Quality evaluation processing method and device based on service data, equipment and medium

Abstract

The invention discloses a quality evaluation processing method and device based on service data, equipment and a medium. Acquiring a current task to be subjected to quality evaluation in real time, and acquiring current service description data through a data acquisition layer; in the evaluation calculation layer, according to the current service description structured data and the current service description unstructured data, through an evaluation index system construction method, an evaluation index and an evaluation index weight are generated; according to each secondary evaluation index and the secondary evaluation index weight, calculation is carried out through a multi-algorithm fusion calculation method to obtain a current evaluation index calculation score, and a current abnormal root cause positioning result is determined in combination with an abnormal root cause positioning method; and carrying out analysis and display processing through the analysis and display layer to obtain a current visual analysis and display result, and feeding back the result. The problems of low service management efficiency and low accuracy caused by a manual sampling evaluation method and a simple data statistics software scheme are solved, and the efficiency and the accuracy of quality evaluation of the service data are improved.

Description

Technical Field

[0001] This invention relates to the field of service management data processing, and in particular to a method, apparatus, equipment, and medium for quality assessment processing based on service data. Background Technology

[0002] In service management scenarios within the field of computer software technology, such as e-commerce, finance, telecommunications, or online education—industries requiring large-scale customer service—technology for efficient and accurate service management is crucial.

[0003] In the process of developing this invention, the inventors discovered the following shortcomings in the existing technology: Currently, service quality management relies on manual sampling assessment methods to generate service quality reports, or on simple data statistical software solutions to calculate indicators for service management. However, manual sampling assessment methods lead to problems such as insufficient sample representativeness, low assessment efficiency, and significant influence from subjective factors; while simple data statistical software solutions result in problems such as a single assessment dimension, lack of correlation analysis, and low service management efficiency. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and medium for quality assessment processing based on service data, so as to improve the efficiency and accuracy of service data quality assessment.

[0005] According to one aspect of the present invention, a quality assessment processing method based on service data is provided, comprising:

[0006] The system acquires the current tasks to be evaluated in real time and collects the current service description data through the data acquisition layer based on the current tasks to be evaluated.

[0007] The current service description data includes structured data and unstructured data; the quality assessment and processing system based on service data includes a data acquisition layer, an assessment and calculation layer, and an analysis and display layer.

[0008] In the evaluation calculation layer, based on the current service description structured data and the current service description unstructured data, at least one primary evaluation indicator, as well as at least one secondary evaluation indicator and secondary evaluation indicator weights corresponding to each primary evaluation indicator are generated through a pre-set evaluation indicator system construction method.

[0009] In the evaluation calculation layer, the current evaluation index score is calculated by using a pre-set multi-algorithm fusion calculation method based on each of the secondary evaluation indicators and their weights. The current abnormal root cause location result is then determined by combining the pre-set abnormal root cause location method.

[0010] The analysis and display layer calculates scores for the current evaluation indicators and analyzes and displays the current root cause localization results to obtain the current visual analysis and display results, and then provides feedback to the user.

[0011] According to another aspect of the present invention, a quality assessment processing apparatus based on service data is provided, comprising:

[0012] The current service description data acquisition module is used to acquire the current quality assessment task in real time, and to collect the current service description data through the data acquisition layer according to the current quality assessment task.

[0013] The current service description data includes structured data and unstructured data; the quality assessment and processing system based on service data includes a data acquisition layer, an assessment and calculation layer, and an analysis and display layer.

[0014] The evaluation index and evaluation index weight generation module is used in the evaluation calculation layer to generate at least one primary evaluation index, and at least one secondary evaluation index and secondary evaluation index weight corresponding to each primary evaluation index, based on the current service description structured data and the current service description unstructured data, through a pre-set evaluation index system construction method.

[0015] The current anomaly root cause localization result determination module is used in the evaluation calculation layer to calculate the current evaluation index score according to each of the secondary evaluation indicators and the weight of the secondary evaluation indicators through a pre-set multi-algorithm fusion calculation method, and to determine the current anomaly root cause localization result by combining the pre-set anomaly root cause localization method.

[0016] The current visualization analysis and display result determination module is used to analyze and display the current evaluation index score and the current abnormal root cause location result through the analysis and display layer to obtain the current visualization analysis and display result and provide feedback to the user.

[0017] According to another aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the service data-based quality assessment processing method described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the service data-based quality assessment processing method according to any embodiment of the present invention.

[0019] The technical solution of this invention acquires the current quality assessment task in real time and collects current service description data through a data acquisition layer based on the current quality assessment task. In the assessment calculation layer, based on the current service description structured data and current service description unstructured data, at least one primary assessment indicator and at least one secondary assessment indicator and its weight are generated using a pre-set assessment indicator system construction method. In the assessment calculation layer, based on each secondary assessment indicator and its weight, a pre-set multi-algorithm fusion calculation method is used to calculate the current assessment indicator score, and combined with a pre-set anomaly root cause localization method, the current anomaly root cause localization result is determined. The analysis and display layer analyzes and displays the current assessment indicator score and the current anomaly root cause localization result to obtain a current visual analysis and display result, which is then fed back to the user. This solution solves the problems of low service management efficiency and low accuracy caused by manual sampling assessment methods and simple data statistics software solutions, improves the efficiency and accuracy of service data quality assessment, increases the diversity of assessment dimensions, and reduces the influence of subjective factors and the workload of manual analysis.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a quality assessment processing method based on service data provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a schematic diagram of a quality assessment processing device based on service data according to Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of an electronic device provided according to Embodiment 3 of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "target," "current," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] It is worth noting that the information collected in the technical solution of this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data all comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse; if the user chooses to refuse, the process will proceed to the expert decision-making process.

