Applet-based video recommendation method and device, equipment and storage medium

Abstract

The application relates to the field of video recommendation, and discloses a video recommendation method and device based on a small program, equipment and a storage medium. The method comprises the following steps: querying a target account based on an API interface of a video software; receiving a small program screening instruction, and mounting a target small program corresponding to the small program screening instruction to the target account; extracting video data in the target small program, and publishing the video data in the target account. In the embodiment of the application, the video content attached in the small program is screened and published in the selected video software account, the accuracy and benefit of the recommended video are improved, and the income of the creator and the video spreading range are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of video recommendation, and in particular to a video recommendation method and device based on a small program, an equipment and a storage medium. BACKGROUND

[0002] With the development of short videos, creators have strong demand for short video monetization, and the most recognized short video monetization is using advertising monetization. Advertising monetization can be achieved by mounting a small program in a video work, guiding users to click on the small program, and users obtaining the use rights and interests of the small program by watching advertising content, and then short video creators can obtain benefits.

[0003] However, the conversion rate of the small program mounting is related to the video content of the creator, the fan portrait, the copy guidance and the recommendation mechanism of the Douyin platform. The existing technology does not correlate the relationship between the content of the small program and the recommendation mechanism of the platform, and the correlation between the video platform account and the small program video is not high, resulting in the inability of the creator to effectively increase the benefits, and therefore a new technology is needed to solve the current problem. SUMMARY

[0004] The main purpose of the present application is to solve the technical problem that the correlation between the video platform account and the small program video is not high, resulting in the inability of the creator to effectively increase the benefits.

[0005] The first aspect of the present application provides a video recommendation method based on a small program, which comprises:

[0006] querying a target account based on the API interface of the video software;

[0007] receiving a small program filtering instruction, and mounting a target small program corresponding to the small program filtering instruction in the target account;

[0008] extracting video data in the target small program, and publishing the video data in the target account.

[0009] Optionally, in the first implementation manner of the first aspect of the present application, the receiving a small program filtering instruction, and mounting a target small program corresponding to the small program filtering instruction in the target account comprises:

[0010] receiving a parameter filtering instruction, performing parameter filtering processing in the preset small program database, and obtaining a preliminary filtering set;

[0011] receiving a keyword filtering instruction, performing keyword matching processing in the preliminary filtering set, and obtaining a target small program with a keyword.

[0012] Optionally, in a second implementation form of the first aspect of the present application, the parameter screening instruction comprises: an advertisement revenue efficiency parameter, an AI face changing type proportion value, and a recommendation matching degree.

[0013] Optionally, in a third implementation form of the first aspect of the present application, after receiving the applet screening instruction and mounting the target account with the target applet corresponding to the applet screening instruction, before extracting the video data in the target applet and publishing the video data in the target account, the method further comprises:

[0014] receiving a publishing script, and performing semantic screening processing on all video data in the target applet according to the publishing script and a preset semantic recognition algorithm to obtain screened video data.

[0015] Optionally, in a fourth implementation form of the first aspect of the present application, the extracting the video data in the target applet and publishing the video data in the target account comprises:

[0016] extracting the screened video data in the target applet, and publishing the screened video data in combination with the publishing script in the target account.

[0017] Optionally, in a fifth implementation form of the first aspect of the present application, the extracting the screened video data in the target applet and publishing the screened video data in combination with the publishing script in the target account comprises:

[0018] reading a video type proportion setting of the target account;

[0019] extracting the screened video data in the target applet, and judging whether the screened video data meets the video type proportion setting;

[0020] if the screened video data meets the video type proportion setting, publishing the screened video data in combination with the publishing script in the target account;

[0021] if the screened video data does not meet the video type proportion setting, reextracting the screened video data in the target applet.

[0022] Optionally, in a sixth implementation form of the first aspect of the present application, the extracting the video data in the target applet and publishing the video data in the target account comprises:

[0023] extracting the video data in the target applet and publishing the video data in the target account based on a preset setting publishing period.

[0024] The second aspect of the present application provides a mini-program-based video recommendation device, the mini-program-based video recommendation device comprises:

[0025] The query module is configured to query a target account based on an API interface of a video software.

[0026] The mounting module is configured to receive a mini-program filtering instruction and mount a target mini-program corresponding to the mini-program filtering instruction in the target account.

[0027] The extraction and publishing module is configured to extract video data in the target mini-program and publish the video data in the target account.

[0028] The third aspect of the present application provides a mini-program-based video recommendation device, comprising a memory and at least one processor, the memory stores instructions, and the memory and the at least one processor are interconnected by a circuit; the at least one processor calls the instructions in the memory, so that the mini-program-based video recommendation device executes the above-mentioned mini-program-based video recommendation method.

