A user experience feedback system for platform services

Abstract

The present invention discloses a user experience feedback system for platform services, and relates to the field of information science and technology. The user experience feedback system for platform services extracts friendly feedback data, processes these data to analyze the density of friendly feedback and user retention rate, determines the friendly feedback level of the platform service, and reflects the user's positive acceptance of the service. Unfriendly feedback data is extracted, the density of unfriendly feedback, the problem recurrence rate and the processing load are analyzed, and the unfriendly feedback level of the platform service is determined to reflect the user's negative reaction to the service and the frequency of problems. The overall feedback processing data is collected, and the friendly and unfriendly feedback data are combined to determine the comprehensive feedback level of the platform service, which reflects the overall service quality and efficiency, effectively monitors and evaluates the quality of the platform service, and by subdividing user feedback into two categories, friendly and unfriendly, in-depth analysis is performed to help platform operators more accurately identify the advantages and problem points in the service.

Description

Technical Field

[0001] The present invention relates to the field of information science and technology, and in particular to a user experience feedback system for platform services. Background Art

[0002] User experience is a purely subjective feeling that users develop in the process of using a product. However, for a well-defined user group, the commonality of their user experience can be recognized through well-designed experiments.

[0003] The Chinese invention patent application with publication number CN113888014A discloses a feedback system based on user experience, including an information input module, a data storage center, a data processing center and an information display module. The information input module includes a user feedback terminal, and the user feedback terminal is composed of a display screen, a control panel, and a built-in data processing and wireless receiver. The present invention collects and integrates information entered by different users, and then classifies and integrates the collected information through a remote cloud, so as to rate the experience of different users according to good or bad, and then conducts a probability analysis of the user experience according to the data analysis server, so as to analyze the electricity demand of users of different age groups, so that the efficiency of power transmission can be optimized according to the user experience. Secondly, the user experience data after detailed processing and integration can be transmitted back to the user feedback terminal for user reference.

[0004] The Chinese invention patent application with publication number CN117974241A discloses a user experience feedback system for a virtual library, which is used to solve the problem that there are relatively few ways for readers to communicate in the existing virtual library, lack the reader community feeling in the physical library, cannot accurately analyze the operation of the virtual library, and it is difficult to accurately grasp the reader's experience feedback, resulting in the inability to effectively improve the user experience of the virtual library. Specifically, it is a user experience feedback system for a virtual library, including a behavior state analysis module, a feedback state analysis module, a performance state analysis module, a user experience comprehensive analysis module, a cloud database and a display terminal, a cloud database. The present invention obtains and analyzes the behavior data, feedback data of each target user and the operation performance service data of the virtual library, so as to clarify the needs and feedback of users in the virtual library, and then improve and optimize the services of the virtual library in a targeted manner to improve the user experience.

[0005] Although existing technologies can analyze user behavior data and understand user needs, they do not classify feedback data, and the analysis is not in-depth enough to help platform operators more accurately identify the advantages and problems in their services. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a user experience feedback system for platform services, which can effectively monitor and evaluate the quality of platform services. By subdividing user feedback into two categories, friendly and unfriendly, and conducting in-depth analysis, it can help platform operators more accurately identify the advantages and problems in the services.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a user experience feedback system for platform services, comprising a friendly feedback evaluation module, an unfriendly feedback evaluation module and a comprehensive feedback evaluation module, wherein: the friendly feedback evaluation module is used to obtain user experience platform service feedback data, obtain friendly feedback data based on the user experience platform service feedback data, process the friendly feedback data, and determine the friendly feedback level of the platform service, wherein the friendly feedback data includes friendly feedback density and user retention rate; the unfriendly feedback evaluation module is used to obtain user experience platform service feedback data, obtain unfriendly feedback data based on the user experience platform service feedback data, process the unfriendly feedback data, and determine the unfriendly feedback level of the platform service, wherein the unfriendly feedback data includes unfriendly feedback density, problem recurrence rate and unfriendly feedback processing load; the comprehensive feedback evaluation module is used to obtain feedback processing data, and determine the comprehensive feedback evaluation level of the platform service based on the feedback processing data, the friendly feedback data and the unfriendly feedback data, wherein the feedback processing data includes average feedback processing time, feedback response time and problem resolution rate.

