Complaint information processing method, device and equipment
Through the complaint model, the complaint information is processed, clustered and sorted, the problem of low processing flexibility in the existing technology is solved, and the quality inspection personnel can handle it in sequence according to the priorities of complaint information, improving the processing efficiency.
Patent Information
- Application Number
- CN202310540867.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-12
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the prior art, quality inspection personnel handle the complaint information at the moment of receiving the complaint information, resulting in low processing flexibility and important complaint information may not be processed in a timely manner.
Through the complaint model, multiple complaint information are processed, the object of complaint is obtained, the cause of the failure and the emotions of complaints are predicted, and the processing is carried out in clustering. The processing order is determined based on the number and emotions of the complaint information, and the processing flexibility is improved.
It has realized that quality inspection personnel handled the complaint information in sequence according to the priorities and urgent needs, improved the flexibility of handling complaint information, and ensured that important information was processed in a timely manner.
Smart Images

Figure CN118941301A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of computer technology, and specifically relates to a method, device and equipment for processing complaint information. Background Art
[0002] Quality inspectors can analyze the multiple complaint messages received one by one through manual investigation to determine the complaint objects corresponding to the multiple complaint messages and the fault causes corresponding to each complaint object, so as to make timely improvements to these complaint objects based on these fault causes.
[0003] In the related art, faced with complaint information from numerous users, quality inspectors usually process the complaint information in sequence according to the time when each complaint information is received.
[0004] However, processing multiple complaint information according to the receiving time will result in some important complaint information not being processed in a timely manner (for example, the complaint object corresponding to the complaint information has a serious fault problem, etc.), resulting in low flexibility in processing the complaint information. Summary of the invention
[0005] The present application provides a method, device and equipment for processing complaint information, so as to solve the defect of low flexibility in processing complaint information in the prior art.
[0006] In a first aspect, the present application provides a method for processing complaint information, including:
[0007] Get multiple complaint information received during the historical period;
[0008] For any complaint information, the complaint model is used to process the complaint information to obtain the complaint result, which includes: the complaint object, the predicted fault cause and the complaint sentiment;
[0009] Clustering the plurality of complaint information according to the complaint objects and predicted fault causes of the plurality of complaint information to obtain at least one complaint information set, wherein the complaint information set includes at least one complaint information;
[0010] Determining a processing order corresponding to the plurality of complaint information according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information;
[0011] The processing sequence is displayed, or the processing sequence is sent to a preset device.
[0012] In a possible implementation manner, clustering is performed on the plurality of complaint information according to the complaint objects and predicted fault causes of the plurality of complaint information to obtain at least one complaint information set, including:
[0013] According to the complaint objects of the plurality of complaint information, the plurality of complaint information are divided into at least one initial set, wherein the complaint objects of the complaint information included in the initial set are the same;
[0014] For any initial set, clustering is performed on the complaint information in the initial set according to the predicted fault cause of each complaint information in the initial set to obtain at least one complaint information set corresponding to the initial set.
[0015] In a possible implementation, clustering is performed on the complaint information in the initial set according to the predicted fault cause of each complaint information in the initial set to obtain at least one complaint information set corresponding to the initial set, including:
[0016] Determine the similarity of the predicted fault causes of each two complaint information in the initial set;
[0017] According to the similarity of the predicted fault causes of each two complaint information in the initial set, the complaint information in the initial set is clustered to obtain at least one complaint information set corresponding to the initial set.
[0018] In a possible implementation, determining the processing order corresponding to the plurality of complaint information according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information includes:
[0019] For any complaint information set, determining the first priority of each complaint information in the complaint information set according to the number of complaint information included in the complaint information set;
[0020] For any complaint information, determine the second priority of the complaint information according to the complaint sentiment of the complaint information;
[0021] The processing order of the plurality of complaint information is determined according to the first priority and the second priority of the plurality of complaint information.
[0022] In a possible implementation manner, determining the first priority of each complaint information in the complaint information set according to the number of complaint information included in the complaint information set includes:
[0023] If the number of complaint information included in the complaint information set is greater than or equal to a preset threshold, determining that the first priority of each complaint information in the complaint information set is a first value;
[0024] If the number of complaint information included in the complaint information set is less than the preset threshold, the first priority of each complaint information in the complaint information set is determined to be a second value, and the first value is greater than the second value.
