade maximum are recommended user.
Further, according to user's friend circle, choose the video film of user preferences, comprise the steps:
Calculate every good friend in user's friend circle and jointly watch more video, extract front 10 films as recommendation results;
Find in close friend's circle of user and jointly watch more video, extract front 10 films as recommendation results;
According to user good friend's propagation effect power, extract front 10 films as recommendation results.
Further, also comprise the steps: that the video that described video recommending module is chosen according to friend circle gives weights, and according to the generating recommendations list of sorting of described weights.
Further, the video that described video recommending module is chosen according to friend circle is given weights, and according to the generating recommendations list of sorting of described weights, comprises the steps:
Good friend's recommendation results and the recommendation results of common circle of the recommendation results drawing for close friend's circle respectively, propagation effect power maximum are given weights;
Calculate all weights sums that appear at the film in recommendation results;
And according to the generating recommendations list of sorting of described weights, as final recommendation results.
Video commending system provided by the invention and method, by acquisition of information module, obtain and comprise userspersonal information, the multi-source data of the user social contact network information and video classification information, by data preprocessing module, described multi-source data is carried out to pre-service, the subscriber database stores multi-source data after pretreatment building through data memory module again, the microblogging data acquisition user's who sends according to user by user's characteristic analysis module again personality and mood and the good friend cluster analysis of social networks analysis module to user, obtain described user's friend circle, video recommending module is according to described user's personality, mood and friend circle, choose the video of described user preferences and by front end display module, to described user, show the video of choosing.
Accompanying drawing explanation
Fig. 1 is the composition schematic diagram of video commending system provided by the invention;
Fig. 2 is the composition schematic diagram of acquisition of information module provided by the invention;
Fig. 3 is the composition schematic diagram of data preprocessing module provided by the invention;
Fig. 4 is the composition schematic diagram of user's characteristic analysis module provided by the invention;
Fig. 5 is the flow chart of steps of video recommendation method provided by the invention;
Fig. 6 is microblogging data acquisition user's personality and the flow chart of steps of mood sending according to user provided by the invention;
Fig. 7 is the good friend's cluster analysis to user provided by the invention, obtains the flow chart of steps of described user's friend circle;
Fig. 8 is the flow chart of steps of choosing the video film of user preferences according to user's personality and mood provided by the invention;
Fig. 9 is the flow chart of steps that the friend circle according to user provided by the invention is chosen the video film of user preferences.
Embodiment
In order to make object of the present invention, technical scheme and advantage more clear, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Refer to Fig. 1, Fig. 1 is the composition schematic diagram of video commending system 100 provided by the invention, comprising: acquisition of information module 110, data preprocessing module 120, data memory module 130, user's characteristic analysis module 140, social networks analysis module 150, video recommending module 160 and front end display module 170.
Refer to Fig. 2, acquisition of information module 110 is for obtaining the multi-source data that comprises userspersonal information, the user social contact network information and video classification information.Preferably, acquisition of information module 110 comprises: userspersonal information obtains submodule 111, social network information obtains submodule 112 and video classification acquisition of information submodule 113.Userspersonal information obtains submodule 111 by the user registration module of webpage version, obtains user's personal information, and wherein, personal information comprises age, sex, occupation, nationality, location, the video type of liking, the list of videos of watching; Social network information obtains submodule 112 and obtains the user social contact network information by intercommunion platform, for example, the opening API interface that can utilize the platforms such as Sina's microblogging, Tengxun's microblogging, Tencent QQ, Yoqoo to provide obtains user profile, wherein, the user social contact network information comprises user's friend information, the microblogging content that user pushes and the when and where that sends microblogging, the list of videos that user watched, user's video marking information; Video classification acquisition of information submodule 113 obtains video classification information by video website, such as extracting needed information from bean cotyledon, the excellent main flow video website such as cruel, wherein, video classification packets of information is drawn together title, director, age, type, video scoring, video tab etc.
Refer to Fig. 3, data preprocessing module 120 is for carrying out pre-service to multi-source data.Preferably, data preprocessing module 120 comprises: data cleansing submodule 121, data stipulations submodule 122 and data integration submodule 123.Data cleansing submodule 121, for rejecting the incomplete data of described multi-source data, is not filled in the data recording of any personal information and will can analyzed recommending module do not used except name such as user; Data stipulations submodule 122 is for unifying the form of the multi-source data from different platform, for example, by personal register information of user and the personal information that puts forward from websites such as microblogging, QQ unified be following form: user name, age, sex, occupation, nationality, location, the video type of liking, the list of videos of watching, user's video marking information; By the social network information unification from microblogging, QQ, be following form: user name, user good friend 1, user good friend 2, user good friend 3 etc.; By the video information stipulations from bean cotyledon, the excellent network such as cruel, be following form: video name, video age, director, protagonist, region, type, scoring, label; Data integration submodule 123 for by the data integration from disparate databases after stipulations to identical database.
Refer to Fig. 4, user's characteristic analysis module 140 is for the microblogging data acquisition user's that sends according to user personality and mood.Preferably, user's characteristic analysis module 140 comprises user's character analysis submodule 141 and user emotion analysis submodule 142, user's character analysis submodule 141 is for the microblogging data analysis user's that sent according to user personality in the past, and user emotion is analyzed submodule 142 for the microblogging data analysis user's that sent according to user mood in the past.
Particularly, user's character analysis submodule 141, for the microblogging data analysis user's that sent according to user personality in the past, specifically adopts the analysis of following step to user's personality:
Mathematical abstractions is the vector space of a N dimension, and each vectorial corresponding personality fundamental, and the vector space of N dimension is P=[x
1, x
2... ];
Described microblogging data are carried out to participle, obtain semantic feature, be defined as C=[c
1, c
2... ];
Set up Function Mapping relation, P=f(C), wherein, P is the set of personality fundamental sum key element, and C is the semantic feature set obtaining after microblogging data participle, and f is corresponding mapping function;
From described microblogging, collect microblogging data C, its personality/emotion trait of manual analysis, resolves to personality fundamental P, by artificial labeled data, obtains training dataset;
Utilize neural network algorithm to learn to obtain model of fit for training dataset, then according to the model prediction user personality obtaining.
