Service quality evaluation method and device, computer device and storage medium
By acquiring the current interaction data and historical evaluation results of the target object, and generating an evaluation template based on the evaluation items, the problem of insufficient accuracy in traditional service quality evaluation is solved, and a more accurate service quality evaluation is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN POWER SUPPLY BUREAU
- Filing Date
- 2023-11-14
- Publication Date
- 2026-06-23
AI Technical Summary
Traditional service quality assessment methods rely on subjective customer feedback, leading to lower accuracy in the assessment results.
By acquiring the current interaction data and historical evaluation results of the target object, the target evaluation item is determined based on the evaluation value of the historical evaluation item, a target evaluation template is generated, and the current interaction data is evaluated using the template. The evaluation template is updated in real time to adapt to the current data, thereby improving the evaluation accuracy.
This improves the accuracy of service quality assessment results, ensuring that the results are more consistent with reality and better reflect the service quality of the target audience.
Smart Images
Figure CN117495191B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a service quality assessment method, apparatus, computer equipment, storage medium, and computer program product. Background Technology
[0002] With the development of computer technology, power grid companies can provide convenient and high-quality services to users while providing electrical energy products. In order to improve service quality, it is necessary to evaluate the service and then adjust the way and content of providing services based on the service evaluation results.
[0003] In traditional techniques, customer feedback is typically collected through questionnaires. Service quality assessment results are obtained by analyzing the customer feedback. However, customer feedback is usually subjective, which leads to low accuracy in the service quality assessment results. Summary of the Invention
[0004] Therefore, it is necessary to provide a service quality assessment method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of service quality assessment results in response to the above-mentioned technical problems.
[0005] Firstly, this application provides a service quality assessment method. The method includes:
[0006] Obtain the current interaction data and historical evaluation results corresponding to the target object identifier;
[0007] Based on the historical evaluation values corresponding to the historical evaluation items in the historical evaluation results, the target evaluation item corresponding to the current interaction data is determined;
[0008] Based on the target evaluation items, generate the target evaluation template corresponding to the current interaction data;
[0009] Based on the target evaluation template and the current interaction data, the service quality of the target object corresponding to the target object identifier is evaluated to obtain the current evaluation result corresponding to the target object identifier.
[0010] In one embodiment, determining the target evaluation item corresponding to the current interaction data based on the historical evaluation values corresponding to the historical evaluation items in the historical evaluation results includes:
[0011] For each historical evaluation item, the average evaluation value corresponding to the historical evaluation item is determined based on the historical evaluation value of the historical evaluation item in the historical evaluation results;
[0012] The average evaluation value corresponding to the historical evaluation item is compared with the evaluation threshold corresponding to the historical evaluation item. If the average evaluation value is less than the evaluation threshold, the historical evaluation item is determined as the first reference evaluation item corresponding to the current interaction data.
[0013] The first reference evaluation item is input into the evaluation item determination model to obtain the target evaluation item corresponding to the current interaction data; the target evaluation item includes the first reference evaluation item and the second reference evaluation item, and the second reference evaluation item is determined by the evaluation item determination model based on at least one of the first reference evaluation items.
[0014] In one embodiment, generating the target evaluation template corresponding to the current interaction data based on the target evaluation item includes:
[0015] For each of the target evaluation items, a target category is determined; the target category is one of a combined evaluation item and a basic evaluation item.
[0016] If the target category of the target evaluation item is a combined evaluation item, then obtain the set of evaluation sub-items corresponding to the target evaluation item;
[0017] Obtain the average evaluation value corresponding to the target evaluation item; based on the average evaluation value and the set of evaluation sub-items, determine the target evaluation sub-items corresponding to the target evaluation item; the number of target evaluation sub-items is inversely proportional to the average evaluation value.
[0018] A target evaluation template is composed of at least one of the target evaluation items based on the target category as the basic evaluation item and the target evaluation sub-items corresponding to the target evaluation items whose target type is a combined evaluation item.
[0019] In one embodiment, the step of performing a service quality assessment on the target object corresponding to the target object identifier based on the target assessment template and the current interaction data, and obtaining the current assessment result corresponding to the target object identifier, includes:
[0020] For each target evaluation item in the target evaluation template, obtain the target category of the target evaluation item;
[0021] If the target category of the target evaluation item is a basic evaluation item, then the target evaluation method corresponding to the target evaluation item is obtained, and the target evaluation method is used to evaluate the current interaction data to obtain the current evaluation value of the target evaluation item.
[0022] If the target category of the target evaluation item is a combined evaluation item, then the target evaluation method corresponding to each target evaluation sub-item in the target evaluation item is obtained, and the target evaluation method is used to evaluate the current interaction data to obtain the sub-item evaluation value corresponding to the target evaluation sub-item; based on the sub-item evaluation values corresponding to each target evaluation sub-item, the current evaluation value corresponding to the target evaluation item is determined.
[0023] Based on the current evaluation value corresponding to each of the target evaluation items, the current evaluation result corresponding to the target object identifier is obtained.
[0024] In one embodiment, obtaining the current interaction data and historical evaluation results corresponding to the target object identifier includes:
[0025] When the target object corresponding to the target object identifier ends the service, the initial interaction data corresponding to the target object identifier is obtained;
[0026] Perform integrity checks on the initial interaction data to obtain the check results corresponding to the initial interaction data;
[0027] If the detection result is equal to or greater than the threshold, the initial interaction data is determined as the current interaction data corresponding to the target object identifier;
[0028] Obtain the interaction time corresponding to the current interaction data, and obtain the historical evaluation results corresponding to the target object identifier within a preset time period adjacent to the interaction time.
[0029] In one embodiment, the method further includes:
[0030] If the detection result is less than the threshold, then the service object identifier corresponding to the initial interaction data and the service interaction data corresponding to the service object identifier are obtained.
