A method, device, equipment and storage medium for automatically rewarding store exploration videos

Abstract

The present application relates to a method, device, equipment and storage medium for automated rewarding of store exploration videos, the method comprising obtaining registered user information based on a user registration digital link, and sending a video publishing digital link to the user corresponding to the registered user information, wherein the video publishing digital link is bound to a unique video identifier; when a user publishes a store exploration video through the video publishing digital link, an association relationship between the registered user information and the store exploration video is established based on the unique video identifier; based on the association relationship, the store exploration video status corresponding to the registered user information is monitored in real time to obtain store exploration video data; based on the association relationship, the store exploration video data is compared with preset reward conditions to determine whether the reward conditions are met, and if the determination is yes, a reward is sent to the user corresponding to the registered user information based on the preset reward target of the corresponding reward condition. The present application has the effect of improving the accuracy of automated rewarding of store exploration videos.

Description

Technical Field

[0001] The present invention relates to the technical field of automated rewards, and in particular to a method, device, equipment and storage medium for automated rewards for store exploration videos. Background Art

[0002] At present, under the traditional store exploration model, merchants are faced with the problems of high costs and low efficiency. For example, store exploration activities usually require sending professional store explorers to physical stores for on-site inspections and to shoot videos or write reports. In this process, merchants need to bear the store explorers' salaries, travel expenses, training fees and other expenses, resulting in a significant increase in labor costs; from planning store exploration activities to the final video release, the entire process needs to go through multiple links, including site selection, appointment, shooting, editing, review, etc., all of which take a lot of time; under the traditional store exploration model, the collection, organization and analysis of information often rely on manual operations, which is not only time-consuming and labor-intensive, but also prone to errors and omissions. In addition, due to the lag in information processing, it is difficult for merchants to obtain effective market feedback and consumer demand in a timely manner.

[0003] Therefore, in order to improve the efficiency of store exploration, some merchants have begun to try to let consumers post store exploration videos and automatically reward them, which has improved the efficiency of store exploration to a certain extent. However, these automated reward systems only evaluate the store exploration effect based on simple indicators (such as the number of videos posted and the number of views), ignoring more important factors such as the quality of video content and the depth of audience interaction. This single evaluation standard leads to unfair and unreasonable reward distribution. In addition, due to the limitations of data sources and the simplicity of data processing methods, these automated reward systems may not accurately reflect the true value and influence of store exploration videos, resulting in deviations or misjudgments in reward distribution. Summary of the invention

[0004] In order to improve the accuracy of automated rewards for store exploration videos, the present application provides a method, device, equipment and storage medium for automated rewards for store exploration videos.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0006] An automated reward method for store exploration videos, the automated reward method for store exploration videos comprising:

[0007] Based on the user registration digital link, the registration user information is obtained, and a video publishing digital link is sent to the user corresponding to the registration user information, wherein the video publishing digital link is bound to a unique video identifier;

[0008] After the user publishes the store exploration video through the video publishing digital link, an association relationship between the registered user information and the store exploration video is established based on the unique video identifier;

[0009] Based on the association relationship, the store exploration video status corresponding to the registered user information is monitored in real time to obtain the store exploration video data;

[0010] The store exploration video data is compared with the preset reward conditions based on the association relationship to determine whether the reward conditions are met. If so, a reward is sent to the user corresponding to the registered user information based on the preset reward target corresponding to the reward conditions.

[0011] By adopting the above technical solution, user information is obtained through the user registration digital link, and a video publishing digital link bound to a unique video identifier is sent, ensuring that an accurate association can be established between each user and the store exploration video he or she publishes, which is convenient for subsequent data tracking and reward issuance, and improves the reliability and accuracy of the entire system; based on the established association, the system can monitor the status of the store exploration video corresponding to the registered user information in real time, and obtain relevant video data, including but not limited to important indicators for evaluating video quality and user participation, such as the number of views, the number of likes, and the number of comments. Subsequently, the system will automatically compare these data according to the preset reward conditions to determine whether the reward conditions are met, thereby realizing automated data monitoring and reward determination, greatly reducing manual intervention and improving It improves efficiency and accuracy. In addition, it allows setting a variety of preset reward conditions and corresponding reward targets. Different reward conditions can incentivize different types of user behaviors or video quality, thereby meeting the needs and expectations of different users. At the same time, clear reward standards and immediate reward feedback can stimulate users' enthusiasm and creativity, prompting them to create more high-quality store exploration videos. Based on this, the design of the entire automated reward process revolves around improving user experience and participation. Users only need to complete related operations through simple digital links, without complicated settings or waiting. Through the automated reward mechanism, the platform or brand can guide users to create store exploration videos that meet specific requirements or themes, thereby improving the quality and diversity of the videos to a certain extent.

[0012] In a preferred example, the present application may be further configured as follows: before comparing the store exploration video data with the preset reward conditions based on the association relationship to determine whether the reward conditions are met, the store exploration video automatic reward method further includes:

[0013] Acquire store information, analyze the store information and the reward target based on preset reuse evaluation criteria, and obtain user investment prediction information;

[0014] Generate a termination reward investment standard based on the user investment prediction information and the reward conditions;

[0015] The termination reward investment standard is compared with the store exploration video data. When the store exploration video data meets the conditions of the termination reward investment standard, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end.