And the microblogging data analysis user's that employing user emotion analysis submodule 142 sent according to user mood and 141 realizations of above-mentioned user's character analysis submodule are in full accord to user's character analysis in the past, do not repeat them here.
Social networks analysis module 150, for the good friend's cluster analysis to user, obtains described user's friend circle.Social networks analysis module 150 these modules are carried out multiple analysis for user social contact network data, mainly comprise following analysis:
One, user's good friend is carried out to cluster, its good friend is divided into some classifications according to feature.User's good friend is expressed as to the set of series of features vector: region, age, sex, occupation, the video type of liking, the list of videos of watching, and calculate the similarity between good friend and good friend, and according to similarity, user's good friend is divided into some types.
Two, calculate user and its good friend's intimate degree, obtain its close friend's circle.By calculating the similarity between user and good friend, select the highest several good friends of similarity to enter close friend's circle of user, when recommending, strengthen weight.
Three, calculate its good friend's propagation effect power, and then determine its size of influence power for this user.The propagation effect power of calculating user according to user good friend's microblogging quantity forwarded and forwarding quantity:
P=0.2S+0.8F
Wherein P is good friend's propagation effect power, and S is microblogging quantity forwarded, and F is the number of times that microblogging is forwarded.
And the propagation effect power according to its good friend decides its shared proportion in analyzing recommending module, and the proportion that the good friend that influence power is larger accounts in analyzing recommending module is larger.
One, show that according to userspersonal information the algorithm of recommendation results is as follows:
A) every video is described with region, age, protagonist, four attributes of type.
B) from user's personal information, obtain this user for the preference degree with the film of certain attribute, also with weights, represent.
C), for a certain portion film, this user is summed up and can obtain the fancy grade of user to this film corresponding to the preference value of this film attribute.
D) all films are calculated, and choose 10 films that fancy grade is larger and recommend user.
Its two, according to user's social network information, recommend video information, its algorithm is as follows:
A) in (6) social networks analysis module, user's good friend is divided for some classifications, calculate user's personal information and the similarity between good friend's classification, thereby determine which kind of user more may belong to.
B) calculate every good friend in this classification and jointly watch more video, extract front 10 as recommendation results.
C) find in close friend's circle of user and jointly watch more video, extract front 10 as recommendation results.
D) find and have more influential good friend, extract front 10 as recommendation results.
Front end display module 170 is for showing the video of choosing to described user.Front end display module comprises form web page, television terminal or mobile phone terminal.
In addition, above-mentioned video commending system 100 also comprises the real-time capture module 180 of user profile, for Real-time Obtaining user's social network information, and deposits in described database.Be appreciated that after user is by the login of the terminal such as webpage, system shows that in terminal this user's history watches list, and the recording user video information of watching in real time, and then new database more.For users such as microblogging, QQ, pass through the social information of data acquisition module track user in nearly a period of time simultaneously, as the microblogging pushing, the renewal of individual good friend's data etc., and deposit database in.
In addition, above-mentioned video commending system 100 also comprises result optimizing module 190, for the video that described video recommending module is chosen according to friend circle, gives weights, and according to the generating recommendations list of sorting of described weights.Be appreciated that after each result drawing for video recommending module 160 is optimized by result optimizing module 190 and draw net result, specifically comprise:
A) recommendation results drawing for close friend's circle is given weights 1, and the recommendation results drawing for the larger good friend of influence power is given weights 1.5, and the recommendation results drawing for common circle is given weights 0.8;
B) calculate all weights sums that appear at the film in recommendation results;
C) after sequence, select front 20 videos of circle maximum, as final recommendation results.
Refer to Fig. 5, for video recommendation method 200 provided by the invention, comprise the steps:
Step S210: obtain the multi-source data that comprises userspersonal information, the user social contact network information and video classification information;
Be appreciated that and can pass through the user registration module of webpage version, obtain user's personal information, personal information comprises age, sex, occupation, nationality, location, the video type of liking, the list of videos of watching; By intercommunion platform, obtain the user social contact network information, for example, the opening API interface that can utilize the platforms such as Sina's microblogging, Tengxun's microblogging, Tencent QQ, Yoqoo to provide obtains user profile, wherein, the user social contact network information comprises user's friend information, the microblogging content that user pushes and the when and where that sends microblogging, the list of videos that user watched, user's video marking information; By video website, obtain video classification information, such as extracting needed information from bean cotyledon, the excellent main flow video website such as cruel, wherein, video classification packets of information is drawn together title, director, age, type etc., video scoring, video tab.
Step S220: multi-source data is carried out to pre-service;
Specifically comprise: reject incomplete data in described multi-source data, such as user, except name, do not fill in the data recording of any personal information and will can analyzed recommending module not use; The form of the multi-source data from different platform is unified, for example, by personal register information of user and the personal information that puts forward from websites such as microblogging, QQ unified be following form: user name, age, sex, occupation, nationality, location, the video type of liking, the list of videos of watching, user's video marking information; By the social network information unification from microblogging, QQ, be following form: user name, user good friend 1, user good friend 2,
User good friend 3 etc.; By the video information stipulations from bean cotyledon, the excellent network such as cruel, be following form: video name, video age, director, protagonist, region, type, scoring, label; And by the data integration from disparate databases after stipulations in identical database.