[0029] The fourth aspect of the present application provides a computer-readable storage medium, the computer-readable storage medium stores instructions, when the instructions are run on a computer, the computer executes the above-mentioned mini-program-based video recommendation method.

[0030] In the embodiment of the present application, the mounting recommendation of the TikTok mini-program is performed according to the video content of the creator and the fan portrait of the TikTok account, so as to improve the conversion rate of the creator video mounting the mini-program, improve the income of the short video monetization, and solve the technical problem that the correlation between the video platform account and the mini-program video is not high, so that the income of the creator cannot be effectively increased. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 An embodiment of the mini-program-based video recommendation method in the embodiment of the present application is shown in the figure;

[0032] Figure 2 An embodiment of the mini-program-based video recommendation device in the embodiment of the present application is shown in the figure;

[0033] Figure 3 Another embodiment of the mini-program-based video recommendation device in the embodiment of the present application is shown in the figure;

[0034] Figure 4 An embodiment of the mini-program-based video recommendation device in the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0035] The embodiment of the present application provides a video recommendation method and device based on a small program, equipment and a storage medium.

[0036] The terms "first", "second", "third", "fourth" and the like in the description, claims, as well as the above-mentioned drawings (if any) of the present application are used to distinguish similar objects, and do not necessarily have to be described in a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] For the sake of understanding, the specific flow of the embodiment of the present application is described below, please refer to Figure 1 One embodiment of the video recommendation method based on the small program in the embodiment of the present application comprises:

[0038] 101, querying a target account based on the API interface of the video software;

[0039] In this embodiment, the API interface provided by Douyin or other video software is used to query the relevant data of the account with the id of the Douyin account, for example, account diagnosis data, fan gender ratio, fan age range, fan favorite video content, fan attention source, fan interest distribution, fan favorite keywords and the like.

[0040] 102, receiving a small program screening instruction, and mounting the target small program corresponding to the small program screening instruction on the target account;

[0041] In this embodiment, the video of the small program that needs to be mounted in the associated Douyin account is selected, the keywords of the video content are input, for example, face changing, dressing, ancient style, beautiful women, special effects, classic characters and a series of keywords, and the target small program is selected with the keywords.

[0042] Further, the following steps can be performed in step 102:

[0043] 1021, receiving a parameter screening instruction, performing parameter screening processing in the preset small program database to obtain a preliminary screening set;

[0044] 1022, receiving a keyword screening instruction, performing keyword matching processing in the preliminary screening set to obtain a target small program with keywords.

[0045] In the steps 1021-1022, the parameter screening instruction includes: an advertisement revenue efficiency parameter, an AI face changing type proportion value, and a recommendation matching degree. The ECPM (effective cost per mille, which refers to the advertisement revenue obtained per thousand displays), type, and recommendation matching degree are set, for example: the ecpm is set to 180, the AI face changing type proportion is set to 80%, and the recommendation matching degree is set to 80%.

[0046] Then, a series of keywords such as face changing, dressing, ancient style, beautiful women, special effects, and classic characters are inputted, and the target applet is selected by the applet selection with the keywords.

[0047] Further, after 102, before 103, the following steps can be performed:

[0048] 1023, receiving a publishing script, performing semantic screening processing on all video data in the target applet according to the publishing script and a preset semantic recognition algorithm, and obtaining screened video data.

[0049] In the step 1023, for example, the publishing script “Flowers bloom and wither for thousands of years, my love for you will never change” is inputted, the semantics of “Flowers bloom and wither for thousands of years, my love for you will never change” are recognized, and then the video data in the target applet are screened for the features of “male and female”, “flowers”, and “ancient style” to obtain the screened video data.

[0050] 103, extracting video data in the target applet and publishing the video data in the target account.

[0051] In this embodiment, the video data is grabbed from the applets that meet a series of keywords such as face changing, dressing, ancient style, beautiful women, special effects, and classic characters, and is published in the account of the Douyin or other video platforms. The applets with matching video content and the corresponding mounting cases are screened from a series of applets, the creator can view the mounting cases of the corresponding applets in the list of alternative applets, publish the video works mounted with the applets on the Douyin platform, and match the related guide scripts.

[0052] Further, under the premise of 1023, 103 can perform the following steps:

[0053] 1031, extracting the screened video data in the target applet, combining the screened video data with the publishing script, and publishing the combination in the target account.

[0054] In this embodiment, the screened video data is combined with the script “Flowers bloom and wither for thousands of years, my love for you will never change” and published in the account of the Douyin or other video platforms.

[0055] Further, the following steps can also be performed at 1031:

[0056] 10311、Read the video type proportion setting of the target account;

[0057] 10312、Extract the filtered video data in the target mini-program, and determine whether the filtered video data meets the video type proportion setting;

[0058] 10313、If the video type proportion setting is met, the filtered video data and the publishing script are combined and published in the target account;

[0059] 10314、If the video type proportion setting is not met, the filtered video data in the target mini-program is re-extracted.