[0025] In a possible implementation, determining the processing order of the plurality of complaint information according to the first priority and the second priority of the plurality of complaint information includes:
[0026] For any complaint information, weighted calculation is performed on the first priority and the second priority of the complaint information to obtain the target priority of the complaint information;
[0027] The processing order of the plurality of complaint information is determined according to the target priorities of the plurality of complaint information.
[0028] In a possible implementation manner, the complaint result further includes predictive maintenance measures; and the method further includes:
[0029] Obtaining a maintenance result of the first complaint information by after-sales personnel, wherein the maintenance result includes an actual fault cause and an actual maintenance measure, and the first complaint information is any one of the multiple complaint information;
[0030] updating the complaint model according to the maintenance result of the first complaint information and the complaint result of the first complaint information to obtain a first complaint model;
[0031] Obtaining correction information of the maintenance result by the quality inspector, wherein the correction information includes a correction fault cause and a correction maintenance measure;
[0032] The first complaint model is updated according to the correction information and the maintenance result.
[0033] In a second aspect, the present application provides a complaint information processing device, including: an acquisition module, a processing module, a determination module, a display module or a sending module, wherein:
[0034] The acquisition module is used to acquire multiple complaint information received within a historical period;
[0035] The processing module is used to process any complaint information through the complaint model to obtain a complaint result, which includes: the complaint object, the predicted fault cause and the complaint emotion;
[0036] The processing module is further used to cluster the plurality of complaint information according to the complaint objects and predicted fault causes of the plurality of complaint information to obtain at least one complaint information set, wherein the complaint information set includes at least one complaint information;
[0037] The determination module is used to determine the processing order corresponding to the plurality of complaint information according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information;
[0038] The display module is used to display the processing sequence;
[0039] The sending module is used to send the processing sequence to a preset device.
[0040] In a possible implementation manner, the processing module is specifically used to:
[0041] According to the complaint objects of the plurality of complaint information, the plurality of complaint information are divided into at least one initial set, wherein the complaint objects of the complaint information included in the initial set are the same;
[0042] For any initial set, clustering is performed on the complaint information in the initial set according to the predicted fault cause of each complaint information in the initial set to obtain at least one complaint information set corresponding to the initial set.
[0043] In a possible implementation manner, the processing module is further configured to:
[0044] Determine the similarity of the predicted fault causes of each two complaint information in the initial set;
[0045] According to the similarity of the predicted fault causes of each two complaint information in the initial set, the complaint information in the initial set is clustered to obtain at least one complaint information set corresponding to the initial set.
[0046] In a possible implementation manner, the determining module is specifically configured to:
[0047] For any complaint information set, determining the first priority of each complaint information in the complaint information set according to the number of complaint information included in the complaint information set;
[0048] For any complaint information, determine the second priority of the complaint information according to the complaint sentiment of the complaint information;
[0049] The processing order of the plurality of complaint information is determined according to the first priority and the second priority of the plurality of complaint information.
[0050] In a possible implementation manner, the determining module is further configured to:
[0051] If the number of complaint information included in the complaint information set is greater than or equal to a preset threshold, determining that the first priority of each complaint information in the complaint information set is a first value;
[0052] If the number of complaint information included in the complaint information set is less than the preset threshold, the first priority of each complaint information in the complaint information set is determined to be a second value, and the first value is greater than the second value.
[0053] In a possible implementation manner, the determining module is further configured to:
[0054] For any complaint information, weighted calculation is performed on the first priority and the second priority of the complaint information to obtain the target priority of the complaint information;
[0055] The processing order of the plurality of complaint information is determined according to the target priorities of the plurality of complaint information.
[0056] In a possible implementation manner, the complaint information processing device further includes an updating module, wherein:
[0057] The acquisition module is used to obtain the maintenance result of the after-sales personnel on the first complaint information, the maintenance result including the actual fault cause and the actual maintenance measures, and the first complaint information is any one of the multiple complaint information;
[0058] The updating module is used to update the complaint model according to the maintenance result of the first complaint information and the complaint result of the first complaint information to obtain a first complaint model;
[0059] The acquisition module is also used to obtain the correction information of the maintenance result by the quality inspector, wherein the correction information includes the correction fault cause and the correction maintenance measures;
[0060] The updating module is used to update the first complaint model according to the correction information and the maintenance result.