Step S230: build customer data base, and multi-source data after pretreatment is stored in described database;
Preferably, userspersonal information is stored in the relevant database of Sqlserver or Mysql and by the figure relational database of user social contact network information store M ongoDB.Be appreciated that Sqlserver or Mysql or MongoDB database are a kind of optimal way wherein, and can also adopt other database in reality.
Step S240: the microblogging data acquisition user's who sends according to user personality and mood;
Refer to Fig. 6, the microblogging data acquisition user's who sends according to user personality and mood, comprise the steps:
Step S241: mathematical abstractions is the vector space of a N dimension, and each vectorial corresponding personality/mood fundamental, wherein personality fundamental is: introversion, flare, stable, unstable, mood fundamental is: happy, angry, sad, frightened, detest, surprised, the vector space that described N ties up is P=[x
1, x
2... ];
Step S242: described microblogging data are carried out to participle, obtain semantic feature, be defined as C=[c
1, c
2... ];
Step S243: set up Function Mapping relation, P=f(C), wherein, P is the set of personality/mood fundamental sum key element, and C is the semantic feature set obtaining after microblogging data participle, and f is corresponding mapping function;
Step S244: collect microblogging data C from described microblogging, invite the professional person with psychological consultation experience to read microblogging, judge the score of every fundamental, thereby obtain personality/mood fundamental P, composing training data set;
Step S245: utilize neural network algorithm to learn to obtain model of fit for training dataset, then according to the model prediction user personality/mood obtaining.
Step S250: the good friend's cluster analysis to user, obtain described user's friend circle, described friend circle comprises close friend's circle, good friend's circle and maximum propagation influence power good friend;
Refer to Fig. 7, the good friend's cluster analysis to user, obtains described user's friend circle, comprises the steps:
Step S251: user's good friend is expressed as to the set of series of features vector, described set comprises region, age, sex, occupation, the video type of liking and the list of videos of watching;
Step S252: the distance of calculating between good friend's vector characterizes the similarity between good friend and good friend, and by good friend's automatic cluster of user, be some types according to similarity employing clustering algorithm KMeans;
Step S253: choose front 20 good friends that similarity is higher and form its close friend's circle;
Step S254: the propagation effect power of calculating user good friend according to user good friend's microblogging quantity forwarded and forwarding quantity, described computing formula is p=0.2S+0.8F, and wherein P is good friend's propagation effect power, and S is microblogging quantity forwarded, and F is the number of times that microblogging is forwarded.The propagation effect power according to its good friend that is appreciated that decides its shared proportion in analyzing recommending module, and the proportion that the good friend that influence power is larger accounts in analyzing recommending module is larger.
Step S260: according to described user's personality, mood and friend circle, choose the video of described user preferences;
According to described user's personality, mood and friend circle, choose the flow chart of steps of the video of described user preferences, comprise the steps:
Step S261: the video film of choosing user preferences according to user's personality and mood; :
Refer to Fig. 8, according to user's personality and mood, choose the video film of user preferences, comprise the steps:
Step S2611: every film is described with region, age, protagonist, four attributes of type;
Step S2612: obtain this user for the preference degree with the film of certain attribute according to user's personality and mood, and give weights;
Step S2613: for any film, described user sums up corresponding to the preference degree of described film attribute, obtains the fancy grade of described user to described film;
Step S2614: all films are calculated, and 10 films choosing fancy grade maximum are recommended user.
Be appreciated that choosing 10 films recommends just preferred a kind of mode wherein of user, can also choose other film quantity to user in reality.
Step S262: the video film of choosing user preferences according to user's friend circle.
Refer to Fig. 9, according to user's friend circle, choose the video film of user preferences, comprise the steps:
Step S2621: calculate every good friend in user's friend circle and jointly watch more video, extract front 10 films as recommendation results;
Step S2622: find in close friend's circle of user and jointly watch more video, extract front 10 films as recommendation results;
Step S2623: according to user good friend's propagation effect power, extract front 10 films as recommendation results.
Step S270: for show the video of choosing to user.
Be appreciated that by above-mentioned steps S210~S270 and can realize user's video is recommended.The method that above-mentioned video is recommended can also comprise the steps:
The video that described video recommending module is chosen according to friend circle is given weights, and according to the generating recommendations list of sorting of described weights.Good friend's recommendation results and the recommendation results of common circle of the recommendation results drawing for close friend's circle respectively particularly,, propagation effect power maximum are given weights; Calculate all weights sums that appear at the film in recommendation results; And according to the generating recommendations list of sorting of described weights, as final recommendation results.A) recommendation results drawing for close friend's circle is given weights 1, and the recommendation results drawing for the larger good friend of influence power is given weights 1.5, and the recommendation results drawing for common circle is given weights 0.8; Calculate again all weights sums that appear at the film in recommendation results; After sequence, select front 20 videos of circle maximum, as final recommendation results.
Video commending system provided by the invention and method, by acquisition of information module, obtain and comprise userspersonal information, the multi-source data of the user social contact network information and video classification information, by data preprocessing module, described multi-source data is carried out to pre-service, the subscriber database stores multi-source data after pretreatment building through data memory module again, the microblogging data acquisition user's who sends according to user by user's characteristic analysis module again personality and mood and the good friend cluster analysis of social networks analysis module to user, obtain described user's friend circle, video recommending module is according to described user's personality, mood and friend circle, choose the video of described user preferences and by front end display module, to described user, show the video of choosing.
Be understandable that, for the person of ordinary skill of the art, can make other various corresponding changes and distortion by technical conceive according to the present invention, and all these change and distortion all should belong to the protection domain of the claims in the present invention.