[0060] In steps 10311-10314, the video type proportion setting of the target account is a percentage, for example: AI type accounts for 10%, face changing type accounts for 10%, AI face changing type accounts for 10%, AI intelligent type accounts for 8%, dressing type accounts for 10%, face changing type accounts for 10%, ancient style type accounts for 5%, beautiful type accounts for 8%, etc. Read the type of the filtered video data of the currently selected target mini-program, and determine whether the publishing of the video exceeds the video type proportion setting of the target account. If it does not exceed, the filtered video data and the publishing script are combined and published in the target account. If it exceeds the proportion, other types of video need to be re-selected from the mini-program to meet the operation and positioning needs of the account.

[0061] Further, the following steps can also be performed at 103:

[0062] 1032、Based on the preset publishing period, extract the video data in the target mini-program, and publish the video data in the target account.

[0063] In step 1032, the video data in the target mini-program is extracted according to the set publishing period, for example, every 24 hours or 12 hours, and then published in the target account, achieving the effect of fixed video library and publishing time for mini-program made videos.

[0064] In the embodiments of the present application, the mounting recommendation of the Douyin mini-program is made according to the video content of the creator and the fan portrait of the Douyin account, so as to improve the conversion rate of the creator video mounting the mini-program and improve the income of the short video monetization, solving the technical problem that the correlation between the video platform account and the mini-program video is not high, resulting in the inability to effectively increase the income of the creator.

[0065] The video recommendation method based on the applet in the embodiment of the application is described above, and the video recommendation device based on the applet in the embodiment of the application is described below. Please refer to Figure 2 The video recommendation device based on the applet in the embodiment of the application includes:

[0066] The query module 201 is configured to query a target account based on an API interface of a video software.

[0067] The mounting module 202 is configured to receive an applet screening instruction and mount a target applet corresponding to the applet screening instruction in the target account.

[0068] The extraction and publishing module 203 is configured to extract video data in the target applet and publish the video data in the target account.

[0069] In the embodiment of the application, the mounting recommendation of the TikTok applet is performed according to the video content of the creator and the fan portrait of the TikTok account of the creator, so as to improve the conversion rate of the creator video mounting the applet and improve the income of the short video monetization. The technical problem that the correlation between the video platform account and the applet video is not high, so that the income of the creator cannot be effectively increased is solved.

[0070] Please refer to Figure 3 Another embodiment of the video recommendation device based on the applet in the embodiment of the application includes:

[0071] The query module 201 is configured to query a target account based on an API interface of a video software.

[0072] The mounting module 202 is configured to receive an applet screening instruction and mount a target applet corresponding to the applet screening instruction in the target account.

[0073] The extraction and publishing module 203 is configured to extract video data in the target applet and publish the video data in the target account.

[0074] The mounting module 202 is specifically configured to:

[0075] Receive a parameter screening instruction, perform parameter screening processing in a preset applet database, and obtain a preliminary screening set.

[0076] Receive a keyword screening instruction, perform keyword matching processing in the preliminary screening set, and obtain a target applet with a keyword.

[0077] The video recommendation device based on the applet further includes a video screening module 204, which is specifically configured to:

[0078] receive a publishing script, and perform semantic filtering processing on all video data in the target applet according to the publishing script and a preset semantic recognition algorithm to obtain filtered video data.

[0079] The video filtering module 204 can be specifically configured to:

[0080] extract the filtered video data in the target applet, and publish the filtered video data in combination with the publishing script in the target account.

[0081] The video filtering module 204 can be specifically configured to:

[0082] read a video type proportion setting of the target account;

[0083] extract the filtered video data in the target applet, and determine whether the filtered video data meets the video type proportion setting;

[0084] if the video type proportion setting is met, publish the filtered video data in combination with the publishing script in the target account;

[0085] if the video type proportion setting is not met, re-extract the filtered video data in the target applet.

[0086] The extraction and publishing module 203 can be specifically configured to:

[0087] extract video data in the target applet based on a preset setting publishing period, and publish the video data in the target account.

[0088] In the embodiment of the application, the mounting recommendation of the TikTok applet is performed according to the video content of the creator and the fan portrait of the TikTok account of the creator, so as to improve the conversion rate of the creator video mounting the applet and improve the income of the short video monetization, and solve the technical problem that the correlation between the video platform account and the applet video is not high, so that the income of the creator cannot be effectively increased.

[0089] The above Figure 2 and Figure 3 The video recommendation device based on the applet in the embodiment of the application is described in detail from the perspective of the modular functional entity, and the video recommendation device based on the applet in the embodiment of the application is described in detail from the perspective of hardware processing.