[0008] Further, the determining of the comprehensive feedback evaluation level of the platform service based on the feedback processing data, the friendly feedback data and the unfriendly feedback data comprises the following steps: processing the feedback processing data to obtain a feedback processing coefficient; processing the friendly feedback data to obtain a friendly feedback coefficient, the friendly feedback coefficient being used as an analysis basis for determining the friendly feedback level of the platform service; processing the unfriendly feedback data to obtain an unfriendly feedback coefficient, the unfriendly feedback coefficient being used as an analysis basis for determining the unfriendly feedback level of the platform service; processing the feedback processing coefficient, the friendly feedback coefficient and the unfriendly feedback coefficient to obtain a comprehensive feedback index; comparing the comprehensive feedback index with the comprehensive feedback threshold stored in the database to determine whether the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database: if the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database, the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database; and If the feedback index is greater than the comprehensive feedback threshold stored in the database, the comprehensive feedback index is compared with the comprehensive feedback evaluation levels of the platform services corresponding to each comprehensive feedback index stored in the database to obtain the comprehensive feedback evaluation level of the platform services corresponding to the successfully compared comprehensive feedback index; if the comprehensive feedback index is not greater than the comprehensive feedback threshold stored in the database, the difference between the comprehensive feedback index and the comprehensive feedback threshold stored in the database is obtained, and the difference between the comprehensive feedback index and the comprehensive feedback threshold stored in the database is compared with the comprehensive feedback evaluation levels of the platform services corresponding to the difference between each comprehensive feedback index stored in the database and the comprehensive feedback threshold stored in the database to obtain the comprehensive feedback evaluation level of the platform services corresponding to the difference between the successfully compared comprehensive feedback index and the comprehensive feedback threshold stored in the database.

[0009] Furthermore, the calculation formula of the comprehensive feedback index is as follows:

[0010]

[0011] Where ZFk is the comprehensive feedback index, cX is the feedback processing coefficient, yX is the friendly feedback coefficient, bX is the unfriendly feedback coefficient, and e is a natural constant.

[0012] Furthermore, the feedback processing data is processed to obtain the feedback processing coefficient, and the specific steps are as follows: obtaining the feedback processing reference data stored in the database, the feedback processing reference data stored in the database includes the average feedback processing reference time, the feedback response reference time and the problem reference resolution rate; processing the feedback processing data with the feedback processing reference data stored in the database to obtain the feedback processing coefficient, wherein the calculation formula of the feedback processing coefficient is as follows:

[0013]

[0014] Where cX is the feedback processing coefficient, Tf is the average feedback processing time, Tx is the feedback response time, Wx is the problem solving rate, cTf is the average feedback processing reference time, cTx is the feedback response reference time, and cWx is the problem reference solving rate.

[0015] Furthermore, the step of determining the platform service friendly feedback level is as follows: comparing the friendly feedback coefficient with the platform service friendly feedback levels corresponding to each friendly feedback coefficient stored in the database, and obtaining the platform service friendly feedback level corresponding to the friendly feedback coefficient that has been successfully compared.

[0016] Furthermore, the friendly feedback data is processed to obtain a friendly feedback coefficient, and the specific steps are as follows: obtaining friendly feedback parameter data stored in a database, the friendly feedback parameter data stored in the database including a friendly feedback parameter density and a user parameter retention rate; obtaining weight data stored in the database, the weight data stored in the database including a friendly feedback parameter density weight factor and a user parameter retention rate weight factor; processing the friendly feedback data, the weight data stored in the database and the friendly feedback parameter data stored in the database to obtain a friendly feedback coefficient.

[0017] Furthermore, the calculation formula of the friendly feedback coefficient is as follows:

[0018]

[0019] Where yX is the friendly feedback coefficient, My is the friendly feedback density, By is the user retention rate, cMy is the friendly feedback parameter density, cBy is the user parameter retention rate, α1 is the friendly feedback density weight factor stored in the database, and α2 is the user retention rate weight factor stored in the database.

