Intelligent Carousel Method and System Based on Big Data Analysis

Abstract

The present invention relates to big data processing technology, and discloses an intelligent carousel method and system based on big data analysis. The method includes: collecting viewing data through a viewing collection system; storing the collected viewing data combined with the program attributes of the electronic program guide in a collection database; an acquisition system, according to the electronic program guide, acquires the broadcast programs, stores the program files of the acquired programs in an acquisition storage unit, and stores the program information in an acquisition database; the carousel system creates channels, calculates weights for the programs in the collection database according to the viewing data and generates a program schedule, and performs carousel in combination with the program files acquired by the acquisition storage unit; through the mutual cooperation of the collection system, the acquisition system and the carousel system, the present invention realizes program scheduling and monitoring update according to the viewing data, thereby reducing the workload of manual participation, improving the timeliness and accuracy of program scheduling and program broadcast, greatly reducing the time consumed in the program scheduling link, and improving the efficiency of the entire business process.

Description

Technical Field

[0001] The present invention relates to big data processing technology, and in particular to an intelligent carousel method and system based on big data analysis. Background Art

[0002] With the gradual development of the broadcasting and television industry, existing cable television and new media services are gradually reaching bottlenecks. Most broadcasting and internet video companies are expanding their carousel services in various ways to attract more users. Carousel services have become an essential part of the broadcasting, new media, IPTV / OTT, and internet video industries. However, the currently used carousel systems in the industry primarily rely on manual methods to select, schedule, and manage broadcast programs, requiring significant manpower.

[0003] Traditional carousel services, such as those covered by patent CN201510247552.7, are manually scheduled, resulting in arbitrary scheduling. This makes it impossible to ensure timely scheduling of popular programs, and consequently, the viewership of broadcast programs. Traditional carousel services can only schedule a single channel at a time and cannot schedule and broadcast multiple channels simultaneously. Summary of the Invention

[0004] The present invention aims to solve the problem in the prior art that the manual programming of carousel programs is arbitrary and cannot guarantee the timely arrangement of hot programs, thereby failing to guarantee the viewing effect of the broadcast programs. An intelligent carousel method and system based on big data analysis are provided.

[0005] In order to solve the above technical problems, the present invention is solved by the following technical solutions:

[0006] An intelligent carousel method based on big data analysis is applied to the video carousel process, including a viewing collection system, a recording system, and a carousel system. The method includes:

[0007] The audience data is collected through the audience collection system; the collected audience data is combined with the program attributes of the electronic program guide and stored in the collection database;

[0008] Acquisition of recorded programs: The recording system records the broadcast programs according to the electronic program guide, stores the files of the recorded programs in the recording storage unit, and stores the program information in the recording database;

[0009] The program carousel system creates channels, compiles weighted lists of the audience data in the acquisition database, and performs carousel in combination with the program files recorded in the recording storage unit.

[0010] Preferably, the program carousel includes:

[0011] S1, create a channel and specify the channel type,

[0012] S2, in a data synchronization manner, filters the audience ratings of programs of the channel type from the audience data collection system, obtains programs of the current channel type, combines the audience ratings data, performs data analysis and calculates the broadcast weight, automatically arranges broadcast programs according to the broadcast weight, and sends them to the broadcast center of the carousel system;

[0013] S3, the material is prepared synchronously with the editing list and copied to the carousel broadcast center; when the broadcast time arrives, the carousel broadcast center encodes the material according to the editing list, encapsulates it into a protocol suitable for downstream playback, and outputs the live stream.

[0014] As a preferred method, the broadcast weight calculation method includes:

[0015] Take the time period △t according to the channel type, and take the program broadcast weight within the △t time period;

[0016] Program broadcast weight = number of live broadcasts × φ1 + number of replays × φ2 / △t + (number of replays - number of replays) × φ3 / △t

[0017] The number of live broadcasts is the number of first broadcasts, that is, the number of program plays collected by audience data; the number of replays is the number of terminal replays within △t; the number of replays is the number of plays; △t has different definition periods for different channels and is dynamically determined by channel type; φ1, φ2, and φ3 are weight values, which are dynamically determined by channel type.

[0018] Preferably, the program attributes include the number of live broadcasts of the program, the number of people who have replayed the program, the number of times the program has been replayed, and the type of the program.