[0031] The service interaction data is used as the initial interaction data corresponding to the target object identifier, and the step of performing integrity detection on the initial interaction data and obtaining the detection result corresponding to the initial interaction data is repeated.
[0032] In one embodiment, the method further includes:
[0033] Obtain the feedback result corresponding to the current evaluation result;
[0034] The current evaluation result is optimized based on the feedback result to obtain the target evaluation result;
[0035] Analyze the current interaction data to determine the interaction features corresponding to the current interaction data;
[0036] Based on the target evaluation results and the interaction features, a training scheme corresponding to the target object identifier is generated.
[0037] Secondly, this application also provides a service quality assessment device. The device includes:
[0038] The acquisition module is used to acquire the current interaction data and historical evaluation results corresponding to the target object identifier;
[0039] The determination module is used to determine the target evaluation item corresponding to the current interaction data based on the historical evaluation values corresponding to the historical evaluation items in the historical evaluation results;
[0040] The generation module is used to generate a target evaluation template corresponding to the current interaction data based on the target evaluation item.
[0041] The evaluation module is used to evaluate the service quality of the target object corresponding to the target object identifier based on the target evaluation template and the current interaction data, and obtain the current evaluation result corresponding to the target object identifier.
[0042] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described in the first aspect.
[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.
[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the first aspects.
[0045] The aforementioned service quality assessment method, apparatus, computer equipment, storage medium, and computer program product acquire current interaction data and historical assessment results corresponding to the target object identifier; based on the historical assessment values corresponding to historical assessment items in the historical assessment results, determine the target assessment item corresponding to the current interaction data; based on the target assessment item, generate a target assessment template corresponding to the current interaction data; based on the target assessment template and the current interaction data, perform a service quality assessment on the target object corresponding to the target object identifier, and obtain the current assessment result corresponding to the target object identifier. By determining the target assessment item through the historical assessment results corresponding to the target object identifier, generating the target assessment template corresponding to the current interaction data based on the target assessment item, and updating the target assessment template in real time, the target assessment template is more suitable for evaluating the current interaction data corresponding to the target object identifier. Using the target assessment template and the current interaction data to perform a service quality assessment on the target object corresponding to the target object identifier, and obtaining the current assessment result corresponding to the target object identifier, the accuracy of the current assessment result is improved. Attached Figure Description
[0046] Figure 1 This is a diagram illustrating the application environment of a service quality assessment method in one embodiment.
[0047] Figure 2 This is a flowchart illustrating a service quality assessment method in one embodiment;
[0048] Figure 3 This is a flowchart illustrating the steps for determining the target evaluation item in one embodiment;
[0049] Figure 4 This is a flowchart illustrating the target evaluation template determination step in one embodiment;
[0050] Figure 5 This is a flowchart illustrating the steps for determining the current evaluation result in one embodiment;
[0051] Figure 6 This is a flowchart illustrating the current interactive data acquisition step in one embodiment;
[0052] Figure 7 This is a flowchart illustrating the steps for determining the training scheme in one embodiment;
[0053] Figure 8 This is a flowchart illustrating the service quality assessment process in one embodiment;
[0054] Figure 9 This is a flowchart illustrating the service quality assessment process in another embodiment;
[0055] Figure 10 This is a structural block diagram of a service quality assessment device in one embodiment;
[0056] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0058] The service quality assessment method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated on server 104 or placed on the cloud or other network servers. Both the terminal and server can be used independently to execute the service quality assessment method provided in this embodiment. The terminal and server can also be used collaboratively to execute the service quality assessment method provided in this embodiment. For example, the terminal obtains the current interaction data and historical assessment results corresponding to the target object identifier; based on the historical assessment values corresponding to the historical assessment items in the historical assessment results, it determines the target assessment item corresponding to the current interaction data; based on the target assessment item, it generates the target assessment template corresponding to the current interaction data; based on the target assessment template and the current interaction data, it performs a service quality assessment on the target object corresponding to the target object identifier, obtaining the current assessment result corresponding to the target object identifier. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.
[0059] In one embodiment, such as Figure 2 As shown, a service quality assessment method is provided. This embodiment uses the application of this method to computer equipment as an example for illustration, including steps 202 to 208.
[0060] Step 202: Obtain the current interaction data and historical evaluation results corresponding to the target object identifier.
[0061] The target object identifier is a string representing the target object. It can consist of numbers, characters, and symbols, and there is a one-to-one correspondence between the target object identifier and the target object. Current interaction data refers to the most recent service interaction data of the target object corresponding to the target object identifier. Interaction data refers to the communication data between the target object and the service object, and can be text or voice data. Historical evaluation results refer to the evaluation results already obtained. Historical evaluation results can be evaluation results within a preset time period. Each historical evaluation result corresponds to a historical evaluation template, and multiple historical evaluation results can have the same or different historical evaluation templates.
[0062] For example, when the target object corresponding to the target object identifier finishes a service, the terminal obtains the current interaction data and historical evaluation results corresponding to the target object identifier.
[0063] Step 204: Based on the historical evaluation values corresponding to the historical evaluation items in the historical evaluation results, determine the target evaluation item corresponding to the current interactive data.
[0064] Here, "historical evaluation items" refers to the evaluation items in historical evaluation results. This can be understood as evaluation items within historical evaluation templates, with each historical evaluation result including at least one historical evaluation item. "Historical evaluation values" refer to the project evaluation results corresponding to historical evaluation items. "Target evaluation items" refer to the evaluation items used to evaluate the current interactive data, i.e., the evaluation items that make up the target evaluation template.
[0065] For example, the terminal determines the target evaluation item corresponding to the current interaction data based on the historical evaluation value corresponding to the historical evaluation item in the historical evaluation results.