[0028] Example 1

[0029] Figure 1 The flowchart of a service data-based quality assessment processing method is provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of performing quality assessment processing calculations on the acquired service data. The method can be executed by a service data-based quality assessment processing device, which can be implemented in hardware and / or software.

[0030] Correspondingly, such as Figure 1 As shown, the method includes:

[0031] S110. Obtain the current task to be evaluated in real time, and collect the current service description data through the data acquisition layer according to the current task to be evaluated.

[0032] The current service description data includes structured data and unstructured data; the quality assessment and processing system based on service data includes a data acquisition layer, an assessment and calculation layer, and an analysis and display layer.

[0033] The quality assessment task currently pending can be either periodically issued or received in real time.

[0034] Specifically, the structured data for the current service description includes at least one of the following: customer service response time, customer waiting time, one-time problem resolution rate, number of customer complaints, customer satisfaction score, and customer service recommendation value; the unstructured data for the current service description includes at least one of the following: communication records between customer service representatives and customers, customer feedback text, and customer service ticket remarks.

[0035] In this embodiment, the current service description data can be collected in real time and synchronized at regular intervals. Specifically, the real-time collection interval can be set to be less than a preset time threshold, such as less than one minute. The regular synchronization time is 2:00 AM every day, which can complete the historical data.

[0036] The communication records between customer service representatives and customers can be transcripts of recorded phone calls or online chat logs. Customer feedback texts can be evaluation messages or questionnaire entries.

[0037] S120. In the evaluation calculation layer, based on the current service description structured data and the current service description unstructured data, at least one primary evaluation indicator, and at least one secondary evaluation indicator and secondary evaluation indicator weight corresponding to each primary evaluation indicator are generated through a pre-set evaluation indicator system construction method.

[0038] Optionally, the step of generating at least one primary evaluation indicator and at least one secondary evaluation indicator and its weight corresponding to each primary evaluation indicator, based on the current service description structured data and the current service description unstructured data, through a pre-set evaluation indicator system construction method, includes: generating primary structured evaluation indicators based on the customer service response time, customer waiting time, one-time problem resolution rate, number of customer complaints, customer satisfaction score, and customer service recommendation value, through the evaluation indicator system construction method; wherein, the primary structured evaluation indicator is a service efficiency evaluation indicator, which includes average response time and problem resolution result parameter values; generating a first primary unstructured evaluation indicator based on the communication records between the customer service representative and the customer, through the evaluation indicator system construction method; the first primary unstructured evaluation indicator is a professional service evaluation indicator, which includes the accuracy rate of professional terminology and the completeness of problem answers; generating a second primary unstructured evaluation indicator based on the communication records between the customer service representative and the customer and the customer service work order remarks information, through the evaluation indicator system construction method; the second primary unstructured evaluation indicator is a service attitude evaluation indicator, which includes the service attitude... The evaluation indicators include the percentage of positive statements; based on the customer feedback text, a third-level unstructured evaluation indicator is generated using the evaluation indicator system construction method; the third-level unstructured evaluation indicator is the customer feedback evaluation indicator; the customer feedback evaluation indicator includes customer satisfaction score and customer complaint rate; wherein, the first-level evaluation indicators include first-level structured evaluation indicators, first-level unstructured evaluation indicators, second-level unstructured evaluation indicators, and third-level unstructured evaluation indicators; the second-level evaluation indicators include average response time, problem resolution results, technical terminology accuracy rate, problem answer completeness, percentage of positive statements, customer satisfaction score, and customer complaint rate; the evaluation indicators are obtained and adjusted according to the target corresponding to the current quality evaluation task, and the weight adjustment optimization sub-method corresponding to the evaluation indicator system construction method is used to adjust and optimize the average response time, problem resolution results parameter value, technical terminology accuracy rate, problem answer completeness, percentage of positive statements, customer satisfaction score, and customer complaint rate respectively, generating average response time weight, problem resolution results parameter value weight, technical terminology accuracy rate weight, problem answer completeness weight, positive statement percentage weight, customer satisfaction score weight, and customer complaint rate weight.

[0039] Specifically, the average response time can be calculated using an evaluation indicator system based on customer service response time and customer waiting time. The average response time is the average time it takes for customer service to initially respond to a customer. Problem resolution results can be calculated based on the one-time resolution rate, the number of customer complaints, customer satisfaction scores, and customer service recommendation values. Specifically, the one-time resolution rate can be the percentage of orders where customer issues are resolved without transfer or secondary follow-up.

[0040] Furthermore, the accuracy rate of technical terminology can be measured by the percentage of correct use of product or business technical terms in customer service conversations out of the total number of uses; the completeness of problem-solving can be measured by the degree to which customer service responses cover the core needs of customer issues, specifically quantified on a scale of 0 to 100, and determined using a natural language processing model. The percentage of positive expressions can be measured by the percentage of polite phrases such as "Hello," "Please," or "Sorry" in customer service conversations. Customer satisfaction ratings can be the ratings given after customer service is completed. The customer complaint rate can be measured by the percentage of service orders that generate complaints out of the total number of service orders; for inverse indicators, such as the complaint rate, a positive score can be converted using a positive conversion formula: the positive score equals 100 points minus the actual complaint rate divided by the industry average complaint rate, and it is necessary to ensure that the direction of the indicators is consistent.