Claims (17)
1. a video commending system, is characterized in that, comprising:
Acquisition of information module, for obtaining the multi-source data that comprises userspersonal information, the user social contact network information and video classification information;
Data preprocessing module, for carrying out pre-service to described multi-source data;
Data memory module, builds customer data base, and multi-source data after pretreatment is stored in described database;
User's characteristic analysis module, for the microblogging data acquisition user's that sends according to user personality and mood;
Social networks analysis module, for the good friend's cluster analysis to user, obtains described user's friend circle;
Video recommending module, for according to described user's personality, mood and friend circle, chooses the video of described user preferences; And
Front end display module, for showing the video of choosing to described user.
2. video commending system according to claim 1, is characterized in that, described acquisition of information module comprises:
Userspersonal information obtains submodule, by the user registration module of webpage version, obtains user's personal information, and described personal information comprises age, sex, occupation, nationality, location, the video type of liking, the list of videos of watching;
Social network information obtains submodule, by intercommunion platform, obtain the user social contact network information, the described user social contact network information comprises user's friend information, the microblogging content that user pushes and the when and where that sends microblogging, the list of videos that user watched, user's video marking information; And
Video classification acquisition of information submodule, obtains video classification information by video website, and described video classification packets of information is drawn together title, director, age, type, video scoring, video tab.
3. video commending system according to claim 1, is characterized in that, described data preprocessing module comprises:
Data cleansing submodule, for rejecting the incomplete data of described multi-source data;
Data stipulations submodule, for unifying the form of the multi-source data from different platform; And
Data integration submodule, for by the data integration from disparate databases after stipulations to identical database.
4. video commending system according to claim 1, it is characterized in that, described data memory module is for storing described userspersonal information the relevant database of Sqlserver or Mysql into and by the figure relational database of user social contact network information store M ongoDB.
5. video commending system according to claim 1, is characterized in that, described user's characteristic analysis module comprises:
User's character analysis submodule, for the microblogging data analysis user's that sent according to user personality in the past; And
User emotion is analyzed submodule, for the microblogging data analysis user's that sent according to user mood in the past.
6. video commending system according to claim 1, is characterized in that, described video recommending module comprises:
Userspersonal information's recommending module, for choosing the video film of user preferences according to user's personality and mood; And
Social network information recommending module, for choosing the video film of user preferences according to user's friend circle.
7. video commending system according to claim 1, is characterized in that, also comprises the real-time capture module of user profile, for Real-time Obtaining user's social network information, and deposits in described database.
8. video commending system according to claim 1, is characterized in that, also comprises result optimizing module, for the video that described video recommending module is chosen according to friend circle, gives weights, and according to the generating recommendations list of sorting of described weights.
9. video commending system according to claim 8, is characterized in that, described front end display module comprises form web page, television terminal or mobile phone terminal.
10. a video recommendation method, is characterized in that, comprises the steps:
Obtain the multi-source data that comprises userspersonal information, the user social contact network information and video classification information;
Described multi-source data is carried out to pre-service;
Build customer data base, and multi-source data after pretreatment is stored in described database;
The microblogging data acquisition user's who sends according to user personality and mood;
Good friend's cluster analysis to user, obtains described user's friend circle, and described friend circle comprises close friend's circle, good friend's circle and maximum propagation influence power good friend;
According to described user's personality, mood and friend circle, choose the video of described user preferences; And
For show the video of choosing to described user.
11. video recommendation methods according to claim 10, is characterized in that, the microblogging data acquisition user's who sends according to user personality and mood, comprise the steps:
Mathematical abstractions is the vector space of a N dimension, and each vectorial corresponding personality/mood fundamental, wherein personality fundamental is: introversion, flare, stable, unstable, mood fundamental is: happy, angry, sad, frightened, detest, surprised, the vector space that described N ties up is designated as P=[x
1, x
2... ];
Described microblogging data are carried out to participle, obtain semantic feature, be defined as C=[c
1, c
2... ];
Set up Function Mapping relation, P=f(C), wherein, P is the set of personality/mood fundamental, and C is the semantic feature set obtaining after microblogging data participle, and f is corresponding mapping function;
From described microblogging, collect microblogging data C, judge the score of every fundamental, thereby obtain personality/mood fundamental P, composing training data set;
Utilize neural network algorithm to learn to obtain model of fit for training dataset, then according to the model prediction user personality/mood obtaining.
12. video recommendation methods according to claim 10, is characterized in that, described user's friend circle is obtained in the good friend's cluster analysis to user, comprises the steps:
User's good friend is expressed as to the set of series of features vector, described set comprises region, age, sex, occupation, the video type of liking and the list of videos of watching;
The distance of calculating between good friend's vector characterizes the similarity between good friend and good friend, and by good friend's automatic cluster of user, is some types according to similarity employing clustering algorithm KMeans;
Choose front 20 good friends that similarity is higher and form its close friend's circle;
The propagation effect power of calculating user good friend according to user good friend's microblogging quantity forwarded and forwarding quantity, described computing formula is p=0.2S+0.8F, and wherein P is good friend's propagation effect power, and S is microblogging quantity forwarded, and F is the number of times that microblogging is forwarded.
13. video recommendation methods according to claim 10, is characterized in that, according to described user's personality, mood and friend circle, choose the video of described user preferences, comprise the steps:
According to user's personality and mood, choose the video film of user preferences; And
According to user's friend circle, choose the video film of user preferences.
14. video recommendation methods according to claim 13, is characterized in that, choose the video film of user preferences according to user's personality and mood, comprise the steps:
Every film is described with region, age, protagonist, four attributes of type;
According to user's personality and mood, obtain this user for the preference degree with the film of certain attribute, and give weights;
For any film, described user sums up corresponding to the preference degree of described film attribute, obtains the fancy grade of described user to described film;
All films are calculated, and 10 films choosing fancy grade maximum are recommended user.