[0066] Step 206: Based on the target evaluation items, generate the target evaluation template corresponding to the current interaction data.
[0067] The target evaluation template refers to the evaluation template used to evaluate the current interaction data.
[0068] For example, the terminal assembles the target evaluation items into a target evaluation template corresponding to the current interaction data.
[0069] Step 208: Based on the target evaluation template and the current interaction data, perform a service quality evaluation on the target object corresponding to the target object identifier to obtain the current evaluation result corresponding to the target object identifier.
[0070] Here, the target object refers to the object providing the service. The current evaluation result refers to the result of evaluating the current interaction data.
[0071] For example, the terminal uses the target evaluation template to evaluate the current interaction data and obtains the current evaluation result of the target object corresponding to the target object identifier.
[0072] In this embodiment, the target evaluation item is determined by the historical evaluation results corresponding to the target object identifier. Based on the target evaluation item, the target evaluation template corresponding to the current interaction data is generated. The target evaluation template is updated in real time. The target evaluation template is more suitable for evaluating the current interaction data corresponding to the target object identifier. The target evaluation template and the current interaction data are used to evaluate the service quality of the target object corresponding to the target object identifier, and the current evaluation result corresponding to the target object identifier is obtained, which improves the accuracy of the current evaluation result.
[0073] In one embodiment, such as Figure 3 As shown, based on the historical evaluation values corresponding to the historical evaluation items in the historical evaluation results, the target evaluation item corresponding to the current interaction data is determined, including:
[0074] Step 302: For each historical evaluation item, determine the average evaluation value corresponding to the historical evaluation item based on the historical evaluation value of the historical evaluation item in the historical evaluation results.
[0075] The average evaluation value refers to the average of multiple historical evaluation values corresponding to a historical evaluation item.
[0076] For example, for each historical evaluation item, the terminal obtains the historical evaluation value corresponding to the historical evaluation item from each historical evaluation result, and then averages the multiple historical evaluation values to obtain the average evaluation value corresponding to the historical evaluation item.
[0077] Step 304: Compare the average evaluation value corresponding to the historical evaluation item with the evaluation threshold corresponding to the historical evaluation item. If the average evaluation value is less than the evaluation threshold, then the historical evaluation item is determined as the first reference evaluation item corresponding to the current interaction data.
[0078] The evaluation threshold refers to the minimum evaluation value determined as the first reference evaluation item. Different historical evaluation items can correspond to different evaluation thresholds, and different historical evaluation items can also correspond to the same evaluation threshold. The first reference evaluation item refers to the target evaluation item determined based on the average evaluation value and the evaluation threshold.
[0079] For example, the terminal obtains the evaluation threshold corresponding to the historical evaluation item, compares the average evaluation value corresponding to the historical evaluation item with the evaluation threshold corresponding to the historical evaluation item, and if the average evaluation value is less than the evaluation threshold, the historical evaluation item is determined as the first reference evaluation item corresponding to the current interaction data; if the average evaluation value is greater than or equal to the evaluation threshold, the historical evaluation item is determined as a non-first reference evaluation item.
[0080] Step 306: Input the first reference evaluation item into the evaluation item determination model to obtain the target evaluation item corresponding to the current interaction data; the target evaluation item includes the first reference evaluation item and the second reference evaluation item, and the second reference evaluation item is determined by the evaluation item determination model based on at least one first reference evaluation item.
[0081] The evaluation item determination model refers to the model that determines the second reference evaluation item based on the first reference evaluation item. This evaluation item determination model is a trained neural network model. The second reference evaluation item refers to the evaluation item determined by the evaluation item determination model based on the first reference evaluation item.
[0082] For example, the terminal inputs a first reference evaluation item into the evaluation item determination model to obtain a second reference evaluation item, and then combines the first reference evaluation item and the second reference evaluation item into a target evaluation item.
[0083] In this embodiment, historical evaluation items with average evaluation values less than an evaluation threshold are identified as first reference evaluation items. This means that analysis of historical evaluation values for these items shows that the target object's score for that item is relatively low, reflecting a low service quality for that target object. Therefore, these historical evaluation items need to be used to evaluate the current interaction data. This method improves the accuracy of the first reference evaluation item. The evaluation item determination model predicts a second reference evaluation item based on the first reference evaluation item. The second reference evaluation item can refine the evaluation of the current interaction data. By identifying the first and second reference evaluation items as target evaluation items, the accuracy of the target evaluation items is improved.
[0084] In one embodiment, such as Figure 4 As shown, based on the target evaluation items, a target evaluation template corresponding to the current interaction data is generated, including:
[0085] Step 402: For each target evaluation item, determine the target category of the target evaluation item; the target category is one of the combined evaluation items and the basic evaluation items.
[0086] Here, "target category" refers to the category of the target evaluation item. "Combined evaluation item" refers to an evaluation item that includes multiple evaluation sub-items, and "basic evaluation item" refers to an evaluation item that does not contain any evaluation sub-items.
[0087] For example, for each target evaluation item, the terminal obtains the target category of the target evaluation item.
[0088] Step 404: If the target category of the target evaluation item is a combined evaluation item, then obtain the set of evaluation sub-items corresponding to the target evaluation item.
[0089] The evaluation sub-item set refers to the set of multiple evaluation sub-items corresponding to the evaluation item, and the evaluation sub-item set corresponds one-to-one with the evaluation item.
[0090] For example, if the terminal determines that the target category of the target evaluation item is a combined evaluation item, then it obtains the set of evaluation sub-items corresponding to the target evaluation item.
[0091] Step 406: Obtain the average evaluation value corresponding to the target evaluation item. Based on the average evaluation value and the set of evaluation sub-items, determine the target evaluation sub-items corresponding to the target evaluation item. The number of target evaluation sub-items is inversely proportional to the average evaluation value.