[0061] In a third aspect, the present application provides a complaint information processing device, including: a processor and a memory;
[0062] The memory is used to store computer-executable instructions;
[0063] The processor is used to execute the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects.
[0064] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method as described in any one of the first aspects.
[0065] In a fifth aspect, the present application provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the method as described in any one of the first aspects is implemented.
[0066] The complaint information processing method, device and equipment provided by the present application obtain multiple complaint information received in a historical period; and for any complaint information, the complaint information can be processed through a complaint model to obtain a complaint result; multiple complaint information is clustered according to the complaint objects and predicted fault causes of the multiple complaint information to obtain at least one complaint information set; the processing order corresponding to the multiple complaint information is determined according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information; the processing order is displayed, or the processing order is sent to a preset device. By determining the processing order of multiple complaint information, it is helpful for quality inspectors to process multiple complaint information in sequence according to the importance of the complaint information, thereby improving the flexibility of processing complaint information. BRIEF DESCRIPTION OF THE DRAWINGS
[0067] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0068] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application;
[0069] Figure 2 A flowchart of a method for processing complaint information provided in an embodiment of the present application;
[0070] Figure 3 A schematic diagram of a clustering process of multiple complaint information provided in an embodiment of the present application;
[0071] Figure 4 A flowchart of another method for processing complaint information provided in an embodiment of the present application;
[0072] Figure 5 A method for updating a complaint model provided in an embodiment of the present application;
[0073] Figure 6 A schematic diagram of the structure of a complaint information processing device provided in an embodiment of the present application;
[0074] Figure 7A schematic diagram of the structure of another device for processing complaint information provided in an embodiment of the present application;
[0075] Figure 8 A schematic diagram of the structure of a complaint information processing device provided in an embodiment of the present application.
[0076] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0077] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0078] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein, for example.
[0079] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.
[0080] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present application. Figure 1 , including a complaint information processing device, in which a complaint model is set. Multiple complaint information can be processed by the complaint information processing device to obtain the processing order of the multiple complaint information. After obtaining the processing order of the multiple complaint information, the quality inspector or after-sales personnel can determine the urgency of the processing of the multiple complaint information according to the processing order, and process the complaint information in order according to the urgency.
[0081] In the related art, when faced with numerous user complaints, quality inspectors usually process the complaints one by one according to the time each complaint was received. However, processing multiple complaint messages according to the time they were received will result in some important complaint messages not being processed in a timely manner (for example, the object of the complaint corresponding to the complaint message has a serious fault problem, etc.), resulting in low flexibility in the processing of complaint messages.
[0082] In response to the above problems, the present application provides a method for processing complaint information, which can process multiple complaint information through a complaint model to obtain the complaint object, predicted fault cause and complaint sentiment corresponding to each complaint information; cluster multiple complaint information according to the complaint object and predicted fault cause corresponding to each complaint information to obtain at least one complaint information set; and then determine the processing order of multiple complaint information according to the number of complaint information included in each complaint information set and the complaint sentiment of each complaint information; and can also display the processing order, or send the processing order to a preset device. By determining the processing order of multiple complaint information, it is beneficial for quality inspectors or after-sales personnel to process multiple complaint information in sequence according to the importance of the complaint information, thereby improving the flexibility of processing complaint information.
[0083] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0084] Figure 2 A flowchart of a method for processing complaint information provided in an embodiment of the present application. Figure 2 , the method may include:
[0085] S201: Acquire multiple complaint information received within a historical period.
[0086] The execution subject of the embodiment of the present application may be a complaint information processing device, or a complaint information processing apparatus provided in the complaint information processing device. The complaint information processing apparatus may be implemented by software, or by a combination of software and hardware.
[0087] Multiple complaint information can be obtained from the after-sales service platform, and the complaint information can include voice complaint information and text complaint information. For example, the voice complaint information can be the voice call information generated by the user complaining to the customer service staff via the phone; the text complaint information can be the text information generated by the user complaining to the customer service staff via the after-sales service application or after-sales service webpage.