[0016] By adopting the above technical solution, the store information and reward targets are analyzed, and the investment required by users to complete the store exploration video, including time, energy and resources, is predicted, that is, the cost-effectiveness of the reward mechanism is evaluated to avoid unnecessary waste of resources. At the same time, the generated termination reward investment standard can be used as a basis for risk control. When the store exploration video data shows that the user investment has not met expectations or there are abnormalities, the reward is terminated in time, thereby effectively controlling costs and reducing the risk of potential malicious data brushing. When the store exploration video data meets the conditions for the termination reward investment standard, although the termination reward may affect the user's enthusiasm to a certain extent, a reasonable termination reward investment standard can guide users to participate in store exploration activities more rationally while ensuring the accuracy of the reward; therefore, by introducing user investment prediction information and termination reward investment standards, the effect of the reward mechanism can be evaluated more accurately, and adjusted and optimized according to actual conditions. For example, if it is found that a certain type of store or reward target attracts generally low user investment, the system can adjust the reward conditions or reward targets accordingly to attract more users to participate and improve video quality, improve the efficiency and effect of the reward mechanism, and promote the sustainable and healthy development of store exploration activities.

[0017] In a preferred example, the present application can be further configured as follows: the reuse evaluation criteria are generated in the following manner:

[0018] Obtain the corresponding historical store exploration video automated reward data and historical user investment information;

[0019] The historical store exploration video automated reward data and the historical user input information are input into a preset machine learning model, and based on the machine learning model, a reuse evaluation standard is selected from several preset historical reuse evaluation standards in the machine learning model.

[0020] By adopting the above technical solution and using machine learning models to process historical data, it is possible to automatically learn and identify the key factors that affect the reward effect of store exploration videos and user investment. The generation of reused evaluation criteria is based on historical data, which ensures the objectivity and scientificity of the decision-making process. The machine learning model can extract valuable information and patterns from a large amount of data. Through the preset machine learning model and several historical reuse evaluation criteria, the system can flexibly select and adjust the reuse evaluation criteria according to actual conditions. With the continuous accumulation of historical data and the continuous optimization of the machine learning model, the reuse evaluation criteria will also be continuously iterated and updated. This continuous optimization process can ensure that the reuse evaluation criteria always keep pace with the actual situation and better adapt to market changes and changes in user needs. In addition, the historical store exploration video automated reward data and historical user investment information themselves have huge value. Through the in-depth mining and analysis of these data by machine learning models, not only can reuse evaluation criteria be generated, but also more valuable information and patterns can be discovered, providing strong support for the decision-making of platforms or brands.

[0021] In a preferred example, the present application may be further configured as follows: generating a termination reward investment standard according to the user investment prediction information and the reward condition, including:

[0022] Generating an investment value range for each reward sub-condition of the corresponding reward condition according to the user investment prediction information and the reward condition;

[0023] Based on the investment value range of each reward sub-condition, a termination reward investment standard is generated.

[0024] By adopting the above technical solution, the reward conditions are subdivided into multiple reward sub-conditions, and an independent investment value range is generated for each sub-condition, thereby realizing refined management of the store exploration video reward mechanism, which helps to more accurately evaluate the user's investment in different sub-conditions, thereby more accurately controlling the issuance of rewards, ensuring that users can obtain relatively fair rewards when completing the same sub-conditions, avoiding unfair rewards due to a single reward condition that is too broad, and improving users' enthusiasm and satisfaction in participating in store exploration video activities; by comparing the user's actual investment with the termination reward investment standard, the system can promptly discover potential risks and problems. When the user's investment is lower than the investment value range of a certain sub-condition, the system can automatically trigger the early warning mechanism and send an abnormal reminder instruction to the merchant side.

[0025] In a preferred example, the present application may be further configured as follows: the comparison between the termination reward investment standard and the store exploration video data, when the store exploration video data meets the condition of the termination reward investment standard, terminating the reward and generating an abnormal reminder instruction to be sent to the merchant end, including:

[0026] Comparing the termination reward investment standard with the store exploration video data, and when the store exploration video data meets the condition of the termination reward investment standard, extracting the store exploration video, and generating a specific comparison result between the termination reward investment standard and the store exploration video data;

[0027] Inputting the specific comparison result and the store exploration video into a preset video review model, and judging the accuracy of the specific comparison result based on the video review model;

[0028] When it is determined that the specific comparison result is accurate, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end.

[0029] By adopting the above technical solution and comparing the termination reward investment standard with the store exploration video data, it is possible to accurately determine which video data meets the conditions for terminating the reward. When the store exploration video data meets the conditions for terminating the reward investment standard, the system not only extracts the video, but also generates specific comparison results, ensuring that the anomaly detection process has a basis and provides sufficient evidence support for subsequent judgments. At the same time, the specific comparison results and the store exploration video are input into the video review model for further judgment. The video review model is introduced for automated judgment, which greatly improves the review efficiency and accuracy and enhances the reliability and accuracy of anomaly detection. Once the specific comparison result is determined to be accurate, the reward is terminated immediately and an abnormal reminder instruction is sent to the merchant side. By terminating the reward for store exploration videos that do not meet the conditions, unnecessary waste of resources can be avoided. At the same time, limited resources can be invested in more valuable videos, which helps to improve the overall resource utilization efficiency.