[0019] Preferably, the program information includes program ID, program name, and program duration.

[0020] In order to solve the above technical problems, the present invention also provides an intelligent carousel system based on big data analysis, which is applied to the video carousel process and includes a viewing collection system, a collection system, and a carousel system. The system is characterized in that it includes a system implemented by an intelligent carousel method based on big data analysis, including:

[0021] The audience data collection module collects audience data through the audience collection system; the collected audience data is combined with the program attributes of the electronic program guide and stored in the collection database;

[0022] The acquisition module of the recorded programs, the recording system records the broadcast programs according to the electronic program guide, stores the files of the recorded programs in the recording storage unit, and stores the program information in the recording database;

[0023] The carousel module of the program. The carousel system creates channels, edits the weights of the viewing data in the acquisition database, and combines the program files collected and stored in the collection and storage unit to perform carousel broadcasting.

[0024] To solve the above technical problems, the present invention also provides an electronic device, which includes a memory and a processor. The memory is used to store one or more computer instructions. Among them, the one or more computer instructions are executed by the processor to implement an intelligent carousel method based on big data analysis.

[0025] To solve the above technical problems, the present invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a computer, it implements an intelligent carousel method based on big data analysis.

[0026] Due to the adoption of the above technical solutions, the present invention has significant technical effects:

[0027] The present invention collects, extracts, and analyzes the program viewing data, associates it with the channel attributes, automatically arranges and forms a broadcast program list. The carousel system issues broadcast tasks, prepares materials, and broadcasts based on the program list, completing the intelligent carousel service based on the viewing data.

[0028] Through the cooperation of the acquisition system, the collection system, and the carousel system, the present invention realizes program list compilation and monitoring update according to the viewing data, thereby reducing the workload of manual participation, improving the timeliness and accuracy of program list compilation and program broadcasting, significantly reducing the time consumed in the program list compilation link, and improving the efficiency of the entire business process. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flowchart of the present invention.

[0030] Figure 2 is the channel creation page of the present invention.

[0031] Figure 3 is the automatically compiled program list page output by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] The present invention will be further described in detail below with reference to the drawings and embodiments.

[0033] Embodiment 1

[0034] An intelligent carousel method based on big data analysis, applied to the video carousel process, includes a viewing data acquisition system, a collection system, and a carousel system. The method includes:

[0035] Collection of viewing data. The viewing data acquisition system collects the viewing data; the collected viewing data is stored in the acquisition database in combination with the program attributes of the electronic program guide;

[0036] Obtaining of the recorded programs. The recording system records the broadcast programs according to the electronic program guide, stores the files of the recorded programs in the recording storage unit, and stores the program information in the recording database;

[0037] Program carousel. The carousel system creates channels, performs weighted programming on the viewing data in the collection database, and combines the program files recorded in the recording storage unit to perform carousel.

[0038] Among them, the collection system, the recording system, and the carousel system are independently deployed on their respective servers (i.e., the servers where the programs run), with a total of three servers. The collection of program viewing data is the data basis for the subsequent operation of each link. This module provides program viewing data and program type attributes, that is, the ID, name, viewing situation, and program category of a certain program; the recording system collects the broadcast programs and provides information such as the ID, name, storage location, and size of the recorded files; the carousel system extracts, analyzes, and associates the viewing data according to the channel attributes, generates a program list, improves the accuracy of program programming and the real-time and accuracy of the broadcast task, and then performs preparation and distribution for broadcast based on the recorded files to ensure the arrangement and automatic broadcast of high-rated programs, forming a complete carousel service from collection to broadcast.

[0039] The collection system collects the viewing data through methods such as front-end set-top box embedding, combines the program attributes in the EPG (electronic program guide), and counts data such as the play count, replay times, and replay frequencies of each program by region, time period, and type, and stores them in the database. According to the EPG (electronic program guide), the broadcast programs are recorded, the recorded files are stored on a specific hard disk or shared storage, and data such as the program name and duration are recorded in the recording database.

[0040] By creating channels and specifying channel types, such as variety shows, movies (which can also be subdivided into domestic movies, foreign movies, science fiction movies, action movies, etc.), TV dramas (which can also be subdivided into love dramas, suspense dramas, ancient costume dramas, etc.), current affairs news, etc.; in the data synchronization method, screen the viewing situation of the programs of the channel from the viewing data collection system, select the programs of the current channel type, combine the viewing data situation, perform data analysis and calculation of the broadcast weight, perform automatic programming and scheduling according to the broadcast weight and send them to the carousel broadcast center; then synchronize the programming for material preparation and copy the materials to the carousel broadcast center; when it reaches the broadcast time, the carousel broadcast center encodes the materials according to the programming and encapsulates them into live streams suitable for downstream playback in protocols such as UDP, RTMP, and SRT for output.

[0041] The program carousel includes:

[0042] S1, create a channel and specify the channel type,

[0043] S2, in a data synchronization manner, screen the viewership of programs of this channel type from the viewership data collection system, select the programs of the current channel type, combine with the viewership data situation, conduct data analysis to calculate the broadcast weight, and automatically compile and schedule according to the broadcast weight and send it to the broadcast center of the carousel system;

[0044] S3, synchronize the compilation and conduct material preparation, copy the materials to the carousel broadcast center; when the broadcast time arrives, the carousel broadcast center encodes the materials according to the compilation, encapsulates them into a protocol suitable for downstream playback, and outputs the live stream.

[0045] The methods for calculating the broadcast weight include:

[0046] Take the time period △t according to the channel type, and obtain the program broadcast weight within the △t time period;

[0047] Program broadcast weight = live broadcast play count × φ1 + number of replay times × φ2 / △t + (number of replay viewers - number of replay times) × φ3 / △t;

[0048] Among them, the live broadcast play count is the play count of the first broadcast, that is, the program play count collected by the viewership data; the number of replay times is the number of terminal replays within the △t time; the number of replay viewers is the number of play times; △t has different defined periods according to different channels and dynamically takes values according to the channel type; φ1, φ2, and φ3 are weight values and dynamically take values according to the channel type.

[0049] △t has different defined periods according to different channels and dynamically takes values according to the channel type. Generally, the value range is shown in Table 1;

[0050] Table 1

[0051] Channel Type △t (days) Current Affairs News 0-2 Variety shows 0-30 TV drama 0-14 Movie 0-14 … …

[0052] φ1, φ2, and φ3 are weight values and dynamically take values according to the channel type. Generally, the value range is shown in Table 2:

[0053] Table 2

[0054] parameter value φ1 0.5-0.8 φ2 0.2-0.5 φ3 0-0.1

[0055] Program attributes include the live broadcast play count of the program, the number of replay viewers of the program, the number of replay times of the program, and the type of the program.

[0056] Program information includes program ID, program name, and program duration.

[0057] Embodiment 2

[0058] Based on Example 1, this embodiment is an intelligent carousel system based on big data analysis, which is applied to the video carousel process and includes a viewing collection system, a recording system, and a carousel system. It is characterized by including a system implemented by an intelligent carousel method based on big data analysis, including:

[0059] The audience data collection module collects audience data through the audience collection system; the collected audience data is combined with the program attributes of the electronic program guide and stored in the collection database;

[0060] The acquisition module of the recorded programs, the recording system records the broadcast programs according to the electronic program guide, stores the files of the recorded programs in the recording storage unit, and stores the program information in the recording database;

[0061] The program carousel module, the carousel system creates channels, compiles weighted lists of the viewing data in the acquisition database, and performs carousel in combination with the program files recorded in the recording storage unit.

[0062] Example 3

[0063] Based on Example 1, this embodiment is an electronic device, which includes a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement an intelligent carousel method based on big data analysis.

[0064] Example 4

[0065] Based on Example 1, this embodiment is a computer-readable storage medium storing a computer program, and when the computer program is executed by a computer, an intelligent carousel method based on big data analysis is implemented.