[0092] For example, the terminal obtains the average evaluation value corresponding to the target evaluation item, determines the number of evaluation sub-items based on the average evaluation value, the number of target evaluation sub-items is inversely proportional to the average evaluation value, and then determines the target evaluation sub-item corresponding to the target evaluation item from the set of evaluation sub-items based on the number of evaluation sub-items.
[0093] Step 408: Based on the target category as the basic evaluation item, the target evaluation item is composed of at least one of the target evaluation sub-items corresponding to the target evaluation item whose target type is a combined evaluation item, forming a target evaluation template.
[0094] For example, if all target evaluation items correspond to target categories that are basic evaluation items, then target evaluation items based on target categories as basic evaluation items form a target evaluation template; if all target evaluation items correspond to target categories that are combined evaluation items, then target evaluation templates are formed based on target evaluation sub-items corresponding to target evaluation items whose target type is a combined evaluation item; if there are target evaluation items whose target category is a basic evaluation item and target evaluation items whose target type is a combined evaluation item, then target evaluation templates are formed based on target evaluation items whose target category is a basic evaluation item and target evaluation sub-items corresponding to target evaluation items whose target type is a combined evaluation item.
[0095] In this embodiment, by determining the target evaluation sub-items of the target evaluation item as a combined evaluation item, the target evaluation sub-items that make up the target evaluation template are obtained, providing the basic data for generating the target evaluation template.
[0096] In one embodiment, such as Figure 5 As shown, based on the target evaluation template and current interaction data, a service quality evaluation is performed on the target object corresponding to the target object identifier, resulting in the current evaluation result corresponding to the target object identifier, including:
[0097] Step 502: For each target evaluation item in the target evaluation template, obtain the target category of the target evaluation item.
[0098] For example, the terminal determines a target evaluation template, and before using the target evaluation template to evaluate the current interaction data, it obtains the target category of each target evaluation item in the target evaluation template.
[0099] Step 504: If the target category of the target evaluation item is the basic evaluation item, then obtain the target evaluation method corresponding to the target evaluation item, use the target evaluation method to evaluate the current interaction data, and obtain the current evaluation value of the target evaluation item.
[0100] The target evaluation method refers to the method used to evaluate the current interaction data and obtain the current evaluation value corresponding to the target evaluation item. If the target category of the target evaluation item is a basic evaluation item, then the target evaluation method corresponds one-to-one with the target evaluation item, and the target evaluation method is a pre-set calculation method. The current evaluation value refers to the evaluation value of the target evaluation item obtained by evaluating the current interaction data.
[0101] For example, if the terminal determines that the target category of the target evaluation item is the basic evaluation item, it will obtain the target evaluation method corresponding to the target evaluation item, use the target evaluation method to evaluate the current interaction data, and obtain the current evaluation value of the target evaluation item.
[0102] Step 506: If the target category of the target evaluation item is a combined evaluation item, then obtain the target evaluation method corresponding to each target evaluation sub-item in the target evaluation item, use the target evaluation method to evaluate the current interaction data, and obtain the sub-item evaluation value corresponding to the target evaluation sub-item; based on the sub-item evaluation values corresponding to each target evaluation sub-item, determine the current evaluation value corresponding to the target evaluation item.
[0103] If the target category of the target evaluation item is a combined evaluation item, then the target evaluation method corresponds one-to-one with the target evaluation sub-items in the target evaluation item.
[0104] For example, if the terminal determines that the target category of the target evaluation item is a combined evaluation item, then it obtains the target evaluation method corresponding to each target evaluation sub-item in the target evaluation item, uses the target evaluation method to evaluate the current interaction data, obtains the sub-item evaluation value corresponding to the target evaluation sub-item, and then performs a weighted average of the sub-item evaluation values corresponding to each target evaluation sub-item to obtain the current evaluation value corresponding to the target evaluation item.
[0105] Step 508: Based on the current evaluation value corresponding to each target evaluation item, obtain the current evaluation result corresponding to the target object identifier.
[0106] For example, the terminal combines the current evaluation values corresponding to each target evaluation item into the current evaluation result corresponding to the target object identifier.
[0107] In this embodiment, different methods are used to determine the current evaluation value of the target evaluation item according to the different target categories of the target evaluation item, which improves the accuracy of the target evaluation value. The current evaluation values corresponding to each target evaluation item are combined to form the current evaluation result corresponding to the target object identifier, thereby improving the accuracy of the current evaluation result.
[0108] In one embodiment, such as Figure 6 As shown, the current interaction data and historical evaluation results corresponding to the target object identifier are obtained, including:
[0109] Step 602: When the target object corresponding to the target object identifier ends the service, obtain the initial interaction data corresponding to the target object identifier.
[0110] Terminating service refers to ending communication with the service recipient.
[0111] For example, when the target object corresponding to the target object identifier ends its service, the terminal obtains the initial interaction data corresponding to the target object identifier.
[0112] Step 604: Perform integrity checks on the initial interaction data to obtain the check results corresponding to the initial interaction data.
[0113] Integrity detection refers to checking the integrity of the initial interaction data; the method of integrity detection is not limited. The detection result refers to the outcome obtained from the integrity detection.
[0114] For example, the terminal performs integrity checks on the initial interaction data and obtains the detection results corresponding to the initial interaction data.
[0115] Step 606: If the detection result is equal to or greater than the threshold, the initial interaction data is determined as the current interaction data corresponding to the target object identifier.
[0116] For example, the terminal compares the detection result with a threshold. If the detection result is equal to or greater than the threshold, the initial interaction data is determined as the current interaction data corresponding to the target object identifier.
[0117] Step 608: Obtain the interaction time corresponding to the current interaction data, and obtain the historical evaluation results corresponding to the target object identifier within a preset time period adjacent to the interaction time.