[0090] Figure 4is a structural schematic diagram of a video recommendation device based on a small program provided by an embodiment of the present application. The video recommendation device based on a small program 400 can have great differences due to different configurations or performances, and can include one or more processors (central processing units, CPUs) 410 (for example, one or more processors) and a memory 420, one or more storage media 430 (for example, one or more mass storage devices) for storing application programs 433 or data 432. Among them, the memory 420 and the storage medium 430 can be temporary storage or persistent storage. The programs stored in the storage medium 430 can include one or more modules (not shown in the figure), and each module can include a series of instruction operations in the video recommendation device based on a small program 400. Further, the processor 410 can be configured to communicate with the storage medium 430 and execute a series of instruction operations in the storage medium 430 on the video recommendation device based on a small program 400.

[0091] The video recommendation device based on a small program 400 can also include one or more power supplies 440, one or more wired or wireless network interfaces 450, one or more input and output interfaces 460, and / or one or more operating systems 431, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art can understand that, Figure 4 The video recommendation device based on a small program structure shown does not constitute a limitation on the video recommendation device based on a small program, and can include more or fewer components than shown, or combine certain components, or different component arrangements.

[0092] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium, and can also be a volatile computer readable storage medium. The computer readable storage medium has instructions stored therein, and when the instructions are run on a computer, the computer executes the steps of the video recommendation method based on a small program.

[0093] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system or device, unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0094] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0095] The above description and the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features. These modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for video recommendation based on applet, characterized in that, The method comprises the steps of: querying a target account based on an API interface of video software; receiving a mini-program screening instruction and mounting the target account on a target mini-program corresponding to the mini-program screening instruction; extracting video data in the target mini-program and publishing the video data in the target account; wherein, after the receiving of the mini-program screening instruction and the mounting of the target account on the target mini-program corresponding to the mini-program screening instruction, before the extracting of the video data in the target mini-program and the publishing of the video data in the target account, the method further comprises: receiving a publishing script, performing semantic screening processing on all video data in the target mini-program according to the publishing script and a preset semantic recognition algorithm, and obtaining screened video data; wherein, the extracting of the video data in the target mini-program and the publishing of the video data in the target account comprises: reading a video type proportion setting of the target account; extracting the screened video data in the target mini-program and judging whether the screened video data meets the video type proportion setting; if the video type proportion setting is met, combining and publishing the screened video data and the publishing script in the target account; if the video type proportion setting is not met, reextracting the screened video data in the target mini-program.

2. The applet-based video recommendation method of claim 1, wherein, The receiving of the mini-program screening instruction and the mounting of the target account on the target mini-program corresponding to the mini-program screening instruction comprises: receiving a parameter screening instruction, performing parameter screening processing in a preset mini-program database, and obtaining a preliminary screening set; receiving a keyword screening instruction, performing keyword matching processing in the preliminary screening set, and obtaining a target mini-program with a keyword. 3.The applet-based video recommendation method of claim 2, wherein, The parameter screening instruction comprises an advertising revenue efficiency parameter, an AI face changing type proportion value, and a recommendation matching degree. 4.The applet-based video recommendation method of claim 1, wherein, The extracting of the video data in the target mini-program and the publishing of the video data in the target account comprises: extracting the video data in the target mini-program and publishing the video data in the target account based on a preset setting publishing period.

5. An applet-based video recommendation apparatus, characterized by comprising: The video recommendation device based on a mini-program comprises: a query module configured to query a target account based on an API interface of video software; a mounting module configured to receive a mini-program screening instruction and mount the target account on a target mini-program corresponding to the mini-program screening instruction; an extraction and publishing module configured to extract video data in the target mini-program and publish the video data in the target account; wherein, the video recommendation device based on a mini-program further comprises a video screening module, and the video screening module is specifically configured to: receive a publishing script, perform semantic screening processing on all video data in the target mini-program according to the publishing script and a preset semantic recognition algorithm, and obtain screened video data; wherein, the video screening module can be specifically configured to: read a video type proportion setting of the target account; extract the screened video data in the target mini-program and judge whether the screened video data meets the video type proportion setting; If the video type proportion setting is met, the filtered video data is combined with the publishing script and published in the target account; If the video type proportion setting is not met, the filtered video data in the target applet is re-extracted.

6. A widget-based video recommendation device, characterized by, The applet-based video recommendation device comprises a memory and at least one processor, the memory has instructions stored therein, and the memory and the at least one processor are interconnected by a circuit; The at least one processor invokes the instructions in the memory to enable the applet-based video recommendation device to perform the applet-based video recommendation method according to any one of claims 1-4.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program is executed by a processor to implement the applet-based video recommendation method according to any one of claims 1-4.

Images