[0041] Accordingly, the accuracy rate of professional terminology, the completeness of answers to questions, the proportion of positive statements, customer satisfaction scores, and customer complaint rates can be calculated using one or more of the following: communication records between customer service representatives and customers, customer feedback texts, and customer service work order notes. Additionally, implicit attitudes (such as implicit dissatisfaction) in customer feedback texts can be identified using sentiment analysis models, categorizing text sentiment into positive, neutral, and negative categories. The proportion of negative sentiment is used as the implicit dissatisfaction rate and added to the service attitude indicators.

[0042] In addition, it is necessary to obtain the target adjustment evaluation index. Assuming that the target adjustment evaluation index is to improve the average response time, it is necessary to use the weight adjustment optimization sub-method to adjust and optimize the average response time, problem resolution result parameter value, technical terminology accuracy, problem answer completeness, positive expression ratio, customer satisfaction score, and customer complaint rate respectively. It is necessary to maximize the weight of the average response time and reduce the weight of other secondary evaluation indicators. Therefore, the weights of the average response time, problem resolution result parameter value, technical terminology accuracy, problem answer completeness, positive expression ratio, customer satisfaction score, and customer complaint rate can be generated.

[0043] Specifically, for the weight adjustment optimization sub-method, the initial weights of each secondary evaluation indicator can be determined by inviting multiple customer service management experts to score the importance of the indicators, and the final weights can be determined after consistency verification. However, in the process of use, it is necessary to adjust the parameters of the evaluation indicators in combination with the specific objectives.

[0044] S130. In the evaluation calculation layer, the current evaluation index score is calculated by using a pre-set multi-algorithm fusion calculation method based on each of the secondary evaluation indicators and the weight of the secondary evaluation indicators. The current abnormal root cause location result is determined by combining the pre-set abnormal root cause location method.

[0045] Optionally, the step of calculating the current evaluation indicator score based on each of the secondary evaluation indicators and their weights using a pre-set multi-algorithm fusion calculation method includes: quantifying the average response time and problem-solving outcome parameter values ​​using a pre-set mean quantification calculation method to obtain the average quantified response time and problem-solving outcome quantified parameter values; performing word matching and quantification calculations on the accuracy of professional terminology, the completeness of problem-solving answers, the proportion of positive statements, customer satisfaction scores, and customer complaint rates using a pre-set text classification model quantification method to obtain the quantified accuracy of professional terminology, the quantified completeness of problem-solving answers, the quantified proportion of positive statements, the quantified customer satisfaction scores, and the quantified customer complaint rates; and calculating the current evaluation indicator score using a multi-algorithm fusion calculation method based on the average quantified response time, the problem-solving outcome quantified parameter values, the quantified accuracy of professional terminology, the quantified completeness of problem-solving answers, the quantified proportion of positive statements, the quantified customer satisfaction scores, and the quantified customer complaint rates.

[0046] In this embodiment, the mean quantization calculation method can be a method of calculating the average value for structured data. Specifically, the average response time and problem resolution result parameter values ​​can be quantized to obtain the average quantized response time and problem resolution result quantized parameter values. For example, the average quantized response time is equal to the sum of the quotients of the response time of each individual service divided by the total number of services.

[0047] Among these methods, text classification model quantification can be used to quantify unstructured data. For example, first, a professional terminology lexicon can be built, which may contain correct terms such as product characteristics or business processes. Then, the complete content of the question and answer is segmented and matched with the lexicon, and the proportion of correctly matched terms to the total number of terms is calculated.

[0048] Therefore, by performing word matching and quantitative calculations on the accuracy of professional terminology, the completeness of answers to questions, the proportion of positive expressions, customer satisfaction scores, and customer complaint rates, we can obtain the quantitative accuracy of professional terminology, the quantitative completeness of answers to questions, the quantitative proportion of positive expressions, the quantitative customer satisfaction scores, and the quantitative customer complaint rates.

[0049] Optionally, the current evaluation indicator score is calculated using a multi-algorithm fusion calculation method based on the average quantitative response time, the quantitative parameter value of the problem resolution result, the quantitative accuracy rate of professional terminology, the quantitative completeness of the problem answer, the quantitative proportion of positive expression, the quantitative customer satisfaction score, and the quantitative customer complaint rate. This includes multiplying and summing the average response time, the quantitative parameter value of the problem resolution result, the quantitative accuracy rate of professional terminology, the quantitative completeness of the problem answer, the quantitative proportion of positive expression, the quantitative customer satisfaction score, and the quantitative customer complaint rate using a multi-algorithm fusion calculation method to obtain the current evaluation indicator score.

[0050] In this embodiment, the quantitative value of each secondary evaluation indicator needs to be converted into a value of 0-100 points through the maximum-minimum standardization conversion method. Specifically, the first difference between the actual value and the minimum value of the indicator is calculated; the second difference between the maximum value and the minimum value of the indicator is calculated; the standardized value is equal to the percentage value of the first difference divided by the second difference.

[0051] Furthermore, by employing a multi-algorithm fusion calculation method, the average quantitative response time, the quantitative parameter value of problem-solving results, the quantitative accuracy rate of professional terminology, the quantitative completeness of problem-solving, the quantitative proportion of positive expression, the quantitative customer satisfaction score, and the quantitative customer complaint rate are each multiplied by their corresponding weights, and the calculated products are summed to obtain the current evaluation indicator score. This method yields a more accurate current evaluation indicator score.