[0118] The interaction time refers to the start time when the target object provides services to the service object; it can be understood as the moment when the current interaction data occurs. The preset time period refers to a pre-set time period. The preset time period adjacent to the interaction time refers to the preset time period before the interaction time. For example, if the interaction time is 12:00 and the preset time period is 2 hours, then the preset time period adjacent to the interaction time is from 10:00 to 12:00.
[0119] For example, the terminal obtains the interaction time corresponding to the current interaction data, and obtains the historical evaluation results corresponding to the target object identifier within a preset time period adjacent to the interaction time.
[0120] In this embodiment, the initial interaction data where the detection result is equal to or greater than a threshold is determined as the current interaction data corresponding to the target object identifier. This ensures the integrity of the current interaction data and provides complete basic data for subsequent service quality assessment. Historical evaluation results corresponding to the target object identifier within a preset time period adjacent to the interaction time are selected; that is, historical evaluation results close to the interaction time are chosen. Historical evaluation results are real-time and have stronger reference value.
[0121] In one embodiment, obtaining the current interaction data and historical evaluation results corresponding to the target object identifier further includes:
[0122] If the detection result is less than the threshold, the service object identifier corresponding to the initial interaction data and the service interaction data corresponding to the service object identifier are obtained; the service interaction data is used as the initial interaction data corresponding to the target object identifier, and the steps of performing integrity detection on the initial interaction data are repeated to obtain the detection result corresponding to the initial interaction data.
[0123] Here, the service object identifier is a string that represents the service object. The service object is the object receiving the service; it can be a user or a consumer. Service interaction data refers to the communication data between the target pair and the service pair.
[0124] For example, the terminal compares the detection result with the threshold. If the detection result is less than the threshold, it obtains the service object identifier corresponding to the initial interaction data and the service interaction data corresponding to the service object identifier. The service interaction data is used as the initial interaction data corresponding to the target object identifier, and steps 604 to 606 are repeated.
[0125] In this embodiment, for initial interaction data whose detection result is less than the threshold, service interaction data is re-acquired based on the service object identifier corresponding to the initial interaction data, and then the service interaction data is subjected to integrity detection to ensure the integrity of the current interaction data.
[0126] In one embodiment, such as Figure 7 As shown, the method also includes:
[0127] Step 702: Obtain the feedback result corresponding to the current evaluation result.
[0128] The feedback result refers to the result of the target object responding to the current evaluation result.
[0129] For example, the terminal sends the current evaluation result to the target object, the target object sends the feedback result to the terminal, and the terminal obtains the feedback result corresponding to the current evaluation result.
[0130] Step 704: Optimize the current evaluation result based on the feedback result to obtain the target evaluation result.
[0131] The target evaluation result refers to the evaluation result obtained by optimizing the current evaluation result.
[0132] For example, the terminal modifies the current evaluation result based on the feedback result to obtain the target evaluation result.
[0133] Step 706: Analyze the current interaction data to determine the interaction features corresponding to the current interaction data.
[0134] Interaction features refer to the characteristics of the interaction between the target object and the service object. They can be understood as the interaction characteristics between the target object and the service object.
[0135] For example, the terminal inputs the current interaction data into the interaction feature extraction model to obtain the interaction features corresponding to the current interaction data.
[0136] Step 708: Based on the target evaluation results and interaction characteristics, generate a training plan corresponding to the target object identifier.
[0137] Among them, the training program refers to the plan used to train the target audience.
[0138] For example, the terminal generates a training plan corresponding to the target object identifier based on the target evaluation results and interaction characteristics.
[0139] In this embodiment, the current evaluation result is optimized based on the feedback from the target object, thereby improving the accuracy of the target evaluation result. A training plan corresponding to the target object identifier is generated based on the target evaluation result and interaction characteristics. The training plan is used to train the target object corresponding to the target object identifier, thereby improving the service quality of the target object.
[0140] In one exemplary embodiment, the service quality assessment system is as follows: Figure 8 As shown, it includes a data acquisition module, an identification and processing module, a quality inspection management module, a quality assessment module, a result management module, a feedback tracking module, and a training and supervision module. The output of the data acquisition module is communicatively connected to the input of the identification and processing module, the output of the identification and processing module is communicatively connected to the input of the quality assessment module, the output of the quality inspection management module is communicatively connected to the input of the quality assessment module, the output of the quality assessment module is communicatively connected to the input of the result management module, the output of the result management module is communicatively connected to the input of the feedback tracking module, and the output of the feedback tracking module is communicatively connected to the input of the training and supervision module.
[0141] The data acquisition module is used to acquire communication data generated by customer service personnel during service delivery in real time, including call voice data and platform chat log data. The data acquisition module includes an audio data acquisition unit and a record data acquisition unit. The audio data acquisition unit acquires the call voice data of customer service personnel, and the record data acquisition unit acquires the chat log data of customer service personnel from various platforms.
[0142] The recognition and processing module decodes the real-time communication data acquired by the data acquisition module and then performs content recognition processing to obtain the processed communication data. The module includes a decoding processing unit and a recognition processing unit. The output of the decoding processing unit is communicatively connected to the input of the recognition processing unit. The decoding processing unit performs decoding preprocessing on the real-time communication data acquired by the data acquisition module to obtain preprocessed communication data. This mainly includes decoding processing such as integrity detection, generally with a preset integrity level of no less than 85%. If the integrity detection fails, re-acquisition is required. The recognition processing unit performs content recognition processing on the preprocessed communication data obtained from the decoding processing unit to obtain the processed communication data with accurate content.