15. video recommendation methods according to claim 13, is characterized in that, choose the video film of user preferences according to user's friend circle, comprise the steps:
Calculate every good friend in user's friend circle and jointly watch more video, extract front 10 films as recommendation results;
Find in close friend's circle of user and jointly watch more video, extract front 10 films as recommendation results;
According to user good friend's propagation effect power, extract front 10 films as recommendation results.
16. video recommendation methods according to claim 12, is characterized in that, also comprise the steps: that the video that described video recommending module is chosen according to friend circle gives weights, and according to the generating recommendations list of sorting of described weights.
17. video recommendation methods according to claim 16, is characterized in that, the video that described video recommending module is chosen according to friend circle is given weights, and according to the generating recommendations list of sorting of described weights, comprise the steps:
Good friend's recommendation results and the recommendation results of common circle of the recommendation results drawing for close friend's circle respectively, propagation effect power maximum are given weights;
Calculate all weights sums that appear at the film in recommendation results;
And according to the generating recommendations list of sorting of described weights, as final recommendation results.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310684807.7A CN103714130B (en) | 2013-12-12 | 2013-12-12 | Video recommendation system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310684807.7A CN103714130B (en) | 2013-12-12 | 2013-12-12 | Video recommendation system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103714130A true CN103714130A (en) | 2014-04-09 |
CN103714130B CN103714130B (en) | 2017-08-22 |
Family
ID=50407105
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310684807.7A Active CN103714130B (en) | 2013-12-12 | 2013-12-12 | Video recommendation system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103714130B (en) |
Cited By (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104765778A (en) * | 2015-03-18 | 2015-07-08 | 百度在线网络技术(北京)有限公司 | Method and device for providing information to be transmitted based on user behaviors |
CN104834969A (en) * | 2015-05-05 | 2015-08-12 | 东南大学 | Film evaluation prediction method and system |
CN105022699A (en) * | 2015-07-14 | 2015-11-04 | 惠龙易通国际物流股份有限公司 | Cache region data preprocessing method and system |
CN105095516A (en) * | 2015-09-16 | 2015-11-25 | 中国传媒大学 | Broadcast television subscriber grouping system and method based on spectral clustering integration |
CN105138551A (en) * | 2015-07-14 | 2015-12-09 | 青岛海信传媒网络技术有限公司 | Method and apparatus for obtaining user interest tag |
CN105224576A (en) * | 2014-07-01 | 2016-01-06 | 上海视畅信息科技有限公司 | A kind of video display intelligent recommendation method |
CN105704231A (en) * | 2016-03-17 | 2016-06-22 | 珠海格力电器股份有限公司 | Information push method and apparatus for network playing resources |
CN105740473A (en) * | 2016-03-14 | 2016-07-06 | 腾讯科技(深圳)有限公司 | User-generated content display method and device |
CN105824818A (en) * | 2015-01-04 | 2016-08-03 | 中国移动通信集团河北有限公司 | Informationized management method, platform and system |
CN105915957A (en) * | 2015-12-15 | 2016-08-31 | 乐视致新电子科技(天津)有限公司 | Intelligent television playing content display method, device and system |
CN105915954A (en) * | 2015-10-30 | 2016-08-31 | 乐视移动智能信息技术(北京)有限公司 | Video recommendation method based on mobile phone screen and video recommendation system thereof |
CN105930532A (en) * | 2016-06-16 | 2016-09-07 | 上海聚力传媒技术有限公司 | Method and device of recommending multimedia resources to user |
CN106034256A (en) * | 2015-03-10 | 2016-10-19 | 腾讯科技(北京)有限公司 | Video social method and video social device |
CN106131684A (en) * | 2016-06-24 | 2016-11-16 | 依偎科技(南昌)有限公司 | A kind of content recommendation method and terminal |
WO2016187768A1 (en) * | 2015-05-25 | 2016-12-01 | 武克易 | Video information pushing method and apparatus |
CN106202570A (en) * | 2016-08-11 | 2016-12-07 | 乐视控股(北京)有限公司 | A kind of user information acquiring method and device |
CN106202103A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | Music recommends method and apparatus |
CN106201184A (en) * | 2016-06-29 | 2016-12-07 | 腾讯科技(深圳)有限公司 | Edit methods, device and the terminal of a kind of SNS message |
CN106202252A (en) * | 2016-06-29 | 2016-12-07 | 厦门趣处网络科技有限公司 | Method, system are recommended in a kind of trip analyzed based on user emotion |
CN106339146A (en) * | 2015-07-09 | 2017-01-18 | 华为终端(东莞)有限公司 | Method and device for recommending applications |
CN106528584A (en) * | 2016-02-15 | 2017-03-22 | 中山大学 | An ensemble learning-based group recommendation method |
CN106649655A (en) * | 2016-12-13 | 2017-05-10 | 宁夏宁信信息科技有限公司 | Personalized recommending method and system in video app |
CN106909907A (en) * | 2017-03-07 | 2017-06-30 | 佛山市融信通企业咨询服务有限公司 | A kind of video communication sentiment analysis accessory system |
WO2017181612A1 (en) * | 2016-04-18 | 2017-10-26 | 乐视控股(北京)有限公司 | Personalized video recommendation method and device |
WO2018023329A1 (en) * | 2016-08-01 | 2018-02-08 | Linkedin Corporation | Quality industry content mixed with friend's posts in social network |
