Training management method based on new media operation

Abstract

The invention discloses a training management method based on new media operation, and relates to the technical field of training management of new media operation, user interaction data, watching duration, content originality score and negative comment quantity during new media operation are collected through a data collection module, a participation degree index C is analyzed and output through a comprehensive data analysis module, and the participation degree index C is calculated through a calculation module. According to the training management method, the user participation degree, the change trend of the content quality and the effect after training are analyzed according to the content quality evaluation index PG and the training effect evaluation index PX, and the new media operation is continuously optimized through the execution and feedback module. The algorithm unit combines multiple aspects of data-driven decision making, user behavior analysis, content quality evaluation and training effect evaluation, aims to improve the effect of new media operation through a scientific method, not only solves the defects and problems in the prior art, but also realizes optimization and innovation of training management.

Description

Technical Field

[0001] The present invention relates to the technical field of training management for new media operations, and in particular to a training management method based on new media operations. Background Art

[0002] New media technologies, such as social media, short video platforms, and live broadcast platforms, have achieved remarkable development in recent years. These platforms not only provide a wealth of content creation and distribution channels, but also achieve accurate content push and in-depth analysis of user behavior through big data and artificial intelligence technologies. With the diversification and personalization of user needs, how to accurately grasp user needs and improve the pertinence and attractiveness of content creation has become an important topic in new media operations. In the new media era, companies are increasingly relying on data-driven decision-making and operations to increase brand exposure, sales performance, and competitiveness. Therefore, applying new media technology to training management has become an important way for companies to improve training effectiveness.

[0003] Existing training management methods are often limited to surface data in terms of data collection, including the number of likes and comments, but ignore the depth and quality of the data. For example, malicious comments and irrelevant comments are not effectively excluded, resulting in data distortion, which limits the collection and processing of data. In addition, many training management methods only use a single indicator to evaluate the training effect, but ignore the multi-dimensionality of user engagement and the comprehensive consideration of content quality. With the development of new media platforms and changes in user behavior, the original evaluation methods and weighting factors are no longer applicable, but existing training management methods often lack a dynamic adjustment mechanism. Traditional training methods often formulate training content based on experience and subjective judgment, and fail to fully consider user needs and the characteristics of new media platforms, resulting in unsatisfactory training results and a disconnect between training content and user needs. Summary of the invention

[0004] The purpose of the present invention is to provide a training management method based on new media operation, which solves the problems raised in the above background technology.

[0005] To achieve the above objectives, the present invention provides the following technical solutions, including a training management method based on new media operations, including participation, originality, content quality and post-training effects;

[0006] It includes data collection module, comprehensive data analysis module and execution and feedback module;

[0007] The specific implementation steps are as follows:

[0008] Through the data collection module, user interaction data, viewing time, content originality score and number of negative comments during new media operation are collected;

[0009] Through the comprehensive data analysis module, the participation index C, the content quality evaluation index PG and the training effect evaluation index PX are analyzed and output, and according to the training effect evaluation index PX, the changing trend of user participation, content quality and the effect after training are analyzed. The comprehensive data analysis module includes a unit for measuring the degree of user participation in content, an originality and overall quality evaluation unit and a unit for evaluating the actual impact after training;

[0010] Based on the training effect evaluation index PX, the positive and negative effects of the post-training effect are analyzed through the execution and feedback module, and the training content, methods and strategies are adjusted to continuously optimize the training management methods of new media operations;

[0011] The equipment used in the data collection module includes data analysis software, social media platform analysis tools, and originality detection tools;

[0012] The equipment used in the comprehensive data analysis module includes a calculator and a programming script;

[0013] The equipment used by the execution and feedback module includes a training management system.

[0014] Optionally, the calculation formula for the unit for measuring the user's participation in the content is as follows:

[0015]

[0016] HC=(D 1 +a*YP 1 )+(D 2 +a*YP 2 );

[0017] in:

[0018] C is the participation index;

[0019] HC is the total number of user interactions;

[0020] F is the total number of content shares;

[0021] GK is the average viewing time;

[0022] D 1 is the total number of likes before sharing, D 2 The total number of likes after sharing;

[0023] YP 1 is the total number of valid comments before sharing, YP 2 The total number of valid comments before sharing;

[0024] a is the weight factor, which is used to adjust the relative importance between likes and valid comments;

[0025] The log function used by log(GK+1) is used to smooth the contribution of long-term viewing to engagement.

[0026] Optionally, the calculation formula for the originality and overall quality assessment unit is as follows:

[0027]

[0028] EF=(D 2 +a*YP 2 ) / N;

[0029] FP=FP t1 +FP tn *e;

[0030] in:

[0031] PG is the content quality evaluation index;

[0032] YC is the originality evaluation index;

[0033] EF is the sharing rate, N is the total number of shares;

[0034] FP is the total number of negative comments;

[0035] FP t1 is the number of negative comments in the beginning period, FP tn is the number of negative comments in the end time period;

[0036] b and e are weight factors. b is the factor for adjusting the weight of the total number of negative comments FP, and e is the number of negative comments FP at the end of the time period. tn The factor for adjusting the weight of

[0037] T is a tuning factor used to adjust the content quality score based on other criteria, including expert review.

[0038] Optionally, the calculation formula for evaluating the actual impact unit after training is as follows:

[0039]

[0040] in:

[0041] PX is the training effect evaluation index;

[0042] XG is the user behavior change index after training, including more frequent creation and higher sharing rate;

[0043] XG prev It is the user behavior benchmark index before training;

[0044] C after is the post-training engagement index;

[0045] C befer is the pre-training participation index;

[0046] c is the weight factor, which is used to adjust the impact of changes in the number of comments on the evaluation of training effectiveness;

[0047] YP after is the number of valid comments after training;

[0048] YP befer is the number of valid comments before training.

[0049] Optionally, the positive and negative impacts and adjustments of the training effect evaluation index PX that actually affects the unit output after the evaluation training are as follows:

[0050] S1. If the training effect evaluation index PX increases, it means that users are more actively involved, which reflects the increase in the participation index C and the content quality evaluation index PG, thus forming a virtuous positive cycle. The current operating status should be maintained.

[0051] S2. If the participation index C and the content quality evaluation index PG decrease, it will directly affect and reflect the decline of the training effect evaluation index PX, thus forming a negative impact. When the training content, methods and strategies are adjusted according to the evaluation results, the positive cycle can be re-stimulated.

[0052] Optionally, during the process of re-evaluation when the training effect evaluation index PX produces a negative impact, as user behavior changes and new media platforms develop, the original weight factors including a, b, c, and the adjustment factor T all need to be recalibrated.

[0053] Optionally, when the unit for measuring the degree of user participation in content calculates the total number of likes D and the total number of valid comments YP, if the same person likes and comments multiple times, it is usually necessary to perform a duplicate check to ensure the accuracy of the data. The specific duplicate check method is as follows:

[0054] S1. In social media and content management systems, each user usually has a unique identifier, namely a user ID. By recording the number of likes and comments for each user ID, duplicate counts are automatically removed;

[0055] S2. For the same user, set a certain time interval, including minutes and hours, to distinguish consecutive likes and comments to avoid treating repeated behaviors in a short period of time as multiple valid interactions;

[0056] S3. For anonymous comments, content analysis is performed through natural language processing to identify duplicate comments, which includes the detection of text similarity.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] 1. The present invention provides scientific data support for training managers by collecting and analyzing multi-dimensional data, including the number of likes, the number of valid comments, the viewing time, the number of content sharing times, and combining it with the user engagement calculated by the unit for measuring the degree of user engagement in the content, so that they can formulate and adjust training strategies based on the data.

[0059] 2. The originality and overall quality assessment unit in the present invention comprehensively considers multiple factors such as the number of content sharing times, the number of negative comments, the originality score and the adjustment factor, and provides a comprehensive and accurate assessment of content quality, which helps training managers identify deficiencies in the content and make targeted improvements. The detailed calculation of the number of negative comments helps to make the content quality assessment more accurate in measuring negative comments.

[0060] 3. The unit for evaluating the actual impact after training in the present invention provides a scientific evaluation method for the training effect by comparing the indicators of user participation, content quality and user behavior changes before and after training. This helps training managers understand the actual effect of training and adjust the training content, methods and strategies according to the evaluation results.

[0061] 4. The entire training management system of the present invention is a dynamic process that requires regular re-evaluation and adjustment. By recalibrating the parameters of weight factors and adjustment factors, the accuracy and effectiveness of the evaluation results are ensured, and the system adapts to the development of new media platforms and changes in user behavior.

[0062] 5. The training management method of the present invention is based on new media operations, focusing on the collection and analysis of user needs and feedback, satisfying user needs by improving user participation and content quality, thereby enhancing user stickiness and loyalty. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A method flow chart of the training management method based on new media operation;

[0064] Figure 2 This is a schematic diagram of the module structure of the training management method based on new media operations;

[0065] Figure 3 It is a structural schematic diagram of the comprehensive data analysis module of the present invention;

[0066] Figure 4 It is a schematic diagram of positive and negative adjustments for improving and reducing the training effect of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Regarding this training management method based on new media operations, it is different from the existing traditional training management methods. Traditional training management methods often focus on the teaching of content creation skills, but ignore how to effectively improve user engagement and content quality, and how to evaluate and optimize training results through data analysis. This algorithm unit combines data-driven decision making, user behavior analysis, content quality assessment, and training effect evaluation. It aims to improve the effectiveness of new media operations through scientific methods. It not only solves the shortcomings and problems of existing technologies, but also realizes the optimization and innovation of training management.

[0069] For example, see Figures 1 to 4 ,This implementation provides a training management method based on new media operation, including participation, originality, content quality and post-training effect, and the training management method based on new media operation includes a data collection module, a comprehensive data analysis module and an execution and feedback module;

[0070] The specific implementation steps are as follows:

[0071] Through the data collection module, collect user interaction data, viewing time, content originality score and number of negative comments during new media operations;

[0072] Through the comprehensive data analysis module, the participation index C, content quality evaluation index PG and training effect evaluation index PX are analyzed and output, and based on the training effect evaluation index PX, the changing trend of user participation, content quality and the effect after training are analyzed. The comprehensive data analysis module includes a unit for measuring the degree of user participation in content, a unit for evaluating originality and overall quality, and a unit for evaluating the actual impact after training;

[0073] Based on the training effect evaluation index PX, the positive and negative effects of post-training effects are analyzed through the execution and feedback module, and the training content, methods and strategies are adjusted to continuously optimize the training management methods of new media operations;

[0074] The equipment used in the data collection module includes data analysis software, social media platform analysis tools, and originality detection tools;

[0075] The equipment used in the comprehensive data analysis module includes calculators and programming scripts;

[0076] The equipment used in the execution and feedback module includes a training management system.

[0077] In this embodiment, the training manager in training needs to emphasize the core role of data in the evaluation of training effectiveness. The trainers need to understand how to collect, organize and analyze user interaction data, which is the basis for evaluating the training effectiveness. The trainers should be reminded to pay attention to the authenticity and accuracy of the data, avoid data falsification and misleading interpretation, explain the difference between effective comments and malicious comments, and guide the trainers on how to identify malicious comments. Keyword filtering, machine learning models and tools will be used to assist in identification, but manual review is also needed to ensure accuracy. It is emphasized that when evaluating user engagement, not only quantity, including the number of likes and comments, but also quality, including the proportion of effective comments, is important. In addition, the importance of originality to content quality is explained, and methods for evaluating originality are introduced. The trainers are reminded to pay attention to the creativity and novelty of the content, avoid plagiarism and Low-quality content creation, emphasizing that training effect evaluation is an ongoing process that requires regular re-evaluation and adjustment. Trainers need to pay attention to the changing trends of user engagement and content quality, and adjust training content, methods and strategies based on the evaluation results. Encourage trainers to establish a feedback mechanism to collect feedback from users and creators in a timely manner in order to better improve training results. Explain to trainers the concepts of positive and negative feedback and how they affect training results. Emphasize that in the training process, attention should be paid to the mutual influence between various links, and efforts should be made to build a virtuous cycle. At the same time, respond to negative feedback in a timely manner and adjust strategies to improve results. Remind trainers to pay attention to the development trends and changes of new media platforms, including changes in user behavior and adjustments to platform policies. Finally, encourage trainers to respond to these changes flexibly and adjust training content and strategies to adapt to new environments and requirements;

[0078] In this embodiment, data analysis software includes Excel, Python and R languages ​​for data processing and calculation, social media platform analysis tools include Hootsuite, Buffer, Sprout Social, which are used to collect and analyze social media data, originality detection tools include Turnitin, Grammarly's Plagiarism Checker, and Copyscape, which are used to detect the originality of content, training management systems include Moodle, Blackboard, and TalentLMS, which are used to organize and manage training activities, and calculators and programming scripts are used to perform complex mathematical operations and formula calculations.

[0079] In this embodiment, the system provides a scientific and objective evaluation method for the training management of new media operations by quantifying user interaction, content quality and training effects through the mutual cooperation of three algorithm units. Combining the three operation results of C, PG and PX, the training managers can clearly understand the actual effect of the training and adjust the training content, methods and strategies accordingly to further improve user engagement and content quality. C is the engagement index, which helps content creators and platform managers understand the dissemination effect and user feedback of the content, so as to optimize the content strategy and promotion method. PG is the content quality evaluation index. The calculation of this unit is crucial for content creators because it can help them identify and improve the deficiencies in the content and improve the attractiveness and competitiveness of the content. At the same time, for platform managers, content quality is very important. Quantitative evaluation is also an important means to maintain the platform ecology and combat low-quality content. PX is the training effect evaluation index. By regularly evaluating the training effect and adjusting the training content, methods and strategies according to the evaluation results, the training quality is continuously improved and the common growth of content creators and users is promoted. At the same time, the training effect evaluation also helps to identify potential problems and challenges in training, and provide improvement directions for future training activities. The calculation results of C can also affect the feedback to the calculation of PG and PX, thereby enhancing user participation, improving content quality and promoting dynamic adjustment. These influences jointly promote the continuous optimization and improvement of new media operation training management methods, making the three algorithms of this system have a high correlation and entanglement, so that the overall algorithm system can perform automatic feedback and optimization according to actual conditions to be closer to reality.

[0080] See also Figures 1 to 4 , the calculation formula for measuring the user's content participation unit is as follows:

[0081]

[0082] HC=(D 1 +a*YP 1 )+(D 2 +a*YP 2 );

[0083] in:

[0084] C is the participation index;

[0085] HC is the total number of user interactions;

[0086] F is the total number of content shares;

[0087] GK is the average viewing time;

[0088] D 1 is the total number of likes before sharing, D 2 The total number of likes after sharing;

[0089] YP 1 is the total number of valid comments before sharing, YP 2 The total number of valid comments before sharing;

[0090] a is the weight factor, which is used to adjust the relative importance between likes and valid comments;

[0091] The log function used by log(GK+1) is used to smooth the contribution of long-term viewing to engagement.

[0092] In this embodiment: First, in this algorithm unit, the interaction between new media operations and users is not a traditional face-to-face interaction, so some methods are needed to establish interactive connections, and this method is the expression of users' likes and disinterest in the content, including the total number of content shares F, average viewing time GK, total number of likes D and total number of valid comments YP in the unit for measuring the user's content participation. Under the weight adjustment of the weight factor a, multiple dimensions are comprehensively considered, the overall degree of user participation in the content is measured, and the popularity and attractiveness of the content among the target audience can be comprehensively evaluated, and the participation index C is output;

[0093] Among them, "(D 1 +a*YP 1 The calculation part of "(D )" evaluates the interaction of users before sharing. The user interaction before sharing is a direct reflection of the attractiveness of the content. These interactions reflect the initial attractiveness of the content before it is widely disseminated. For content creators, it is an important indicator for evaluating the initial acceptance of the content. High pre-sharing interactions prompt more users to choose to share the content, thereby increasing the number of content sharing, and then improving the overall participation and content exposure. 2 +a*YP 2 )” evaluates the user interaction after sharing. User interaction after sharing not only reflects the dissemination effect of the content, but also reflects the acceptance and influence of the content among a wider audience. The increase in interaction after sharing can further promote the dissemination of content, form a word-of-mouth effect, and attract more potential users. At the same time, these interactions also provide valuable feedback for content creators, helping them understand user needs and optimize subsequent content. Although interaction is shown before and after sharing, distinguishing the interaction before sharing and the interaction after sharing and calculating their effects separately can help content creators have a more comprehensive understanding of the attractiveness and dissemination of content, so as to formulate more accurate content creation and promotion strategies;

[0094] This algorithm unit combines the total number of likes D and the total number of valid comments YP, and introduces a weight factor a to adjust the relative importance between the two, so that the unit measuring the degree of user participation in content can more comprehensively evaluate the degree of user interaction with the content. This multi-dimensional evaluation helps to more accurately understand the real feedback of users on the content. Since valid comments have a certain weight in the unit measuring the degree of user participation in content, this encourages users to post more valuable and in-depth comments rather than simple likes and malicious comments, which helps to improve the high quality of interaction between content creators and users. In addition, by combining the total number of content shares F and the average viewing time GK, the unit measuring the degree of user participation in content can reflect the attractiveness of the content to users, and a high number of shares and a long viewing time usually mean that the content has high attractiveness and value.

[0095] See also Figures 1 to 4 , the calculation formula for the originality and overall quality assessment unit is as follows:

[0096]

[0097] EF=(D 2 +a*YP 2 ) / N;

[0098] FP=FP t1 +FP tn *e;

[0099] in:

[0100] PG is the content quality evaluation index;

[0101] YC is the originality evaluation index;

[0102] EF is the sharing rate, N is the total number of shares;

[0103] FP is the total number of negative comments;

[0104] FP t1 is the number of negative comments in the beginning period, FP tn is the number of negative comments in the end time period;

[0105] b and e are weight factors. b is the factor for adjusting the weight of the total number of negative comments FP, and e is the number of negative comments FP at the end of the time period. tn The factor for adjusting the weight of

[0106] T is a tuning factor used to adjust the content quality score based on other criteria, including expert review.

[0107] In this embodiment, firstly, based on the total number of valid comments YP of the unit for measuring the degree of user participation in content, in the current situation of rapid development of the Internet and diversified information, if there is a total number of valid comments YP, there must be a total number of negative comments FP. Therefore, the total number of negative comments FP is also an important part of measuring content quality that cannot be ignored, that is, it is a potential deduction item for content quality. With the diversification and personalization of user needs, original content will have more traffic and can also improve the overall quality of content. Therefore, in the originality and overall quality evaluation unit, the originality evaluation index YC is also considered and entered into the calculation evaluation. The originality evaluation index YC can be evaluated in a variety of ways, including text similarity inspection, identification of unique elements in text content images and videos, and novelty of creativity;

[0108] In this embodiment, the number of negative comments FP in the beginning time period of the content viewing process is t1 The number of negative comments in the end time period FP tn A detailed processing is performed. In other words, if negative comments are generated in the initial viewing period of the general content, it is considered that the content is of low quality and leads to negative guidance. If negative comments are generated in the viewing period, it is considered that the content is generally of low quality but the probability of negative guidance is low. Therefore, the calculation here reduces the number of negative comments in the end time period FP tn The weight of the content quality evaluation index PG makes the calculation of negative comments more accurate;

[0109] This algorithm unit introduces the original evaluation index YC, so that the original and overall quality evaluation unit encourages content creators to focus on the originality and innovation of the content, which helps to reduce plagiarism and duplicate content and improve the content quality of the entire new media platform. Although negative comments have a negative impact on content quality, the original and overall quality evaluation unit balances the impact of negative comments by introducing the weight factor b and adjustment factor T of negative comments, which helps to evaluate content quality more fairly and avoid deviations caused by a single factor. The original and overall quality evaluation unit comprehensively considers multiple factors such as the number of content shares, the number of negative comments, user engagement, and content originality, providing a comprehensive and accurate evaluation of content quality.

[0110] See also Figures 1 to 4 , the calculation formula for evaluating the actual impact unit after training is as follows:

[0111]

[0112] in:

[0113] PX is the training effect evaluation index;

[0114] XG is the user behavior change index after training, including more frequent creation and higher sharing rate;

[0115] XG prev It is the user behavior benchmark index before training;

[0116] C after is the post-training engagement index;

[0117] C befer is the pre-training participation index;

[0118] c is the weight factor, which is used to adjust the impact of changes in the number of comments on the evaluation of training effectiveness;

[0119] YP after is the number of valid comments after training;

[0120] YP befer is the number of valid comments before training.

[0121] In this embodiment, the algorithm unit firstly calculates the content quality evaluation index PG output by the original and overall quality evaluation unit, XG is the user behavior change index after training, and the user behavior change index XG after training can be the quantity and quality improvement of the content created by the user after training and the positive change of user behavior. Then, the difference of participation and effective evaluation before and after training is calculated by in-depth analysis and comparison, and the training effect evaluation index PX under comprehensive consideration and evaluation is output through the weight adjustment of the weight factor c.

[0122] In this algorithm unit, by comparing user engagement, content quality and user behavior changes before and after training, the actual impact after training evaluation unit can quantitatively evaluate the training effect. This provides an objective evaluation standard for training managers and helps to understand the actual effect of training. According to the evaluation results of the actual impact after training evaluation unit, training managers can identify deficiencies in training and adjust training content, methods and strategies in a targeted manner, which helps to improve training effects and promote continuous improvement in user engagement and content quality. By evaluating the training effects and adjusting the training content and methods accordingly, the actual impact after training evaluation unit helps to stimulate a positive cycle, that is, the improvement of training effects will promote the increase of user engagement and the improvement of content quality, thereby forming a virtuous circle.

[0123] See also Figures 1 to 4 , based on the positive and negative impacts and adjustments of the training effect evaluation index PX that actually affects the unit output after the evaluation training are as follows:

[0124] S1. If the training effect evaluation index PX increases, it means that users are more actively involved, which reflects the increase in the participation index C and the content quality evaluation index PG, thus forming a virtuous positive cycle. The current operating status should be maintained.

[0125] S2. If the participation index C and the content quality evaluation index PG decrease, it will directly affect and reflect the decline of the training effect evaluation index PX, thus forming a negative impact. When the training content, methods and strategies are adjusted according to the evaluation results, the positive cycle can be re-stimulated;

[0126] In the process of re-evaluation of the training effect evaluation index PX which has a negative impact, with the changes in user behavior and the development of new media platforms, the original weight factors including a, b, c, and the adjustment factor T all need to be recalibrated.

[0127] In this embodiment, this algorithm unit is based on the analysis and adjustment of the training effect evaluation index PX. When the training effect evaluation index PX increases, according to the evaluation results in the actual impact unit after the training, the training manager needs to adjust the training content and methods to better meet the needs of users, which will help improve the participation index C, because users will be more likely to be attracted by high-quality, interesting and relevant content, thereby enhancing user participation. The improvement of training effect also means that content creators have acquired more knowledge and skills during the training process, so that they can create higher-quality content. High-quality content will further attract user participation, forming a positive cycle. The evaluation results in the actual impact unit after the training not only reflect the training effect, but also reveal the changing trend of user behavior and content quality, which helps training managers to discover and respond to potential problems in a timely manner, and maintain the continuity of the positive cycle by dynamically adjusting the training content and methods.

[0128] In summary, the cyclical impact of the unit for evaluating the actual impact after training on the unit for measuring the degree of user engagement in content is mainly reflected in enhancing user engagement, improving content quality, and promoting dynamic adjustment. These influences jointly promote the continuous optimization and improvement of new media operation training management methods.

[0129] For example 2, please refer to Figures 1 to 4 When calculating the total number of likes D and the total number of valid comments YP, if the same person likes and comments multiple times, it is usually necessary to check for duplicates to ensure the accuracy of the data. The specific method of checking for duplicates is as follows:

[0130] S1. In social media and content management systems, each user usually has a unique identifier, namely a user ID. By recording the number of likes and comments for each user ID, duplicate counts are automatically removed;

[0131] S2. For the same user, set a certain time interval, including minutes and hours, to distinguish consecutive likes and comments to avoid treating repeated behaviors in a short period of time as multiple valid interactions;

[0132] S3. For anonymous comments, content analysis is performed through natural language processing to identify duplicate comments, which includes the detection of text similarity.

[0133] In this embodiment, duplicate checking can ensure that each user's likes and comments are counted only once, thereby avoiding data distortion caused by duplicate counting, which is crucial for evaluating content quality, user engagement, and formulating marketing strategies, because accurate data is the basis for making scientific decisions. In the process of content creation and promotion, understanding real user feedback is crucial for optimizing resource allocation. Duplicate checking can help identify which users are truly active and valuable, allowing content creators and platform managers to invest more resources in these users and improve overall operational efficiency. Through duplicate checking, the platform can reduce spam caused by user misoperation and malicious behavior, including likes and comments, thereby improving overall With a better user experience, users will be more likely to see real and valuable interactive content, which will enhance their trust and satisfaction with the platform. On social media and content platforms, duplicate checking helps maintain a fair competition environment. By preventing malicious brushing and other behaviors, it ensures that comparisons between content creators are based on real and fair data, thereby incentivizing creators to create higher-quality content to attract users. Based on accurate data, the platform can implement more precise marketing strategies. For example, by analyzing users' likes and comments, the platform can understand users' interests and preferences, and recommend content and products that better meet their needs. This personalized recommendation not only improves user satisfaction, but also increases the platform's conversion rate and profitability.

[0134] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A training management method based on new media operation, characterized in that: A training management method based on new media operations that includes participation, originality, content quality, and post-training effects; It includes data collection module, comprehensive data analysis module and execution and feedback module; The specific implementation steps are as follows: Through the data collection module, user interaction data, viewing time, content originality score and number of negative comments during new media operation are collected; Through the comprehensive data analysis module, the participation index C, the content quality evaluation index PG and the training effect evaluation index PX are analyzed and output, and according to the training effect evaluation index PX, the changing trend of user participation, content quality and the effect after training are analyzed. The comprehensive data analysis module includes a unit for measuring the degree of user participation in content, an originality and overall quality evaluation unit and a unit for evaluating the actual impact after training; Based on the training effect evaluation index PX, the positive and negative impacts of the post-training effect are analyzed through the execution and feedback module, the training content, methods and strategies are adjusted, and the training management methods of new media operations are continuously optimized.

2. A training management method based on new media operation according to claim 1, characterized in that: The equipment used in the data collection module includes data analysis software, social media platform analysis tools, and originality detection tools; The equipment used in the comprehensive data analysis module includes a calculator and a programming script; The equipment used by the execution and feedback module includes a training management system.

3. A training management method based on new media operation according to claim 2, characterized in that: The calculation formula for measuring the user's content participation unit is as follows: HC = (D1 + a*YP1) + (D2 + a*YP2); in: C is the participation index; HC is the total number of user interactions; F is the total number of content shares; GK is the average viewing time; D1 is the total number of likes before sharing, and D2 is the total number of likes after sharing; YP1 is the total number of valid comments before sharing, and YP2 is the total number of valid comments before sharing; a is the weight factor, which is used to adjust the relative importance between likes and valid comments; The log function used by log(GK+1) is used to smooth the contribution of long-term viewing to engagement; The calculation of D1+a*YP1 is used to evaluate the user interaction before sharing. The user interaction before sharing is a direct reflection of the attractiveness of the content, reflecting the initial attractiveness of the content before it is widely disseminated. For content creators, it is an important indicator for evaluating the initial acceptance of the content. High pre-sharing interaction prompts more users to choose to share the content, thereby increasing the number of content sharing and improving the overall participation and content exposure. The calculation of D2+a*YP2 is used to evaluate the interaction of users after sharing. The interaction of users after sharing not only reflects the dissemination effect of the content, but also reflects the acceptance and influence of the content among a wide audience. The increase in interaction after sharing further promotes the dissemination of the content, forms a word-of-mouth effect, and attracts more potential users. By combining the total number of likes D and the total number of valid comments YP and introducing the weight factor a to adjust the importance between the two, the unit for measuring the degree of user participation in content can comprehensively evaluate the degree of user interaction with the content.

4. A training management method based on new media operation according to claim 3, characterized in that: The calculation formula for the originality and overall quality assessment unit is as follows: EF=(D2+a*YP2) / N; FP=FP t1 +FP tn *e; in: PG is the content quality evaluation index; YC is the originality evaluation index; EF is the sharing rate, N is the total number of shares; FP is the total number of negative comments; FP t1 is the number of negative comments in the beginning period, FP tn is the number of negative comments in the end time period; b and e are weight factors. b is the factor for adjusting the weight of the total number of negative comments FP, and e is the number of negative comments FP at the end of the time period. tn The factor for adjusting the weight of T is a moderating factor used to adjust the content quality score based on other criteria, including expert review; If negative comments are generated during the initial viewing period of the content, it is considered that the content is of low quality and leads to negative influence; If negative comments are generated at the end of the viewing period, the content is considered to be of low quality but with a low probability of negative guidance, so FP t1 +FP tn *e calculation part reduces the number of negative comments in the end time period FP tn The weight of the content quality evaluation index PG makes the calculation of negative comments more accurate; By introducing the originality evaluation index YC, the originality and overall quality evaluation unit encourages content creators to focus on the originality and innovation of their content, helping to reduce plagiarism and duplication of content, and improving the content quality of the entire new media platform; By introducing the weight factor b and adjustment factor T of negative comments, the impact of negative comments can be balanced, which helps to fairly evaluate the quality of content and avoid deviations caused by a single factor.

5. A training management method based on new media operation according to claim 4, characterized in that: The calculation formula for evaluating the actual impact unit after training is as follows: in: PX is the training effect evaluation index; XG is the user behavior change index after training, including more frequent creation and higher sharing rate; XG prev It is the user behavior benchmark index before training; C after is the post-training engagement index; C befer is the pre-training participation index; c is the weight factor, which is used to adjust the impact of changes in the number of comments on the evaluation of training effectiveness; YP after is the number of valid comments after training; YP befer is the number of valid comments before training.

6. A training management method based on new media operation according to claim 5, characterized in that: The positive and negative impacts and adjustments of the training effect evaluation index PX that actually affects the unit output after the evaluation training are as follows: S1. If the training effect evaluation index PX increases, it means that users are more actively involved, which reflects the increase in the participation index C and the content quality evaluation index PG, thus forming a virtuous positive cycle. The current operating status should be maintained. S2. If the participation index C and the content quality evaluation index PG decrease, it will directly affect and reflect the decline of the training effect evaluation index PX, thus forming a negative impact. When the training content, methods and strategies are adjusted according to the evaluation results, the positive cycle can be re-stimulated.

7. A training management method based on new media operation according to claim 6, characterized in that: In the process of re-evaluating the training effect evaluation index PX that has a negative impact, with the changes in user behavior and the development of new media platforms, the original weight factors including a, b, c, and the adjustment factor T all need to be recalibrated.

8. A training management method based on new media operation according to claim 3, characterized in that: When the unit for measuring the degree of user participation in content calculates the total number of likes D and the total number of valid comments YP, if the same person likes and comments multiple times at the same time, it is usually necessary to perform a duplicate check to ensure the accuracy of the data. The specific duplicate check method is as follows: S1. In social media and content management systems, each user has a unique identifier, namely the user ID. By recording the number of likes and comments for each user ID, duplicate counts are automatically removed; S2. For the same user, set time intervals, including minutes and hours, to distinguish consecutive likes and comments to avoid treating repeated behaviors in a short period of time as multiple valid interactions; S3. For anonymous comments, content analysis is performed through natural language processing to identify duplicate comments, which includes the detection of text similarity.

Images