[0143] The quality inspection management module manages quality inspection feature templates, including creation, combination, modification, and deletion. Quality inspection features include basic features and combined features. Basic features include volume features, silence features, speech rate features, interruption features, emotion features, and script features. Combined features are obtained by combining any two or more basic features. The quality inspection management module includes a feature storage unit and a feature operation unit. The feature storage unit is bidirectionally connected to the feature operation unit. The feature storage unit stores quality inspection features, while the feature operation unit manages the feature storage unit, performing creation, combination, modification, and deletion operations on the stored quality inspection features to ensure that the quality inspection feature templates are always up-to-date and adaptable to ever-changing service needs.
[0144] The quality assessment module is used to automatically assess the quality of communication data processed by the identification processing module according to the preset quality inspection feature templates in the quality inspection management module, and obtain the quality assessment result. The quality assessment module includes a receiving unit and a comparison unit. The output end of the receiving unit is communicatively connected to the input end of the comparison unit. The receiving unit is used to receive the communication data processed by the identification processing module and the quality inspection features of the quality inspection management module. The comparison unit is used to compare and analyze the communication data and quality inspection features in the receiving unit, and then perform quality assessment on the communication data to obtain the quality assessment result.
[0145] The results management module stores and manages the quality assessment results obtained from the quality assessment module. It marks, categorizes, and organizes the results, generating a visual quality inspection report. The module includes a results storage unit, a results organization unit, and a report generation unit. The output of the results storage unit is communicatively connected to the input of the results organization unit, and vice versa. The results storage unit stores the quality assessment results obtained from the quality assessment module. The results organization unit marks, categorizes, and organizes the stored results. The report generation unit generates a visual quality inspection report based on the organized results, allowing managers to easily view the results, quickly identify problems, and assess trends.
[0146] The feedback tracking module is used to conduct follow-up visits and track results with relevant customer service personnel based on the quality inspection results in the quality inspection report, identifying and correcting any issues found in the report. The feedback tracking module includes a follow-up unit and a report optimization unit. The output of the follow-up unit is communicatively connected to the input of the report optimization unit. The follow-up unit is used to conduct follow-up visits and track results with relevant customer service personnel based on the quality inspection report generated by the results management module, promptly identifying any issues found in the report. The report optimization unit is used to correct any issues found in the quality inspection report and update and optimize the report.
[0147] The training supervision module is used to confirm the quality assessment results of customer service personnel based on the quality inspection report updated and optimized by the feedback tracking module, and to generate training plans for customer service personnel to provide targeted training and supervision. The training supervision module includes a result confirmation unit, a training unit, and a supervision unit. The output of the result confirmation unit is communicatively connected to the input of the training unit, and the output of the training unit is communicatively connected to the input of the supervision unit. The result confirmation unit confirms the quality assessment results of customer service personnel based on the quality inspection report updated and optimized by the feedback tracking module. The training unit generates training plans for the corresponding customer service personnel based on the quality assessment results confirmed in the result confirmation unit, and trains the corresponding customer service personnel according to the training plans. Personalized training for customer service personnel can effectively improve shortcomings and enhance their service quality. The supervision unit supervises and manages the service process of customer service personnel after training by the training unit.
[0148] In one exemplary embodiment, the service quality assessment system is as follows: Figure 9As shown, it also includes an optimization module. The input of the optimization module is communicatively connected to the output of the data acquisition module. The optimization module is used to mine and analyze feature information from the communication data obtained by the data acquisition module based on customer feedback, in order to optimize the service process. The optimization module includes an information mining unit, an information analysis unit, and a service optimization unit. The output of the information mining unit is communicatively connected to the input of the information analysis unit, and the output of the information analysis unit is communicatively connected to the input of the service optimization unit. The information mining unit is used to mine feature information from the communication data obtained by the data acquisition module based on customer feedback. The feature information includes customer needs, sentiment tendencies, and satisfaction ratings. The information analysis unit is used to perform data analysis on the feature information obtained from the information mining unit to derive service optimization strategies. The service optimization unit is used to further train customer service personnel based on the service optimization strategies obtained from the information analysis unit to improve service quality.
[0149] An optimization suggestion unit can also be added, allowing customer service personnel to provide feedback on the quality evaluation system in order to better adapt to actual needs and provide more comprehensive, efficient, and high-quality customer service.
[0150] In the above service quality assessment method, the target assessment item is determined by the historical assessment results corresponding to the target object identifier. Based on the target assessment item, the target assessment template corresponding to the current interaction data is generated. The target assessment template is updated in real time. The target assessment template is more suitable for assessing the current interaction data corresponding to the target object identifier. The service quality of the target object corresponding to the target object identifier is assessed by using the target assessment template and the current interaction data, and the current assessment result corresponding to the target object identifier is obtained, which improves the accuracy of the current assessment result.
[0151] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.
[0152] Based on the same inventive concept, this application also provides a service quality assessment apparatus for implementing the service quality assessment method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more service quality assessment apparatus embodiments provided below can be found in the limitations of the service quality assessment method described above, and will not be repeated here.
[0153] In one embodiment, such as Figure 10 As shown, a service quality assessment device is provided, including: an acquisition module 1002, a determination module 1004, a generation module 1006, and an assessment module 1008, wherein:
[0154] The acquisition module 1002 is used to acquire the current interaction data and historical evaluation results corresponding to the target object identifier;
[0155] The determination module 1004 is used to determine the target evaluation item corresponding to the current interactive data based on the historical evaluation value corresponding to the historical evaluation item in the historical evaluation results.
[0156] The generation module 1006 is used to generate a target evaluation template corresponding to the current interaction data based on the target evaluation item.
[0157] The evaluation module 1008 is used to evaluate the service quality of the target object corresponding to the target object identifier based on the target evaluation template and the current interaction data, and obtain the current evaluation result corresponding to the target object identifier.
