CN110418200A - A kind of video recommendation method, device and terminal device - Google Patents
A kind of video recommendation method, device and terminal device Download PDFInfo
- Publication number
- CN110418200A CN110418200A CN201810391907.3A CN201810391907A CN110418200A CN 110418200 A CN110418200 A CN 110418200A CN 201810391907 A CN201810391907 A CN 201810391907A CN 110418200 A CN110418200 A CN 110418200A
- Authority
- CN
- China
- Prior art keywords
- video
- user
- recommendation
- candidate
- time period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Abstract
The present invention is suitable for video recommendations technical field, provides a kind of video recommendation method, device and terminal device.This method comprises: based in the second time period user behaviors log and video matchmaker provide library, Candidate Recommendation video is selected according to scheduled proposed algorithm;According in the first time period user behaviors log and video matchmaker provide library, obtain the video preference information of the user;Sequence is optimized to the Candidate Recommendation video according to the video preference information, for output top n as recommendation results, N is the integer greater than 1.The present invention comprehensively considers the shot and long term user behaviors log information of user, the stage behavioural characteristic generation candidate video recommendation collection short-term based on user is recalled in Candidate Recommendation result, Candidate Set video is reset in the sequence output stage combination user of recommendation results long-term Behavior preference, to effectively improve the predictablity rate of video recommendation system.
Description
Technical field
The invention belongs to fire Safety Assessment technical fields more particularly to a kind of video recommendation method, device and terminal to set
It is standby.
Background technique
Under the promotion of artificial intelligence and big data upsurge, recommender system is widely applied to such as video, information and electricity
The user oriented service field such as quotient.Recommender system sums up the main row recalled comprising Candidate Recommendation result with recommendation results
Sequence exports two stages, and the groundwork that wherein Candidate Recommendation result is recalled is the input data and business field different for system
Scape generates recommendation results using a variety of proposed algorithms, and all results is combined into Candidate Recommendation result set, recommendation results
The groundwork of sequence output is to be ranked up optimization for the Candidate Recommendation result set for recalling stage generation, so that user most feels
The article of interest can be ordered into foremost.The personnel that traditional video service website generally requires a large amount of professions are manually transported
Battalion is recommended, and existing Personalized Intelligent Recommendation system often only needs the user behaviors log data of user that can meet or exceed specially
The artificial operational effect of industry, thus it is widely used in major major video website.Therefore, for existing video recommendations system
System, in recommender system proposed algorithm and strategy optimizes and improvement is very necessary and valuable.
Existing video recommendation system is primarily present following problems: the proposed algorithm in existing recommender system mostly considers to use
The short-term user behaviors log information in family carries out personalized recommendation, and in fact the short-term video preference of user is dynamic change, is based on
The video that the short-term video preference of user is associated recommendation may not be that user is interested, so as to cause recommender system
Accuracy rate is not high.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of video recommendation method, device and terminal device, it is existing to solve
Not the problem of not supporting various dimensions relevant to movie and television contents flexibly to search in technology.
The first aspect of the embodiment of the present invention provides a kind of video recommendation method, comprising:
It obtains user behaviors log and video matchmaker in the user preset period and provides library, it includes that user watches video that video matchmaker, which provides library,
The attribute of the video object and the video object in the process;The preset time period includes first time period and the second time
Section, the first time period are greater than the second time period;
Based in the second time period user behaviors log and video matchmaker provide library, candidate is selected according to scheduled proposed algorithm
Recommend video;
According in the first time period user behaviors log and video matchmaker provide library, obtain the user video preference letter
Breath;
Sequence is optimized to the Candidate Recommendation video according to the video preference information, output top n is as recommendation
As a result, N is the integer greater than 1.
