CN115510270A - Video data recommendation method and device - Google Patents
Video data recommendation method and device Download PDFInfo
- Publication number
- CN115510270A CN115510270A CN202211285070.7A CN202211285070A CN115510270A CN 115510270 A CN115510270 A CN 115510270A CN 202211285070 A CN202211285070 A CN 202211285070A CN 115510270 A CN115510270 A CN 115510270A
- Authority
- CN
- China
- Prior art keywords
- video
- data
- historical
- user
- browsing data
- 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
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
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/75—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A video data recommendation method and device can be used in the financial field or other fields. The method comprises the following steps: obtaining historical video browsing data authorized by a user; the historical video browsing data comprises video browsing time and total video duration; determining a video score value according to the video browsing time and the total video duration, and obtaining a characteristic value corresponding to historical video browsing data according to the video score value; obtaining historical search data authorized by a user, and performing characteristic value calculation on the historical search data to obtain a characteristic value corresponding to the historical search data; and inputting the characteristic value corresponding to the historical video browsing data and the characteristic value corresponding to the historical search data into a preset recommendation model to obtain a video recommendation result. According to the method and the device, the video meeting the requirements of the user is provided for the user by processing the video browsing data of the user, the cost of the user for obtaining the information is reduced, the waiting time of the user is shortened, the user experience is improved, the processing speed is high, the error rate is low, and a large amount of time and labor cost can be saved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a video data recommendation method and apparatus.
Background
At present, financial related videos such as live broadcast, road show, teaching and the like which accord with asset qualification, wind bias and personal preference of a user are recommended for the user through a mobile banking, but the videos cannot be recommended according to related browsing information of the user, and the problems of inaccurate recommendation, poor user experience and the like exist.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiments of the present invention mainly aim to provide a video data recommendation method and apparatus, so as to reduce the cost of a user for obtaining and screening video data and improve the user experience.
In order to achieve the above object, an embodiment of the present invention provides a video data recommendation method, where the method includes:
obtaining historical video browsing data authorized by a user; the historical video browsing data comprises video browsing time and total video duration;
determining a video score value according to the video browsing time and the total video duration, and obtaining a characteristic value corresponding to the historical video browsing data according to the video score value;
obtaining historical search data authorized by a user, and performing characteristic value calculation on the historical search data to obtain a characteristic value corresponding to the historical search data;
and inputting the characteristic value corresponding to the historical video browsing data and the characteristic value corresponding to the historical searching data into a preset recommendation model to obtain a video recommendation result.
Optionally, in an embodiment of the present invention, the historical video browsing data further includes a video click time, a click interval, and video basic information.
Optionally, in an embodiment of the present invention, obtaining, according to the video score value, a feature value corresponding to the historical video browsing data includes:
determining video characteristics corresponding to historical video browsing data according to the video basic information;
performing high-dimensional mapping processing on the video features to obtain high-dimensional embedded features corresponding to the historical video browsing data;
and performing empowerment calculation on the high-dimensional embedded features corresponding to the historical video browsing data according to the video score value to obtain feature values corresponding to the historical video browsing data.
Optionally, in an embodiment of the present invention, the method further includes:
acquiring position taking data of a user authorized by the user, and determining high-dimensional embedded characteristics corresponding to the position taking data of the user;
and performing empowerment calculation and risk level processing on the high-dimensional embedded features corresponding to the user position taking data to obtain the user position taking risk preference information.
Optionally, in an embodiment of the present invention, inputting the feature value corresponding to the historical video browsing data and the feature value corresponding to the historical search data into a preset recommendation model, and obtaining the video recommendation result includes:
and inputting the characteristic value corresponding to the historical video browsing data, the characteristic value corresponding to the historical search data and the user position taking risk preference information into a preset recommendation model to obtain a video recommendation result.
An embodiment of the present invention further provides a video data recommendation apparatus, where the apparatus includes:
the browsing data module is used for acquiring historical video browsing data authorized by a user; the historical video browsing data comprises video browsing time and total video duration;
the score value module is used for determining a video score value according to the video browsing time and the total video duration, and obtaining a characteristic value corresponding to historical video browsing data according to the video score value;
the search data module is used for acquiring historical search data authorized by a user and calculating the characteristic value of the historical search data to obtain the characteristic value corresponding to the historical search data;
and the video recommendation module is used for inputting the characteristic values corresponding to the historical video browsing data and the characteristic values corresponding to the historical search data into a preset recommendation model to obtain a video recommendation result.