[0052] Optionally, determining the current anomaly root cause location result by combining a preset anomaly root cause location method includes: determining whether the current evaluation indicator calculation score meets the normal evaluation indicator calculation score conditions; if it does, providing feedback to the user; if it does not, using the association rule mining algorithm sub-method in the anomaly root cause location method, analyzing the relationship between the average quantitative response time, the quantitative parameter value of the problem resolution result, the quantitative accuracy rate of professional terminology, the quantitative completeness of the problem answer, the quantitative proportion of positive expression, the quantitative score of customer satisfaction, and the quantitative complaint rate of customers, and determining at least one indicator strong correlation result; using the decision tree model sub-method corresponding to the anomaly root cause location method, performing root cause location processing on each of the indicator strong correlation results, and obtaining the current anomaly root cause location result respectively.

[0053] In this embodiment, it is first necessary to determine whether the calculated score of the current evaluation indicator meets the normal evaluation indicator calculation conditions. If it does, it indicates a normal score value, and therefore, feedback needs to be provided to the user that the current quality evaluation task is within the normal range. Otherwise, it indicates an abnormal score value, and therefore, it is necessary to combine the association rule mining algorithm sub-method in the abnormal root cause localization method to analyze the relationship between average quantitative response time, quantitative parameter value of problem resolution results, quantitative accuracy rate of professional terminology, quantitative completeness of problem answering, quantitative proportion of positive expression, quantitative score of customer satisfaction, and quantitative complaint rate of customers, and determine at least one indicator with a strong correlation. Specifically, the association rule mining algorithm sub-method is first used to mine frequent itemsets. For example, it is found that the support of a response time greater than 60 seconds and the confidence of customer satisfaction less than 3 points are 0.35 and 0.82, indicating that the two are strongly correlated, which is also the result of a strong correlation between the indicators.

[0054] Furthermore, the root cause analysis can be performed on the strongly correlated results of each indicator using the decision tree model sub-method corresponding to the anomaly root cause localization method, thereby obtaining the current anomaly root cause localization result. Specifically, the strongly correlated results of the indicators in the above example can be further analyzed using the decision tree model sub-method to locate the root cause. For example, in the case of a sudden increase in complaints about a certain product, the model can output that the root cause is that customer service staff lack sufficient knowledge of the new features of the product.

[0055] S140. The analysis and display layer calculates the score of the current evaluation index and analyzes and displays the current abnormal root cause location result to obtain the current visual analysis and display result, and provides feedback to the user.

[0056] In this embodiment, the current evaluation index score and the current root cause localization result can be used to generate a multi-dimensional analysis report and visualization chart through the analysis and display layer, which is the current visualization analysis display result.

[0057] Specifically, current visualization analysis results can be displayed across multiple dimensions. For example, dimensions can be categorized by individual customer service representative, service team, or business scenario, and can be generated for different products or customer groups. Furthermore, report content can include overall score rankings, achievement rates for each indicator (e.g., based on industry benchmarks or company targets), root causes of abnormal indicators, and trend changes (e.g., score changes over the past 7 or 30 days). Visualization formats can include line charts (e.g., trends), bar charts (e.g., rankings), heatmaps (e.g., indicator correlation strength), or funnel charts (e.g., problem-solving processes), supporting keyword searches. For example, clicking on a customer service representative with a low score allows viewing their detailed indicator breakdown and corresponding dialogue samples.

[0058] Optionally, the service data-based quality assessment processing system includes an improved execution layer; after the analysis and display layer calculates scores for the current assessment indicators and analyzes and displays the current root cause localization method to obtain the current visual analysis and display result, the system further includes: matching the current visual analysis and display result with a preset analysis result strategy and method matching library corresponding to the improved execution layer; if a match is found, a current multi-dimensional strategy and method suggestion is obtained and fed back to the user; if a match is not found, the current visual analysis and display result is fed back to the user, so as to update and optimize the analysis result strategy and method matching library based on the current multi-dimensional strategy and method suggestion fed back by the user in real time.

[0059] In this embodiment, the current root cause localization result in the current visualization analysis display needs to be matched with the analysis result strategy method matching library. If a match is found, it means that there is a current multi-dimensional strategy method suggestion corresponding to the current root cause localization result in the database, and the correction is made according to the suggestion. Otherwise, if there is no match, it means that there is no current multi-dimensional strategy method suggestion corresponding to the current root cause localization result in the database, and the current visualization analysis display result needs to be fed back to the user, and the current multi-dimensional strategy method suggestion fed back by the user needs to be received in real time to update and optimize the analysis result strategy method matching library.

[0060] For improving the execution layer, targeted multi-dimensional strategy and method suggestions can be generated based on the analysis results, which can be divided into two categories. The first category is personalized training suggestions for individual customer service representatives. Specifically, training resources are matched based on the shortcomings of individual customer service representatives' indicators. For example, if the accuracy rate of professional terminology is less than 70%, online courses on product knowledge (corresponding to the terminology module for the shortcomings) and simulated dialogue practice training (including terminology error correction feedback) are recommended. If the average response time is greater than 50 seconds, a quick reply script optimization guide and training to improve multi-task processing efficiency can be recommended. At the same time, a training progress tracking table should be generated to record the customer service representatives' completion status and the improvement rate of indicators after training. The second category is enterprise operation optimization solutions, which are suggestions based on the root causes of anomalies at the team or scenario level. For example, if the customer waiting time suddenly increases during a certain period, it can be suggested to adjust the number of customer service representatives on duty during that period. If the one-time problem resolution rate of a certain product is less than 80%, it can be suggested to update the customer service script library of the product and add a pop-up prompt for common problems of the product to the customer service system. In addition, the recommendations can also include a resource allocation list (such as the required training resources or manpower adjustment plan) and an effect prediction model (such as predicting that the waiting time can be shortened to within 30 seconds after adding customer service).

[0061] Furthermore, after executing the above suggested steps, the corresponding indicators (such as the accuracy rate of professional terminology one week after training) can be recalculated through the evaluation calculation layer. An improvement effect comparison report can be generated based on the analysis decision layer. If the indicators in the report meet the standards (for example, the accuracy rate is greater than or equal to 85%), the loop is closed; if the standards are not met, the process returns to the current anomaly root cause localization method for re-localization, and the optimized solution is executed again.

[0062] The technical solution of this invention acquires the current quality assessment task in real time and collects current service description data through a data acquisition layer based on the current quality assessment task. In the assessment calculation layer, based on the current service description structured data and current service description unstructured data, at least one primary assessment indicator and at least one secondary assessment indicator and its weight are generated using a pre-set assessment indicator system construction method. In the assessment calculation layer, based on each secondary assessment indicator and its weight, a pre-set multi-algorithm fusion calculation method is used to calculate the current assessment indicator score, and combined with a pre-set anomaly root cause localization method, the current anomaly root cause localization result is determined. The analysis and display layer analyzes and displays the current assessment indicator score and the current anomaly root cause localization result to obtain a current visual analysis and display result, which is then fed back to the user. This solution solves the problems of low service management efficiency and low accuracy caused by manual sampling assessment methods and simple data statistics software solutions, improves the efficiency and accuracy of service data quality assessment, increases the diversity of assessment dimensions, and reduces the influence of subjective factors and the workload of manual analysis.

[0063] Example 2

[0064] Figure 2 This is a schematic diagram of a service data-based quality assessment processing device provided in Embodiment 2 of the present invention. The service data-based quality assessment processing device provided in this embodiment can be implemented by software and / or hardware, and can be configured in a terminal device or server to implement a service data-based quality assessment processing method according to the embodiments of the present invention. Figure 2 As shown, the device includes: a current service description data acquisition module 210, an evaluation index and evaluation index weight generation module 220, a current anomaly root cause location result determination module 230, and a current visualization analysis display result determination module 240.

[0065] The current service description data acquisition module 210 is used to acquire the current quality assessment task in real time, and to collect the current service description data through the data acquisition layer according to the current quality assessment task.

[0066] The current service description data includes structured data and unstructured data; the quality assessment and processing system based on service data includes a data acquisition layer, an assessment and calculation layer, and an analysis and display layer.

[0067] The evaluation index and evaluation index weight generation module 220 is used in the evaluation calculation layer to generate at least one primary evaluation index, and at least one secondary evaluation index and secondary evaluation index weight corresponding to each of the primary evaluation indexes, based on the current service description structured data and the current service description unstructured data, through a pre-set evaluation index system construction method.

[0068] The current anomaly root cause localization result determination module 230 is used in the evaluation calculation layer to calculate the current evaluation index score according to each of the secondary evaluation indicators and the weight of the secondary evaluation indicators through a pre-set multi-algorithm fusion calculation method, and determine the current anomaly root cause localization result in combination with the preset anomaly root cause localization method.

[0069] The current visualization analysis and display result determination module 240 is used to analyze and display the current evaluation index score and the current abnormal root cause location result through the analysis and display layer to obtain the current visualization analysis and display result and provide feedback to the user.

[0070] The technical solution of this invention acquires the current quality assessment task in real time and collects current service description data through a data acquisition layer based on the current quality assessment task. In the assessment calculation layer, based on the current service description structured data and current service description unstructured data, at least one primary assessment indicator and at least one secondary assessment indicator and its weight are generated using a pre-set assessment indicator system construction method. In the assessment calculation layer, based on each secondary assessment indicator and its weight, a pre-set multi-algorithm fusion calculation method is used to calculate the current assessment indicator score, and combined with a pre-set anomaly root cause localization method, the current anomaly root cause localization result is determined. The analysis and display layer analyzes and displays the current assessment indicator score and the current anomaly root cause localization result to obtain a current visual analysis and display result, which is then fed back to the user. This solution solves the problems of low service management efficiency and low accuracy caused by manual sampling assessment methods and simple data statistics software solutions, improves the efficiency and accuracy of service data quality assessment, increases the diversity of assessment dimensions, and reduces the influence of subjective factors and the workload of manual analysis.

[0071] Based on the above embodiments, the service data-based quality assessment processing system includes an improved execution layer.

[0072] Based on the above embodiments, the system further includes a current multi-dimensional strategy method suggestion determination module, which can be specifically used to: after the analysis and display layer calculates the score of the current evaluation index and analyzes and displays the current abnormal root cause localization method to obtain the current visual analysis and display result, perform matching processing with the current visual analysis and display result and the preset analysis result strategy method matching library corresponding to the improved execution layer; if a match is found, the current multi-dimensional strategy method suggestion is obtained and fed back to the user; if a match is not found, the current visual analysis and display result is fed back to the user, so as to update and optimize the analysis result strategy method matching library based on the current multi-dimensional strategy method suggestion fed back by the user in real time.

[0073] Based on the above embodiments, the current service description structured data includes at least one of the following: customer service response time, customer waiting time, one-time problem resolution rate, number of customer complaints, customer satisfaction score, and customer service recommendation value; the current service description unstructured data includes at least one of the following: communication records between customer service and customer, customer feedback text, and customer service ticket remarks.

[0074] Based on the above embodiments, the evaluation indicators and evaluation indicator weight generation module 220 can be specifically used to: generate primary structured evaluation indicators based on the customer service response time, customer waiting time, one-time problem resolution rate, number of customer complaints, customer satisfaction score, and customer service recommendation value, using the evaluation indicator system construction method; wherein, the primary structured evaluation indicators are service efficiency evaluation indicators, which include average response time and problem resolution result parameter values; generate a first primary unstructured evaluation indicator based on the communication records between customer service and customer, using the evaluation indicator system construction method; the first primary unstructured evaluation indicator is a professional service evaluation indicator, which includes the accuracy rate of professional terminology and the completeness of problem answers; generate a second primary unstructured evaluation indicator based on the communication records between customer service and customer and the customer service work order remarks information, using the evaluation indicator system construction method; the second primary unstructured evaluation indicator is a service attitude evaluation indicator, which includes the percentage of positive statements; and generate a second primary unstructured evaluation indicator based on the customer feedback text, using the evaluation... The indicator system construction method generates a third-level unstructured evaluation indicator; the third-level unstructured evaluation indicator is a customer feedback evaluation indicator; the customer feedback evaluation indicator includes customer satisfaction score and customer complaint rate; wherein, the first-level evaluation indicators include first-level structured evaluation indicators, first-level unstructured evaluation indicators, second-level unstructured evaluation indicators, and third-level unstructured evaluation indicators; the second-level evaluation indicators include average response time, problem resolution results, professional terminology accuracy rate, problem answer completeness, positive expression ratio, customer satisfaction score, and customer complaint rate; the evaluation indicators are obtained and adjusted according to the target corresponding to the current quality evaluation task, and the weight adjustment optimization sub-method corresponding to the evaluation indicator system construction method is used to adjust and optimize the average response time, problem resolution results parameter value, professional terminology accuracy rate, problem answer completeness, positive expression ratio, customer satisfaction score, and customer complaint rate respectively, generating the average response time weight, problem resolution results parameter value weight, professional terminology accuracy rate weight, problem answer completeness weight, positive expression ratio weight, customer satisfaction score weight, and customer complaint rate weight.

[0075] Based on the above embodiments, the current anomaly root cause localization result determination module 230 can be specifically used to: quantify the average response time and problem resolution result parameter values ​​respectively using a pre-set mean quantification calculation method to obtain the average quantified response time and problem resolution result quantified parameter values; perform word matching and quantification calculation on the accuracy of professional terms, the completeness of problem answers, the proportion of positive expression, the customer satisfaction score, and the customer complaint rate respectively using a pre-set text classification model quantification method to obtain the quantified accuracy of professional terms, the quantified completeness of problem answers, the quantified proportion of positive expression, the quantified customer satisfaction score, and the quantified customer complaint rate; and calculate the current evaluation indicator score using a multi-algorithm fusion calculation method based on the average quantified response time, the quantified parameter values ​​of problem resolution result, the quantified accuracy of professional terms, the quantified completeness of problem answers, the quantified proportion of positive expression, the quantified customer satisfaction score, and the quantified customer complaint rate.

[0076] Based on the above embodiments, the current anomaly root cause localization result determination module 230 can also be specifically used to: calculate the current evaluation index score by multiplying and summing the average quantitative response time, the quantitative parameter value of the problem resolution result, the quantitative accuracy rate of professional terminology, the quantitative completeness of the problem answer, the quantitative proportion of positive expression, the quantitative score of customer satisfaction, and the quantitative customer complaint rate, as well as the matching average response time weight, the quantitative parameter value weight of the problem resolution result, the quantitative accuracy rate weight of the problem answer, the quantitative completeness weight of the problem answer, the quantitative proportion of positive expression, the quantitative score of customer satisfaction, and the quantitative complaint rate weight.

[0077] Based on the above embodiments, the current anomaly root cause localization result determination module 230 can be specifically used to: determine whether the current evaluation indicator calculation score meets the normal evaluation indicator calculation score conditions; if it does, provide feedback to the user; if it does not, analyze the relationship between the average quantitative response time, the quantitative parameter value of the problem-solving result, the quantitative accuracy rate of professional terminology, the quantitative completeness of problem answering, the quantitative proportion of positive expression, the quantitative score of customer satisfaction, and the quantitative complaint rate of customers through the association rule mining algorithm sub-method in the anomaly root cause localization method, and determine at least one indicator strong correlation result; and perform root cause localization processing on each indicator strong correlation result through the decision tree model sub-method corresponding to the anomaly root cause localization method to obtain the current anomaly root cause localization result.

[0078] The service data-based quality assessment processing apparatus provided in the embodiments of the present invention can execute the service data-based quality assessment processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0079] Example 3

[0080] Figure 3 A schematic diagram of an electronic device 10, which can be used to implement Embodiment 3 of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0081] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0082] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0083] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as service data-based quality assessment processing methods.

[0084] In some embodiments, the service data-based quality assessment processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the service data-based quality assessment processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the service data-based quality assessment processing method by any other suitable means (e.g., by means of firmware).

[0085] The method includes: acquiring the current quality assessment task in real time, and collecting current service description data through a data acquisition layer based on the current quality assessment task; wherein, the current service description data includes structured data and unstructured data of the current service description; the service data-based quality assessment processing system includes a data acquisition layer, an assessment calculation layer, and an analysis and display layer; in the assessment calculation layer, based on the current service description structured data and current service description unstructured data, generating at least one primary assessment indicator, and at least one secondary assessment indicator and weight corresponding to each primary assessment indicator through a pre-set assessment indicator system construction method; in the assessment calculation layer, calculating the current assessment indicator score based on each secondary assessment indicator and the weight of the secondary assessment indicator through a pre-set multi-algorithm fusion calculation method, and determining the current anomaly root cause location result by combining it with a pre-set anomaly root cause location method; and analyzing and displaying the current assessment indicator score and the current anomaly root cause location result through the analysis and display layer to obtain the current visual analysis and display result, and providing feedback to the user.

[0086] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0088] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0089] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0090] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0091] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0092] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0093] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

[0094] Example 4

[0095] Embodiment 4 of the present invention also provides a computer-readable storage medium, wherein the computer-readable instructions, when executed by a computer processor, are used to perform a quality assessment processing method based on service data. The method includes: real-time acquisition of a current quality assessment task, and acquisition of current service description data through a data acquisition layer based on the current quality assessment task; wherein the current service description data includes structured current service description data and unstructured current service description data; the service data-based quality assessment processing system includes a data acquisition layer, an assessment calculation layer, and an analysis and display layer; in the assessment calculation layer, based on the current service description structured data and the current service description unstructured data... The system generates at least one primary evaluation indicator and at least one secondary evaluation indicator and its weight, corresponding to each primary evaluation indicator, through a pre-set evaluation indicator system construction method. In the evaluation calculation layer, a pre-set multi-algorithm fusion calculation method is used to calculate the current evaluation indicator score based on each secondary evaluation indicator and its weight. This score is then combined with a pre-set anomaly root cause localization method to determine the current anomaly root cause localization result. The analysis and display layer analyzes and displays the current evaluation indicator score and the current anomaly root cause localization result to obtain the current visual analysis and display result, which is then fed back to the user.

[0096] Of course, the computer-executable instructions provided in the embodiments of the present invention, which include a computer-readable storage medium, are not limited to the method operations described above, but can also perform related operations in the quality assessment processing based on service data provided in any embodiment of the present invention.

[0097] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0098] It is worth noting that in the above embodiments of quality assessment processing based on service data, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A quality assessment processing method based on service data, characterized in that, include: The system acquires the current tasks to be evaluated in real time and collects the current service description data through the data acquisition layer based on the current tasks to be evaluated. The current service description data includes structured data and unstructured data; the quality assessment and processing system based on service data includes a data acquisition layer, an assessment and calculation layer, and an analysis and display layer. In the evaluation calculation layer, based on the current service description structured data and the current service description unstructured data, at least one primary evaluation indicator, as well as at least one secondary evaluation indicator and secondary evaluation indicator weights corresponding to each primary evaluation indicator are generated through a pre-set evaluation indicator system construction method. In the evaluation calculation layer, the current evaluation index score is calculated by using a pre-set multi-algorithm fusion calculation method based on each of the secondary evaluation indicators and their weights. The current abnormal root cause location result is then determined by combining the pre-set abnormal root cause location method. The analysis and display layer calculates scores for the current evaluation indicators and analyzes and displays the current root cause localization results to obtain the current visual analysis and display results, and then provides feedback to the user.

2. The method according to claim 1, characterized in that, The service data-based quality assessment and processing system includes an improved execution layer; After the analysis and display layer calculates the score of the current evaluation index and analyzes and displays the current abnormal root cause localization method to obtain the current visual analysis and display result, the method further includes: Based on the current visualization analysis results, a matching process is performed with the preset analysis result strategy method matching library corresponding to the improved execution layer; If a match is found, the current multi-dimensional strategy method suggestion is obtained and fed back to the user. If there is no match, the current visualization analysis result will be fed back to the user so as to update and optimize the analysis result strategy method matching library based on the user's real-time feedback on the current multi-dimensional strategy method suggestions.

3. The method according to claim 1, characterized in that, The current service description structured data includes at least one of the following: customer service response time, customer waiting time, first-time problem resolution rate, number of customer complaints, customer satisfaction score, and customer service recommendation value; The unstructured data describing the current service includes at least one of the following: communication records between customer service representatives and customers, customer feedback text, and customer service ticket notes.