CN107918652A (en) * | 2017-11-15 | 2018-04-17 | 浙江大学 | A kind of method that the film recommendation based on social networks is carried out using multi-modal e-learning |
CN107948732A (en) * | 2017-12-04 | 2018-04-20 | 京东方科技集团股份有限公司 | Playback method, video play device and the system of video |
CN108431833A (en) * | 2015-12-23 | 2018-08-21 | 多伦多道明银行 | End-to-end depth collaborative filtering |
CN108632671A (en) * | 2018-03-29 | 2018-10-09 | 北京恒信彩虹信息技术有限公司 | A kind of recommendation method and system |
CN108681601A (en) * | 2018-05-21 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of method, apparatus and electronic equipment of video sharing |
CN108848152A (en) * | 2018-06-05 | 2018-11-20 | 腾讯科技(深圳)有限公司 | A kind of method and server of object recommendation |
CN108959323A (en) * | 2017-05-25 | 2018-12-07 | 腾讯科技(深圳)有限公司 | Video classification methods and device |
CN109002490A (en) * | 2018-06-26 | 2018-12-14 | 腾讯科技(深圳)有限公司 | User's portrait generation method, device, server and storage medium |
CN109104620A (en) * | 2018-07-26 | 2018-12-28 | 腾讯科技(深圳)有限公司 | A kind of short video recommendation method, device and readable medium |
CN109245989A (en) * | 2018-08-15 | 2019-01-18 | 咪咕动漫有限公司 | A kind of processing method, device and computer readable storage medium shared based on information |
CN109698820A (en) * | 2018-09-03 | 2019-04-30 | 长安通信科技有限责任公司 | A kind of domain name Similarity measures and classification method and system |
CN109783686A (en) * | 2019-01-21 | 2019-05-21 | 广州虎牙信息科技有限公司 | Behavioral data processing method, device, terminal device and storage medium |
CN109902753A (en) * | 2019-03-06 | 2019-06-18 | 深圳市珍爱捷云信息技术有限公司 | User's recommended models training method, device, computer equipment and storage medium |
CN109933700A (en) * | 2019-03-07 | 2019-06-25 | 王芃翰 | Students ' reading based on big data suggests generation method and relevant device |
CN110096613A (en) * | 2019-04-12 | 2019-08-06 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method, device, electronic equipment and storage medium |
US10521482B2 (en) | 2017-04-24 | 2019-12-31 | Microsoft Technology Licensing, Llc | Finding members with similar data attributes of a user for recommending new social connections |
CN110647678A (en) * | 2019-09-02 | 2020-01-03 | 杭州数理大数据技术有限公司 | Recommendation method based on user character label |
CN110837598A (en) * | 2019-11-11 | 2020-02-25 | 腾讯科技(深圳)有限公司 | Information recommendation method, device, equipment and storage medium |
CN111680224A (en) * | 2020-04-22 | 2020-09-18 | 威比网络科技(上海)有限公司 | Cross-platform course pushing method and device, electronic equipment and storage medium |
CN111859102A (en) * | 2020-02-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Prompt information determination method, system, medium and storage medium |
US10860941B2 (en) | 2014-09-18 | 2020-12-08 | Huawei Technologies Co., Ltd. | Method and device for predicting information propagation in social network |
CN112365447A (en) * | 2020-10-20 | 2021-02-12 | 四川长虹电器股份有限公司 | Multidimensional movie and television scoring method |
CN113239041A (en) * | 2021-05-13 | 2021-08-10 | 大连交通大学 | Computer big data processing acquisition system and method |
CN116739814A (en) * | 2023-04-23 | 2023-09-12 | 广州市疾病预防控制中心(广州市卫生检验中心、广州市食品安全风险监测与评估中心、广州医科大学公共卫生研究院) | Method for preventing disease transmission and social platform |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102184235A (en) * | 2011-05-13 | 2011-09-14 | 广州星海传媒有限公司 | Set top box-based digital television program recommending method and system |
CN102571978A (en) * | 2012-02-10 | 2012-07-11 | 上海视畅信息科技有限公司 | Intelligent video viewing system |
US20120226651A1 (en) * | 2011-03-03 | 2012-09-06 | Xerox Corporation | System and method for recommending items in multi-relational environments |
CN103327045A (en) * | 2012-03-21 | 2013-09-25 | 腾讯科技(深圳)有限公司 | User recommendation method and system in social network |
CN103327400A (en) * | 2012-03-22 | 2013-09-25 | 鸿富锦精密工业(深圳)有限公司 | Customer premise equipment and method for creating social video channel |
-
2013
- 2013-12-12 CN CN201310684807.7A patent/CN103714130B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120226651A1 (en) * | 2011-03-03 | 2012-09-06 | Xerox Corporation | System and method for recommending items in multi-relational environments |
CN102184235A (en) * | 2011-05-13 | 2011-09-14 | 广州星海传媒有限公司 | Set top box-based digital television program recommending method and system |
CN102571978A (en) * | 2012-02-10 | 2012-07-11 | 上海视畅信息科技有限公司 | Intelligent video viewing system |
CN103327045A (en) * | 2012-03-21 | 2013-09-25 | 腾讯科技(深圳)有限公司 | User recommendation method and system in social network |
CN103327400A (en) * | 2012-03-22 | 2013-09-25 | 鸿富锦精密工业(深圳)有限公司 | Customer premise equipment and method for creating social video channel |
Cited By (65)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105224576A (en) * | 2014-07-01 | 2016-01-06 | 上海视畅信息科技有限公司 | A kind of video display intelligent recommendation method |
US10860941B2 (en) | 2014-09-18 | 2020-12-08 | Huawei Technologies Co., Ltd. | Method and device for predicting information propagation in social network |
CN105824818A (en) * | 2015-01-04 | 2016-08-03 | 中国移动通信集团河北有限公司 | Informationized management method, platform and system |