Optionally, in an embodiment of the present invention, the historical video browsing data further includes video click time, click interval, and video basic information.
Optionally, in an embodiment of the present invention, the score value module includes:
the video characteristic unit is used for determining the video characteristics corresponding to the historical video browsing data according to the video basic information;
the high-dimensional mapping unit is used for performing high-dimensional mapping processing on the video characteristics to obtain high-dimensional embedded characteristics corresponding to historical video browsing data;
and the characteristic value unit is used for performing empowerment calculation on the high-dimensional embedded characteristics corresponding to the historical video browsing data according to the video score value to obtain the characteristic value corresponding to the historical video browsing data.
Optionally, in an embodiment of the present invention, the apparatus further includes:
the position data module is used for acquiring position data of a user authorized by the user and determining high-dimensional embedded characteristics corresponding to the position data of the user;
and the risk preference module is used for performing empowerment calculation and risk level processing on the high-dimensional embedded features corresponding to the position taking data of the user to obtain position taking risk preference information of the user.
Optionally, in an embodiment of the present invention, the video recommendation module is further configured to input a feature value corresponding to the historical video browsing data, a feature value corresponding to the historical search data, and user position taking risk preference information into a preset recommendation model, so as to obtain a video recommendation result.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the program.
The present invention also provides a computer-readable storage medium having stored thereon a computer program for executing the above method.
The invention also provides a computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the above method.
According to the invention, through processing the video browsing data of the user, videos meeting the requirements of the user are provided for the user, the cost of the user for acquiring screening information is reduced, the waiting time of the user is reduced, the user experience is improved, the processing speed is high, the error rate is low, and a large amount of time cost and labor cost can be saved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
Fig. 1 is a flowchart of a video data recommendation method according to an embodiment of the present invention;
FIG. 2 is a flow chart of obtaining a feature value in an embodiment of the present invention;
FIG. 3 is a flow chart of obtaining risk preference information in an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a video data recommendation apparatus according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating a structure of a score module according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of a video data recommendation device according to another embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a video data recommendation method and device, which can be used in the financial field and other fields.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Fig. 1 is a flowchart illustrating a video data recommendation method according to an embodiment of the present invention, where an execution subject of the video data recommendation method according to the embodiment of the present invention includes, but is not limited to, a computer. According to the invention, through processing the video browsing data of the user, the video meeting the requirements of the user is provided for the user, the cost of the user for acquiring the screening information is reduced, the waiting time of the user is reduced, the user experience is improved, the processing speed is high, the error rate is low, and a large amount of time cost and labor cost can be saved. The method shown in the figure comprises the following steps:
s1, acquiring historical video browsing data authorized by a user; the historical video browsing data comprises video browsing time and total video duration;
s2, determining a video score value according to the video browsing time and the total video duration, and obtaining a characteristic value corresponding to historical video browsing data according to the video score value;
s3, obtaining historical search data authorized by a user, and calculating characteristic values of the historical search data to obtain characteristic values corresponding to the historical search data;
and S4, inputting the characteristic values corresponding to the historical video browsing data and the characteristic values corresponding to the historical search data into a preset recommendation model to obtain a video recommendation result.
The method comprises the steps of collecting the whole amount of video data historically browsed by a user, and specifically, obtaining historical video browsing data of the user in a user authorization mode. The historical video browsing data comprises video browsing time and total video duration.
Further, the video score value is calculated according to the video browsing time and the total video duration, and specifically, the video score value can be obtained by calculating the ratio of the browsing duration to the total video duration. For example, assuming that a video has a video time length of 5min, and the user browses the a video for 3min, the a video score is 3min/5min =0.6.
As an embodiment of the present invention, the historical video browsing data further includes video click time, click interval and video basic information.
In this embodiment, as shown in fig. 2, obtaining the feature value corresponding to the historical video browsing data according to the video score value includes:
s21, determining video characteristics corresponding to historical video browsing data according to the video basic information;
s22, performing high-dimensional mapping processing on the video features to obtain high-dimensional embedded features corresponding to historical video browsing data;
and S23, performing empowerment calculation on the high-dimensional embedded features corresponding to the historical video browsing data according to the video score values to obtain feature values corresponding to the historical video browsing data.