The second aspect of the embodiment of the present invention provides a kind of video recommendations device, comprising:
First obtains module, for obtaining user behaviors log and video matchmaker money library in the user preset period, video matchmaker money
Library include user watch video during the video object and the video object attribute;The preset time period includes first
Period and second time period, the first time period are greater than the second time period;
Selecting module, for based in the second time period user behaviors log and video matchmaker provide library, pushed away according to scheduled
It recommends algorithm and selects Candidate Recommendation video;
Second obtains module, for according in the first time period user behaviors log and video matchmaker provide library, described in acquisition
The video preference information of user;
Sorting module is exported for optimizing sequence to the Candidate Recommendation video according to the video preference information
For top n as recommendation results, N is the integer greater than 1.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, which is characterized in that described in the processor executes
It is performed the steps of when computer program
It obtains user behaviors log and video matchmaker in the user preset period and provides library, it includes that user watches video that video matchmaker, which provides library,
The attribute of the video object and the video object in the process;The preset time period includes first time period and the second time
Section, the first time period are greater than the second time period;
Based in the second time period user behaviors log and video matchmaker provide library, candidate is selected according to scheduled proposed algorithm
Recommend video;
According in the first time period user behaviors log and video matchmaker provide library, obtain the user video preference letter
Breath;
Sequence is optimized to the Candidate Recommendation video according to the video preference information, output top n is as recommendation
As a result, N is the integer greater than 1.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, which is characterized in that the computer program performs the steps of when being executed by processor
It obtains user behaviors log and video matchmaker in the user preset period and provides library, it includes that user watches video that video matchmaker, which provides library,
The attribute of the video object and the video object in the process;The preset time period includes first time period and the second time
Section, the first time period are greater than the second time period;
Based in the second time period user behaviors log and video matchmaker provide library, candidate is selected according to scheduled proposed algorithm
Recommend video;
According in the first time period user behaviors log and video matchmaker provide library, obtain the user video preference letter
Breath;
Sequence is optimized to the Candidate Recommendation video according to the video preference information, output top n is as recommendation
As a result, N is the integer greater than 1.
In embodiments of the present invention, user behaviors log and video matchmaker in the user preset period are obtained and provides library, video matchmaker money
Library include user watch video during the video object and the video object attribute;The preset time period includes first
Period and second time period, the first time period is greater than the second time period, based on the row in the second time period
Library is provided for log and video matchmaker, Candidate Recommendation video is selected according to scheduled proposed algorithm, according in the first time period
User behaviors log and video matchmaker provide library, the video preference information of the user are obtained, according to the video preference information to the time
Choosing recommends video to optimize sequence, and for output top n as recommendation results, N is the integer greater than 1, and the embodiment of the present invention is comprehensive
The shot and long term user behaviors log information and video matchmaker for considering user provides library, and it is short-term based on user to recall the stage in Candidate Recommendation result
Behavioural characteristic generates candidate video and recommends collection, in the long-term Behavior preference of the sequence output stage combination user of recommendation results to time
Selected works video is reset, to effectively improve the predictablity rate of video recommendation system, has stronger ease for use and practical
Property.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation process schematic diagram for the video recommendation method that the embodiment of the present invention one provides;
Fig. 2 is the specific implementation flow schematic diagram of step S104 in embodiment of the embodiment of the present invention one;
Fig. 3 is the schematic diagram of the rearrangement process of Candidate Recommendation video set of the present invention;
Fig. 4 is the structural block diagram of video recommendations device provided by Embodiment 2 of the present invention;
Fig. 5 is the schematic diagram for the terminal device that the embodiment of the present invention three provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " instruction is described special
Sign, entirety, step, operation, the presence of element and/or component, but be not precluded one or more of the other feature, entirety, step,
Operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that "
Or " if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to
Determine " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Embodiment one
Fig. 1 shows the implementation process schematic diagram of the video recommendation method of the offer of the embodiment of the present invention one.As shown in Figure 1,
The video recommendation method specifically comprises the following steps S101 to step S104.The video recommendation method of the present embodiment is generally used for
Video recommendation system.
Step S101: user behaviors log and video matchmaker in the user preset period are obtained and provides library, it includes using that video matchmaker, which provides library,
The attribute of the video object and the video object during family viewing video;The preset time period include first time period and
Second time period, the first time period are greater than the second time period;
These two types of information progress individualized videos are provided according to the viewing user behaviors log of user and video matchmaker in the present embodiment to push away
It recommends, when carrying out video recommendations by specific proposed algorithm, these two types of information of default are existing, separately below briefly
Illustrate the particular content and acquisition methods of these two types of data.
In video recommendation system, User action log refers mainly to the behavior record that user generates during viewing, such as
User is to information such as the click of video, search, collection and broadcastings.The collection of User action log generally buries side a little using system
Formula, is implanted into the program of log collection according to demand in the background program of user's viewing system, and by log information real-time Transmission
To the log storage system in cloud.Video matchmaker provides library and refers to the video object and its set of attribute during user's viewing, specifically
Unique identification, video name, video type (such as TV play, film and variety) and video content mark comprising video in systems
Sign (such as love, terrible and ethics) information.The attributive character of video is mainly provided by video production side, and the operator of video is negative
The finish message of all videos is provided library at video matchmaker by duty, to facilitate subsequent operation management.