[0030] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions:

[0031] An automated reward device for store exploration videos, the automated reward device for store exploration videos comprising:

[0032] A registration module, used to obtain registration user information based on the user registration digital link, and send a video publishing digital link to the user corresponding to the registration user information, wherein the video publishing digital link is bound to a unique video identifier;

[0033] An association module, configured to establish an association relationship between the registered user information and the store exploration video based on the unique video identifier after the user publishes the store exploration video through the video publishing digital link;

[0034] A data acquisition module, for monitoring the store exploration video status corresponding to the registered user information in real time based on the association relationship, and acquiring the store exploration video data;

[0035] A reward judgment module is used to compare the store exploration video data with the preset reward conditions based on the association relationship to determine whether the reward conditions are met. If the judgment is yes, a reward is sent to the user corresponding to the registered user information based on the preset reward target corresponding to the reward condition.

[0036] Optionally, the store exploration video automated reward device further includes:

[0037] An investment prediction module is used to obtain store information, analyze the store information and the reward target based on a preset multiplexed evaluation standard, and obtain user investment prediction information;

[0038] A termination standard judgment module, used to generate a termination reward investment standard according to the user investment prediction information and the reward condition;

[0039] The termination judgment module is used to compare the termination reward investment standard with the store exploration video data. When the store exploration video data meets the conditions of the termination reward investment standard, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end.

[0040] Optionally, the store exploration video automated reward device further includes:

[0041] The information acquisition module is used to obtain the corresponding historical store exploration video automatic reward data and historical user investment information;

[0042] The standard selection module is used to input the historical store exploration video automated reward data and the historical user input information into a preset machine learning model, and based on the machine learning model, select a reuse evaluation standard from several preset historical reuse evaluation standards in the machine learning model.

[0043] In the third aspect, the above invention objective of the present application is achieved through the following technical solutions:

[0044] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for automating rewarding store exploration videos when executing the computer program.

[0045] In a fourth aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions:

[0046] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned store exploration video automated reward method.

[0047] In summary, the present application includes at least one of the following beneficial technical effects:

[0048] 1. Obtain user information through the user registration digital link, and send a video release digital link bound to a unique video identifier, ensuring that an accurate association can be established between each user and the store exploration video they publish, facilitating subsequent data tracking and reward issuance, and improving the reliability and accuracy of the entire system; based on the established association, the system can monitor the status of the store exploration video corresponding to the registered user information in real time, and obtain relevant video data, including but not limited to important indicators for evaluating video quality and user engagement, such as the number of views, likes, and comments. Subsequently, the system will automatically compare these data according to the preset reward conditions to determine whether the reward conditions are met, thereby realizing automated data monitoring and reward determination, greatly reducing manual intervention and improving efficiency and Accuracy; in addition, it allows setting a variety of preset reward conditions and corresponding reward targets. Different reward conditions can incentivize different types of user behaviors or video quality to meet the needs and expectations of different users. At the same time, clear reward standards and immediate reward feedback can stimulate users' enthusiasm and creativity, prompting them to create more high-quality store exploration videos. Based on this, the design of the entire automated reward process revolves around improving user experience and participation. Users only need to complete related operations through simple digital links without complicated settings or waiting. Through the automated reward mechanism, the platform or brand can guide users to create store exploration videos that meet specific requirements or themes, thereby improving the quality and diversity of videos to a certain extent.

[0049] 2. Analyze store information and reward targets, predict the investment required by users to complete store exploration videos, including time, energy, and resources, that is, evaluate the cost-effectiveness of the reward mechanism and avoid unnecessary waste of resources. At the same time, the generated termination reward investment standard can be used as a basis for risk control. When the store exploration video data shows that the user investment has not met expectations or there are abnormalities, the reward is terminated in time, thereby effectively controlling costs and reducing the risk of potential malicious data brushing. When the store exploration video data meets the conditions for terminating the reward investment standard, although the termination of the reward may affect the user's enthusiasm to a certain extent, a reasonable termination reward investment standard can guide users to participate in store exploration activities more rationally while ensuring the accuracy of the reward; therefore, by introducing user investment prediction information and termination reward investment standards, the effect of the reward mechanism can be evaluated more accurately, and adjusted and optimized according to actual conditions. For example, if it is found that a certain type of store or reward target attracts generally low user investment, the system can adjust the reward conditions or reward targets accordingly to attract more users to participate and improve video quality, improve the efficiency and effectiveness of the reward mechanism, and promote the sustainable and healthy development of store exploration activities;

[0050] 3. Using machine learning models to process historical data can automatically learn and identify the key factors that affect the reward effect of store exploration videos and user investment. The generation of reused evaluation criteria is based on historical data, which ensures the objectivity and scientificity of the decision-making process. The machine learning model can extract valuable information and patterns from a large amount of data. Through the preset machine learning model and several historical reuse evaluation criteria, the system can flexibly select and adjust the reuse evaluation criteria according to actual conditions. With the continuous accumulation of historical data and the continuous optimization of machine learning models, the reuse evaluation criteria will also be continuously iterated and updated. This continuous optimization process can ensure that the reuse evaluation criteria always keep pace with the actual situation and better adapt to market changes and changes in user needs. In addition, the historical store exploration video automated reward data and historical user investment information themselves have huge value. Through in-depth mining and analysis of these data by machine learning models, not only can reuse evaluation criteria be generated, but also more valuable information and patterns can be discovered, providing strong support for the decision-making of platforms or brands. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a first implementation flow chart of the method for automatically rewarding store exploration videos in an embodiment of the present application;