Wherein, according to the basic information of the video, such as the video subject, content, genre, title, etc., the characteristics of the complete information of the video, i.e., the video characteristics, can be summarized. And specifically, carrying out information coding based on the characteristics, and calculating the coded characteristics through a plurality of high-dimensional matrixes to obtain the high-order embedded characteristic representation of the video. The information encoding, the high-dimensional mapping and the high-dimensional matrix calculation adopt conventional technical means, and are not described herein again.
Furthermore, according to the video score value, performing empowerment calculation on the high-dimensional embedded features corresponding to the historical video browsing data, and thus calculating to obtain feature values corresponding to the historical video browsing data. Specifically, the calculated video score values are directly acted on the high-dimensional features, namely, the feature values corresponding to the historical video browsing data can be obtained by direct multiplication.
In this embodiment, a user authorization manner is adopted to obtain historical search data of a user, and search records are classified according to a preset classification manner, for example, according to financial products, functions, and video types. And performing high-dimensional feature mapping on all records in each large class, adding all features in the large classes, and then calculating an average value to be used as historical data representation of the large class, namely a feature value corresponding to historical video browsing data. Specifically, the data mapped to the high-dimensional space can be obtained by performing high-dimensional calculation on the data features and processing the data through a plurality of high-dimensional matrixes.
As an embodiment of the present invention, as shown in fig. 3, the method further includes:
step S31, obtaining position taking data of a user authorized by the user, and determining high-dimensional embedded characteristics corresponding to the position taking data of the user;
and S32, performing empowerment calculation and risk level processing on the high-dimensional embedded features corresponding to the position taking data of the user to obtain position taking risk preference information of the user.
The position taking data of the user is obtained in a user authorization mode, and specifically, the position taking data can be financial asset position taking data. And coding the position-taken product to obtain the corresponding high-dimensional embedding characteristics. Specifically, the characteristics of the complete information of the product can be summarized according to the content, the type, the yield, the risk level and the like of the product, information coding is carried out on the basis of the characteristics, and the coded characteristics are calculated through a plurality of high-dimensional matrixes, so that the high-order embedded characteristic representation of the product can be obtained. And performing weighting calculation on each high-dimensional embedded feature by using the ratio of each type product to the total asset value, specifically, directly acting on the high-dimensional features by using the calculated ratio, namely directly multiplying the high-dimensional embedded features.
Further, after all the features are added and averaged, the position holding feature representation is obtained. And calculating the proportion of each risk grade product to the total assets according to the risk grade of the position-taking product to obtain the position-taking risk preference information of the user. Specifically, the risk grade is that the product is graded according to the volatility and graded in advance according to the specific performance of the product in the history. The proportion of each risk grade product to the total assets can be calculated by directly calculating the ratio of the product position taken to the total assets.
In this embodiment, the collected user risk evaluation information is obtained by means of user authorization, and each item of information in the risk evaluation is encoded to obtain a corresponding high-dimensional embedding feature, so as to obtain the risk evaluation encoded information representation. Specifically, the characteristics of the complete information of the product can be summarized according to the content, the type, the yield, the risk level and the like of the product, information coding is carried out based on the characteristics, the coded characteristics are calculated through a plurality of high-dimensional matrixes, and high-dimensional embedded characteristic representation of the product, namely risk assessment coding information, can be obtained.
In this embodiment, inputting the feature value corresponding to the historical video browsing data and the feature value corresponding to the historical search data into a preset recommendation model, and obtaining the video recommendation result includes: and inputting the characteristic value corresponding to the historical video browsing data, the characteristic value corresponding to the historical search data and the user position taking risk preference information into a preset recommendation model to obtain a video recommendation result.
And inputting the characteristic value corresponding to the historical video browsing data, the characteristic value corresponding to the historical search data, the user position taking risk preference information and the high-dimensional embedded characteristic representation of the product which are obtained through calculation into a preset recommendation model for processing to obtain a video recommendation result. Specifically, the preset recommendation model may be a neural network model, and the initial neural network model may be trained by using data such as the above characteristic values, and the obtained model output result is the next watching video after the user clicks the video, that is, the video recommendation result.
In an embodiment of the present invention, a specific process of video data recommendation includes:
1) And collecting the total video data historically browsed by the user, calculating the score value of each video according to the browsing time and the total video duration of each video, and sorting the training data according to the video click time and the click interval. And carrying out high-dimensional mapping on each video characteristic to obtain high-dimensional embedded characteristic representation of the video, and grading and weighting each video high-dimensional embedded characteristic according to the grade value. And adding all weighted high-dimensional embedded feature representations and averaging to obtain the feature value of the historical video data.