Wherein, first time period and second time period respectively refer to long-term and short-term.The long and short phase user behaviors log of user is root
Divided according to the time series of user's viewing behavior, shot and long term be specifically defined be it is opposite, it is main and current recommender system
Hardware resource is related with business demand, if hardware resource is sufficient, " shot and long term user behaviors log " can be defined as: " long-term row
For log " be user's half a year or more viewing record, " acts and efforts for expediency log " is user one month or bimestrial viewing note
Record.Generally, time setting is longer, and the data volume of user is bigger, and the recommendation effect of entire recommender system is better.In reality
Recommender system in, also need to consider system hardware resources and response time, so the time span of user's shot and long term user behaviors log
It is not too large, it is dynamically arranged the time range of " shot and long term " in a word to meet application demand.
Step S102: based in the second time period user behaviors log and video matchmaker provide library, according to scheduled recommendations calculation
Method selects Candidate Recommendation video.
Existing recommender system sums up the main sequence output two recalled comprising Candidate Recommendation result with recommendation results
In a stage, what wherein Candidate Recommendation result was recalled mainly includes the input data and business scenario different for system, using more
Kind proposed algorithm generates recommendation results, and all results are combined into the Candidate Recommendation result set of system, the row of recommendation results
Sequence output mainly includes being ranked up optimization for the Candidate Recommendation result set for recalling stage generation, so that user is most interested
Article can be ordered into foremost.Existing video recommendation system Candidate Recommendation result recall the stage using proposed algorithm it is main
There are following three classes: the video recommendations algorithm based on collaborative filtering, the proposed algorithm based on video content label and based on mould
The proposed algorithm of type, this paper emphasis are optimized for the sequence output stage of recommendation results, and therefore, Candidate Recommendation result is recalled
Specific proposed algorithm principle and its realization process will not be described in great detail in stage.
Step S103: according in the first time period user behaviors log and video matchmaker provide library, obtain the view of the user
Frequency preference information.
Step S104: sequence is optimized to the Candidate Recommendation video according to the video preference information, exports top n
As recommendation results, N is the integer greater than 1.
The candidate video recommendation results generated for the accuracy rate and coverage rate for effectively improving recommender system, step S102 step
General bigger (several hundred or thousands), but in actual recommender system, user mostly only focuses on the forward recommendation results that sort, because
This, need to be by resetting Candidate Recommendation video set, before being ordered into most so as to the multiple videos that may be most interested in user
Face, to guarantee that recommender system has relatively good accuracy rate and coverage rate in the limited situation of recommendation results collection.
Wherein, as shown in Fig. 2, optimizing sequence to the Candidate Recommendation video according to the video preference information can wrap
It includes:
Step S201: judge whether Candidate Recommendation video collection is empty.
Step S202: if it is not, then successively traversing user and the time corresponding with the user in Candidate Recommendation video collection
Video set is selected, after recommending the choosing value of video collection to traverse, exports M video after sorting, the M is greater than
Equal to N;If so, directly exporting recommendation results.
Optionally, after M video after output sequence, further includes:
Step S203: all videos are concentrated to carry out descending sort according to weight size the candidate video, N before obtaining
A video is as recommendation results.
Further, user and candidate video corresponding with the user in Candidate Recommendation video collection are successively being traversed
After collection, further includes:
Step S204: the video preference list in the first time period of user is obtained.
Step S205: whether the candidate video collection that the user is judged according to video preference list is sky, if it is not, then successively
Candidate video collection is traversed, the weight that the candidate video concentrates video is calculated and/or updated based on the video preference list.
Wherein, being calculated based on the video preference list and/or updating the candidate video concentrates the weight of video that can wrap
It includes:
Step S301: matchmaker's standing breath in library is provided based on video matchmaker, defines preference label of the user to video, preference label
Calculation formula it is as follows:
Wherein, Tk(i) i-th of label in k-th of visual classification label of user is indicated
Weight, m be k-th of visual classification label total number of labels, wherein T (i)=N (i)/P, N (i) indicate include label i view
Frequency sum, P are the video sum of user's viewing;
Step S302: weight update is carried out to video V in conjunction with the video preference label and weight information, weight updates public
Formula is as follows:
Wherein, V0For the initial weight of video, k is the labeling number of video, and m is the mark of i-th of visual classification label
Label sum, T (j) are the weight of j-th of label in user video preference.
For example, the video sequence output process based on user's long-term action log is as follows:
In the recommender system of video field, all users and its right process are recalled by Candidate Recommendation result can exported
The Candidate Recommendation video set (C={ U, V }) answered, wherein U represents the set of user, and V represents the corresponding list of videos set of user.
Fig. 3 be Candidate Recommendation video set rearrangement process schematic diagram, video sort output stage using set C as input data,
Itself the specific implementation process is as follows:
S1: the user U in set C is successively traversediAnd its corresponding candidate video collection Vi, traversed until by the value of set C
Video recommendations result (R) after complete, after output sequence.