[0158] In one embodiment, the determining module 1004 is further configured to: for each historical evaluation item, determine the average evaluation value corresponding to the historical evaluation item based on the historical evaluation value of the historical evaluation item in the historical evaluation results; compare the average evaluation value corresponding to the historical evaluation item with the evaluation threshold corresponding to the historical evaluation item; if the average evaluation value is less than the evaluation threshold, determine the historical evaluation item as the first reference evaluation item corresponding to the current interaction data; input the first reference evaluation item into the evaluation item determining model to obtain the target evaluation item corresponding to the current interaction data; the target evaluation item includes the first reference evaluation item and the second reference evaluation item, and the second reference evaluation item is determined by the evaluation item determining model based on at least one first reference evaluation item.
[0159] In one embodiment, the generation module 1006 is further configured to: for each target evaluation item, determine the target category of the target evaluation item; the target category is one of a combined evaluation item and a basic evaluation item; if the target category of the target evaluation item is a combined evaluation item, obtain the set of evaluation sub-items corresponding to the target evaluation item; obtain the average evaluation value corresponding to the target evaluation item, and determine the target evaluation sub-items corresponding to the target evaluation item based on the average evaluation value and the set of evaluation sub-items; the number of target evaluation sub-items is inversely proportional to the average evaluation value; and form a target evaluation template based on at least one of the target evaluation items that are basic evaluation items and the target evaluation sub-items corresponding to the target evaluation items that are combined evaluation items.
[0160] In one embodiment, the evaluation module 1008 is further configured to: for each target evaluation item in the target evaluation template, obtain the target category of the target evaluation item; if the target category of the target evaluation item is a basic evaluation item, obtain the target evaluation method corresponding to the target evaluation item, use the target evaluation method to evaluate the current interaction data, and obtain the current evaluation value of the target evaluation item; if the target category of the target evaluation item is a combined evaluation item, obtain the target evaluation method corresponding to each target evaluation sub-item in the target evaluation item, use the target evaluation method to evaluate the current interaction data, and obtain the sub-item evaluation value corresponding to the target evaluation sub-item; determine the current evaluation value corresponding to the target evaluation item based on the sub-item evaluation values corresponding to each target evaluation sub-item; and obtain the current evaluation result corresponding to the target object identifier based on the current evaluation values corresponding to each target evaluation item.
[0161] In one embodiment, the acquisition module 1002 is further configured to: acquire the initial interaction data corresponding to the target object identifier when the target object corresponding to the target object identifier ends the service; perform integrity detection on the initial interaction data to obtain the detection result corresponding to the initial interaction data; if the detection result is equal to or greater than a threshold, determine the initial interaction data as the current interaction data corresponding to the target object identifier; acquire the interaction time corresponding to the current interaction data, and acquire the historical evaluation results corresponding to the target object identifier within a preset time period adjacent to the interaction time.
[0162] In one embodiment, the acquisition module 1002 is further configured to: if the detection result is less than a threshold, acquire the service object identifier corresponding to the initial interaction data and the service interaction data corresponding to the service object identifier; use the service interaction data as the initial interaction data corresponding to the target object identifier, and repeatedly perform the step of performing integrity detection on the initial interaction data to obtain the detection result corresponding to the initial interaction data.
[0163] In one embodiment, the evaluation module 1008 is further configured to: obtain feedback results corresponding to the current evaluation result; optimize the current evaluation result based on the feedback results to obtain a target evaluation result; analyze the current interaction data to determine the interaction features corresponding to the current interaction data; and generate a training scheme corresponding to the target object identifier based on the target evaluation result and the interaction features.
[0164] Each module in the aforementioned service quality assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can invoke and execute the corresponding operations of each module.
[0165] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 11 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a quality of service assessment method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.
[0166] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0167] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0168] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.
[0169] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.
[0170] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0171] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0172] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0173] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A service quality assessment method, characterized in that, The method includes: Obtain the current interaction data and historical evaluation results corresponding to the target object identifier; the current interaction data refers to the interaction data of the target object in the most recent service corresponding to the target object identifier, and the interaction data refers to the data of communication between the target object and the service object. The interaction data can be text data or voice data. For each historical evaluation item, an average evaluation value is determined based on the historical evaluation value of the historical evaluation item in the historical evaluation results. The average evaluation value of the historical evaluation item is compared with the evaluation threshold corresponding to the historical evaluation item. If the average evaluation value is less than the evaluation threshold, the historical evaluation item is determined as the first reference evaluation item corresponding to the current interaction data. The first reference evaluation item is input into the evaluation item determination model to obtain the target evaluation item corresponding to the current interaction data. The target evaluation item includes the first reference evaluation item and a second reference evaluation item, and the second reference evaluation item is determined by the evaluation item determination model based on at least one first reference evaluation item. For each target evaluation item, a target category is determined; the target category is either a combined evaluation item or a basic evaluation item; if the target category of the target evaluation item is a combined evaluation item, a set of evaluation sub-items corresponding to the target evaluation item is obtained; the average evaluation value corresponding to the target evaluation item is obtained, and based on the average evaluation value and the set of evaluation sub-items, a target evaluation sub-item corresponding to the target evaluation item is determined; the number of target evaluation sub-items is inversely proportional to the average evaluation value; a target evaluation template is formed based on at least one of the target evaluation items that are basic evaluation items and the target evaluation sub-items corresponding to target evaluation items that are combined evaluation items. For each target evaluation item in the target evaluation template, the target category of the target evaluation item is obtained; if the target category of the target evaluation item is a basic evaluation item, the target evaluation method corresponding to the target evaluation item is obtained, and the target evaluation method is used to evaluate the current interaction data to obtain the current evaluation value of the target evaluation item; if the target category of the target evaluation item is a combined evaluation item, the target evaluation method corresponding to each target evaluation sub-item in the target evaluation item is obtained, and the target evaluation method is used to evaluate the current interaction data to obtain the sub-item evaluation value corresponding to the target evaluation sub-item; based on the sub-item evaluation values corresponding to each target evaluation sub-item, the current evaluation value corresponding to the target evaluation item is determined; based on the current evaluation values corresponding to each target evaluation item, the current evaluation result corresponding to the target object identifier is obtained.