[0020] Furthermore, the step of determining the platform service unfriendly feedback level is as follows: comparing the unfriendly feedback coefficient with the platform service unfriendly feedback level corresponding to each unfriendly feedback coefficient stored in the database, and obtaining the platform service unfriendly feedback level corresponding to the unfriendly feedback coefficient that has been successfully compared.

[0021] Furthermore, the unfriendly feedback data is processed to obtain an unfriendly feedback coefficient, and the specific steps are as follows: obtaining unfriendly feedback parameter data stored in a database, the unfriendly feedback parameter data stored in the database including unfriendly feedback parameter density, problem parameter recurrence rate and unfriendly feedback parameter processing load; processing the unfriendly feedback data with the unfriendly feedback parameter data stored in the database to obtain an unfriendly feedback coefficient.

[0022] Furthermore, the calculation formula of the unfriendly feedback coefficient is as follows:

[0023]

[0024] Where bX is the unfriendly feedback coefficient, mbf is the unfriendly feedback density, wxx is the problem recurrence rate, wfx is the unfriendly feedback processing load, cbf is the unfriendly feedback parameter density, cwx is the problem parameter recurrence rate, and cfx is the unfriendly feedback parameter processing load.

[0025] The present invention has the following beneficial effects:

[0026] 1. The user experience feedback system for platform services extracts friendly feedback data from user feedback, processes this data to analyze the density of friendly feedback and user retention rate, and determines the friendly feedback level of the platform service based on the processing results, reflecting the user's positive acceptance of the service. Extract unfriendly feedback data from user feedback, analyze the density of unfriendly feedback, problem recurrence rate and processing load, and determine the unfriendly feedback level of the platform service based on the analysis results, reflecting the user's negative reaction to the service and the frequency of problems. Collect overall feedback processing data, including response time, processing time and problem resolution rate, combine friendly and unfriendly feedback data, conduct comprehensive analysis, determine the comprehensive feedback level of the platform service, reflect the overall service quality and efficiency, and can effectively monitor and evaluate the quality of platform services. By subdividing user feedback into two categories, friendly and unfriendly, and conducting in-depth analysis, it can help platform operators more accurately identify the advantages and problem points in the service.

[0027] 2. The user experience feedback system for platform services, through the analysis of the comprehensive evaluation module, can comprehensively evaluate the services, optimize user satisfaction, and improve the efficiency of problem solving, thereby improving the overall service level and enhancing user loyalty.

[0028] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flowchart of the user experience feedback system used for platform services in the present invention. DETAILED DESCRIPTION

[0030] The embodiment of the present application can effectively monitor and evaluate the quality of platform services through a user experience feedback system for platform services. By subdividing user feedback into two categories, friendly and unfriendly, and conducting in-depth analysis, it can help platform operators more accurately identify the advantages and problems in the services.

[0031] See also Figure 1The embodiment of the present invention provides a technical solution: a user experience feedback system for platform services, including a friendly feedback evaluation module, an unfriendly feedback evaluation module and a comprehensive feedback evaluation module, wherein: the friendly feedback evaluation module is used to obtain user experience platform service feedback data, obtain friendly feedback data based on the user experience platform service feedback data, process the friendly feedback data, and determine the friendly feedback level of the platform service, wherein the friendly feedback data includes friendly feedback density and user retention rate; the unfriendly feedback evaluation module is used to obtain user experience platform service feedback data, obtain unfriendly feedback data based on the user experience platform service feedback data, process the unfriendly feedback data, and determine the unfriendly feedback level of the platform service, wherein the unfriendly feedback data includes unfriendly feedback density, problem recurrence rate and unfriendly feedback processing load; the comprehensive feedback evaluation module is used to obtain feedback processing data, and determine the comprehensive feedback evaluation level of the platform service based on the feedback processing data, the friendly feedback data and the unfriendly feedback data, wherein the feedback processing data includes average feedback processing time, feedback response time and problem resolution rate.