The video score value is obtained by calculating the ratio of the browsing duration to the total video duration. Assuming that the video A has a video time length of 5min, and the user browses the video A for 3min, the score value of the video A is 3min/5min =0.6. In addition, the training data is data of a subsequent training model.
Furthermore, the characteristics of the complete video information can be summarized according to the video theme, content, type, title and the like, information coding is carried out based on the characteristics, and the coded characteristics are calculated through a plurality of high-dimensional matrixes, so that high-order embedded characteristic representation of the video can be obtained. In addition, the score assignment directly acts on the high-dimensional features by using the calculated score value, namely directly multiplying.
2) And collecting historical search records of the user, classifying the search records according to financial products, functions and video types, performing high-dimensional feature mapping on all records in each large class, adding all features in the large classes, and then calculating an average value to be used as historical data of the large class to represent.
The high-dimensional feature mapping is to perform high-dimensional calculation on data features, and process data through a plurality of high-dimensional matrixes to obtain data mapped to a high-dimensional space.
3) And collecting the position data of the financial assets of the user, and coding the position products to obtain the corresponding high-dimensional embedded features. Weighting calculation is carried out on each high-dimensional embedded feature by using the wallpaper of each type of product occupying the total asset value, and after all the features are added and averaged, a position-taking feature representation is obtained; and calculating the proportion of each risk grade product to the total assets according to the risk grade of the position-taking product to obtain the position-taking risk preference information of the user.
The characteristics of the complete information of the product can be summarized according to the content, the type, the yield, the risk level and the like of the product, information coding is carried out based on the characteristics, and the coded characteristics are calculated through a plurality of high-dimensional matrixes, so that the high-order embedded characteristic representation of the product can be obtained. In addition, the weighted calculation can be carried out by directly acting on the high-dimensional characteristics by using the calculated ratio, namely directly multiplying.
Further, the product is graded according to the risk of fluctuation and the specific performance of the product in the history. And directly calculating the ratio of the product position taken to the total assets according to the ratio of the product at each risk level to the total assets.
4) And collecting user risk evaluation information, and coding each item of information in the risk evaluation to obtain corresponding high-dimensional embedding characteristics and obtain risk evaluation coding information expression.
The characteristics of the complete information of the product can be summarized according to the content, the type, the yield, the risk level and the like of the product, information coding is carried out on the basis of the characteristics, and the coded characteristics are calculated through a plurality of high-dimensional matrixes, so that the high-dimensional embedded characteristic representation of the product can be obtained. Specifically, the high-dimensional features are coded information for risk assessment.
5) And training the model by using the information as an auxiliary input feature vector and combining with the features of each video, wherein the model input is the feature representation of each video and all the auxiliary features, and the model output is the next watching video after the user clicks the video.
Wherein, the model training process may specifically be: and assuming that the video A is training data, the video A is represented by high-dimensional features of the video A, all information such as position taking and windage yaw are combined to serve as input information, and the next video clicked by a user after the video A is browsed is taken as a label for calculation.
According to the invention, through processing the video browsing data of the user, the video meeting the requirements of the user is provided for the user, the cost of the user for acquiring the screening information is reduced, the waiting time of the user is reduced, the user experience is improved, the processing speed is high, the error rate is low, and a large amount of time cost and labor cost can be saved. In addition, the invention has the advantages of high mobility, low migration cost, wide application range, low popularization cost and the like.
Fig. 4 is a schematic structural diagram of a video data recommendation apparatus according to an embodiment of the present invention, where the apparatus includes:
a browsing data module 10, configured to obtain historical video browsing data authorized by a user; the historical video browsing data comprises video browsing time and total video duration;
the score value module 20 is configured to determine a video score value according to the video browsing time and the total video duration, and obtain a feature value corresponding to historical video browsing data according to the video score value;
the search data module 30 is configured to obtain historical search data authorized by a user, and perform feature value calculation on the historical search data to obtain a feature value corresponding to the historical search data;
and the video recommendation module 40 is configured to input the feature value corresponding to the historical video browsing data and the feature value corresponding to the historical search data into a preset recommendation model to obtain a video recommendation result.