[0088] Optionally, the device for processing complaint information may be a tablet computer, a laptop computer, a desktop computer, a portable computer or a smart phone, etc.
[0089] S202: For any complaint information, the complaint information is processed through the complaint model to obtain the complaint result.
[0090] The complaint results may include: the object of the complaint, the predicted cause of the fault and the complaint sentiment. The complaint results may also include the reason for the complaint.
[0091] The complaint model may be an Artificial Intelligence generated content (AIGC) model, or the complaint model may be a ChatGPT (Chat Generative Pre-trained Transformer) model.
[0092] Optionally, the complaint model can be used to perform keyword extraction processing on the complaint information. For example, the complaint information can be subjected to keyword extraction processing to obtain the complaint object keywords and complaint reason keywords corresponding to the complaint information.
[0093] Optionally, the object of the complaint may be a product, or a component or function of a product. For example, the object of the complaint may be a washing machine, a display panel of the washing machine, or a dry cleaning function of the washing machine.
[0094] S203: Clustering the multiple complaint information according to the complaint objects and predicted fault causes of the multiple complaint information to obtain at least one complaint information set.
[0095] The complaint information set may include at least one complaint information.
[0096] In order to facilitate the understanding of the process of clustering multiple complaint information, Figure 3 , the clustering process of multiple complaint information is explained.
[0097] Figure 3 A schematic diagram of a clustering process of multiple complaint information provided in an embodiment of the present application. Figure 3 , including four complaint information, each complaint information can include the complaint object and the predicted fault cause.
[0098] Among them, the complaint objects and predicted fault causes in complaint information 1 and complaint information 3 are the same, so complaint information 1 and complaint information 3 can be clustered to obtain complaint information set 1. The complaint objects and predicted fault causes in complaint information 2 and complaint information 4 are the same, so complaint information 2 and complaint information 4 can be clustered to obtain complaint information set 2.
[0099] By clustering multiple complaint information, batch complaint objects or batch failure causes in the multiple complaint information can be determined, thereby avoiding repeated processing of multiple complaint information corresponding to the batch complaint objects or batch failure causes by quality inspectors or after-sales personnel, thereby improving the processing efficiency of complaint information.
[0100] S204: Determine a processing order corresponding to the plurality of complaint information according to the number of complaint information included in at least one complaint information set and the complaint sentiment of each complaint information.
[0101] Optionally, the processing order of multiple complaint information can be determined in the following manner: for any complaint information set, determine the first priority of each complaint information in the complaint information set based on the number of complaint information included in the complaint information set; for any complaint information, determine the second priority of the complaint information based on the complaint sentiment of the complaint information; determine the processing order of multiple complaint information based on the first priority and second priority of the multiple complaint information.
[0102] S205: Display the processing sequence, or send the processing sequence to a preset device.
[0103] For example, the complaint information processing device can display the above processing sequence to after-sales personnel or quality inspectors, or the complaint information processing device can send the above processing sequence to the work platform of after-sales personnel or quality inspectors, so that after-sales personnel or quality inspectors can handle the faults corresponding to the batch complaint objects in the important complaint information in a timely manner according to the above processing sequence, avoid the subsequent occurrence of complaint information of the same type, and reduce user complaints.
[0104] The method for processing complaint information provided in this embodiment obtains multiple complaint information received in a historical period; and for any complaint information, the complaint information can be processed through a complaint model to obtain a complaint result; the multiple complaint information is clustered according to the complaint objects and predicted fault causes of the multiple complaint information to obtain at least one complaint information set; the processing order corresponding to the multiple complaint information is determined according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information; the processing order can also be displayed, or the processing order can be sent to a preset device. By determining the processing order of multiple complaint information, it is beneficial for quality inspectors to process multiple complaint information in sequence according to the importance of the complaint information, thereby improving the flexibility of processing complaint information.
[0105] Based on any of the above embodiments, Figure 4 ,right Figure 2 The method for processing complaint information shown in the embodiment is further described in detail.
[0106] Figure 4 A flowchart of another method for processing complaint information provided in an embodiment of the present application. Figure 4 , the method may include:
[0107] S401: Acquire multiple complaint information received within a historical period.
[0108] S402: For any complaint information, the complaint information is processed through the complaint model to obtain the complaint result.
[0109] It should be noted that the specific execution process of S401 to S402 may refer to S201 to S202 and will not be described in detail here.
[0110] S403: Divide the plurality of complaint information into at least one initial set according to the complaint objects of the plurality of complaint information.
[0111] The complaint objects of each complaint information included in the initial set are the same.
[0112] For example, suppose there are 5 complaint information, namely complaint information 1 to complaint information 5. Among them, the complaint objects of complaint information 1, complaint information 2 and complaint information 3 are product A, and the complaint objects of complaint information 4 and complaint information 5 are product B. Then, complaint information 1 to complaint information 3 can be divided into an initial set corresponding to product A, and complaint information 4 to complaint information 5 can be divided into an initial set corresponding to product B.
[0113] S404: For any initial set, cluster the complaint information in the initial set according to the predicted fault cause of each complaint information in the initial set to obtain at least one complaint information set corresponding to the initial set.
[0114] Specifically, at least one complaint information set corresponding to the initial set can be obtained in the following manner: determine the similarity of the predicted fault causes of each two complaint information in the initial set; cluster the complaint information in the initial set according to the similarity of the predicted fault causes of each two complaint information in the initial set to obtain at least one complaint information set corresponding to the initial set.
[0115] Optionally, a similarity threshold can be preset. If the similarity of the predicted fault causes of every two complaint information is greater than or equal to the similarity threshold, the two complaint information are clustered; if the similarity of the predicted fault causes of every two complaint information is less than the similarity threshold, no clustering is performed.
[0116] For example, the preset similarity threshold is 85%. In the initial set corresponding to product A above, if the similarity between the predicted fault cause of complaint information 1 and the predicted fault cause of complaint information 2 is 88%, and the similarity between the predicted fault cause of complaint information 1 and the predicted fault cause of complaint information 3 is 30%, then complaint information 1 and complaint information 2 can be clustered to obtain a complaint information set.
[0117] S405: For any complaint information set, determine the first priority of each complaint information in the complaint information set according to the number of complaint information included in the complaint information set.
[0118] Optionally, the first priority of each complaint information can be determined in the following manner: if the number of complaint information included in the complaint information set is greater than or equal to a preset threshold, then the first priority of each complaint information in the complaint information set is determined to be a first numerical value; if the number of complaint information included in the complaint information set is less than the preset threshold, then the first priority of each complaint information in the complaint information set is determined to be a second numerical value, and the first numerical value is greater than the second numerical value.
[0119] Optionally, for any complaint information set, the first priority of each complaint information in the complaint information set may be averaged to obtain the first priority of the complaint information set.
[0120] S406: For any complaint information, determine the second priority of the complaint information according to the complaint sentiment of the complaint information.
[0121] Optionally, the complaint emotion may be assigned a value according to the emotion intensity. The larger the assigned value is, the stronger the user's complaint emotion is, and the higher the value of the second priority of the complaint information is.
[0122] For example, the value range of the emotional intensity of the complaint emotion may be between 0 and 10, and the corresponding relationship between the emotional intensity of the complaint emotion and the numerical value of the second priority of the complaint emotion may be as shown in Table 1:
[0123] Table 1
[0124]
[0125] It can be seen from Table 1 that when the value corresponding to the emotional intensity of the complaint emotion is 10, the second priority value of the complaint emotion is 100, and at this time the second priority of the complaint information is the highest.
[0126] Optionally, for any complaint information set, the second priority of each complaint information in the complaint information set may be averaged to obtain the second priority of the complaint information set.
[0127] S407: Determine the processing order of the multiple complaint information according to the target priorities of the multiple complaint information.
[0128] Optionally, the processing order of multiple complaint information can be determined in the following manner: for any complaint information, the first priority and the second priority of the complaint information are weighted to obtain the target priority of the complaint information; and the processing order of the multiple complaint information is determined according to the target priorities of the multiple complaint information.
[0129] Optionally, for any complaint information set, the target priority of the complaint information set can be obtained by comparing the first priority and the second priority corresponding to the complaint information set; and the processing order of the multiple complaint information sets can be determined according to the target priorities of the multiple complaint information sets.
[0130] S408: Display the processing sequence, or send the processing sequence to a preset device.
[0131] It should be noted that the execution process of S408 can refer to the execution process of S205, which will not be described in detail here.
[0132] The method for processing complaint information provided in this embodiment obtains multiple complaint information received in a historical period; and for any complaint information, the complaint information can be processed through a complaint model to obtain a complaint result; the multiple complaint information is clustered according to the complaint objects and predicted fault causes of the multiple complaint information to obtain at least one complaint information set; the processing order corresponding to the multiple complaint information is determined according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information; the processing order can also be displayed, or the processing order can be sent to a preset device. By determining the processing order of multiple complaint information, it is beneficial for quality inspectors or after-sales personnel to process multiple complaint information in sequence according to the importance of the complaint information, thereby improving the flexibility of processing complaint information.
[0133] In a possible implementation, for any complaint information, the complaint information is processed by the complaint model, and the obtained complaint result may also include predicted maintenance measures. In practical applications, the complaint model may be updated to make the predicted maintenance measures predicted by the complaint model more accurate.
[0134] Next, combine Figure 5 , the updating method of the complaint model is explained.
[0135] Figure 5 A method for updating a complaint model provided in an embodiment of the present application. Figure 5 , the method specifically comprises:
[0136] S501: Obtain the repair result of the after-sales personnel for the first complaint information.
[0137] The maintenance result may include the actual cause of the fault and the actual maintenance measures, and the first complaint information may be any one of multiple complaint information.
[0138] Optionally, the maintenance results may be processed for keyword extraction through the complaint model to obtain actual fault cause keywords and actual maintenance measure keywords.
[0139] S502: Update the complaint model according to the maintenance result of the first complaint information and the complaint result of the first complaint information to obtain a first complaint model.
[0140] Optionally, a first sample training set may be constructed using maintenance results and complaint results of multiple first complaint information, and the complaint model may be retrained using the first sample training set to obtain a first complaint model.
[0141] After executing S502, the method may further include the following steps:
[0142] S503: Obtaining the correction information of the maintenance result by the quality inspector.
[0143] The correction information may include correction of the cause of the fault and correction of the repair measures.
[0144] S504: Update the first complaint model according to the correction information and maintenance results.
[0145] A second sample training set may be constructed using maintenance results and correction information of a plurality of first complaint information, and the first complaint model may be retrained using the second sample training set to update the first complaint model.
[0146] The update method of the complaint model provided in this embodiment can obtain the repair result of the after-sales personnel on the first complaint information, and update the complaint model according to the repair result of the first complaint information and the complaint result of the first complaint information; it can also obtain the correction information of the repair result by the quality inspection personnel, and update the complaint model according to the correction information and the repair result. During the use of the complaint model, the complaint model can be updated multiple times through the repair results and correction information to improve the prediction accuracy of the complaint model.
[0147] Figure 6 This is a schematic diagram of a complaint information processing device provided in an embodiment of the present application. Figure 6The complaint information processing device 10 includes: an acquisition module 11, a processing module 12, a determination module 13, a display module 14 or a sending module 15, wherein:
[0148] The acquisition module 11 is used to acquire multiple complaint information received within a historical period;
[0149] The processing module 12 is used to process any complaint information through the complaint model to obtain a complaint result, which includes: the complaint object, the predicted fault cause and the complaint emotion;
[0150] The processing module 12 is further used to cluster the plurality of complaint information according to the complaint objects and predicted fault causes of the plurality of complaint information to obtain at least one complaint information set, wherein the complaint information set includes at least one complaint information;
[0151] The determination module 13 is used to determine the processing order corresponding to the plurality of complaint information according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information;
[0152] The display module 14 is used to display the processing sequence;
[0153] The sending module 15 is used to send the processing sequence to a preset device.
[0154] The complaint information processing device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.
[0155] In a possible implementation manner, the processing module 12 is specifically configured to:
[0156] According to the complaint objects of the plurality of complaint information, the plurality of complaint information are divided into at least one initial set, wherein the complaint objects of the complaint information included in the initial set are the same;
[0157] For any initial set, clustering is performed on the complaint information in the initial set according to the predicted fault cause of each complaint information in the initial set to obtain at least one complaint information set corresponding to the initial set.
[0158] In a possible implementation manner, the processing module 12 is further configured to:
[0159] Determine the similarity of the predicted fault causes of each two complaint information in the initial set;
[0160] According to the similarity of the predicted fault causes of each two complaint information in the initial set, the complaint information in the initial set is clustered to obtain at least one complaint information set corresponding to the initial set.
[0161] In a possible implementation manner, the determining module 13 is specifically configured to:
[0162] For any complaint information set, determining the first priority of each complaint information in the complaint information set according to the number of complaint information included in the complaint information set;
[0163] For any complaint information, determine the second priority of the complaint information according to the complaint sentiment of the complaint information;
[0164] The processing order of the plurality of complaint information is determined according to the first priority and the second priority of the plurality of complaint information.
[0165] In a possible implementation manner, the determining module 13 is specifically configured to:
[0166] If the number of complaint information included in the complaint information set is greater than or equal to a preset threshold, determining that the first priority of each complaint information in the complaint information set is a first value;
[0167] If the number of complaint information included in the complaint information set is less than the preset threshold, the first priority of each complaint information in the complaint information set is determined to be a second value, and the first value is greater than the second value.
[0168] In a possible implementation manner, the determining module 13 is specifically configured to:
[0169] For any complaint information, weighted calculation is performed on the first priority and the second priority of the complaint information to obtain the target priority of the complaint information;
[0170] The processing order of the plurality of complaint information is determined according to the target priorities of the plurality of complaint information.
[0171] Figure 7 This is a schematic diagram of another device for processing complaint information provided in an embodiment of the present application. Figure 7 ,exist Figure 6 Based on the structure of the complaint information processing device shown in FIG. 1 , the complaint information processing device 10 further includes an updating module 16, wherein:
[0172] The acquisition module 11 is further used to obtain a maintenance result of the after-sales personnel on the first complaint information, wherein the maintenance result includes an actual fault cause and an actual maintenance measure, and the first complaint information is any one of the multiple complaint information;
[0173] The updating module 16 is used to update the complaint model according to the maintenance result of the first complaint information and the complaint result of the first complaint information to obtain a first complaint model;
[0174] The acquisition module 11 is also used to obtain the correction information of the maintenance result by the quality inspector, wherein the correction information includes the correction fault cause and the correction maintenance measures;
[0175] The updating module 16 is further used to update the first complaint model according to the correction information and the maintenance result.
[0176] The complaint information processing device provided in the embodiment of the present application can execute the technical solution shown in the above method embodiment. Its implementation principle and beneficial effects are similar and will not be repeated here.
[0177] Figure 8 This is a schematic diagram of a complaint information processing device provided in an embodiment of the present application. Figure 8 The complaint information processing device 20 includes: a receiver 21, a transmitter 22, a processor 23 and a memory 24.
[0178] A receiver 21, for receiving instructions and data;
[0179] A transmitter 22, used for sending instructions and data;
[0180] Memory 24, used to store computer-executable instructions;
[0181] The processor 23 is used to execute the computer-executable instructions stored in the memory 24 to implement the various steps performed by the method for processing complaint information in any of the above embodiments. For details, please refer to the relevant description in the above embodiment of the method for processing complaint information.
[0182] Optionally, the memory 24 may be independent or integrated with the processor 23 .
[0183] When the memory 24 is independently provided, the electronic device further includes a bus for connecting the memory 24 and the processor 23 .
[0184] Optionally, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.
[0185] The present application also provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, a method for processing complaint information as executed by the complaint information processing device mentioned above is implemented.
[0186] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the computer executes the above-mentioned method for processing complaint information.
[0187] All or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a readable memory. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned memory (storage medium) includes: read-only memory (English: read-only memory, abbreviated: ROM), RAM, flash memory, hard disk, solid state drive, magnetic tape (English: magnetic tape), floppy disk (English: floppy disk), optical disc (English: optical disc) and any combination thereof.