[0052] Figure 2 This is a second implementation flow chart of the method for automatically rewarding store exploration videos in an embodiment of the present application;

[0053] Figure 3 is a flowchart of the method for obtaining the multiplexed evaluation criteria in the embodiment of the present application;

[0054] Figure 4 This is a flowchart for implementing S240 of the method for automatically rewarding store exploration videos in an embodiment of the present application;

[0055] Figure 5 This is a flowchart for implementing S340 of the method for automatically rewarding store exploration videos in an embodiment of the present application;

[0056] Figure 6 This is a principle block diagram of the automatic reward device for store exploration videos in the embodiment of the present application;

[0057] Figure 7 It is a diagram of the internal structure of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0058] The following is combined with Figure 1-7 This application is described in further detail.

[0059] In one embodiment, if Figure 1 As shown, the present application discloses a method for automatically rewarding store exploration videos, which specifically includes the following steps:

[0060] S10: Based on the user registration digital link, the registration user information is obtained, and a video publishing digital link is sent to the user corresponding to the registration user information. The video publishing digital link is bound to a unique video identifier.

[0061] In this embodiment, the automated reward method for store exploration videos is applied to an automated reward system (or store exploration applet), which includes a reward configuration module, a user registration module, a video publishing and link processing module, a video status monitoring module, a reward determination and issuance module, and an activity management module, etc. The user registration digital link refers to a digital link for consumers to register for activities. The video publishing digital link refers to a digital link for consumers to publish store exploration videos.

[0062] Specifically, when the merchant completes the planning of the store visit activity, the automated reward system generates a digital link for consumers to sign up for the activity, namely, the user registration digital link. The user registration digital link can be in the form of a QR code or a website link. For example, when the user registration digital link is a QR code, the content of the QR code is the address link for WeChat mini program registration, such as pages / newShare / sharePage? invitedUserId=10, where invitedUserId represents the merchant's number, indicating that the registrations in this link are all for the reward activities of the merchant numbered 10;

[0063] When a user registers through the user registration digital link, the registered user information representing the user's identity information is obtained. In this embodiment, the registered user information can be obtained by the user filling in and inputting it by himself, or the user does not need to fill in anything. Only with the user's consent, the user's openId in the automated reward system (or the store exploration mini program) is obtained. The openId represents the user's unique identification code in the automated reward system (or the store exploration mini program), which is used to reward the user when the conditions are met;

[0064] In addition, when planning a store exploration activity, the merchant will also set the number of places for this store exploration activity. Therefore, after the user registers through the user registration digital link, the merchant will check whether there are any remaining places. If there are enough places, the merchant will be successfully registered. Otherwise, the merchant will be prompted that the places are full.

[0065] After the user successfully registers through the user registration digital link, the automated reward system will automatically generate a digital link for the consumer user to register for the event, namely, the video release digital link. The video release digital link can be in the form of a QR code or a website link. It should be noted that the video release digital link at this time does not correspond to the currently registered user, that is, before the user publishes the store exploration video through the current video release digital link, the video release digital link has not established an association with the currently registered user. The video release digital link is bound to a unique video identifier. For example, the video release digital link can include publishVideo? invitedUserId =10&userCode=sfsf, where invitedUserId represents the merchant number and userCode represents the unique video identifier.

[0066] In addition, after the user successfully registers through the user registration digital link, the user will be granted the qualification to publish according to the predetermined duration, such as 10 minutes, 20 minutes or 30 minutes, etc., that is, the user will be qualified to publish within the 10-minute countdown, and will be automatically disqualified if the time limit is exceeded. Because the number of rewarded users is limited, if the user has not published a work after registration, it will always occupy the registration quota and make it impossible to complete the specified number of rewards. Therefore, by canceling the qualification restriction if the work is not published within the specified time, the release of store exploration works will be accelerated, and other users who want to participate will have the opportunity to participate.

[0067] S20: After the user publishes a store exploration video through a video publishing digital link, an association relationship between the registered user information and the store exploration video is established based on the unique video identifier.

[0068] Specifically, when a user publishes a store exploration video through a video publishing digital link, the video publishing digital link is connected to a public video platform, such as the TikTok short video platform, and the video platform has established a communication connection with the automated reward system. Therefore, when the user's store exploration video is successfully published on the video platform, the video link and video ID returned by the video platform are obtained, wherein the video link refers to the digital link of the user's store exploration video on the video platform, and the video ID refers to the unique video ID bound to the video publishing digital link. In this way, an association relationship between the video ID and the registered user information is established, that is, an association relationship between the registered user information and the store exploration video is established.

[0069] S30: Based on the association relationship, the store exploration video status of the corresponding registered user information is monitored in real time to obtain the store exploration video data.