[0032] Extract friendly feedback data from user feedback, process this data to analyze the density of friendly feedback and user retention rate, and determine the friendly feedback level of platform services based on the processing results, reflecting users' positive acceptance of services. Extract unfriendly feedback data from user feedback, analyze the density of unfriendly feedback, problem recurrence rate, and processing load, and determine the unfriendly feedback level of platform services based on the analysis results, reflecting users' negative reactions to services and problem frequency. Collect overall feedback processing data, including response time, processing time, and problem resolution rate, and conduct a comprehensive analysis based on friendly and unfriendly feedback data to determine the comprehensive feedback level of platform services, reflecting overall service quality and efficiency.

[0033] The user experience platform service feedback data includes feedback forms, questionnaires, online evaluations or direct communication submitted by users. Friendly feedback data refers to the data of positive feedback in the user experience platform service feedback data, including praise, suggestions or other positive evaluations, reflecting the user's good experience of the platform service. The friendly feedback density refers to the ratio of the number of these positive evaluations in a cycle to the cycle time, and the unit of the cycle time is hours. The user retention rate reflects the continuous use of the platform service by users, which is the proportion of users who are still active and continue to use the platform in a cycle. Unfriendly feedback data refers to the data of negative feedback in the user experience platform service feedback data, including complaints, problem reports or other unsatisfactory evaluations, reflecting the problems or dissatisfaction of users with the service. The unfriendly feedback density refers to the ratio of the number of these unsatisfactory evaluations in a cycle to the cycle time, and the unit of the cycle time is hours. The problem recurrence rate refers to the average proportion of the reappearance of various similar unsatisfactory evaluations in a cycle. The unfriendly feedback processing load refers to the number of unfriendly feedbacks processed in a cycle. The average feedback processing time is the average time from receiving user feedback to completing feedback processing. The feedback response time is the average time from receiving feedback to the first response to the user within a cycle. The problem resolution rate is the proportion of problems that have been resolved among the received feedback.

[0034] Specifically, the method of determining the comprehensive feedback evaluation level of the platform service based on the feedback processing data, the friendly feedback data and the unfriendly feedback data includes the following steps: processing the feedback processing data to obtain a feedback processing coefficient; processing the friendly feedback data to obtain a friendly feedback coefficient, and the friendly feedback coefficient is used as an analysis basis for determining the friendly feedback level of the platform service; processing the unfriendly feedback data to obtain an unfriendly feedback coefficient, and the unfriendly feedback coefficient is used as an analysis basis for determining the unfriendly feedback level of the platform service; processing the feedback processing coefficient, the friendly feedback coefficient and the unfriendly feedback coefficient to obtain a comprehensive feedback index; comparing the comprehensive feedback index with the comprehensive feedback threshold stored in the database to determine whether the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database: if the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database, the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database; ... index, the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database. If the feedback index is greater than the comprehensive feedback threshold stored in the database, the comprehensive feedback index is compared with the comprehensive feedback evaluation levels of the platform services corresponding to each comprehensive feedback index stored in the database to obtain the comprehensive feedback evaluation level of the platform services corresponding to the successfully compared comprehensive feedback index; if the comprehensive feedback index is not greater than the comprehensive feedback threshold stored in the database, the difference between the comprehensive feedback index and the comprehensive feedback threshold stored in the database is obtained, and the difference between the comprehensive feedback index and the comprehensive feedback threshold stored in the database is compared with the comprehensive feedback evaluation levels of the platform services corresponding to the difference between each comprehensive feedback index stored in the database and the comprehensive feedback threshold stored in the database to obtain the comprehensive feedback evaluation level of the platform services corresponding to the difference between the successfully compared comprehensive feedback index and the comprehensive feedback threshold stored in the database.

[0035] First, the feedback processing data (such as the average feedback processing time, response time, and problem resolution rate) is processed to calculate a coefficient, which reflects the service processing efficiency and effectiveness. Friendly feedback data (such as friendly feedback density and user retention rate) is analyzed to generate a coefficient reflecting the positive impact of the service. Similarly, unfriendly feedback data (such as unfriendly feedback density, problem recurrence rate, and processing load) is processed to obtain a coefficient reflecting service problems and user dissatisfaction. Combining the above three coefficients (feedback processing coefficient, friendly feedback coefficient, and unfriendly feedback coefficient), a comprehensive feedback index is calculated. The comprehensive feedback index is compared with the preset threshold in the database. If the index exceeds the threshold, the corresponding evaluation level is determined according to the mapping table in the database. If the index does not exceed the threshold, the difference is calculated and the corresponding evaluation level is determined according to the difference.