CN106034256A (en) * | 2015-03-10 | 2016-10-19 | 腾讯科技(北京)有限公司 | Video social method and video social device |
CN106034256B (en) * | 2015-03-10 | 2019-11-05 | 腾讯科技(北京)有限公司 | Video social contact method and device |
CN104765778A (en) * | 2015-03-18 | 2015-07-08 | 百度在线网络技术(北京)有限公司 | Method and device for providing information to be transmitted based on user behaviors |
CN104834969A (en) * | 2015-05-05 | 2015-08-12 | 东南大学 | Film evaluation prediction method and system |
CN106202103A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | Music recommends method and apparatus |
WO2016187768A1 (en) * | 2015-05-25 | 2016-12-01 | 武克易 | Video information pushing method and apparatus |
CN106339146A (en) * | 2015-07-09 | 2017-01-18 | 华为终端(东莞)有限公司 | Method and device for recommending applications |
CN105138551A (en) * | 2015-07-14 | 2015-12-09 | 青岛海信传媒网络技术有限公司 | Method and apparatus for obtaining user interest tag |
CN105022699B (en) * | 2015-07-14 | 2018-04-24 | 惠龙易通国际物流股份有限公司 | The preprocess method and system of buffer area data |
CN105022699A (en) * | 2015-07-14 | 2015-11-04 | 惠龙易通国际物流股份有限公司 | Cache region data preprocessing method and system |
CN105095516B (en) * | 2015-09-16 | 2019-02-15 | 中国传媒大学 | The radio and television tenant group system and method integrated based on spectral clustering |
CN105095516A (en) * | 2015-09-16 | 2015-11-25 | 中国传媒大学 | Broadcast television subscriber grouping system and method based on spectral clustering integration |
WO2017071244A1 (en) * | 2015-10-30 | 2017-05-04 | 乐视控股(北京)有限公司 | Mobile phone screen-based video recommendation method and system |
CN105915954A (en) * | 2015-10-30 | 2016-08-31 | 乐视移动智能信息技术(北京)有限公司 | Video recommendation method based on mobile phone screen and video recommendation system thereof |
CN105915957A (en) * | 2015-12-15 | 2016-08-31 | 乐视致新电子科技(天津)有限公司 | Intelligent television playing content display method, device and system |
CN108431833B (en) * | 2015-12-23 | 2022-09-16 | 多伦多道明银行 | End-to-end depth collaborative filtering |
CN108431833A (en) * | 2015-12-23 | 2018-08-21 | 多伦多道明银行 | End-to-end depth collaborative filtering |
CN106528584A (en) * | 2016-02-15 | 2017-03-22 | 中山大学 | An ensemble learning-based group recommendation method |
CN106528584B (en) * | 2016-02-15 | 2019-10-29 | 中山大学 | A kind of group recommending method based on ensemble learning |
CN105740473A (en) * | 2016-03-14 | 2016-07-06 | 腾讯科技(深圳)有限公司 | User-generated content display method and device |
CN105704231B (en) * | 2016-03-17 | 2019-04-30 | 珠海格力电器股份有限公司 | The information-pushing method and device of netcast resource |
CN105704231A (en) * | 2016-03-17 | 2016-06-22 | 珠海格力电器股份有限公司 | Information push method and apparatus for network playing resources |
WO2017181612A1 (en) * | 2016-04-18 | 2017-10-26 | 乐视控股(北京)有限公司 | Personalized video recommendation method and device |
CN105930532A (en) * | 2016-06-16 | 2016-09-07 | 上海聚力传媒技术有限公司 | Method and device of recommending multimedia resources to user |
CN105930532B (en) * | 2016-06-16 | 2019-08-02 | 上海聚力传媒技术有限公司 | A kind of method and apparatus from multimedia resource to user that recommending |
CN106131684A (en) * | 2016-06-24 | 2016-11-16 | 依偎科技(南昌)有限公司 | A kind of content recommendation method and terminal |
CN106202252A (en) * | 2016-06-29 | 2016-12-07 | 厦门趣处网络科技有限公司 | Method, system are recommended in a kind of trip analyzed based on user emotion |
CN106201184A (en) * | 2016-06-29 | 2016-12-07 | 腾讯科技(深圳)有限公司 | Edit methods, device and the terminal of a kind of SNS message |
WO2018023329A1 (en) * | 2016-08-01 | 2018-02-08 | Linkedin Corporation | Quality industry content mixed with friend's posts in social network |
CN106202570A (en) * | 2016-08-11 | 2016-12-07 | 乐视控股(北京)有限公司 | A kind of user information acquiring method and device |
CN106649655A (en) * | 2016-12-13 | 2017-05-10 | 宁夏宁信信息科技有限公司 | Personalized recommending method and system in video app |
CN106909907A (en) * | 2017-03-07 | 2017-06-30 | 佛山市融信通企业咨询服务有限公司 | A kind of video communication sentiment analysis accessory system |
US10521482B2 (en) | 2017-04-24 | 2019-12-31 | Microsoft Technology Licensing, Llc | Finding members with similar data attributes of a user for recommending new social connections |
CN108959323A (en) * | 2017-05-25 | 2018-12-07 | 腾讯科技(深圳)有限公司 | Video classification methods and device |
CN108959323B (en) * | 2017-05-25 | 2021-12-07 | 腾讯科技(深圳)有限公司 | Video classification method and device |
CN107918652A (en) * | 2017-11-15 | 2018-04-17 | 浙江大学 | A kind of method that the film recommendation based on social networks is carried out using multi-modal e-learning |
CN107948732B (en) * | 2017-12-04 | 2020-12-01 | 京东方科技集团股份有限公司 | Video playing method, video playing device and video playing system |
CN107948732A (en) * | 2017-12-04 | 2018-04-20 | 京东方科技集团股份有限公司 | Playback method, video play device and the system of video |
CN108632671A (en) * | 2018-03-29 | 2018-10-09 | 北京恒信彩虹信息技术有限公司 | A kind of recommendation method and system |
CN108681601A (en) * | 2018-05-21 | 2018-10-19 | 北京奇艺世纪科技有限公司 | A kind of method, apparatus and electronic equipment of video sharing |
CN108681601B (en) * | 2018-05-21 | 2020-12-11 | 北京奇艺世纪科技有限公司 | Video sharing method and device and electronic equipment |
CN108848152A (en) * | 2018-06-05 | 2018-11-20 | 腾讯科技(深圳)有限公司 | A kind of method and server of object recommendation |
CN108848152B (en) * | 2018-06-05 | 2021-09-21 | 腾讯科技(深圳)有限公司 | Object recommendation method and server |