[0070] Specifically, after the association relationship is generated, the status of the store exploration video corresponding to the association relationship and the registered user information is monitored in real time. The store exploration video status includes deleted, hidden, removed by Douyin, under review and public. When the store exploration video status is public, monitoring and obtaining the store exploration video data, such as the number of views, likes, comments and reposts, etc.

[0071] S40: Compare the store exploration video data with the preset reward conditions based on the association relationship to determine whether the reward conditions are met. If so, send a reward to the user corresponding to the registered user information based on the preset reward target corresponding to the reward condition.

[0072] Specifically, based on the store exploration video corresponding to the association relationship, the store exploration video data corresponding to the store exploration video is compared with the preset reward conditions to determine whether the reward conditions are met. When it is determined to be yes, the user of the corresponding registered user information can be marked as "under review" based on the association relationship, and the final status can be confirmed again after a predetermined time, for example, waiting for 12 hours or 24 hours. After the predetermined time, the store exploration video marked as "under review" is monitored to determine whether the store exploration video status and the store exploration video data still meet the conditions, for example, determine whether the store exploration video status is public and whether the store exploration video data meets the reward conditions. At this time, if it is determined that the store exploration video status of the store exploration video marked as "under review" is public and the store exploration video data meets the reward conditions, the store exploration video mark is changed from "under review" to "awarded", and based on the preset reward target of the corresponding reward condition, the reward is sent to the user of the corresponding registered user information and the user is notified that the reward has been received.

[0073] In this embodiment, the reward conditions can be set by the merchant. The fields that can be set for the reward conditions are:

[0074] 1. Reward conditions (posting videos, number of views, number of likes, number of comments, number of reposts)

[0075] 2. Quantity (number of plays, likes, comments, and reposts)

[0076] 3. Reward type (fixed red envelope, random red envelope, other)

[0077] 4. Reward amount (available when the reward type is red envelope)

[0078] 5. Maximum amount (available when the reward type is random red envelope)

[0079] 6. Reward content (non-red envelope rewards)

[0080] 7. Number of rewards.

[0081] For example, the reward condition is set to posting a video, and the corresponding reward type is a fixed red envelope, the reward amount is 2 yuan, and the number of rewards is 10. This means that when a user posts a video, he or she can get a 2 yuan reward, and a maximum of 10 users can be rewarded. The reward condition is set to the number of plays, the number is 100, the reward type is a random red envelope, the maximum amount is set to 2, and the number of rewards is 10. This means that when a user posts a video and the number of video plays reaches 100, he or she can get a random amount of 0.01-2 yuan reward, and a maximum of 10 users can be rewarded. In addition, multiple reward conditions can be combined, etc.

[0082] In one embodiment, if Figure 2 As shown, in step S40: before comparing the store exploration video data with the preset reward conditions based on the association relationship and determining whether the reward conditions are met, the store exploration video automated reward method further includes:

[0083] S140: Obtain store information, analyze store information and reward targets based on preset reuse evaluation criteria, and obtain user investment prediction information.

[0084] In this embodiment, the reused evaluation criteria refers to the criteria used to evaluate the content of the current store exploration activity.

[0085] Specifically, before comparing the store exploration video data with the preset reward conditions, it is also necessary to determine whether the current store exploration video data is abnormal, because there may be cases where users use some improper means to control the store exploration video data in order to win rewards. For example, users may tamper with the store exploration video data through technical means, such as modifying the number of views, likes, comments, etc., and users may use false propaganda to attract users to watch and interact, such as publishing misleading titles and content for false promotion, and users may organize or hire others to perform brushing operations, that is, artificially increase the number of views, likes, comments, etc. of store exploration videos;

[0086] Therefore, first obtain the store information, that is, the relevant information of the store promoted through the store exploration video, including the store’s recent product sales and corresponding sales, hot-selling product information, product types and inventory, specific content of positive and negative reviews, specific feedback from customers, geographical location, business hours, current promotions, and social media attention, etc. Through the store information, comprehensively analyze the business conditions of the currently promoted store and its advantage in the store exploration promotion activities. Therefore, extract the standard for evaluating the content of the current store exploration activity, that is, the reused evaluation standard. The reused evaluation standard predicts the specific investment of users in the store exploration video according to the different advantages of the store in the store exploration promotion activities and different reward targets. For example, through the store information, the store’s brand awareness, reputation and market positioning, the product’s innovation, uniqueness, quality and fit with market demand, the store’s service attitude, efficiency, The store's advantage is judged comprehensively based on professionalism and customer satisfaction, promotional activities provided by the store, and the strength and attractiveness of the discounts. Combined with the comparison of the reward targets with the reward targets of similar store exploration activities, the attractiveness of store exploration activities to users is judged, thereby predicting the user's investment, such as the time cost invested by the user (for example, judging whether the user spends time on on-site inspections of the store, shooting video materials, editing videos, and adding subtitles, music and other post-production work. Depending on the complexity and sophistication of the video, the judged time investment may range from a few hours to a few days), the creative cost invested by the user in the store exploration video (for example, the degree of innovation in planning video content, the degree of innovation in shooting plans), resource investment (purchasing shooting equipment, renting venues, purchasing props or costumes, etc.), promotion cost investment, and interaction and feedback investment (users actively respond to the audience's comments and messages, and establish a good interactive relationship with the audience).

[0087] S240: Generate a termination reward investment standard based on the user investment prediction information and reward conditions.