[0036] The calculation formula of the comprehensive feedback index is as follows:

[0037]

[0038] Where ZFk is the comprehensive feedback index, cX is the feedback processing coefficient, yX is the friendly feedback coefficient, bX is the unfriendly feedback coefficient, and e is a natural constant.

[0039] In this implementation, the feedback processing coefficient and the unfriendly feedback coefficient are combined, and the decreasing characteristics of the exponential function are used to reflect the negative impact of these two coefficients, that is, the reducing effect of bad feedback and low processing efficiency on the comprehensive index, and the increasing characteristics of the exponential function are used to express the positive contribution of friendly feedback to the comprehensive feedback index, that is, positive feedback can significantly improve the overall evaluation.

[0040] Specifically, the feedback processing data is processed to obtain the feedback processing coefficient, and the specific steps are as follows: obtaining the feedback processing reference data stored in the database, the feedback processing reference data stored in the database includes the average feedback processing reference time, the feedback response reference time and the problem reference resolution rate; processing the feedback processing data with the feedback processing reference data stored in the database to obtain the feedback processing coefficient, wherein the calculation formula of the feedback processing coefficient is as follows:

[0041]

[0042] Where cX is the feedback processing coefficient, Tf is the average feedback processing time, Tx is the feedback response time, Wx is the problem solving rate, cTf is the average feedback processing reference time, cTx is the feedback response reference time, and cWx is the problem reference solving rate.

[0043] In this embodiment, the formula compares the actual feedback processing data (average processing time, response time, problem resolution rate) with the reference data in the database (reference average processing time, reference response time, reference resolution rate). This comparison can intuitively show the deviation of service performance from the established standard.

[0044] The logarithmic function is used to process the ratio, which can mathematically smooth the impact of extreme values ​​and improve the stability and sensitivity of the calculation. The use of logarithmic functions also helps to transform proportional data to make it more suitable for linear processing. The sum of the ratios (here one is added to ensure that the domain of the logarithmic function is a positive number) and the inverse ratio of the problem-solving rate are added to achieve the integration of data of different dimensions.

[0045] Typically, a system with a smaller Tf may tend to have a smaller Tx, because a system that responds quickly when processing feedback also means that the processing time may be shorter. A fast response time may help improve the problem resolution rate, because timely feedback can reduce user waiting and unnecessary repeated feedback, thereby speeding up the resolution of problems. Although fast processing time does not directly affect the resolution rate, an efficient processing process usually improves overall user satisfaction and may indirectly improve the problem resolution rate. The three parameters are selected for calculating the feedback processing coefficient in order to comprehensively evaluate the efficiency and effectiveness of feedback processing, thereby comprehensively quantifying and evaluating the service quality.

[0046] The weight factors in the database are usually obtained through historical data analysis and statistical methods. Specifically, the weight factors can be obtained through the following steps: first, collect and organize a large amount of historical data, including data records of various feedback processing indicators such as processing time, response time and resolution rate; second, analyze these data, and use statistical methods such as mean value, standard deviation, etc. to understand the distribution of each indicator and its actual performance in the feedback processing process; finally, based on the analysis results, the weights of different indicators in calculating the feedback processing coefficient can be set, so that the calculation results more accurately reflect the actual feedback processing situation and effect. Such weight setting can help optimize the feedback processing process and improve service quality based on objective analysis of historical data.

[0047] Specifically, the step of determining the platform service friendly feedback level is as follows: comparing the friendly feedback coefficient with the platform service friendly feedback levels corresponding to each friendly feedback coefficient stored in the database, and obtaining the platform service friendly feedback level corresponding to the friendly feedback coefficient that has been successfully compared.