[0066] Example 5

[0067] Based on the above embodiment, the order editing rules of the carousel system of this embodiment are as follows: Figure 2 :After calculating the program broadcast weight according to the above rules, calculate the broadcast duration of the program with the limited number of programs according to the number of program items. If the duration is not exceeded, the program will continue to be broadcast according to the weight in rotation, and the excess part will be cut off. Figure 3 ;

[0068] In the viewership big data system, viewing data is obtained and provided to the carousel system through the synchronization module. The carousel system analyzes and extracts program data, associates channel attributes, generates a program schedule, and issues it for preparation and broadcast. In the carousel system, users are supported to perform operations such as adjusting, adding, or deleting the generated programming order, and querying the programming list is also supported. The viewership data collection system, the recording system, and the carousel system are started synchronously and operate independently. The viewership data collection system collects viewing data at the front end of the broadcast in real time, and the recording system records and stores files according to programs. The three systems communicate with each other through the data synchronization and material preparation modules to ensure the synchronization of viewership data and broadcast files. Among them, the data synchronization module automatically synchronizes at 00:00 every day, and the material preparation module triggers synchronization according to the issued programming list. Through the mutual cooperation of these three systems, program scheduling and monitoring updates are realized based on viewership data, thereby reducing the workload of manual participation, improving the timeliness and accuracy of scheduling and program broadcast, significantly reducing the time consumed in the scheduling process, and improving the efficiency of the entire business process.

Claims

1. An intelligent carousel method based on big data analysis, which is applied to the video carousel process and includes a viewing data collection system, an acquisition system, and a carousel system. The method includes: Collecting viewing data by collecting viewing data through the viewing data collection system; Storing the collected viewing data combined with the program attributes of the electronic program guide in the collection database; Obtaining the acquired programs. The acquisition system acquires the broadcast programs according to the electronic program guide, stores the program files of the acquired programs in the acquisition storage unit, and stores the program information in the acquisition database; Carousel of programs. The carousel system creates channels, calculates the weights of the programs in the collection database according to the viewing data and compiles the schedule, and combines the program files collected in the acquisition storage unit for carousel. The carousel of programs includes: S1, creating a channel and specifying the channel type; S2, in a data synchronization manner, screening the viewing conditions of the programs of this channel type from the viewing data collection system, selecting the programs of the current channel type, combining the viewing data conditions, performing data analysis to calculate the broadcast weight, automatically compiling the schedule and arranging the broadcast according to the broadcast weight, and sending it to the broadcast center of the carousel system; S3, synchronizing the schedule for material preparation, and copying the materials to the carousel broadcast center; when the broadcast time arrives, the carousel broadcast center encodes the materials according to the schedule, encapsulates them into a protocol suitable for downstream playback, and outputs the live stream. The methods for calculating the broadcast weight include: Taking the time period △t according to the channel type, and obtaining the program broadcast weight within the △t time period; Program broadcast weight = live play count × φ1 + number of replay times × φ2 / △t + (number of replay viewers - number of replay times) × φ3 / △t Among them, the live play count is the play count of the first broadcast, that is, the program play count collected by the viewing data; the number of replay times is the number of terminal replays within the △t time; the number of replay viewers is the number of play times; △t has different defined periods according to different channels and dynamically takes values according to the channel type; φ1, φ2, and φ3 are weight values and dynamically take values according to the channel type.

2. The intelligent carousel method based on big data analysis according to claim 1, characterized in that, Program attributes include the live play count of the program, the number of replay viewers of the program, the number of replay times of the program, and the type of the program.

3. The intelligent carousel method based on big data analysis according to claim 1, wherein Program information includes program ID, program name, and program duration.

4. An intelligent carousel system based on big data analysis, which is applied to the video carousel process and includes a viewing collection system, an inclusion system, and a carousel system, is characterized in that, A system implemented by the intelligent carousel method based on big data analysis according to any one of claims 1-3, including: A viewing data collection module, which collects viewing data through the viewing data collection system; stores the collected viewing data combined with the program attributes of the electronic program guide in the collection database; An acquired program obtaining module, where the acquisition system acquires the broadcast programs according to the electronic program guide, stores the program files of the acquired programs in the acquisition storage unit, and stores the program information in the acquisition database; A program carousel module, where the carousel system creates channels, compiles the weights of the viewing data in the collection database, and combines the program files collected in the acquisition storage unit for carousel.

5. An electronic device, characterized in that, Including a memory and a processor, the memory is used to store one or more computer instructions, and among them, the one or more computer instructions are executed by the processor to implement the intelligent carousel method based on big data analysis according to any one of claims 1-3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a computer, it implements the intelligent carousel method based on big data analysis according to any one of claims 1-3.

Images