2. The method according to claim 1, characterized in that, The step of inputting the first reference evaluation item into the evaluation item determination model to obtain the target evaluation item corresponding to the current interaction data includes: The first reference evaluation item is input into the evaluation item determination model to obtain the second reference evaluation item; The first reference evaluation item and the second reference evaluation item are combined to form the target evaluation item corresponding to the current interaction data.
3. The method according to claim 1, characterized in that, The step of obtaining the average evaluation value corresponding to the target evaluation item, and determining the target evaluation sub-item corresponding to the target evaluation item based on the average evaluation value and the set of evaluation sub-items, includes: Obtain the average evaluation value corresponding to the target evaluation item; The number of evaluation items is determined based on the average evaluation value, and the number of evaluation items is inversely proportional to the average evaluation value. Based on the number of evaluation sub-items, the target evaluation sub-item corresponding to the target evaluation item is determined from the set of evaluation sub-items.
4. The method according to claim 1, characterized in that, The target evaluation template comprises at least one of the target evaluation items based on the target category as the basic evaluation item, and the target evaluation sub-items corresponding to the target evaluation items whose target category is a combined evaluation item, including: If all the target evaluation items correspond to target categories that are basic evaluation items, then the target evaluation items based on the target categories as basic evaluation items form a target evaluation template; If all the target evaluation items correspond to target categories that are combined evaluation items, then a target evaluation template is formed based on the target evaluation sub-items corresponding to the target evaluation items whose target categories are combined evaluation items; If there are target evaluation items with target category as the basic evaluation item and target evaluation items with target category as the combined evaluation item, then the target evaluation sub-items corresponding to the target evaluation items with target category as the basic evaluation item and the target evaluation items with target category as the combined evaluation item constitute the target evaluation template.
5. The method according to claim 1, characterized in that, The step of obtaining the current interaction data and historical evaluation results corresponding to the target object identifier includes: When the target object corresponding to the target object identifier ends the service, the initial interaction data corresponding to the target object identifier is obtained; Perform integrity checks on the initial interaction data to obtain the check results corresponding to the initial interaction data; If the detection result is equal to or greater than the threshold, the initial interaction data is determined as the current interaction data corresponding to the target object identifier; Obtain the interaction time corresponding to the current interaction data, and obtain the historical evaluation results corresponding to the target object identifier within a preset time period adjacent to the interaction time.
6. The method according to claim 5, characterized in that, The method further includes: If the detection result is less than the threshold, then the service object identifier corresponding to the initial interaction data and the service interaction data corresponding to the service object identifier are obtained. The service interaction data is used as the initial interaction data corresponding to the target object identifier, and the step of performing integrity detection on the initial interaction data and obtaining the detection result corresponding to the initial interaction data is repeated.
7. The method according to claim 1, characterized in that, The method further includes: Obtain the feedback result corresponding to the current evaluation result; The current evaluation result is optimized based on the feedback result to obtain the target evaluation result; Analyze the current interaction data to determine the interaction features corresponding to the current interaction data; Based on the target evaluation results and the interaction features, a training scheme corresponding to the target object identifier is generated.
8. A service quality assessment device, characterized in that, The device includes: The acquisition module is used to acquire the current interaction data and historical evaluation results corresponding to the target object identifier; the current interaction data refers to the interaction data of the target object corresponding to the target object identifier in the most recent service, and the interaction data refers to the data of communication between the target object and the service object, which can be text data or voice data. A determination module is configured to, for each historical evaluation item, determine the average evaluation value corresponding to the historical evaluation item based on the historical evaluation value of the historical evaluation item in the historical evaluation results; compare the average evaluation value corresponding to the historical evaluation item with the evaluation threshold corresponding to the historical evaluation item; if the average evaluation value is less than the evaluation threshold, then determine the historical evaluation item as the first reference evaluation item corresponding to the current interaction data; input the first reference evaluation item into the evaluation item determination model to obtain the target evaluation item corresponding to the current interaction data; the target evaluation item includes the first reference evaluation item and a second reference evaluation item, the second reference evaluation item being determined by the evaluation item determination model based on at least one first reference evaluation item; A generation module is used to determine the target category of each target evaluation item; the target category is one of a combined evaluation item and a basic evaluation item; if the target category of the target evaluation item is a combined evaluation item, then obtain the set of evaluation sub-items corresponding to the target evaluation item; obtain the average evaluation value corresponding to the target evaluation item, and determine the target evaluation sub-items corresponding to the target evaluation item based on the average evaluation value and the set of evaluation sub-items; the number of target evaluation sub-items is inversely proportional to the average evaluation value; and at least one of the target evaluation items based on the target category as basic evaluation items and the target evaluation sub-items corresponding to the target evaluation items with the target category as combined evaluation items is used to form a target evaluation template; The evaluation module is used to: obtain the target category of each target evaluation item in the target evaluation template; if the target category of the target evaluation item is a basic evaluation item, obtain the target evaluation method corresponding to the target evaluation item, use the target evaluation method to evaluate the current interaction data, and obtain the current evaluation value of the target evaluation item; if the target category of the target evaluation item is a combined evaluation item, obtain the target evaluation method corresponding to each target evaluation sub-item in the target evaluation item, use the target evaluation method to evaluate the current interaction data, and obtain the sub-item evaluation value corresponding to the target evaluation sub-item; determine the current evaluation value corresponding to the target evaluation item based on the sub-item evaluation values corresponding to each target evaluation sub-item; and obtain the current evaluation result corresponding to the target object identifier based on the current evaluation values corresponding to each target evaluation item.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.
11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.