S2: based on the user U in above-mentioned stepsi, obtain its corresponding static video preference list (D=[t1,
T2 ..]), wherein t1, t2 are user to the preference label of video type or classification, specific preference label such as (film: 0.8, electricity
Depending on play: 0.1, terrible: 0.5), the acquisition process of static video preference label is as follows:
S21: matchmaker's standing breath all in library is provided based on video matchmaker, defines preference label of the user to video, preference label
Definition such as table 1:
Labeling | Label description |
Video classification | Film, TV play, variety, animation etc. |
Video type | Love, science fiction, terrible, day South Korean TV soaps, ethics etc. |
Video language | English, mandarin, Guangdong language etc. |
Table 1
It should be understood that the video preference of the long-term viewing behavior of user is metastable, therefore the present embodiment use is " quiet
State video preference " indicates.
S22: the weight calculation of video preference label
The long-term viewing user behaviors log of user is able to reflect user's interest preference more stable to video, by user
The statistical analysis of a large amount of viewing video datas, can effectively measure user to the weight of video preference label, specific formula for calculation
It is as follows:
T in formula (1)k(i) weight of i-th of label in k-th of visual classification label of user is indicated, m is k-th of video point
The total number of labels of class label, T (i) are defined as follows:
T (i)=N (i)/N (2)
N (i) indicates that the video sum comprising label i, N are the video sum of user's viewing in formula (2).
S3: traversal video set ViIn all videos (v), the static state video preference label in conjunction with known to user in S2 step
And weight information carries out weight update to video v, weight more new formula is as follows:
V in formula (3)0For the initial weight of video, k is the labeling number of video, and m is i-th of visual classification label
Total number of labels, T (j) are the weight of j-th of label in user's static state video preference.
S4: as video set ViIn all video v traverse after the completion of, based on video weight to ViIn all videos into
The arrangement of row descending retains the video of specified TOP.
In embodiments of the present invention, user behaviors log and video matchmaker in the user preset period are obtained and provides library, video matchmaker money
Library include user watch video during the video object and the video object attribute;The preset time period includes first
Period and second time period, the first time period is greater than the second time period, based on the row in the second time period
Library is provided for log and video matchmaker, Candidate Recommendation video is selected according to scheduled proposed algorithm, according in the first time period
User behaviors log and video matchmaker provide library, the video preference information of the user are obtained, according to the video preference information to the time
Choosing recommends video to optimize sequence, and for output top n as recommendation results, N is the integer greater than 1, and the embodiment of the present invention is comprehensive
The shot and long term user behaviors log information and video matchmaker for considering user provides library, and it is short-term based on user to recall the stage in Candidate Recommendation result
Behavioural characteristic generates candidate video and recommends collection, in the long-term Behavior preference of the sequence output stage combination user of recommendation results to time
Selected works video is reset, to effectively improve the predictablity rate of video recommendation system, has stronger ease for use and practical
Property.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment two
Referring to FIG. 4, it illustrates the structural block diagrams of video recommendations device provided by Embodiment 2 of the present invention.Video recommendations
Device 40 includes: the first acquisition module 41, selecting module 42, the second extraction module 43 and sorting module 44.Wherein, each module
Concrete function is as follows:
First obtains module 41, for obtaining user behaviors log and video matchmaker money library in the user preset period, video matchmaker
Money library include user watch video during the video object and the video object attribute;The preset time period includes the
One period and second time period, the first time period are greater than the second time period;
Selecting module 42, for based in the second time period user behaviors log and video matchmaker provide library, according to scheduled
Proposed algorithm selects Candidate Recommendation video;
Second obtain module 43, for according in the first time period user behaviors log and video matchmaker provide library, obtain institute
State the video preference information of user;
Sorting module 44, it is defeated for optimizing sequence to the Candidate Recommendation video according to the video preference information
For top n as recommendation results, N is the integer greater than 1 out.
Optionally, the sorting module includes:
Judging unit, for judging whether Candidate Recommendation video collection is empty;
Output unit, for if it is not, then successively traversing the user and corresponding with the user in Candidate Recommendation video collection
Candidate video collection, until by it is described choosing recommend video collection value traversed after, output sequence after M video, the M
More than or equal to N.
Optionally, video recommendations device 40 further include:
Third obtains module, the video preference list in first time period for obtaining user;
Computing module, for judging whether the candidate video collection of the user is sky according to video preference list, if it is not, then
Candidate video collection is successively traversed, the power that the candidate video concentrates video is calculated and/or updated based on the video preference list
Weight.
Optionally, video recommendations device 40 further include:
Sort recommendations module, for concentrating all videos to carry out descending row according to weight size the candidate video
Sequence obtains top n video as recommendation results.