4. The method according to claim 3, characterized in that, The step of generating at least one primary evaluation indicator, and at least one secondary evaluation indicator and its weight corresponding to each primary evaluation indicator, based on the current service description structured data and the current service description unstructured data, through a pre-set evaluation indicator system construction method, includes: Based on the customer service response time, customer waiting time, one-time problem resolution rate, number of customer complaints, customer satisfaction score, and customer service recommendation value, a primary structured evaluation index is generated using the evaluation index system construction method. This primary structured evaluation index is a service efficiency evaluation index, which includes average response time and problem resolution result parameter values. Based on the communication records between the customer service representative and the customer, a first-level unstructured evaluation indicator is generated using the evaluation indicator system construction method. The first-level unstructured evaluation indicator is a professional service evaluation indicator, which includes the accuracy of professional terminology and the completeness of answering questions. Based on the communication records between the customer service representative and the customer and the customer service work order notes, a second-level unstructured evaluation indicator is generated using the evaluation indicator system construction method. The second-level unstructured evaluation indicator is a service attitude evaluation indicator, which includes the percentage of positive statements. Based on the customer feedback text, a third-level unstructured evaluation indicator is generated using the evaluation indicator system construction method; the third-level unstructured evaluation indicator is the customer feedback evaluation indicator; the customer feedback evaluation indicator includes customer satisfaction score and customer complaint rate; The primary evaluation indicators include primary structured evaluation indicators, primary unstructured evaluation indicators, primary unstructured evaluation indicators, and primary unstructured evaluation indicators; the secondary evaluation indicators include average response time, problem resolution results, accuracy of professional terminology, completeness of problem answers, percentage of positive statements, customer satisfaction score, and customer complaint rate. The evaluation indicators are obtained and adjusted according to the objectives corresponding to the current quality assessment task. Through the weight adjustment and optimization sub-method corresponding to the evaluation indicator system construction method, the average response time, problem resolution result parameter value, professional terminology accuracy, problem answer completeness, positive expression ratio, customer satisfaction score, and customer complaint rate are adjusted and optimized respectively, generating the weights of average response time, problem resolution result parameter value, professional terminology accuracy, problem answer completeness, positive expression ratio, customer satisfaction score, and customer complaint rate.

5. The method according to claim 4, characterized in that, The calculation of the current evaluation indicator score is performed based on each of the secondary evaluation indicators and their weights using a pre-set multi-algorithm fusion calculation method, including: By using a pre-set mean quantization calculation method, the average response time and problem resolution result parameter values ​​are quantized respectively to obtain the average quantized response time and problem resolution result quantized parameter values. The accuracy of professional terminology, the completeness of question answers, the proportion of positive expression, the customer satisfaction score, and the customer complaint rate are calculated by matching the word library using a pre-set text classification model. The results are: quantitative accuracy of professional terminology, quantitative completeness of question answers, quantitative proportion of positive expression, quantitative customer satisfaction score, and quantitative customer complaint rate. The current evaluation index score is calculated using a multi-algorithm fusion calculation method based on the average quantitative response time, the quantitative parameter value of problem resolution results, the quantitative accuracy rate of professional terminology, the quantitative completeness of problem answers, the quantitative proportion of positive expression, the quantitative score of customer satisfaction, and the quantitative customer complaint rate.

6. The method according to claim 5, characterized in that, The current evaluation index score is calculated using a multi-algorithm fusion calculation method based on the average quantitative response time, quantitative parameter values ​​of problem resolution results, quantitative accuracy rate of professional terminology, quantitative completeness of problem answers, quantitative proportion of positive expression, quantitative customer satisfaction score, and quantitative customer complaint rate. This score includes: The current evaluation index score is calculated by multiplying and summing the following parameters: average response time, problem resolution outcome parameter value, technical terminology accuracy rate, problem answer completeness rate, positive expression rate, customer satisfaction score, and customer complaint rate. These parameters are calculated based on the average response time weight, problem resolution outcome parameter value weight, technical terminology accuracy rate weight, problem answer completeness rate weight, positive expression rate weight, customer satisfaction score weight, and customer complaint rate weight.

7. The method according to claim 6, characterized in that, The determination of the current root cause localization result by combining the preset root cause localization method includes: Determine whether the current evaluation indicator score meets the normal evaluation indicator score calculation conditions. If it does, provide feedback to the user. If not satisfied, the association rule mining algorithm sub-method in the anomaly root cause localization method is used to analyze the relationship between the average quantitative response time, the quantitative parameter value of the problem resolution result, the quantitative accuracy of professional terminology, the quantitative completeness of problem answering, the quantitative proportion of positive expression, the quantitative score of customer satisfaction and the quantitative complaint rate of customers, and determine at least one indicator with a strong correlation. The root cause localization results of each indicator are processed by the decision tree model sub-method corresponding to the root cause localization method to obtain the current root cause localization results.

8. A quality assessment and processing device based on service data, characterized in that, include: The current service description data acquisition module is used to acquire the current quality assessment task in real time, and to collect the current service description data through the data acquisition layer according to the current quality assessment task. The current service description data includes structured data and unstructured data; the quality assessment and processing system based on service data includes a data acquisition layer, an assessment and calculation layer, and an analysis and display layer. The evaluation index and evaluation index weight generation module is used in the evaluation calculation layer to generate at least one primary evaluation index, and at least one secondary evaluation index and secondary evaluation index weight corresponding to each primary evaluation index, based on the current service description structured data and the current service description unstructured data, through a pre-set evaluation index system construction method. The current anomaly root cause localization result determination module is used in the evaluation calculation layer to calculate the current evaluation index score according to each of the secondary evaluation indicators and the weight of the secondary evaluation indicators through a pre-set multi-algorithm fusion calculation method, and to determine the current anomaly root cause localization result by combining the pre-set anomaly root cause localization method. The current visualization analysis and display result determination module is used to analyze and display the current evaluation index score and the current abnormal root cause location result through the analysis and display layer to obtain the current visualization analysis and display result and provide feedback to the user.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements a service data-based quality assessment processing method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute a service data-based quality assessment processing method as described in any one of claims 1-7.

Images