As an embodiment of the present invention, the historical video browsing data further includes video click time, click interval and video basic information.
In this embodiment, as shown in fig. 5, the score value module 20 includes:
a video feature unit 21, configured to determine, according to the basic video information, a video feature corresponding to the historical video browsing data;
the high-dimensional mapping unit 22 is configured to perform high-dimensional mapping processing on the video features to obtain high-dimensional embedded features corresponding to historical video browsing data;
and the characteristic value unit 23 is configured to perform empowerment calculation on the high-dimensional embedded characteristics corresponding to the historical video browsing data according to the video score value, so as to obtain a characteristic value corresponding to the historical video browsing data.
As an embodiment of the present invention, as shown in fig. 6, the apparatus further includes:
the position data module 50 is used for acquiring position data of a user authorized by the user and determining high-dimensional embedded characteristics corresponding to the position data of the user;
and the risk preference module 60 is used for performing empowerment calculation and risk level processing on the high-dimensional embedded features corresponding to the position taking data of the user to obtain position taking risk preference information of the user.
In this embodiment, the video recommendation module 40 is further configured to input the feature value corresponding to the historical video browsing data, the feature value corresponding to the historical search data, and the user position taking risk preference information into a preset recommendation model, so as to obtain a video recommendation result.
Based on the same application concept as the video data recommendation method, the invention also provides the video data recommendation device. Because the principle of solving the problems of the video data recommendation device is similar to that of a video data recommendation method, the implementation of the video data recommendation device can refer to the implementation of the video data recommendation method, and repeated parts are not described again.
According to the invention, through processing the video browsing data of the user, videos meeting the requirements of the user are provided for the user, the cost of the user for acquiring screening information is reduced, the waiting time of the user is reduced, the user experience is improved, the processing speed is high, the error rate is low, and a large amount of time cost and labor cost can be saved.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method when executing the program.
The invention also provides a computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the above method.
The present invention also provides a computer-readable storage medium having stored thereon a computer program for executing the above method.
As shown in fig. 7, the electronic device 600 may further include: communication module 110, input unit 120, audio processor 130, display 160, power supply 170. It is noted that the electronic device 600 does not necessarily include all of the components shown in fig. 7; furthermore, the electronic device 600 may also comprise components not shown in fig. 7, which may be referred to in the prior art.
As shown in fig. 7, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable devices. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, an LCD display, but is not limited thereto.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes referred to as an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142 for storing application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging application, address book application, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132 to implement general telecommunications functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 130 is also coupled to the central processor 100, so that recording on the local can be enabled through a microphone 132, and so that sound stored on the local can be played through a speaker 131.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (13)
1. A method for recommending video data, the method comprising:
acquiring historical video browsing data authorized by a user; the historical video browsing data comprises video browsing time and total video duration;
determining a video score value according to the video browsing time and the total video duration, and obtaining a characteristic value corresponding to the historical video browsing data according to the video score value;
obtaining historical search data authorized by a user, and performing characteristic value calculation on the historical search data to obtain a characteristic value corresponding to the historical search data;
and inputting the characteristic value corresponding to the historical video browsing data and the characteristic value corresponding to the historical search data into a preset recommendation model to obtain a video recommendation result.
2. The method of claim 1, wherein the historical video browsing data further comprises video click times, click intervals, and video basic information.
3. The method according to claim 2, wherein the obtaining a feature value corresponding to the historical video browsing data according to the video rating value comprises:
determining video characteristics corresponding to the historical video browsing data according to the video basic information;
performing high-dimensional mapping processing on the video features to obtain high-dimensional embedded features corresponding to the historical video browsing data;
and performing empowerment calculation on the high-dimensional embedded features corresponding to the historical video browsing data according to the video scoring value to obtain feature values corresponding to the historical video browsing data.
4. The method of claim 1, further comprising:
acquiring position taking data of a user authorized by the user, and determining a high-dimensional embedded characteristic corresponding to the position taking data of the user;
and performing empowerment calculation and risk level processing on the high-dimensional embedded features corresponding to the user position taking data to obtain the user position taking risk preference information.
5. The method according to claim 4, wherein the inputting the feature values corresponding to the historical video browsing data and the feature values corresponding to the historical search data into a preset recommendation model to obtain a video recommendation result comprises:
and inputting the characteristic value corresponding to the historical video browsing data, the characteristic value corresponding to the historical search data and the user position taking risk preference information into a preset recommendation model to obtain a video recommendation result.