CN109002490A (en) * | 2018-06-26 | 2018-12-14 | 腾讯科技(深圳)有限公司 | User's portrait generation method, device, server and storage medium |
CN109104620A (en) * | 2018-07-26 | 2018-12-28 | 腾讯科技(深圳)有限公司 | A kind of short video recommendation method, device and readable medium |
CN109245989A (en) * | 2018-08-15 | 2019-01-18 | 咪咕动漫有限公司 | A kind of processing method, device and computer readable storage medium shared based on information |
CN109698820A (en) * | 2018-09-03 | 2019-04-30 | 长安通信科技有限责任公司 | A kind of domain name Similarity measures and classification method and system |
CN109783686A (en) * | 2019-01-21 | 2019-05-21 | 广州虎牙信息科技有限公司 | Behavioral data processing method, device, terminal device and storage medium |
CN109902753B (en) * | 2019-03-06 | 2023-01-13 | 深圳市珍爱捷云信息技术有限公司 | User recommendation model training method and device, computer equipment and storage medium |
CN109902753A (en) * | 2019-03-06 | 2019-06-18 | 深圳市珍爱捷云信息技术有限公司 | User's recommended models training method, device, computer equipment and storage medium |
CN109933700A (en) * | 2019-03-07 | 2019-06-25 | 王芃翰 | Students ' reading based on big data suggests generation method and relevant device |
CN110096613A (en) * | 2019-04-12 | 2019-08-06 | 北京奇艺世纪科技有限公司 | A kind of video recommendation method, device, electronic equipment and storage medium |
CN110647678A (en) * | 2019-09-02 | 2020-01-03 | 杭州数理大数据技术有限公司 | Recommendation method based on user character label |
CN110647678B (en) * | 2019-09-02 | 2022-11-15 | 杭州数理大数据技术有限公司 | Recommendation method based on user character label |
CN110837598A (en) * | 2019-11-11 | 2020-02-25 | 腾讯科技(深圳)有限公司 | Information recommendation method, device, equipment and storage medium |
CN111859102A (en) * | 2020-02-17 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Prompt information determination method, system, medium and storage medium |
CN111680224A (en) * | 2020-04-22 | 2020-09-18 | 威比网络科技(上海)有限公司 | Cross-platform course pushing method and device, electronic equipment and storage medium |
CN112365447A (en) * | 2020-10-20 | 2021-02-12 | 四川长虹电器股份有限公司 | Multidimensional movie and television scoring method |
CN112365447B (en) * | 2020-10-20 | 2022-08-19 | 四川长虹电器股份有限公司 | Multidimensional movie and television scoring method |
CN113239041A (en) * | 2021-05-13 | 2021-08-10 | 大连交通大学 | Computer big data processing acquisition system and method |
CN116739814A (en) * | 2023-04-23 | 2023-09-12 | 广州市疾病预防控制中心(广州市卫生检验中心、广州市食品安全风险监测与评估中心、广州医科大学公共卫生研究院) | Method for preventing disease transmission and social platform |
CN116739814B (en) * | 2023-04-23 | 2024-05-14 | 广州市疾病预防控制中心(广州市卫生检验中心、广州市食品安全风险监测与评估中心、广州医科大学公共卫生研究院) | Method for preventing disease transmission and social platform |
Also Published As
Publication number | Publication date |
---|---|
CN103714130B (en) | 2017-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103714130A (en) | Video recommendation system and method thereof | |
CN110633373B (en) | Automobile public opinion analysis method based on knowledge graph and deep learning | |
US9213996B2 (en) | System and method for analyzing social media trends | |
CN107220365B (en) | Accurate recommendation system and method based on collaborative filtering and association rule parallel processing | |
US7991715B2 (en) | System and method for image classification | |
US20150193889A1 (en) | Digital content publishing guidance based on trending emotions | |
US20140337328A1 (en) | System and method for retrieving and presenting concept centric information in social media networks | |
US20180181667A1 (en) | System and method to model recognition statistics of data objects in a business database | |
US20130304818A1 (en) | Systems and methods for discovery of related terms for social media content collection over social networks | |
US20130297694A1 (en) | Systems and methods for interactive presentation and analysis of social media content collection over social networks | |
CN109190033B (en) | User friend recommendation method and system | |
KR20160057475A (en) | System and method for actively obtaining social data | |
US20140143013A1 (en) | System and method for analyzing social media trends | |
CN111177559B (en) | Text travel service recommendation method and device, electronic equipment and storage medium | |
Okazaki et al. | How to mine brand Tweets: Procedural guidelines and pretest | |
CN104866557A (en) | Customized just-in-time learning support system and method based on constructivist learning theory | |
CN115408618B (en) | Point-of-interest recommendation method based on social relation fusion position dynamic popularity and geographic features | |
Yuan et al. | Sentiment analysis using social multimedia | |
US20170315676A1 (en) | Dynamic content insertion | |
CN106354859A (en) | Scenic spot recommendation device, method and system | |
Saraswathi et al. | Deep Learning Enabled Social Media Recommendation Based on User Comments. | |
Sun et al. | Tourists’ digital footprint: prediction method of tourism consumption decision preference | |
Ashraf et al. | Personalized news recommendation based on multi-agent framework using social media preferences | |
Berlanga et al. | Quality indicators for social business intelligence | |
KR102593996B1 (en) | Apparatus and Method For Providing Recommendation Service Through Social Media Activity Analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |