WO2021098310A1 - 视频生成方法、装置、终端以及存储介质 - Google Patents

视频生成方法、装置、终端以及存储介质 Download PDF

Info

Publication number
WO2021098310A1
WO2021098310A1 PCT/CN2020/110278 CN2020110278W WO2021098310A1 WO 2021098310 A1 WO2021098310 A1 WO 2021098310A1 CN 2020110278 W CN2020110278 W CN 2020110278W WO 2021098310 A1 WO2021098310 A1 WO 2021098310A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
video
display
commodity
display data
Prior art date
Application number
PCT/CN2020/110278
Other languages
English (en)
French (fr)
Inventor
冯伟平
Original Assignee
北京沃东天骏信息技术有限公司
北京京东世纪贸易有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from CN201911125781.6A external-priority patent/CN111784431B/zh
Application filed by 北京沃东天骏信息技术有限公司, 北京京东世纪贸易有限公司 filed Critical 北京沃东天骏信息技术有限公司
Priority to US17/770,583 priority Critical patent/US20220383381A1/en
Priority to EP20891050.5A priority patent/EP4033438A4/en
Publication of WO2021098310A1 publication Critical patent/WO2021098310A1/zh

Links

Images

Classifications

    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0623—Item investigation
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0641—Shopping interfaces
    • G06Q30/0643—Graphical representation of items or shoppers

Definitions

  • the present disclosure is based on the application whose CN application number is 201911125781.6, whose application date is November 18, 2019, and claims its priority.
  • the disclosure of the CN application is hereby incorporated into the present disclosure as a whole.
  • the present disclosure relates to the field of video processing technology, and in particular, to a video generation method, device, terminal, and storage medium.
  • Video is widely used in e-commerce and content communities. Compared with static graphic display, video can attract users and improve users' perception and understanding. It is of great help to increase website traffic, conversion rate, user return visit rate, etc. However, when video is applied in e-commerce and other fields, there will be many problems.
  • the inventors of the present disclosure have found that the technical solutions for video generation in the above-mentioned related technologies have defects: when the video is applied in e-commerce and other fields, problems such as cumbersome video synthesis, difficulty in updating, and fixed video content may occur.
  • a video generation method which includes: when a user accesses a product page, obtaining product attribute information corresponding to a product displayed on the product page, and determining a product display scene based on the product attribute information Obtain the user’s historical behavior data, obtain product display data based on the historical behavior data; obtain a video template according to the product display scene and the product display data; generate and generate a video template based on the product display data and the video template The product display video corresponding to the product.
  • the product attribute information includes: product category and product feature information; the determining a product display scene based on the product attribute information includes: determining all items that match the product category and the product feature information. Describe the merchandise display scene.
  • the obtaining product display data based on the historical behavior data includes: determining a product display data category that the user is interested in according to the historical behavior information; and extracting the product display data from the product page.
  • the product display data corresponding to the data category includes: determining a product display data category that the user is interested in according to the historical behavior information; and extracting the product display data from the product page. The product display data corresponding to the data category.
  • the determining the product display data category that the user is interested in based on the historical behavior information includes: obtaining the number of times the user has viewed a historical product page, and information about the product in the historical product page. The number of clicks on the display area; the click rate of each product information display area of the user is obtained based on the number of clicks and the number of views; the product information display area that the user is interested in is determined based on the click rate, and the The commodity display data category corresponding to the commodity information display area that the user is interested in.
  • the determining the product information display area that the user is interested in based on the click rate includes: sorting all the product information display areas in the order of the click rate from high to low; Select multiple commodity information display areas arranged at the top as the commodity information display areas of interest to the user.
  • the obtaining a video template according to the product display scene and the product display data includes: determining whether there is a video template in the video template library that matches the product display scene and the product display data If yes, obtain the video template; if not, obtain the video template corresponding to the commodity display scene, adjust this video template based on the commodity display data, and obtain the commodity display scene and the And store the video template matching the product display data in the video template library.
  • the generating a product display video corresponding to the product based on the product display data and the video template includes: obtaining display materials corresponding to the product display data; wherein, the display The materials include: one or more of video files, sound files, image files, and text files; determine the product display data and/or the insertion position of the display materials in the video template; display the product The data and/or the display material is inserted into the corresponding insertion position, and the product display video is generated and stored in the display video library.
  • the product display video is obtained from the display video library.
  • a video generation device including: a display scene determination module, configured to obtain product attribute information corresponding to a product displayed on the product page when a user accesses a product page, based on the The product attribute information determines the product display scene; the display data determination module is used to obtain the user's historical behavior data, and the product display data is obtained based on the historical behavior data; the video template acquisition module is used to obtain the product display scene and the product display data.
  • the product display data obtains a video template; a display video production module is used to generate a product display video corresponding to the product based on the product display data and the video template.
  • a video generation device including: a memory; and a processor coupled to the memory, the processor is configured to execute the above based on instructions stored in the memory The method described.
  • a terminal including: the video generating device as described above.
  • a computer-readable storage medium stores computer instructions, and the instructions are executed by a processor as described above.
  • Fig. 1 is a schematic flowchart of some embodiments of a video generation method according to the present disclosure
  • FIG. 2 is a schematic flowchart of some embodiments of obtaining product display data in a video generation method according to the present disclosure
  • FIG. 3A is a schematic flowchart of some embodiments of determining a product display data category of interest to a user in a video generation method according to the present disclosure
  • Figure 3B is a schematic diagram of obtaining product display data from a product page
  • FIG. 4 is a schematic flowchart of some embodiments of obtaining a video template in a video generation method according to the present disclosure
  • FIG. 5 is a schematic flowchart of some embodiments of generating a product display video in a video generating method according to the present disclosure
  • Fig. 6 is a schematic diagram of modules of some embodiments of a video generating device according to the present disclosure.
  • FIG. 7 is a schematic diagram of some embodiments of the display data determining module in the video generating device according to the present disclosure.
  • Fig. 8 is a schematic diagram of modules of other embodiments of a video generating device according to the present disclosure.
  • video synthesis is cumbersome: the video is recorded and edited by professionals, a lot of materials need to be prepared, and the waiting time is also very long; it is difficult to update : Once the video is confirmed and produced, and if you want to adjust and modify it, you can only re-record and synthesize it. It is not applicable to scenes that require "timely response"; video content is fixed: all users see the same video, and different videos cannot be customized according to different users ; Customized for scenes: Only a small part of customized scenes can be supported, and videos cannot be produced in large scale and in batches. Therefore, video usage scenarios are greatly restricted.
  • the embodiments of the present disclosure provide a video generation method, device, terminal, and storage medium; the video generation method, device, terminal, and storage medium of the embodiments of the present disclosure generate a product display based on product display data and a video template Video can reduce the computing pressure on the server side and the pressure on the communication network; it is highly efficient to generate product display videos and can be used in a variety of scenarios; product display data and materials are obtained by real-time analysis, which can ensure that the video content is consistent with the product page, and can Generate different product display videos for different users, achieve accurate playback, and improve user satisfaction.
  • Fig. 1 is a schematic flowchart of some embodiments of a video generation method according to the present disclosure, as shown in Fig. 1:
  • Step 101 When a user accesses a product page, obtain product attribute information corresponding to a product displayed on the product page, and determine a product display scene based on the product attribute information.
  • the product page may be a product page of an e-commerce website, and the product may be a mobile phone, wine, food, clothes, etc.
  • the terminal can be a mobile phone, a tablet computer, etc., and the product page can be accessed through APPs, browsers, applets, etc. installed in the terminal.
  • the terminal can analyze the product webpage file to obtain the product attribute information displayed on the product page.
  • the product attribute information includes: product category, product feature information, etc.; product feature information includes the user to which the product is applicable, the applicable occasion, the purpose of the product, and the highlight of the product The advantages and other information.
  • the merchandise display scene includes the storyline of the merchandise design, the protagonist, other personnel, the scene of the story, the atmosphere, etc.
  • the product display scene can be numbered, the product display scene can be determined on the terminal side based on the product attribute information, and the product display scene number can be determined, or the product attribute information can be sent to the background server, and the background server returns the product display scene number.
  • Step 102 Obtain historical behavior data of the user, and obtain product display data based on the historical behavior data.
  • the historical behavior data includes historical data such as the user's clicks and browsing of webpages.
  • Commodity display data includes data such as commodity prices, commodity specifications, commodity discounts, recommended commodities, commodity pictures, and user uploaded videos.
  • Step 103 Obtain a video template according to the product display scene and the product display data.
  • the video template can be obtained on the terminal side according to the product display scene and product display data, or the product display scene information (commodity display scene number) and product display data can be sent to the background server, and the background server sends the information to the terminal.
  • the corresponding video template can be obtained on the terminal side according to the product display scene and product display data, or the product display scene information (commodity display scene number) and product display data can be sent to the background server, and the background server sends the information to the terminal.
  • the corresponding video template can be obtained on the terminal side according to the product display scene and product display data, or the product display scene information (commodity display scene number) and product display data can be sent to the background server, and the background server sends the information to the terminal.
  • the corresponding video template can be obtained on the terminal side according to the product display scene and product display data, or the product display scene information (commodity display scene number) and product display data can be sent to the background server, and the background server sends the information to the terminal.
  • Step 104 Generate a product display video corresponding to the product based on the product display data and the video template.
  • the video type of the commodity display video can be multiple existing video types.
  • the display video library can be set up on a back-end server or cloud server, etc., to store product display videos.
  • the terminal can send a query request to a back-end server, etc. If it is determined that a product display video matching the product display scene and product display data is stored in the display video library, or a product display video corresponding to the user and the product is stored, then Get this product display video in the display video library. For example, download the product display video from the display video library to the terminal side for playback. If it is determined that the product display video matching the product display scene and product display data is not stored in the display video library, or the product display video corresponding to the user and the product is not stored, the terminal generates a new product display video and plays it.
  • a product display scene that matches the product category and product feature information is determined.
  • the product is a certain learning machine
  • the product category is a learning machine
  • the product feature information includes information suitable for middle school students.
  • the product display scene is a middle school student using a learning machine to learn.
  • the storyline of this product display scene is that a middle school student uses a learning machine to solve a homework problem when a middle school student encounters a homework problem.
  • the protagonist of this product display scene is one Middle school students and so on.
  • the product display scene and the product display scene number corresponding to the product attribute information can be preset, and the product display scene number can be used as a unique identifier of the product display scene.
  • FIG. 2 is a schematic flowchart of some embodiments of obtaining product display data in the video generation method according to the present disclosure, as shown in Fig. 2:
  • Step 201 Determine the product display data category that the user is interested in according to the historical behavior information.
  • Product display data categories include: product prices, product specifications, product discounts, recommended products, product pictures, user uploaded videos, and other data categories.
  • Step 202 Extract the product display data corresponding to the product display data category from the product page.
  • the product page can be analyzed, and data corresponding to the product display data category can be extracted on the product page as the product display data.
  • Various existing analysis methods can be used to analyze the product page.
  • FIG. 3A is a schematic flowchart of some embodiments for determining the category of product display data that a user is interested in according to the video generation method of the present disclosure, as shown in FIG. 3:
  • Step 301 Obtain the number of times the user has viewed the historical product page and the number of clicks on the product information display area in the historical product page.
  • the historical product page is a product page of multiple products that the user has viewed. Get the number of times the user has viewed the historical product page and the number of clicks on the product information display area in the historical product page.
  • the product information display area includes the product price area, product specification area, product discount area, recommended product area, product image area, user upload video area, and other areas on the product page.
  • Step 302 Obtain a user's click rate for each product information display area based on the number of clicks and the number of views.
  • Step 303 Determine the product information display area that the user is interested in based on the click rate, and obtain the product display data category corresponding to the product information display area that the user is interested in.
  • Various methods can be used to determine the product information display area that the user is interested in based on the click-through rate. For example, sort all product information display areas according to the order of click rate from high to low; select multiple product information display areas that are ranked first in the sorting result as the product information display areas that users are interested in.
  • FIG. 4 is a schematic flowchart of some embodiments of obtaining a video template in a video generation method according to the present disclosure, as shown in FIG. 4:
  • Step 401 Determine whether there is a video template matching the product display scene and the product display data in the video template library; if yes, go to step 402, if not, go to step 403.
  • the video template library is set on a background server or a cloud server.
  • the terminal sends a query request (carrying product display scene number, product display data information, etc.) to a background server or cloud server, etc., to determine whether there is a video template matching the product display scene and product display data in the video template library.
  • the video template may be a variety of existing video templates.
  • the video template may include the distribution of various scenes, and the insertion positions of data, pictures, videos, etc., in the video frame corresponding to the product.
  • the template description information includes: the product corresponding to the video template and the product display scene, the product display information that can be displayed by the video template, and so on.
  • the server can determine whether a video template that matches the product display scene and product display data is stored according to the template description information.
  • Step 402 Obtain a video template.
  • the terminal can download the video template and template description information from the video template library.
  • Step 403 Obtain a video template corresponding to the merchandise display scene, adjust the video template based on the merchandise display data, obtain a video template matching the merchandise display scene and merchandise display data, and store it in the video template library.
  • a video template corresponding to the product display scene is preset in the video template library. If it is determined that there is no video template matching the product display scene and the product display data in the video template library, it will be displayed with the product. Adjust the video template corresponding to the scene. Adjusting the video template includes increasing or decreasing the product display information that can be displayed by the video template, and generating corresponding template description information. The video template can be adjusted using various existing methods. After adjusting the video template corresponding to the commodity display scene, a video template matching the commodity display scene and the commodity display data and template description information are obtained, and stored in the video template library.
  • FIG. 5 is a schematic flowchart of some embodiments of generating a product display video in a video generating method according to the present disclosure, as shown in FIG. 5:
  • Step 501 Obtain display materials corresponding to the product display data.
  • the display material includes one or more of video files, sound files, picture files, and text files.
  • the material library can be set on the background server or cloud server.
  • the product display data can include product prices, product specifications, product discounts, recommended products, product pictures, user uploaded videos, etc.
  • the terminal can request the background server or cloud server to obtain and The video, sound, picture or text corresponding to one or more commodity display data are returned to the terminal. If there is no relevant material, the terminal uploads the relevant material to the material library.
  • Step 502 Determine the insertion position of the product display data and/or display material in the video template.
  • Step 503 Insert the product display data and/or display material into the corresponding insertion position to generate a product display video and store it in the display video library.
  • the video template reserves product display data or display materials, product display data and insertion positions of the display materials, and based on the template description information of the video template, the product display data or display materials, and product display data and display materials are reserved. Insert the corresponding position to generate a product display video.
  • the product display video can be a Canvas video, etc., which combines data, templates, and materials to display the video through Canvas animation. Synthesize the animation into a traditional video format and upload it to the video library.
  • the video generation method in the above embodiment generates a product display video based on the product display data and the video template on the terminal side, which can reduce the computing pressure on the server side and the pressure of the communication network; the product display video is highly efficient and can be applied to a variety of similar Scenario:
  • the product display data and materials are obtained by real-time analysis, which can ensure that the video content is consistent with the product page, and the product display video changes accordingly when the product page changes; it can be combined with big data analysis to generate different product display videos for different users. Realize accurate playback and improve user satisfaction; customize templates and materials to meet customized scenarios, and store templates and materials for shared use.
  • the present disclosure provides a video generation device 60, including: a display scene determination module 61, a display data determination module 62, a video template acquisition module 63, a display video production module 64, and a display video Get module 65.
  • the display scene determination module 61 obtains the product attribute information corresponding to the product displayed on the product page when the user accesses the product page, and determines the product display scene based on the product attribute information.
  • the display data determining module 62 obtains historical behavior data of the user, and obtains product display data based on the historical behavior data.
  • the video template obtaining module 63 obtains a video template according to the commodity display scene and the commodity display data.
  • the display video production module 64 generates a product display video corresponding to the product based on the product display data and the video template.
  • the display video acquisition module 65 determines that a product display video matching the product display scene and product display data is stored in the display video library, or a product display video corresponding to the user and the product is stored, then Get this product display video from the display video library.
  • the product attribute information includes: product category, product feature information, etc.; the display scene determination module 61 determines a product display scene that matches the product category and product feature information.
  • the video template obtaining module 63 determines whether there is a video template matching the product display scene and the product display data in the video template library; if so, the video template obtaining module 63 obtains the video template; if not, the video template obtaining module 63 obtains The video template corresponding to the product display scene is adjusted based on the product display data.
  • the video template obtaining module 63 obtains the video template matching the product display scene and the product display data, and stores it in the video template library.
  • the display video production module 64 obtains display materials corresponding to the product display data; wherein, the display materials include: one or more of video files, sound files, image files, and text files.
  • the display video production module 64 determines the insertion position of the product display data and/or display material in the video template, inserts the product display data and/or display material into the corresponding insertion position, generates a product display video and stores it in the display video library.
  • the display data determination module 62 includes: a category acquisition unit 621 and a data extraction unit 622.
  • the category obtaining unit 621 determines the product display data category that the user is interested in based on the historical behavior information.
  • the data extraction unit 622 extracts product display data corresponding to the product display data category from the product page.
  • the category obtaining unit 621 obtains the number of times the user has viewed the historical product page and the number of clicks on the product information display area in the historical product page.
  • the category obtaining unit 621 obtains the user's click rate for each product information display area based on the number of clicks and the number of views.
  • the category acquisition unit 621 determines the product information display area that the user is interested in based on the click rate, and acquires the product display data category corresponding to the product information display area that the user is interested in.
  • the category acquisition unit 621 sorts the product information display areas according to the order of the click rate from high to low, and selects the first multiple product information display areas in the sorting result as the product information display areas of interest to the user.
  • Fig. 8 is a schematic diagram of modules of other embodiments of a video generating device according to the present disclosure.
  • the device may include a memory 81, a processor 82, a communication interface 83, and a bus 84.
  • the memory 81 is configured to store instructions
  • the processor 82 is coupled to the memory 81, and the processor 82 is configured to execute the above-mentioned video generation method based on the instructions stored in the memory 81.
  • the memory 81 may be a high-speed RAM memory, a non-volatile memory (non-volatile memory), etc., and the memory 81 may also be a memory array.
  • the memory 81 may also be divided into blocks, and the blocks may be combined into a virtual volume according to certain rules.
  • the processor 82 may be a central processing unit CPU, or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the video generation method of the present disclosure.
  • the present disclosure provides a terminal, including the video generation device in any of the above embodiments.
  • the terminal can be a mobile phone, a tablet computer, etc.
  • the present disclosure provides a computer-readable storage medium that stores computer instructions, and the instructions are executed by a processor to implement the video generation method in any of the above embodiments.
  • the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. .
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps configured to implement functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram.
  • the video generation method, device, terminal, and storage medium provided in the foregoing embodiments generate product display videos based on product display data and video templates on the terminal side, which can reduce the computing pressure on the server side and the pressure on the communication network; the efficiency of generating product display videos High, can be used in a variety of similar scenarios; product display data and materials are obtained by real-time analysis, which can ensure that the video content is consistent with the product page. When the product page changes, the product display video will also change accordingly; it can be combined with big data analysis for different Users generate different product display videos to achieve accurate playback and improve user satisfaction; through customizing templates and materials, it can meet customized scenarios and realize the shared use of storage templates and materials.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种视频生成方法、装置、终端以及存储介质，其中所述方法包括：在用户访问商品页面时，获取与商品页面展示的商品相对应的商品属性信息，基于商品属性信息确定商品展示场景（101）；获取用户的历史行为数据，基于历史行为数据获得商品展示数据（102）；根据商品展示场景和商品展示数据获取视频模板（103）；基于商品展示数据以及视频模板生成与商品相对应的商品展示视频并发送给客户（104）。所述方法、装置、终端以及存储介质，能够降低运算压力，生成商品展示视频的效率高，可运用于多种场景；商品展示数据和素材为实时分析获取，能够保证视频内容和商品页面一致，并可以为不同用户生成不同的商品展示视频，实现精准播放，提高用户的满意度。

Description

视频生成方法、装置、终端以及存储介质
相关申请的交叉引用
本公开是以CN申请号为201911125781.6申请日为2019年11月18日的申请为基础，并主张其优先权，该CN申请的公开内容在此作为整体引入本公开中。
技术领域
本公开涉及视频处理技术领域，尤其涉及一种视频生成方法、装置、终端以及存储介质。
背景技术
视频在电商和内容社区等领域得到广泛应用，相比静态的图文展示，视频更能吸引用户，提高用户的感知和理解。对提高网站的流量、转化率、用户回访率等都有很大的帮助。但是，当视频在电商等领域中应用时，会有多种问题。
发明内容
本公开的发明人发现上述相关技术中的视频生成的技术方案存在缺陷：视频在电商等领域中应用时会出现视频合成繁琐、更新困难，视频内容固定等问题。
根据本公开的第一方面，提供一种视频生成方法，包括：在用户访问商品页面时，获取与所述商品页面展示的商品相对应的商品属性信息，基于所述商品属性信息确定商品展示场景；获取所述用户的历史行为数据，基于所述历史行为数据获得商品展示数据；根据所述商品展示场景和所述商品展示数据获取视频模板；基于所述商品展示数据以及所述视频模板生成与所述商品相对应的商品展示视频。
在一些实施例中，所述商品属性信息包括：商品类别、商品特征信息；所述基于所述商品属性信息确定商品展示场景包括：确定与所述商品类别和所述商品特征信息相匹配的所述商品展示场景。
在一些实施例中，所述基于所述历史行为数据获得商品展示数据包括：根据所述历史行为信息确定所述用户感兴趣的商品展示数据类别；从所述商品页面中提取与所述商品展示数据类别相对应的所述商品展示数据。
在一些实施例中，所述根据所述历史行为信息确定所述用户感兴趣的商品展示数据类 别包括：获得所述用户对于历史商品页面的浏览次数，以及对于所述历史商品页面中的商品信息显示区域的点击次数；基于所述点击次数和所述浏览次数获得所述用户对每个商品信息显示区域的点击率；基于所述点击率确定所述用户感兴趣的商品信息显示区域，获取与所述用户感兴趣的商品信息显示区域对应的商品展示数据类别。
在一些实施例中，所述基于所述点击率确定所述用户感兴趣的商品信息显示区域包括：按照所述点击率由高到低的顺序，对全部商品信息显示区域进行排序；在排序结果中选择排列在最前的多个商品信息显示区域，作为所述用户感兴趣的商品信息显示区域。
在一些实施例中，所述根据所述商品展示场景和所述商品展示数据获取视频模板包括：判断在视频模板库中是否有与所述商品展示场景和所述商品展示数据相匹配的视频模板；如果是，则获取所述视频模板；如果否，则获取与所述商品展示场景相对应的视频模板，基于所述商品展示数据对此视频模板进行调整，获得与所述商品展示场景和所述商品展示数据相匹配的视频模板，并存储在所述视频模板库中。
在一些实施例中，所述基于所述商品展示数据以及所述视频模板生成与所述商品相对应的商品展示视频包括：获取与所述商品展示数据相对应的展示素材；其中，所述展示素材包括：视频文件、声音文件、图片文件和文字文件中的一种或多种；确定所述商品展示数据和/或所述展示素材在所述视频模板中的***位置；将所述商品展示数据和/或所述展示素材***相对应的所述***位置，生成所述商品展示视频并存储在展示视频库中。
在一些实施例中，如果判断在所述展示视频库中存储有与所述商品展示场景和所述商品展示数据相匹配的商品展示视频，或存储有与所述用户以及所述商品相对应的商品展示视频，则从所述展示视频库中获取此商品展示视频。
根据本公开的第二方面，提供一种视频生成装置，包括：展示场景确定模块，用于在用户访问商品页面时，获取与所述商品页面展示的商品相对应的商品属性信息，基于所述商品属性信息确定商品展示场景；展示数据确定模块，用于获取所述用户的历史行为数据，基于所述历史行为数据获得商品展示数据；视频模板获取模块，用于根据所述商品展示场景和所述商品展示数据获取视频模板；展示视频制作模块，用于基于所述商品展示数据以及所述视频模板生成与所述商品相对应的商品展示视频。
根据本公开的第三方面，提供一种视频生成装置，包括：存储器；以及耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行如上所述的方法。
根据本公开的第四方面，提供一种终端，包括：如上所述的视频生成装置。
根据本公开的第五方面，提供一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，所述指令被处理器执行如上所述的方法。
附图说明
为了更清楚地说明本公开实施例或相关技术中的技术方案，下面将对实施例或相关技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图仅仅是本公开的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为根据本公开的视频生成方法的一些实施例的流程示意图；
图2为根据本公开的视频生成方法中的获得商品展示数据的一些实施例的流程示意图；
图3A为根据本公开的视频生成方法中的确定用户感兴趣的商品展示数据类别的一些实施例的流程示意图；
图3B为从商品页面中获取商品展示数据的示意图；
图4为根据本公开的视频生成方法中的获取视频模板的一些实施例的流程示意图；
图5为根据本公开的视频生成方法中的生成商品展示视频的一些实施例的流程示意图；
图6为根据本公开的视频生成装置的一些实施例的模块示意图；
图7为根据本公开的视频生成装置中的展示数据确定模块的一些实施例的模块示意图；
图8为根据本公开的视频生成装置的另一些实施例的模块示意图。
具体实施方式
下面参照附图对本公开进行更全面的描述，其中说明本公开的示例性实施例。下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。基于本公开中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开保护的范围。下面结合各个图和实施例对本公开的技术方案进行多方面的描述。
发明人所知晓的相关技术中，当视频在电商等领域中应用时会有如下问题：视频合成繁琐：视频有专业人士录制和剪辑，需要准备大量的材料，等待时间也很长；更新困难： 视频一旦确认并制作出来，再想调整修改，只能重新录制合成，对于需要“及时响应的场景”无法适用；视频内容固定：所有用户看到视频都一样，不能根据不同用户，定制不同视频；为场景而定制：只能支持小部分定制场景，无法大范围、批量生产视频。因此，视频使用场景受到了很大限制。
有鉴于此，本公开的实施例提供了一种视频生成方法、装置、终端以及存储介质；本公开实施例的视频生成方法、装置、终端以及存储介质，基于商品展示数据以及视频模板生成商品展示视频，能够降低服务器端的运算压力以及通信网络的压力；生成商品展示视频的效率高，可运用于多种场景；商品展示数据和素材为实时分析获取，能够保证视频内容和商品页面一致，并可以为不同用户生成不同的商品展示视频，实现精准播放，提高用户的满意度。
图1为根据本公开的视频生成方法的一些实施例的流程示意图，如图1所示：
步骤101，在用户访问商品页面时，获取与商品页面展示的商品相对应的商品属性信息，基于商品属性信息确定商品展示场景。
在一些实施例中，商品页面可以为电商网站的商品页面等，商品可以为手机、酒、食品、衣服等。终端可以为手机、平板电脑等，可以通过安装在终端中的APP、浏览器、小程序等访问商品页面。终端可以对商品网页文件进行分析，获得与商品页面展示的商品属性信息，商品属性信息包括：商品类别、商品特征信息等；商品特征信息包括商品适用的用户、适用的场合、商品用途以及商品突出的优点等信息。
将商品与商品展示场景相结合，能够起到更好的宣传效果。商品展示场景包括对商品设计的故事情节、主人公、其他人员、故事发生的场景、氛围等。可以对商品展示场景进行编号，可以在终端侧基于商品属性信息确定商品展示场景，确定商品展示场景编号，也可以将商品属性信息发送到后台服务器，后台服务器返回商品展示场景编号。
步骤102，获取用户的历史行为数据，基于历史行为数据获得商品展示数据。
在一些实施例中，历史行为数据包括用户对于网页的点击、浏览等历史数据。商品展示数据包括：商品价格、商品规格、商品优惠、推荐商品、商品图片、用户上传视频等数据。
步骤103，根据商品展示场景和商品展示数据获取视频模板。
在一些实施例中，可以在终端侧根据商品展示场景和商品展示数据获取视频模板，也可以将商品展示场景信息(商品展示场景编号)和商品展示数据发送给后台服务器，后台服务器向终端发送相对应的视频模板。
步骤104，基于商品展示数据以及视频模板生成与商品相对应的商品展示视频。商品展示视频的视频类型可以为现有的多种视频类型。
展示视频库可以设置在后台服务器或云服务器等，用于存储商品展示视频。终端可以向后台服务器等发送查询请求，如果判断在展示视频库中存储有与商品展示场景和商品展示数据相匹配的商品展示视频，或存储有与用户以及商品相对应的商品展示视频，则从展示视频库中获取此商品展示视频。例如，从展示视频库下载商品展示视频到终端侧，进行播放。如果判断在展示视频库中没有存储与商品展示场景和商品展示数据相匹配的商品展示视频，或没有存储与用户以及商品相对应的商品展示视频，则终端生成新的商品展示视频并进行播放。
在一些实施例中，确定与商品类别和商品特征信息相匹配的商品展示场景。例如，商品为某某学习机，商品类别为学习机，商品特征信息包括适用于中学生等信息。基于商品属性信息确定商品展示场景为中学生使用学习机学习的场景，此商品展示场景的故事情节为一个中学生在遇到功课问题时，使用学习机解决了功课问题，此商品展示场景的主人公为一个中学生等。可以预先设置与商品属性信息相对应的商品展示场景以及商品展示场景编号，商品展示场景编号可以作为商品展示场景的唯一标识。
基于历史行为数据获得商品展示数据可以采用多种方法。图2为根据本公开的视频生成方法中的获得商品展示数据的一些实施例的流程示意图，如图2所示：
步骤201，根据历史行为信息确定用户感兴趣的商品展示数据类别。商品展示数据类别包括：商品价格、商品规格、商品优惠、推荐商品、商品图片、用户上传视频等数据类别。
步骤202，从商品页面中提取与商品展示数据类别相对应的商品展示数据。
在一些实施例中，可以对商品页面进行分析，在商品页面上提取与商品展示数据类别相对应的数据，作为商品展示数据。对商品页面进行分析可以采用现有的多种分析方法。
根据历史行为信息确定用户感兴趣的商品展示数据类别可以采用多种方法。图3A为根据本公开的视频生成方法中的确定用户感兴趣的商品展示数据类别的一些实施例的流程示意图，如图3所示：
步骤301，获得用户对于历史商品页面的浏览次数，以及对于历史商品页面中的商品信息显示区域的点击次数。
在一些实施例中，历史商品页面为用户浏览过的多个商品的商品页面。获取用户对于历史商品页面的浏览次数，以及对于历史商品页面中的商品信息显示区域的点击次数。如 图3B所示，商品信息显示区域包括商品页面中的商品价格区域、商品规格区域、商品优惠区域、推荐商品区域、商品图片区域、用户上传视频区域等区域。
步骤302，基于点击次数和浏览次数获得用户对每个商品信息显示区域的点击率。
例如，终端可以从后台服务器获取用户A对于历史商品页面的浏览次数为1000，获取用户A对于历史商品页面中的商品价格区域、商品规格区域、商品优惠区域的点击次数分别为200,100,500，则确定用户A对商品价格区域的点击率为200/1000＝0.2，确定用户A对商品规格区域的点击率为100/1000＝0.1，确定用户A对商品优惠区域的点击率为500/1000＝0.5。
步骤303，基于点击率确定用户感兴趣的商品信息显示区域，获取与用户感兴趣的商品信息显示区域对应的商品展示数据类别。
基于点击率确定用户感兴趣的商品信息显示区域可以使用多种方法。例如，按照点击率由高到低的顺序，对全部商品信息显示区域进行排序；在排序结果中选择排列在最前的多个商品信息显示区域，作为用户感兴趣的商品信息显示区域。
根据商品展示场景和商品展示数据获取视频模板可以使用多种方法。图4为根据本公开的视频生成方法中的获取视频模板的一些实施例的流程示意图，如图4所示：
步骤401，判断在视频模板库中是否有与商品展示场景和商品展示数据相匹配的视频模板；如果是，进入步骤402，如果否，进入步骤403。
在一些实施例中，视频模板库设置在后台服务器或云端服务器等。终端向后台服务器或云端服务器等发送查询请求(携带商品展示场景编号、商品展示数据信息等)，判断在视频模板库中是否有与商品展示场景和商品展示数据相匹配的视频模板。视频模板可以为现有的多种视频模板，视频模板中可以包括各种场景的分布，以及与商品对应的数据、图片、视频等在视频帧中的***位置等。
对视频模板设置对应的模板说明信息，模板说明信息包括：视频模板对应的商品以及商品展示场景、视频模板能够显示的商品展示信息等。服务器端可以根据模板说明信息判断是否存储有与商品展示场景和商品展示数据相匹配的视频模板。
步骤402，获取视频模板。例如，终端可以从视频模板库下载视频模板以及模板说明信息。
步骤403，获取与商品展示场景相对应的视频模板，基于商品展示数据对此视频模板进行调整，获得与商品展示场景和商品展示数据相匹配的视频模板，并存储在视频模板库中。
在一些实施例中，在视频模板库中预先设置与商品展示场景相对应的视频模板，如果判断在视频模板库中没有与商品展示场景和商品展示数据相匹配的视频模板，则将与商品展示场景相对应的视频模板进行调整。对视频模板进行调整包括增加或减少视频模板能够显示的商品展示信息等，并生成对应的模板说明信息，对视频模板进行调整可以采用现有的多种方法。在对与商品展示场景相对应的视频模板进行调整后，获得与商品展示场景和商品展示数据相匹配的视频模板以及模板说明信息，并存储在视频模板库中。
基于商品展示数据以及视频模板生成与商品相对应的商品展示视频可以采用多种方法。图5为根据本公开的视频生成方法中的生成商品展示视频的一些实施例的流程示意图，如图5所示：
步骤501，获取与商品展示数据相对应的展示素材。
在一些实施例中，展示素材包括：视频文件、声音文件、图片文件和文字文件中的一种或多种。素材库可以设置在后台服务器或云端服务器，商品展示数据可以为商品价格、商品规格、商品优惠、推荐商品、商品图片、用户上传视频等，终端可以请求后台服务器或云端服务器在素材库中获取与一个或多个商品展示数据相对应的视频、声音、图片或文字等，并返回给终端。如果没有相关的素材，则终端将相关的素材上传到素材库。
步骤502，确定商品展示数据和/或展示素材在视频模板中的***位置。
步骤503，将商品展示数据和/或展示素材***相对应的***位置，生成商品展示视频并存储在展示视频库中。
在一些实施例中，视频模板中预留有商品展示数据或展示素材以及商品展示数据和展示素材的***位置，基于视频模板的模板说明信息将商品展示数据或展示素材以及商品展示数据和展示素材的***相对应的位置，生成商品展示视频。基于视频模板生成视频可以使用现有的多种方法。商品展示视频可以为Canvas视频等，将数据、模版、素材结合，通过Canvas动画展示视频。将动画合成传统的视频格式，并上传视频库。
上述实施例中的视频生成方法，在终端侧基于商品展示数据以及视频模板生成商品展示视频，能够降低服务器端的运算压力以及通信网络的压力；生成商品展示视频的效率高，可运用于多种类似场景；商品展示数据和素材为实时分析获取，能够保证视频内容和商品页面一致，商品页面变化时商品展示视频也进行相应地变化；可以结合大数据分析，为不同用户生成不同的商品展示视频，实现精准播放，提高用户的满意度；通过定制模版和素材，能够满足定制的场景，并且存储模版和素材，能够共享使用。
在一些实施例中，如图6所示，本公开提供一种视频生成装置60，包括：展示场景确 定模块61、展示数据确定模块62、视频模板获取模块63、展示视频制作模块64和展示视频获取模块65。
展示场景确定模块61在用户访问商品页面时，获取与商品页面展示的商品相对应的商品属性信息，基于商品属性信息确定商品展示场景。展示数据确定模块62获取用户的历史行为数据，基于历史行为数据获得商品展示数据。视频模板获取模块63根据商品展示场景和商品展示数据获取视频模板。展示视频制作模块64基于商品展示数据以及视频模板生成与商品相对应的商品展示视频。
在一些实施例中，展示视频获取模块65如果判断在展示视频库中存储有与商品展示场景和商品展示数据相匹配的商品展示视频，或存储有与用户以及商品相对应的商品展示视频，则从展示视频库中获取此商品展示视频。
商品属性信息包括：商品类别、商品特征信息等；展示场景确定模块61确定与商品类别和商品特征信息相匹配的商品展示场景。视频模板获取模块63判断在视频模板库中是否有与商品展示场景和商品展示数据相匹配的视频模板；如果是，则视频模板获取模块63获取视频模板；如果否，则视频模板获取模块63获取与商品展示场景相对应的视频模板，基于商品展示数据对此视频模板进行调整，视频模板获取模块63获得与商品展示场景和商品展示数据相匹配的视频模板，并存储在视频模板库中。
展示视频制作模块64获取与商品展示数据相对应的展示素材；其中，展示素材包括：视频文件、声音文件、图片文件和文字文件中的一种或多种。展示视频制作模块64确定商品展示数据和/或展示素材在视频模板中的***位置，将商品展示数据和/或展示素材***相对应的***位置，生成商品展示视频并存储在展示视频库中。
在一些实施例中，如图7所示，展示数据确定模块62包括：类别获取单元621和数据提取单元622。类别获取单元621根据历史行为信息确定用户感兴趣的商品展示数据类别。数据提取单元622从商品页面中提取与商品展示数据类别相对应的商品展示数据。
类别获取单元621获得用户对于历史商品页面的浏览次数，以及对于历史商品页面中的商品信息显示区域的点击次数。类别获取单元621基于点击次数和浏览次数获得用户对每个商品信息显示区域的点击率。类别获取单元621基于点击率确定用户感兴趣的商品信息显示区域，获取与用户感兴趣的商品信息显示区域对应的商品展示数据类别。
例如，类别获取单元621按照点击率由高到低的顺序，对商品信息显示区域进行排序，在排序结果中选择排列在最前的多个商品信息显示区域，作为用户感兴趣的商品信息显示区域。
图8为根据本公开的视频生成装置的另一些实施例的模块示意图。如图8所示，该装置可包括存储器81、处理器82、通信接口83以及总线84。存储器81用于存储指令，处理器82耦合到存储器81，处理器82被配置为基于存储器81存储的指令执行实现上述的视频生成方法。
存储器81可以为高速RAM存储器、非易失性存储器(non-volatile memory)等，存储器81也可以是存储器阵列。存储器81还可能被分块，并且块可按一定的规则组合成虚拟卷。处理器82可以为中央处理器CPU，或专用集成电路ASIC(Application Specific Integrated Circuit)，或者是被配置成实施本公开的视频生成方法的一个或多个集成电路。
在一些实施例中，本公开提供一种终端，包括如上任一实施例中的视频生成装置。终端可以为手机、平板电脑等。
在一些实施例中，本公开提供一种计算机可读存储介质，计算机可读存储介质存储有计算机指令，指令被处理器执行时实现如上任一些实施例中的视频生成方法。
本领域内的技术人员应当明白，本公开的实施例可提供为方法、***、或计算机程序产品。因此，本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用非瞬时性存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开是参照根据本公开实施例的方法、设备(***)和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他 可编程设备上执行的指令提供被配置为实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
上述实施例中提供的视频生成方法、装置、终端以及存储介质，在终端侧基于商品展示数据以及视频模板生成商品展示视频，能够降低服务器端的运算压力以及通信网络的压力；生成商品展示视频的效率高，可运用于多种类似场景；商品展示数据和素材为实时分析获取，能够保证视频内容和商品页面一致，商品页面变化时商品展示视频也进行相应地变化；可以结合大数据分析，为不同用户生成不同的商品展示视频，实现精准播放，提高用户的满意度；通过定制模版和素材，能够满足定制的场景，并且实现存储模版和素材的共享使用。
本公开的描述是为了示例和描述起见而给出的，而并不是无遗漏的或者将本公开限于所公开的形式。很多修改和变化对于本领域的普通技术人员而言是显然的。选择和描述实施例是为了更好说明本公开的原理和实际应用，并且使本领域的普通技术人员能够理解本公开从而设计适于特定用途的带有各种修改的各种实施例。

Claims (12)

  1. 一种视频生成方法，包括：
    在用户访问商品页面时，获取与所述商品页面展示的商品相对应的商品属性信息，基于所述商品属性信息确定商品展示场景；
    获取所述用户的历史行为数据，基于所述历史行为数据获得商品展示数据；
    根据所述商品展示场景和所述商品展示数据获取视频模板；
    基于所述商品展示数据以及所述视频模板生成与所述商品相对应的商品展示视频。
  2. 如权利要求1所述的方法，所述商品属性信息包括：商品类别、商品特征信息；所述基于所述商品属性信息确定商品展示场景包括：
    确定与所述商品类别和所述商品特征信息相匹配的所述商品展示场景。
  3. 如权利要求2所述的方法，所述基于所述历史行为数据获得商品展示数据包括：
    根据所述历史行为信息确定所述用户感兴趣的商品展示数据类别；
    从所述商品页面中提取与所述商品展示数据类别相对应的所述商品展示数据。
  4. 如权利要求3所述的方法，所述根据所述历史行为信息确定所述用户感兴趣的商品展示数据类别包括：
    获得所述用户对于历史商品页面的浏览次数，以及对于所述历史商品页面中的商品信息显示区域的点击次数；
    基于所述点击次数和所述浏览次数获得所述用户对每个商品信息显示区域的点击率；
    基于所述点击率确定所述用户感兴趣的商品信息显示区域，获取与所述用户感兴趣的商品信息显示区域对应的商品展示数据类别。
  5. 如权利要求4所述的方法，所述基于所述点击率确定所述用户感兴趣的商品信息显示区域包括：
    按照所述点击率由高到低的顺序，对全部商品信息显示区域进行排序；
    在排序结果中选择排列在最前的多个商品信息显示区域，作为所述用户感兴趣的商品信息显示区域。
  6. 如权利要求1所述的方法，所述根据所述商品展示场景和所述商品展示数据 获取视频模板包括：
    判断在视频模板库中是否有与所述商品展示场景和所述商品展示数据相匹配的视频模板；
    如果是，则获取所述视频模板；如果否，则获取与所述商品展示场景相对应的视频模板，基于所述商品展示数据对此视频模板进行调整，获得与所述商品展示场景和所述商品展示数据相匹配的视频模板，并存储在所述视频模板库中。
  7. 如权利要求1所述的方法，所述基于所述商品展示数据以及所述视频模板生成与所述商品相对应的商品展示视频包括：
    获取与所述商品展示数据相对应的展示素材；其中，所述展示素材包括：视频文件、声音文件、图片文件和文字文件中的一种或多种；
    确定所述商品展示数据和/或所述展示素材在所述视频模板中的***位置；
    将所述商品展示数据和/或所述展示素材***相对应的所述***位置，生成所述商品展示视频并存储在展示视频库中。
  8. 如权利要求7所述的方法，还包括：
    如果判断在所述展示视频库中存储有与所述商品展示场景和所述商品展示数据相匹配的商品展示视频，或存储有与所述用户以及所述商品相对应的商品展示视频，则从所述展示视频库中获取此商品展示视频。
  9. 一种视频生成装置，包括：
    展示场景确定模块，用于在用户访问商品页面时，获取与所述商品页面展示的商品相对应的商品属性信息，基于所述商品属性信息确定商品展示场景；
    展示数据确定模块，用于获取所述用户的历史行为数据，基于所述历史行为数据获得商品展示数据；
    视频模板获取模块，用于根据所述商品展示场景和所述商品展示数据获取视频模板；
    展示视频制作模块，用于基于所述商品展示数据以及所述视频模板生成与所述商品相对应的商品展示视频。
  10. 一种视频生成装置，包括：
    存储器；以及耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器中的指令，执行如权利要求1至8中任一项所述的方法。
  11. 一种终端，包括：
    如权利要求9或10所述的视频生成装置。
  12. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机指令，所述指令被处理器执行如权利要求1至8中任一项所述的方法。
PCT/CN2020/110278 2019-11-18 2020-08-20 视频生成方法、装置、终端以及存储介质 WO2021098310A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/770,583 US20220383381A1 (en) 2019-11-18 2020-08-20 Video generation method, apparatus, terminal and storage medium
EP20891050.5A EP4033438A4 (en) 2019-11-18 2020-08-20 VIDEO GENERATION METHOD AND DEVICE AND TERMINAL AND STORAGE MEDIUM

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911125781.6A CN111784431B (zh) 2019-11-18 视频生成方法、装置、终端以及存储介质
CN201911125781.6 2019-11-18

Publications (1)

Publication Number Publication Date
WO2021098310A1 true WO2021098310A1 (zh) 2021-05-27

Family

ID=72755770

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/110278 WO2021098310A1 (zh) 2019-11-18 2020-08-20 视频生成方法、装置、终端以及存储介质

Country Status (3)

Country Link
US (1) US20220383381A1 (zh)
EP (1) EP4033438A4 (zh)
WO (1) WO2021098310A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114428899A (zh) * 2021-12-17 2022-05-03 北京达佳互联信息技术有限公司 多媒体资源推送方法、装置、电子设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110060647A1 (en) * 2005-10-31 2011-03-10 Troy David Weaver Computer implemented method for marketing business serves
CN104731960A (zh) * 2015-04-03 2015-06-24 北京威扬科技有限公司 基于电子商务网页内容生成视频摘要的方法、装置及***
CN110418196A (zh) * 2019-08-29 2019-11-05 金瓜子科技发展（北京）有限公司 视频生成方法、装置及服务器

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8832226B2 (en) * 2011-10-10 2014-09-09 Eyeview, Inc. Using cloud computing for generating personalized dynamic and broadcast quality videos
US20130326354A1 (en) * 2012-06-01 2013-12-05 James Anderson Systems and Methods for Selection and Personalization of Content Items
US10694222B2 (en) * 2016-01-07 2020-06-23 Microsoft Technology Licensing, Llc Generating video content items using object assets

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110060647A1 (en) * 2005-10-31 2011-03-10 Troy David Weaver Computer implemented method for marketing business serves
CN104731960A (zh) * 2015-04-03 2015-06-24 北京威扬科技有限公司 基于电子商务网页内容生成视频摘要的方法、装置及***
CN110418196A (zh) * 2019-08-29 2019-11-05 金瓜子科技发展（北京）有限公司 视频生成方法、装置及服务器

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114428899A (zh) * 2021-12-17 2022-05-03 北京达佳互联信息技术有限公司 多媒体资源推送方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
EP4033438A1 (en) 2022-07-27
CN111784431A (zh) 2020-10-16
EP4033438A4 (en) 2023-10-04
US20220383381A1 (en) 2022-12-01

Similar Documents

Publication Publication Date Title
US11023545B2 (en) Method and device for displaying recommended contents
KR101511050B1 (ko) 상품 정보를 제공하고 표시하는 방법, 장치, 시스템 및 컴퓨터 프로그램
TWI648642B (zh) Data search processing method and system
US9507480B1 (en) Interface optimization application
CN108573515B (zh) 一种合图生成方法及装置、合图模板生成方法及装置
CN105989004A (zh) 一种信息投放的预处理方法和装置
TW201723960A (zh) 提供業務對象資訊的方法及裝置
US20180157763A1 (en) System and method for generating an electronic page
CN111752557A (zh) 一种展示方法及装置
US20120229391A1 (en) System and methods for generating interactive digital books
Vempati et al. Enabling hyper-personalisation: Automated ad creative generation and ranking for fashion e-commerce
US11308262B2 (en) Systems and methods for converting static image online content to dynamic online content
CN112102445B (zh) 楼盘海报制作方法、装置、设备及计算机可读存储介质
US9471558B2 (en) Generation of introductory information page
WO2020063844A1 (zh) 一种推荐关联信息的方法及其终端、服务器
WO2021098310A1 (zh) 视频生成方法、装置、终端以及存储介质
CN113763009A (zh) 一种图片处理方法、图片跳转方法、装置、设备和介质
CN111475664A (zh) 对象展示方法、装置及电子设备
KR101697290B1 (ko) 웹 브라우저에서 구현되는 웹사이트 제작 방법 및 시스템
CN111782309B (zh) 显示信息的方法、装置及计算机可读存储介质
KR102224782B1 (ko) 지역 콘텐츠 관리 서비스 제공 시스템
CN111784431B (zh) 视频生成方法、装置、终端以及存储介质
CN111966428A (zh) 页面处理方法及装置、页面回溯方法及装置
KR102580126B1 (ko) 영업활동지원을 위한 통합 모바일 플랫폼 서비스 제공 시스템
CA3075233A1 (en) Generating sequential visual narratives

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20891050

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020891050

Country of ref document: EP

Effective date: 20220421

NENP Non-entry into the national phase

Ref country code: DE