Optionally, the computing module includes:
Definition unit defines preference label of the user to video, preference for providing matchmaker's standing breath in library based on video matchmaker
The calculation formula of label is as follows:
Wherein, Tk(i) i-th of label in k-th of visual classification label of user is indicated
Weight, m be k-th of visual classification label total number of labels, wherein T (i)=N (i)/P, N (i) indicate include label i view
Frequency sum, P are the video sum of user's viewing;
Updating unit, for carrying out weight update to video V in conjunction with the video preference label and weight information, weight is more
New formula is as follows:
Wherein, V0For the initial weight of video, k is the labeling number of video, and m is the mark of i-th of visual classification label
Label sum, T (j) are the weight of j-th of label in user video preference.
The video recommendations device of the embodiment of the present invention, by obtaining user behaviors log and video matchmaker in the user preset period
Provide library, video matchmaker provide library include user watch video during the video object and the video object attribute;It is described default
Period includes first time period and second time period, and the first time period is greater than the second time period, based on described the
User behaviors log and video matchmaker in two periods provide library, Candidate Recommendation video are selected according to scheduled proposed algorithm, according to described
User behaviors log and video matchmaker in first time period provide library, obtain the video preference information of the user, inclined according to the video
Good information optimizes sequence to the Candidate Recommendation video, and for output top n as recommendation results, N is the integer greater than 1, this
Inventive embodiments comprehensively consider the shot and long term user behaviors log information of user and video matchmaker provides library, recall the stage in Candidate Recommendation result
Candidate video, which is generated, based on the short-term behavioural characteristic of user recommends collection, it is long-term in the sequence output stage combination user of recommendation results
Behavior preference Candidate Set video is reset, to effectively improve the predictablity rate of video recommendation system, have relatively strong
Usability and practicality.
Embodiment three
Fig. 5 is the schematic diagram for the terminal device that the embodiment of the present invention three provides.As shown in figure 5, the terminal of the embodiment is set
Standby 5 include: processor 50, memory 51 and are stored in the meter that can be run in the memory 51 and on the processor 50
Calculation machine program 52, such as video recommendation method program.The processor 50 is realized above-mentioned each when executing the computer program 52
Step in a video recommendation method embodiment, such as step S101 to S104 shown in FIG. 1.Alternatively, the processor 50 is held
The function of each module in above-mentioned each Installation practice, such as module 41 to 44 shown in Fig. 4 are realized when the row computer program 52
Function.
Illustratively, the computer program 52 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 51, and are executed by the processor 50, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine program instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 52 in the terminal device 5 is described.For example, the computer program 52 can be divided
It is as follows to be cut into acquisition module, the first extraction module, the second extraction module and generation module, the concrete function of each module:
First obtains module, for obtaining user behaviors log and video matchmaker money library in the user preset period, video matchmaker money
Library include user watch video during the video object and the video object attribute;The preset time period includes first
Period and second time period, the first time period are greater than the second time period;
Selecting module, for based in the second time period user behaviors log and video matchmaker provide library, pushed away according to scheduled
It recommends algorithm and selects Candidate Recommendation video;
Second obtains module, for according in the first time period user behaviors log and video matchmaker provide library, described in acquisition
The video preference information of user;
Sorting module is exported for optimizing sequence to the Candidate Recommendation video according to the video preference information
For top n as recommendation results, N is the integer greater than 1.
The terminal device 5 can be desktop PC, notebook, palm PC etc. and calculate equipment.The terminal is set
It is standby to may include, but be not limited only to, processor 50, memory 51.It will be understood by those skilled in the art that Fig. 5 is only that terminal is set
Standby example does not constitute the restriction to terminal device, may include components more more or fewer than diagram, or combine certain
Component or different components, such as the terminal device can also include input-output equipment, network access equipment, bus
Deng.
Alleged processor 50 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 51 can be the internal storage unit of the terminal device 5, such as the hard disk or interior of terminal device 5
It deposits.The memory 51 is also possible to the External memory equipment of the terminal device 5, such as be equipped on the terminal device 5
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 51 can also both include the storage inside list of the terminal device 5
Member also includes External memory equipment.The memory 51 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 51 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.Each functional unit in embodiment, module can integrate in one processing unit, can also
To be that each unit physically exists alone, can also be integrated in one unit with two or more units, it is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.In addition, each function list
Member, the specific name of module are also only for convenience of distinguishing each other, the protection scope being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of logical function partition, there may be another division manner in actual implementation, such as
Multiple units or components can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be through some interfaces, device
Or the INDIRECT COUPLING or communication connection of unit, it can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to the requirement made laws in jurisdiction with patent practice
Subtract, such as does not include electric carrier signal and electricity according to legislation and patent practice, computer-readable medium in certain jurisdictions
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations;Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features;And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of video recommendation method characterized by comprising
It obtains user behaviors log and video matchmaker in the user preset period and provides library, it includes that user watches video process that video matchmaker, which provides library,
In the video object and the video object attribute;The preset time period includes first time period and second time period, institute
First time period is stated greater than the second time period;
Based in the second time period user behaviors log and video matchmaker provide library, Candidate Recommendation is selected according to scheduled proposed algorithm
Video;
According in the first time period user behaviors log and video matchmaker provide library, obtain the video preference information of the user;
Sequence optimized to the Candidate Recommendation video according to the video preference information, output top n as recommendation results,
N is the integer greater than 1.