[0088] Specifically, based on the user input prediction information representing the predicted input of the user in each dimension, the final achievement data of each condition corresponding to the reward condition and other final achievement data not corresponding to the reward condition are predicted, for example, the number of views, the number of likes, the number of comments and other data corresponding to the reward condition and the video duration, the amount of video subtitles, the amount of video editing, the amount of video dubbing, the number of people appearing on the screen and the like not corresponding to the reward condition, combined with the specific reward condition represented by the reward condition (wherein, the same type of condition may have condition thresholds of different levels), the correspondence between the predicted final achievement data of each condition corresponding to the reward condition and the condition thresholds of different levels in the reward condition is determined, that is, the reward condition level that the final achievement data predicted based on the user input prediction information can reach is determined, and then the user investment prediction data under different reward condition levels is inferred based on the corresponding relationship and the proportion of different reward levels, and then the correspondence between all reward condition levels in the reward condition and the user investment prediction data is generated, that is, each different reward condition level and the user investment data predicted when the user reaches each different reward condition level in the reward condition, and the user investment data predicted at each different reward condition level is multiplied by a preset abnormal coefficient to obtain the termination reward investment standard.

[0089] S340: Compare the termination reward investment standard with the store exploration video data. When the store exploration video data meets the conditions of the termination reward investment standard, terminate the reward and generate an abnormal reminder instruction to be sent to the merchant end.

[0090] Specifically, the data corresponding to each reward condition in the store exploration video data and the other data not corresponding to the reward condition are divided, and the data corresponding to each reward condition in the store exploration video data are first compared with the corresponding data in the comparison and termination reward investment standards to determine the reward condition level that the current store exploration video data can reach, and then the other data not corresponding to the reward conditions in the store exploration video data are compared with the standards corresponding to the reward condition level in the termination reward investment standards to determine whether the current user's investment is abnormal. When it is determined that the store exploration video data meets the conditions of the termination reward investment standards, that is, when the other data not corresponding to the reward conditions in the store exploration video data meet the standards corresponding to the reward condition level in the termination reward investment standards, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end.

[0091] In one embodiment, if Figure 3 As shown, the reuse evaluation criteria are generated in the following way:

[0092] S01: Obtain the corresponding historical store exploration video automated reward data and historical user investment information.

[0093] Specifically, the corresponding historical store exploration video automated reward data and historical user investment information are obtained, wherein the historical store exploration video automated reward data includes historical store exploration activity planning information, corresponding store information, reward conditions and reward targets, store exploration video data, etc., and the historical user investment information includes historical predicted user investment information and corresponding user actual investment information.

[0094] S02: Input the historical store exploration video automated reward data and historical user input information into a preset machine learning model, and based on the machine learning model, select a reuse evaluation standard from several preset historical reuse evaluation standards in the machine learning model.

[0095] Specifically, the historical store exploration video automated reward data and historical user input information are input into a preset machine learning model, which has a variety of different reuse evaluation criteria preset in it. Therefore, through the analysis of the historical store exploration video automated reward data and historical user input information by the machine learning model, the reuse evaluation criterion with the smallest error is selected from a variety of different reuse evaluation criteria.

[0096] In one embodiment, if Figure 4 As shown, in step S240, based on the user investment prediction information and the reward conditions, the termination reward investment standard is generated, including:

[0097] S2401: Based on the user investment prediction information and the reward conditions, generate the investment value range of each reward sub-condition corresponding to the reward condition.

[0098] Specifically, according to the different reward condition levels represented by the reward conditions, the specific condition data of the highest reward condition level and the specific condition data of the lowest reward condition level are extracted, and then based on the user investment prediction information, the total investment base is generated, and the total investment base, as well as the specific condition data of the highest reward condition level and the specific condition data of the lowest reward condition level are input into a preset investment analysis model to predict the highest unit final achievement data after the total investment base is evenly distributed to each unit data of each condition data of the corresponding highest reward condition level, and the lowest unit final achievement data after the total investment base is evenly distributed to each unit data of each condition data of the corresponding lowest reward condition level, for example, the proportion of the investment required for a user to obtain a number of comments of the highest reward condition level to the total investment base, thereby generating the investment value range of each reward sub-condition of the corresponding reward condition based on the highest unit final achievement data and the lowest unit final achievement data, that is, the investment value range of each condition data.

[0099] S2402: Generate termination reward investment standards based on the investment value range of each reward sub-condition.

[0100] Specifically, the input value range of each reward sub-condition is multiplied by a preset abnormal coefficient to obtain an abnormal input value range that is greater than the input value range, namely, the termination reward investment standard.

[0101] In one embodiment, if Figure 5 As shown, in step S340, the termination reward investment standard is compared with the store exploration video data. When the store exploration video data meets the conditions of the termination reward investment standard, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end, including:

[0102] S3401: Compare the termination reward investment standard with the store exploration video data. When the store exploration video data meets the conditions of the termination reward investment standard, extract the store exploration video and generate a specific comparison result between the termination reward investment standard and the store exploration video data.

[0103] Specifically, the termination reward investment standard is compared with the store exploration video data. When it is determined that the store exploration video data meets the conditions for the termination reward investment standard, that is, when it is preliminarily determined that the current store exploration video data is abnormal, the store exploration video is extracted and a specific comparison result is generated between the termination reward investment standard and each corresponding data of the store exploration video data.

[0104] S3402: Input the specific comparison result and the store exploration video into a preset video review model, and determine the accuracy of the specific comparison result based on the video review model.

[0105] Specifically, the specific comparison results and the store exploration video are input into a preset video review model, which refers to a model used to specifically analyze the content of the store exploration video and then analyze the input value corresponding to the store exploration video. Therefore, based on the substantive analysis of the store exploration video content by the video review model, it is judged whether the store exploration video data is accurate, and then it is judged whether the specific comparison results are accurate. For example, the store exploration video data includes video length, the amount of video subtitles, the amount of video editing, the amount of video dubbing, the number of people appearing on the screen, etc. The true accuracy of these data is further determined through the substantive analysis of the video review model, thereby judging the accuracy of the specific comparison results.

[0106] S3403: When it is determined that the specific comparison result is accurate, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end.

[0107] Specifically, when the specific comparison result is judged to be accurate, that is, when the store exploration video data is judged to meet the conditions for terminating the reward investment standard, it means that the store exploration video data at this time is abnormal. Therefore, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end.

[0108] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0109] In one embodiment, a device for automatically rewarding store exploration videos is provided, and the device for automatically rewarding store exploration videos corresponds one-to-one to the method for automatically rewarding store exploration videos in the above embodiment. Figure 6 As shown, the store exploration video automatic reward device includes a registration module, an association module, a data acquisition module and a reward judgment module. The detailed description of each functional module is as follows:

[0110] The registration module is used to obtain the registration user information based on the user registration digital link, and send a video release digital link to the user corresponding to the registration user information, and the video release digital link is bound to a unique video identifier;

[0111] An association module is used to establish an association relationship between the registered user information and the store exploration video based on a unique video identifier after the user publishes the store exploration video through the video publishing digital link;

[0112] The data acquisition module is used to monitor the store exploration video status of the corresponding registered user information in real time based on the association relationship and obtain the store exploration video data;

[0113] The reward judgment module is used to compare the store exploration video data with the preset reward conditions based on the association relationship to determine whether the reward conditions are met. If the judgment is yes, a reward is sent to the user corresponding to the registered user information based on the preset reward target corresponding to the reward condition.

[0114] Optionally, the store exploration video automated reward device also includes:

[0115] The investment prediction module is used to obtain store information, analyze store information and reward targets based on preset reuse evaluation criteria, and obtain user investment prediction information;

[0116] The termination standard judgment module is used to generate the termination reward investment standard based on the user's investment prediction information and reward conditions;

[0117] The termination judgment module is used to compare the termination reward investment standard with the store exploration video data. When the store exploration video data meets the conditions of the termination reward investment standard, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end.

[0118] Optionally, the store exploration video automated reward device also includes:

[0119] The information acquisition module is used to obtain the corresponding historical store exploration video automatic reward data and historical user investment information;

[0120] The standard selection module is used to input the historical store exploration video automation reward data and historical user input information into a preset machine learning model, and based on the machine learning model, select the reuse evaluation standard from several preset historical reuse evaluation standards in the machine learning model.

[0121] Optionally, the termination standard judgment module includes:

[0122] The termination range judgment submodule is used to generate the investment value range of each reward sub-condition of the corresponding reward condition according to the user investment prediction information and the reward condition;

[0123] The standard generation submodule is used to generate the termination reward investment standard according to the investment value range of each reward sub-condition.

[0124] Optionally, the termination judgment module includes:

[0125] A comparison submodule is used to compare the termination reward investment standard with the store exploration video data. When the store exploration video data meets the conditions of the termination reward investment standard, the store exploration video is extracted and a specific comparison result between the termination reward investment standard and the store exploration video data is generated;

[0126] The video review submodule is used to input the specific comparison results and the store exploration video into a preset video review model, and judge the accuracy of the specific comparison results based on the video review model;

[0127] The comparison result submodule is used to terminate the reward and generate an abnormal reminder instruction to send to the merchant end when it is determined that the specific comparison result is accurate.

[0128] For the specific limitations of the automated reward device for store exploration videos, please refer to the limitations of the automated reward method for store exploration videos above, which will not be repeated here. Each module in the above-mentioned automated reward device for store exploration videos can be implemented in whole or in part through software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0129] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store user registration digital links, registration user information, video release digital links, associations and store exploration video data, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for automatically rewarding store exploration videos is implemented.

[0130] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0131] Based on the user registration digital link, the registration user information is obtained, and a video release digital link is sent to the user corresponding to the registration user information, where the video release digital link is bound to a unique video identifier;

[0132] When a user publishes a store exploration video through a video publishing digital link, an association between the registered user information and the store exploration video is established based on the unique video identifier;

[0133] Based on the association relationship, the store exploration video status of the corresponding registered user information is monitored in real time to obtain the store exploration video data;

[0134] The store exploration video data is compared with the preset reward conditions based on the association relationship to determine whether the reward conditions are met. If so, a reward is sent to the user corresponding to the registered user information based on the preset reward target corresponding to the reward conditions.