[0188] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processing unit of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0189] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0190] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0191] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A method for processing complaint information, It is characterized in that include: Get multiple complaint information received during the historical period; For any complaint information, the complaint model is used to process the complaint information to obtain the complaint result, which includes: the complaint object, the predicted fault cause and the complaint sentiment; Clustering the plurality of complaint information according to the complaint objects and predicted fault causes of the plurality of complaint information to obtain at least one complaint information set, wherein the complaint information set includes at least one complaint information; Determining a processing order corresponding to the plurality of complaint information according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information; The processing sequence is displayed, or the processing sequence is sent to a preset device.
2. The method according to claim 1, It is characterized in that According to the complaint objects and predicted fault causes of the multiple complaint information, the multiple complaint information are clustered to obtain at least one complaint information set, including: According to the complaint objects of the plurality of complaint information, the plurality of complaint information are divided into at least one initial set, wherein the complaint objects of the complaint information included in the initial set are the same; For any initial set, clustering is performed on the complaint information in the initial set according to the predicted fault cause of each complaint information in the initial set to obtain at least one complaint information set corresponding to the initial set.
3. The method according to claim 2, It is characterized in that According to the predicted fault cause of each complaint information in the initial set, clustering processing is performed on the complaint information in the initial set to obtain at least one complaint information set corresponding to the initial set, including: Determine the similarity of the predicted fault causes of each two complaint information in the initial set; According to the similarity of the predicted fault causes of each two complaint information in the initial set, the complaint information in the initial set is clustered to obtain at least one complaint information set corresponding to the initial set.
4. The method according to any one of claims 1 to 3, It is characterized in that Determining a processing order corresponding to the plurality of complaint information according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information includes: For any complaint information set, determining the first priority of each complaint information in the complaint information set according to the number of complaint information included in the complaint information set; For any complaint information, determine the second priority of the complaint information according to the complaint sentiment of the complaint information; The processing order of the plurality of complaint information is determined according to the first priority and the second priority of the plurality of complaint information.
5. The method according to claim 4, It is characterized in that Determining, according to the number of complaint information included in the complaint information set, the first priority of each complaint information in the complaint information set, including: If the number of complaint information included in the complaint information set is greater than or equal to a preset threshold, determining that the first priority of each complaint information in the complaint information set is a first value; If the number of complaint information included in the complaint information set is less than the preset threshold, the first priority of each complaint information in the complaint information set is determined to be a second value, and the first value is greater than the second value.
6. The method according to claim 4 or 5, It is characterized in that Determining a processing order of the plurality of complaint information according to the first priority and the second priority of the plurality of complaint information includes: For any complaint information, weighted calculation is performed on the first priority and the second priority of the complaint information to obtain the target priority of the complaint information; The processing order of the plurality of complaint information is determined according to the target priorities of the plurality of complaint information.
7. The method according to any one of claims 1 to 6, It is characterized in that The complaint result also includes predictive maintenance measures; the method also includes: Obtaining a maintenance result of the first complaint information by after-sales personnel, wherein the maintenance result includes an actual fault cause and an actual maintenance measure, and the first complaint information is any one of the multiple complaint information; updating the complaint model according to the maintenance result of the first complaint information and the complaint result of the first complaint information to obtain a first complaint model; Obtaining correction information of the maintenance result by the quality inspector, wherein the correction information includes a correction fault cause and a correction maintenance measure; The first complaint model is updated according to the correction information and the maintenance result.
8. A device for processing complaint information, It is characterized in that include: An acquisition module, a processing module, a determination module, a display module or a sending module, wherein: The acquisition module is used to acquire multiple complaint information received within a historical period; The processing module is used to process any complaint information through the complaint model to obtain a complaint result, which includes: the complaint object, the predicted fault cause and the complaint emotion; The processing module is further used to cluster the plurality of complaint information according to the complaint objects and predicted fault causes of the plurality of complaint information to obtain at least one complaint information set, wherein the complaint information set includes at least one complaint information; The determination module is used to determine the processing order corresponding to the plurality of complaint information according to the number of complaint information included in the at least one complaint information set and the complaint sentiment of each complaint information; The display module is used to display the processing sequence; The sending module is used to send the processing sequence to a preset device.
9. A device for processing complaint information, It is characterized in that include: Processor and memory; The memory is used to store computer-executable instructions; The processor is configured to execute computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.
Citation Information
Cited By
System and device for automatically processing user complaints and rapidly returning fees based on AI (Artificial Intelligence)
CN121707570A