2. video recommendation method as described in claim 1, which is characterized in that according to the video preference information to the candidate
Recommendation video optimizes sequence and includes:
Judge whether Candidate Recommendation video collection is empty;
If it is not, user and the candidate video collection corresponding with the user in Candidate Recommendation video collection are then successively traversed, until
After the value of the choosing recommendation video collection has been traversed, M video after sorting is exported, the M is more than or equal to N.
3. video recommendation method as claimed in claim 2, which is characterized in that successively traversing in Candidate Recommendation video collection
After user and candidate video collection corresponding with the user, further includes:
Obtain the video preference list in the first time period of user;
Whether the candidate video collection that the user is judged according to video preference list is sky, if it is not, then successively traversing candidate video
Collection calculates based on the video preference list and/or updates the weight that the candidate video concentrates video.
4. video recommendation method as claimed in claim 3, which is characterized in that after M video after output sequence, also wrap
It includes:
All videos are concentrated to carry out descending sort according to weight size the candidate video, acquisition top n video, which is used as, to be pushed away
Recommend result.
5. video recommendation method as claimed in claim 3, which is characterized in that based on the video preference list calculate and/or
Update the weight that the candidate video concentrates video, comprising:
Matchmaker's standing breath in library is provided based on video matchmaker, defines user to the preference label of video, the calculation formula of preference label is such as
Under:
Wherein, Tk(i) power of i-th of label in k-th of visual classification label of user is indicated
Weight, m are the total number of labels of k-th of visual classification label, wherein T (i)=N (i)/P, N (i) indicate that the video comprising label i is total
Number, P are the video sum of user's viewing;
Weight update is carried out to video V in conjunction with the video preference label and weight information, weight more new formula is as follows:
Wherein, V0For the initial weight of video, k is the labeling number of video, and m is that the label of i-th of visual classification label is total
Number, T (j) are the weight of j-th of label in user video preference.
6. a kind of video recommendations device characterized by comprising
First obtains module, for obtaining user behaviors log and video matchmaker money library in the user preset period, video matchmaker money library packet
Include user watch video during the video object and the video object attribute;The preset time period includes at the first time
Section and second time period, the first time period are greater than the second time period;
Selecting module, for based in the second time period user behaviors log and video matchmaker provide library, according to scheduled recommendations calculation
Method selects Candidate Recommendation video;
Second obtain module, for according in the first time period user behaviors log and video matchmaker provide library, obtain the user
Video preference information;
Sorting module exports top n for optimizing sequence to the Candidate Recommendation video according to the video preference information
As recommendation results, N is the integer greater than 1.
7. video recommendations device as claimed in claim 6, which is characterized in that the sorting module includes:
Judging unit, for judging whether Candidate Recommendation video collection is empty;
Output unit, for if it is not, then successively traversing user and the time corresponding with the user in Candidate Recommendation video collection
Video set is selected, after recommending the choosing value of video collection to traverse, exports M video after sorting, the M is greater than
Equal to N.
8. video recommendations device as claimed in claim 7, which is characterized in that further include:
Third obtains module, the video preference list in first time period for obtaining user;
Computing module, for judging whether the candidate video collection of the user is sky according to video preference list, if it is not, then successively
Candidate video collection is traversed, the weight that the candidate video concentrates video is calculated and/or updated based on the video preference list.
9. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
The step of any one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 5 of realization the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810391907.3A CN110418200A (en) | 2018-04-27 | 2018-04-27 | A kind of video recommendation method, device and terminal device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810391907.3A CN110418200A (en) | 2018-04-27 | 2018-04-27 | A kind of video recommendation method, device and terminal device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110418200A true CN110418200A (en) | 2019-11-05 |
Family
ID=68346628
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810391907.3A Pending CN110418200A (en) | 2018-04-27 | 2018-04-27 | A kind of video recommendation method, device and terminal device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110418200A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110798742A (en) * | 2019-11-11 | 2020-02-14 | 腾讯科技(深圳)有限公司 | Program recommendation method and device, storage medium and computer equipment |
CN110956980A (en) * | 2019-12-10 | 2020-04-03 | 腾讯科技(深圳)有限公司 | Media data processing method, device and storage medium |
CN111079015A (en) * | 2019-12-17 | 2020-04-28 | 腾讯科技(深圳)有限公司 | Recommendation method and device, computer equipment and storage medium |
CN111259248A (en) * | 2020-01-19 | 2020-06-09 | 托普朗宁(北京)教育科技有限公司 | Recommendation method and device of information resources, readable storage medium and electronic equipment |
CN111324733A (en) * | 2020-02-07 | 2020-06-23 | 北京创鑫旅程网络技术有限公司 | Content recommendation method, device, equipment and storage medium |
CN111368209A (en) * | 2020-03-25 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
CN111723289A (en) * | 2020-06-08 | 2020-09-29 | 北京声智科技有限公司 | Information recommendation method and device |
CN112468852A (en) * | 2020-11-24 | 2021-03-09 | 深圳市易平方网络科技有限公司 | Method, device and system for recommending media assets and computer readable storage medium |
CN112637685A (en) * | 2020-12-11 | 2021-04-09 | 上海连尚网络科技有限公司 | Video processing method and device |
CN112800275A (en) * | 2021-01-26 | 2021-05-14 | 广州欢网科技有限责任公司 | Short video feed stream real-time calculation pushing method, device and equipment |
CN112967086A (en) * | 2021-02-27 | 2021-06-15 | 葛纪侠 | Intelligent marketing promotion method and device and electronic equipment |
CN113139122A (en) * | 2020-01-20 | 2021-07-20 | 阿里巴巴集团控股有限公司 | Information recommendation method, system and equipment |
CN113672746A (en) * | 2021-07-27 | 2021-11-19 | 北京达佳互联信息技术有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
CN114079826A (en) * | 2020-08-14 | 2022-02-22 | 北京达佳互联信息技术有限公司 | Video recommendation list generation method and device, server and storage medium |
CN114302242A (en) * | 2022-01-25 | 2022-04-08 | 聚好看科技股份有限公司 | Media asset recommendation method, display device and server |
CN114466250A (en) * | 2020-11-09 | 2022-05-10 | 江苏华软智能信息科技有限公司 | Video recommendation method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103324686A (en) * | 2013-06-03 | 2013-09-25 | 中国科学院自动化研究所 | Real-time individuation video recommending method based on text stream network |
CN103440335A (en) * | 2013-09-06 | 2013-12-11 | 北京奇虎科技有限公司 | Video recommendation method and device |
CN107943932A (en) * | 2017-11-22 | 2018-04-20 | 广州虎牙信息科技有限公司 | Category recommends method, storage device and terminal |
-
2018
- 2018-04-27 CN CN201810391907.3A patent/CN110418200A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103324686A (en) * | 2013-06-03 | 2013-09-25 | 中国科学院自动化研究所 | Real-time individuation video recommending method based on text stream network |
CN103440335A (en) * | 2013-09-06 | 2013-12-11 | 北京奇虎科技有限公司 | Video recommendation method and device |
CN107943932A (en) * | 2017-11-22 | 2018-04-20 | 广州虎牙信息科技有限公司 | Category recommends method, storage device and terminal |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110798742A (en) * | 2019-11-11 | 2020-02-14 | 腾讯科技(深圳)有限公司 | Program recommendation method and device, storage medium and computer equipment |
CN110956980A (en) * | 2019-12-10 | 2020-04-03 | 腾讯科技(深圳)有限公司 | Media data processing method, device and storage medium |
CN110956980B (en) * | 2019-12-10 | 2024-04-09 | 腾讯科技(深圳)有限公司 | Media data processing method, device and storage medium |
CN111079015A (en) * | 2019-12-17 | 2020-04-28 | 腾讯科技(深圳)有限公司 | Recommendation method and device, computer equipment and storage medium |
CN111259248B (en) * | 2020-01-19 | 2023-11-03 | 北京博学广阅教育科技有限公司 | Information resource recommendation method and device, readable storage medium and electronic equipment |
CN111259248A (en) * | 2020-01-19 | 2020-06-09 | 托普朗宁(北京)教育科技有限公司 | Recommendation method and device of information resources, readable storage medium and electronic equipment |
CN113139122A (en) * | 2020-01-20 | 2021-07-20 | 阿里巴巴集团控股有限公司 | Information recommendation method, system and equipment |