[0048] The friendly feedback data is processed to obtain a friendly feedback coefficient, and the specific steps are as follows: obtaining friendly feedback parameter data stored in a database, wherein the friendly feedback parameter data stored in the database includes a friendly feedback parameter density and a user parameter retention rate; obtaining weight data stored in the database, wherein the weight data stored in the database includes a friendly feedback parameter density weight factor and a user parameter retention rate weight factor; and processing the friendly feedback data, the weight data stored in the database, and the friendly feedback parameter data stored in the database to obtain a friendly feedback coefficient.

[0049] The calculation formula of the friendly feedback coefficient is as follows:

[0050]

[0051] Where yX is the friendly feedback coefficient, My is the friendly feedback density, By is the user retention rate, cMy is the friendly feedback parameter density, cBy is the user parameter retention rate, α1 is the friendly feedback density weight factor stored in the database, and α2 is the user retention rate weight factor stored in the database.

[0052] In this implementation, data related to friendly feedback are obtained from the database, including friendly feedback density (My) and user retention rate (By), as well as their respective parameter data (cMy, cBy), and weight factors related to these data are also obtained. These weight factors are used to adjust the influence of different factors in the calculation. A formula is used to calculate the friendly feedback coefficient, which takes into account the proportional relationship between the actual feedback value and the parameter value and is adjusted by the weight factor.

[0053] The calculation of the friendly feedback coefficient quantifies user feedback data, making it easier to analyze and compare. By generating a numerical value, you can quickly understand the user's overall satisfaction with the product or service. In this way, you can evaluate the impact of different factors (such as friendly feedback density and user retention rate) on user experience. For example, if the weight factor of a factor is large, it means that it occupies a more important position in the feedback.

[0054] Friendly feedback density indicates the frequency or density of user feedback, reflecting the user's interest and participation in the product or service. A higher friendly feedback density usually means that users are more actively involved in feedback, which may be positively correlated with user satisfaction and product quality. This parameter can directly reflect the user's attitude towards the product or service. User retention rate refers to the proportion of users who continue to use a product or service within a certain period of time. It is usually used to measure customer loyalty. A higher user retention rate means that users have a higher degree of recognition of the product or service, indicating that users have not chosen to give up during long-term use. This is a key indicator of long-term success and sustainable development.

[0055] There is a strong correlation between friendly feedback density and user retention rate. Generally, if users provide friendly feedback during use, it means that they are more concerned about and satisfied with the product or service, and are more likely to stay. Therefore, these two parameters together reflect the user's emotional connection with the product.

[0056] The weight factors α1 and α2 stored in the database are obtained based on historical data. Multivariate linear regression analysis is performed on the historical data to determine the regression coefficients of friendly feedback density and user retention rate. The regression coefficients are defined as weight factors and stored in the database.

[0057] Specifically, the step of determining the platform service unfriendly feedback level is as follows: comparing the unfriendly feedback coefficient with the platform service unfriendly feedback level corresponding to each unfriendly feedback coefficient stored in the database, and obtaining the platform service unfriendly feedback level corresponding to the unfriendly feedback coefficient that has been successfully compared.

[0058] The unfriendly feedback data is processed to obtain an unfriendly feedback coefficient, and the specific steps are as follows: obtaining unfriendly feedback parameter data stored in a database, the unfriendly feedback parameter data stored in the database including unfriendly feedback parameter density, problem parameter recurrence rate and unfriendly feedback parameter processing load; processing the unfriendly feedback data with the unfriendly feedback parameter data stored in the database to obtain an unfriendly feedback coefficient.

[0059] The calculation formula of the unfriendly feedback coefficient is as follows:

[0060]

[0061] Where bX is the unfriendly feedback coefficient, mbf is the unfriendly feedback density, wxx is the problem recurrence rate, wfx is the unfriendly feedback processing load, cbf is the unfriendly feedback parameter density, cwx is the problem parameter recurrence rate, and cfx is the unfriendly feedback parameter processing load.

[0062] In this implementation scheme, the unfriendly feedback coefficient is compared with the unfriendly feedback level of each platform service stored in the database, and the real-time data can be combined with the historical data to obtain the feedback level of the current service. In this way, the platform can quickly identify which services have more serious unfriendly feedback and take corresponding measures. Calculating the unfriendly feedback coefficient (bX) involves a comprehensive evaluation of multiple indicators, taking into account the ratio of the current unfriendly feedback status to the reference data, thereby obtaining a quantifiable feedback coefficient.

[0063] Unfriendly feedback density measures the ratio of the number of unfriendly feedbacks from users about a service over a certain period of time to the total number of users. It reflects the degree of user dissatisfaction with the service and its concentration. Problem recurrence rate indicates how often the problems reported by users can be reproduced. A high recurrence rate usually means the prevalence of the problem, indicating that there are more serious defects in the service. Unfriendly feedback processing load refers to the resources and time required to resolve unfriendly feedback, that is, how much energy the customer service team needs to devote to handling unfriendly responses. A high load represents an increased pressure on customer service, which may lead to longer response times and reduced service quality.

[0064] When mbf (unfriendly feedback density) rises, it means that more users have raised unfriendly feedback, which will increase wfx (unfriendly feedback processing load) because the customer service team needs to spend more time and resources to handle these feedbacks. In the case of high mbf, continuous negative feedback may lead to fatigue of the customer service team and a decrease in response efficiency, which may affect service quality and user experience. High wxx (problem recurrence rate) means that the dissatisfaction of feedback is widespread, so mbf may also increase. In other words, the problems found by users can be reproduced by a large number of users, reflecting the fundamental problems of the service. If some unfriendly feedback can be verified again frequently, it is necessary for the company to prioritize solving these problems to reduce mbf. In the formula for calculating the unfriendly feedback coefficient bXbX, the relationship between different parameters is balanced by the parameter variables (cbf, cwx, cfx) in the denominator, which helps control the contribution of each parameter to the final result. Using logarithmic functions (such as ln) to process these ratios can effectively reduce the impact of fluctuations and extreme values ​​in the data, making the unfriendly feedback coefficient more stable and easy to understand.

[0065] An electronic device includes: a processor and a memory, wherein computer program instructions are stored in the memory, and when the computer program instructions are executed by the processor, the processor executes the user experience feedback system for platform services as described above.

[0066] A computer-readable storage medium is used to store a program, and when the program is executed by a processor, the user experience feedback system for platform services as described above is implemented.

[0067] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0071] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0072] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A user experience feedback system for platform services, characterized in that: It includes friendly feedback evaluation module, unfriendly feedback evaluation module and comprehensive feedback evaluation module, among which: The friendly feedback evaluation module is used to obtain user experience platform service feedback data, obtain friendly feedback data based on the user experience platform service feedback data, process the friendly feedback data, and determine the platform service friendly feedback level, wherein the friendly feedback data includes friendly feedback density and user retention rate; Determining the comprehensive feedback evaluation level of platform services based on feedback processing data, friendly feedback data, and unfriendly feedback data includes the following steps: Processing the feedback processing data to obtain a feedback processing coefficient; Processing the friendly feedback data to obtain a friendly feedback coefficient, which is used as an analysis basis for determining the friendly feedback level of the platform service; Processing the unfriendly feedback data to obtain an unfriendly feedback coefficient, which is used as an analysis basis for determining the unfriendly feedback level of the platform service; The feedback processing coefficient, the friendly feedback coefficient and the unfriendly feedback coefficient are processed to obtain a comprehensive feedback index; Compare the comprehensive feedback index with the comprehensive feedback threshold stored in the database to determine whether the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database: If the comprehensive feedback index is greater than the comprehensive feedback threshold stored in the database, the comprehensive feedback index is compared with the platform service comprehensive feedback evaluation level corresponding to each comprehensive feedback index stored in the database to obtain the platform service comprehensive feedback evaluation level corresponding to the successfully compared comprehensive feedback index; If the comprehensive feedback index is not greater than the comprehensive feedback threshold stored in the database, then the difference between the comprehensive feedback index and the comprehensive feedback threshold stored in the database is obtained, and the difference between the comprehensive feedback index and the comprehensive feedback threshold stored in the database is compared with the platform service comprehensive feedback evaluation level corresponding to the difference between each comprehensive feedback index stored in the database and the comprehensive feedback threshold stored in the database, and the platform service comprehensive feedback evaluation level corresponding to the difference between the comprehensive feedback index and the comprehensive feedback threshold stored in the database that is successfully compared is obtained; The feedback processing data is processed to obtain the feedback processing coefficient. The specific steps are as follows: Acquire feedback processing reference data stored in a database, wherein the feedback processing reference data stored in the database includes an average feedback processing reference time, a feedback response reference time, and a problem reference resolution rate; The feedback processing data is processed with the feedback processing reference data stored in the database to obtain the feedback processing coefficient, wherein the calculation formula of the feedback processing coefficient is as follows: ； In the formula, is the feedback processing coefficient, is the average feedback processing time, To feedback the response time, is the problem solving rate, is the average processing reference time for feedback, is the feedback response reference time, Reference resolution rate for issues; The friendly feedback data is processed to obtain the friendly feedback coefficient, and the specific steps are as follows: Acquiring friendly feedback parameter data stored in a database, wherein the friendly feedback parameter data stored in the database includes friendly feedback parameter density and user parameter retention rate; Obtaining weight data stored in a database, wherein the weight data stored in the database includes a friendly feedback parameter density weight factor and a user parameter retention rate weight factor; Processing the friendly feedback data, the weight data stored in the database, and the friendly feedback parameter data stored in the database to obtain a friendly feedback coefficient; The calculation formula of friendly feedback coefficient is as follows: ； In the formula, is the friendly feedback coefficient, For friendly feedback density, For user retention rate, To set the density for friendly feedback, Determine the retention rate for users. is the friendly feedback density weight factor stored in the database, The user retention rate weight factor stored in the database; The unfriendly feedback evaluation module is used to obtain user experience platform service feedback data, obtain unfriendly feedback data based on the user experience platform service feedback data, process the unfriendly feedback data, and determine the platform service unfriendly feedback level, wherein the unfriendly feedback data includes unfriendly feedback density, problem recurrence rate, and unfriendly feedback processing load; The unfriendly feedback data is processed to obtain the unfriendly feedback coefficient, and the specific steps are as follows: Acquire unfriendly feedback parameter data stored in a database, wherein the unfriendly feedback parameter data stored in the database includes unfriendly feedback parameter density, problem parameter recurrence rate, and unfriendly feedback parameter processing load; Processing the unfriendly feedback data with the unfriendly feedback parameter data stored in the database to obtain an unfriendly feedback coefficient; The calculation formula of the unfriendly feedback coefficient is as follows: ； In the formula, is the unfriendly feedback coefficient, For unfriendly feedback density, is the problem recurrence rate, Handling load for unfriendly feedback, Determine the density for unfriendly feedback, Determine the recurrence rate for the problem. Determine the processing load for unfriendly feedback; The comprehensive feedback evaluation module is used to obtain feedback processing data, and determine the comprehensive feedback evaluation level of the platform service based on the feedback processing data, friendly feedback data, and unfriendly feedback data. The feedback processing data includes the average feedback processing time, feedback response time, and problem resolution rate; The calculation formula of the comprehensive feedback index is as follows: ； In the formula, is the comprehensive feedback index, is the feedback processing coefficient, is the friendly feedback coefficient, is the unfriendly feedback coefficient, is a natural constant.

2. A user experience feedback system for platform services according to claim 1, characterized in that: The specific steps for determining the platform service friendly feedback level are as follows: The friendly feedback coefficient is compared with the platform service friendly feedback level corresponding to each friendly feedback coefficient stored in the database, and the platform service friendly feedback level corresponding to the successfully compared friendly feedback coefficient is obtained.

3. A user experience feedback system for platform services according to claim 2, characterized in that: The specific steps of determining the platform service unfriendly feedback level are as follows: The unfriendly feedback coefficient is compared with the platform service unfriendly feedback level corresponding to each unfriendly feedback coefficient stored in the database, and the platform service unfriendly feedback level corresponding to the unfriendly feedback coefficient that has been successfully compared is obtained.

Images