6. An apparatus for recommending video data, the apparatus comprising:
the browsing data module is used for acquiring historical video browsing data authorized by a user; the historical video browsing data comprises video browsing time and total video duration;
the score value module is used for determining a video score value according to the video browsing time and the total video duration, and obtaining a characteristic value corresponding to the historical video browsing data according to the video score value;
the search data module is used for acquiring historical search data authorized by a user and calculating the characteristic value of the historical search data to obtain the characteristic value corresponding to the historical search data;
and the video recommendation module is used for inputting the characteristic values corresponding to the historical video browsing data and the characteristic values corresponding to the historical search data into a preset recommendation model to obtain a video recommendation result.
7. The apparatus of claim 6, wherein the historical video browsing data further comprises video click times, click intervals, and video basic information.
8. The apparatus of claim 7, wherein the score value module comprises:
the video characteristic unit is used for determining the video characteristics corresponding to the historical video browsing data according to the video basic information;
the high-dimensional mapping unit is used for performing high-dimensional mapping processing on the video features to obtain high-dimensional embedded features corresponding to the historical video browsing data;
and the characteristic value unit is used for performing empowerment calculation on the high-dimensional embedded characteristics corresponding to the historical video browsing data according to the video score value to obtain the characteristic value corresponding to the historical video browsing data.
9. The apparatus of claim 6, further comprising:
the position taking data module is used for acquiring position taking data of a user authorized by the user and determining high-dimensional embedded characteristics corresponding to the position taking data of the user;
and the risk preference module is used for performing empowerment calculation and risk level processing on the high-dimensional embedded features corresponding to the user position taking data to obtain the user position taking risk preference information.
10. The apparatus according to claim 9, wherein the video recommendation module is further configured to input a feature value corresponding to the historical video browsing data, a feature value corresponding to the historical search data, and the user position taking risk preference information into a preset recommendation model to obtain a video recommendation result.
11. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium, characterized in that it stores a computer program for executing the method of any one of claims 1 to 5.
13. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the steps of the method of any of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211285070.7A CN115510270A (en) | 2022-10-20 | 2022-10-20 | Video data recommendation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211285070.7A CN115510270A (en) | 2022-10-20 | 2022-10-20 | Video data recommendation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115510270A true CN115510270A (en) | 2022-12-23 |
Family
ID=84509803
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211285070.7A Pending CN115510270A (en) | 2022-10-20 | 2022-10-20 | Video data recommendation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115510270A (en) |
-
2022
- 2022-10-20 CN CN202211285070.7A patent/CN115510270A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109819284B (en) | Short video recommendation method and device, computer equipment and storage medium | |
CN110751224B (en) | Training method of video classification model, video classification method, device and equipment | |
CN106487907B (en) | Method and system for sharing promotion information | |
CN111861569A (en) | Product information recommendation method and device | |
CN112785086A (en) | Credit overdue risk prediction method and device | |
CN105009118A (en) | Customized content consumption interface | |
CN111667308A (en) | Advertisement recommendation prediction system and method | |
CN111768231A (en) | Product information recommendation method and device | |
CN107864405B (en) | Viewing behavior type prediction method, device and computer readable medium | |
CN111798244B (en) | Transaction fraud monitoring method and device | |
CN108540860B (en) | Video recall method and device | |
CN112801719A (en) | User behavior prediction method, user behavior prediction device, storage medium, and apparatus | |
CN104243590A (en) | Resource object recommendation method and device | |
CN111522724A (en) | Abnormal account determination method and device, server and storage medium | |
CN112784112A (en) | Message checking method and device | |
CN111931852B (en) | Target pricing method and device | |
CN113037487A (en) | File encryption data processing method and device | |
CN115965456A (en) | Data change analysis method and device | |
CN115510270A (en) | Video data recommendation method and device | |
CN116664227A (en) | Intelligent recommendation method and device for financial products | |
CN117014693A (en) | Video processing method, device, equipment and storage medium | |
CN114357236A (en) | Music recommendation method and device, electronic equipment and computer readable storage medium | |
CN111767435A (en) | User behavior analysis method and device | |
CN111048063A (en) | Audio synthesis method and device | |
CN114528496B (en) | Multimedia data processing method, device, equipment and storage medium |
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 |