CN111324733A (en) * | 2020-02-07 | 2020-06-23 | 北京创鑫旅程网络技术有限公司 | Content recommendation method, device, equipment and storage medium |
CN111368209A (en) * | 2020-03-25 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
CN111368209B (en) * | 2020-03-25 | 2022-04-12 | 北京字节跳动网络技术有限公司 | Information recommendation method and device, electronic equipment and computer-readable storage medium |
CN111723289A (en) * | 2020-06-08 | 2020-09-29 | 北京声智科技有限公司 | Information recommendation method and device |
CN111723289B (en) * | 2020-06-08 | 2024-02-02 | 北京声智科技有限公司 | Information recommendation method and device |
CN114079826B (en) * | 2020-08-14 | 2023-11-28 | 北京达佳互联信息技术有限公司 | Video recommendation list generation method, device, server and storage medium |
CN114079826A (en) * | 2020-08-14 | 2022-02-22 | 北京达佳互联信息技术有限公司 | Video recommendation list generation method and device, server and storage medium |
CN114466250A (en) * | 2020-11-09 | 2022-05-10 | 江苏华软智能信息科技有限公司 | Video recommendation method |
CN112468852B (en) * | 2020-11-24 | 2022-10-14 | 深圳市易平方网络科技有限公司 | Method, device and system for recommending media assets and computer readable storage medium |
CN112468852A (en) * | 2020-11-24 | 2021-03-09 | 深圳市易平方网络科技有限公司 | Method, device and system for recommending media assets and computer readable storage medium |
CN112637685B (en) * | 2020-12-11 | 2024-01-30 | 上海连尚网络科技有限公司 | Video processing method and device |
CN112637685A (en) * | 2020-12-11 | 2021-04-09 | 上海连尚网络科技有限公司 | Video processing method and device |
CN112800275A (en) * | 2021-01-26 | 2021-05-14 | 广州欢网科技有限责任公司 | Short video feed stream real-time calculation pushing method, device and equipment |
CN112967086B (en) * | 2021-02-27 | 2022-08-02 | 北京橙色风暴数字技术有限公司 | Intelligent marketing promotion method and device and electronic equipment |
CN112967086A (en) * | 2021-02-27 | 2021-06-15 | 葛纪侠 | Intelligent marketing promotion method and device and electronic equipment |
CN113672746A (en) * | 2021-07-27 | 2021-11-19 | 北京达佳互联信息技术有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
CN113672746B (en) * | 2021-07-27 | 2024-03-26 | 北京达佳互联信息技术有限公司 | Multimedia resource recommendation method and device, electronic equipment and storage medium |
CN114302242A (en) * | 2022-01-25 | 2022-04-08 | 聚好看科技股份有限公司 | Media asset recommendation method, display device and server |
CN114302242B (en) * | 2022-01-25 | 2023-10-31 | 聚好看科技股份有限公司 | Media asset recommendation method, display equipment and server |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110418200A (en) | A kind of video recommendation method, device and terminal device | |
CN107786943A (en) | A kind of tenant group method and computing device | |
CN109189931A (en) | A kind of screening technique and device of object statement | |
CN112818230B (en) | Content recommendation method, device, electronic equipment and storage medium | |
CN106326243A (en) | Data processing method and apparatus | |
CN109410001A (en) | A kind of Method of Commodity Recommendation, system, electronic equipment and storage medium | |
CN113393306A (en) | Product recommendation method and device, electronic equipment and computer readable medium | |
CN112418258A (en) | Feature discretization method and device | |
CN112749323A (en) | Method and device for constructing user portrait | |
CN111767459A (en) | Item recommendation method and device | |
CN109672706B (en) | Information recommendation method and device, server and storage medium | |
CN104239111B (en) | Application program upgrading method and device and terminal | |
CN110895761A (en) | Method and device for processing after-sale service application information | |
CN113077321A (en) | Article recommendation method and device, electronic equipment and storage medium | |
CN114139052B (en) | Ranking model training method for intelligent recommendation, intelligent recommendation method and device | |
CN112507098B (en) | Question processing method, question processing device, electronic equipment, storage medium and program product | |
CN115080824A (en) | Target word mining method and device, electronic equipment and storage medium | |
CN114817297A (en) | Method and device for processing data | |
CN113344674A (en) | Product recommendation method, device, equipment and storage medium based on user purchasing power | |
CN113449175A (en) | Hot data recommendation method and device | |
CN112732891A (en) | Office course recommendation method and device, electronic equipment and medium | |
CN112256566A (en) | Test case preservation method and device | |
CN109977315A (en) | A kind of article recommended method, device, equipment and storage medium | |
CN112667770A (en) | Method and device for classifying articles | |
CN112783956B (en) | Information processing method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |
|
RJ01 | Rejection of invention patent application after publication |