[0135] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0136] Based on the user registration digital link, the registration user information is obtained, and a video release digital link is sent to the user corresponding to the registration user information, where the video release digital link is bound to a unique video identifier;

[0137] When a user publishes a store exploration video through a video publishing digital link, an association between the registered user information and the store exploration video is established based on the unique video identifier;

[0138] Based on the association relationship, the store exploration video status of the corresponding registered user information is monitored in real time to obtain the store exploration video data;

[0139] The store exploration video data is compared with the preset reward conditions based on the association relationship to determine whether the reward conditions are met. If so, a reward is sent to the user corresponding to the registered user information based on the preset reward target corresponding to the reward conditions.

[0140] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0141] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0142] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for automatically rewarding store exploration videos, characterized in that: The automated reward method for store exploration videos includes: Based on the user registration digital link, the registration user information is obtained, and a video publishing digital link is sent to the user corresponding to the registration user information, wherein the video publishing digital link is bound to a unique video identifier; After the user publishes the store exploration video through the video publishing digital link, an association relationship between the registered user information and the store exploration video is established based on the unique video identifier; Based on the association relationship, the store exploration video status corresponding to the registered user information is monitored in real time to obtain the store exploration video data; Acquire store information, analyze the store information and preset reward targets based on preset reuse evaluation criteria, and obtain user investment prediction information, wherein the reuse evaluation criteria refers to the criteria used to evaluate the content of the current store exploration activity; Generate a termination reward investment standard based on the user investment prediction information and preset reward conditions; Comparing the termination reward investment standard with the store exploration video data, when the store exploration video data meets the conditions of the termination reward investment standard, terminating the reward and generating an abnormal reminder instruction to send to the merchant end; The store exploration video data is compared with the reward conditions based on the association relationship to determine whether the reward conditions are met. If so, a reward is sent to a user corresponding to the registered user information based on the reward target corresponding to the reward conditions.

2. The method for automatically rewarding store exploration videos according to claim 1, characterized in that: The reuse evaluation criteria are generated in the following manner: Obtain the corresponding historical store exploration video automated reward data and historical user investment information; The historical store exploration video automated reward data and the historical user input information are input into a preset machine learning model, and based on the machine learning model, a reuse evaluation standard is selected from several preset historical reuse evaluation standards in the machine learning model.

3. The method for automatically rewarding store exploration videos according to claim 1, characterized in that: The step of generating a termination reward investment standard according to the user investment prediction information and the reward condition includes: Generating an investment value range for each reward sub-condition of the corresponding reward condition according to the user investment prediction information and the reward condition; Based on the investment value range of each reward sub-condition, a termination reward investment standard is generated.

4. The method for automatically rewarding store exploration videos according to claim 1, characterized in that: The step of comparing the termination reward investment standard with the store exploration video data, and when the store exploration video data satisfies the condition of the termination reward investment standard, terminating the reward and generating an abnormal reminder instruction to send to the merchant end, includes: Comparing the termination reward investment standard with the store exploration video data, and when the store exploration video data meets the condition of the termination reward investment standard, extracting the store exploration video, and generating a specific comparison result between the termination reward investment standard and the store exploration video data; Inputting the specific comparison result and the store exploration video into a preset video review model, and judging the accuracy of the specific comparison result based on the video review model; When it is determined that the specific comparison result is accurate, the reward is terminated and an abnormal reminder instruction is generated and sent to the merchant end.

5. An automated reward device for store exploration videos, characterized in that: The store exploration video automatic reward device comprises: A registration module, used to obtain registration user information based on the user registration digital link, and send a video publishing digital link to the user corresponding to the registration user information, wherein the video publishing digital link is bound to a unique video identifier; An association module, configured to establish an association relationship between the registered user information and the store exploration video based on the unique video identifier after the user publishes the store exploration video through the video publishing digital link; A data acquisition module, for monitoring the store exploration video status corresponding to the registered user information in real time based on the association relationship, and acquiring the store exploration video data; An investment prediction module is used to obtain store information, analyze the store information and preset reward targets based on preset reuse evaluation criteria, and obtain user investment prediction information, wherein the reuse evaluation criteria refers to the criteria used to evaluate the content of the current store exploration activity; A termination standard judgment module, used to generate a termination reward investment standard according to the user investment prediction information and preset reward conditions; A termination judgment module, used for comparing the termination reward investment standard with the store exploration video data, and when the store exploration video data meets the conditions of the termination reward investment standard, terminating the reward and generating an abnormal reminder instruction to be sent to the merchant end; A reward judgment module is used to compare the store exploration video data with the reward conditions based on the association relationship to determine whether the reward conditions are met. If the judgment is yes, a reward is sent to the user corresponding to the registered user information based on the reward target corresponding to the reward condition.

6. The automated store exploration video reward device according to claim 5, characterized in that: The store exploration video automatic reward device also includes: The information acquisition module is used to obtain the corresponding historical store exploration video automatic reward data and historical user investment information; The standard selection module is used to input the historical store exploration video automated reward data and the historical user input information into a preset machine learning model, and based on the machine learning model, select a reuse evaluation standard from several preset historical reuse evaluation standards in the machine learning model.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for automated rewarding of store exploration videos as described in any one of claims 1 to 4 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for automated rewarding of store exploration videos as described in any one of claims 1 to 4 are implemented.

Images