Intelligent complaint acceptance method and system based on historical data

Abstract

The invention discloses an intelligent complaint acceptance method and system based on historical data. The method comprises the steps of obtaining multiple pieces of historical complaint data and corresponding acceptance processing information; according to the historical complaint data and the corresponding acceptance processing information, training to obtain a case prediction model; inputting a plurality of to-be-predicted current complaint data into the case prediction model to obtain an output prediction processing scheme; determining a plurality of dispatch processing strategies corresponding to the current complaint data according to the prediction processing scheme and a preset case dispatch algorithm; the dispatching processing strategy is used for limiting a processing department, a processing mode and a processing time limit corresponding to each piece of current complaint data. Therefore, the intelligent degree and the decision-making efficiency of complaint case processing can be improved, and the accuracy of case assignment and the timeliness of processing are ensured.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for intelligently handling complaints based on historical data. Background Art

[0002] In the prior art, the handling of complaint cases usually relies on manual judgment, and the acceptance, assignment and handling of cases are mainly based on manual experience. With the increase in the number of complaint cases and the complexity of case types, the traditional manual handling method has the following problems: on the one hand, manual decision-making efficiency is low, and it is difficult to respond to a large number of complaint cases in a timely manner, resulting in delayed case handling; on the other hand, different case types may require different handling strategies, and manual judgment is easily affected by experience and subjective factors, resulting in unreasonable case assignment and affecting the quality of handling. In addition, the handling department, handling method and time limit of some cases are difficult to accurately determine, which is prone to improper handling or delays, affecting the resolution of complaint cases. It can be seen that the prior art has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for intelligently handling complaints based on historical data, which can improve the intelligence level and decision-making efficiency of complaint case handling and ensure the accuracy of case assignment and timeliness of handling.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for intelligently handling complaints based on historical data, the method comprising: Obtain multiple historical complaint data and corresponding acceptance and processing information; Training a case prediction model based on the plurality of historical complaint data and corresponding acceptance and processing information; Inputting a plurality of current complaint data to be predicted into the case prediction model to obtain an output prediction processing plan; According to the predicted processing plan and the preset case dispatching algorithm, the dispatching processing strategies corresponding to the multiple current complaint data are determined; the dispatching processing strategies are used to limit the processing department, processing method and processing time limit corresponding to each current complaint data.

[0005] As an optional implementation, in the first aspect of the present invention, the historical complaint data or the current complaint data includes at least one of the complaint initiator, complaint object, complaint time, complaint content, complaint transaction type and complaint method.

[0006] As an optional implementation, in the first aspect of the present invention, the acceptance processing information includes at least one of the acceptance department, acceptance type, processing personnel, processing plan, processing results and processing time.

[0007] As an optional implementation, in the first aspect of the present invention, the training of a case prediction model based on the plurality of historical complaint data and the corresponding acceptance and processing information includes: For each of the historical complaint data, according to the acceptance and processing information corresponding to the historical complaint data, calculate the type representation value corresponding to the historical complaint data; Determine the historical complaint data whose type characterization values ​​are greater than the characterization threshold as a positive sample data set, and determine the other historical complaint data as a negative sample data set; According to the positive sample data set and the negative sample data set, the preset prediction basic model is trained and optimized until convergence to obtain a case prediction model.

[0008] As an optional implementation, in the first aspect of the present invention, the calculating, according to the acceptance processing information corresponding to the historical complaint data, the type characterization value corresponding to the historical complaint data includes: Inputting the acceptance and processing information corresponding to the historical complaint data into a preset case handling appropriateness prediction model to obtain the case handling appropriateness degree corresponding to the historical complaint data; the case handling appropriateness prediction model is trained by a training data set including a plurality of training acceptance and processing information and corresponding handling appropriateness degree annotations; Calculate a weight parameter that is inversely proportional to the processing time in the acceptance and processing information corresponding to the historical complaint data; The product of the weight parameter and the degree of proper handling of the case is calculated to obtain the type characterization value corresponding to the historical complaint data.

[0009] As an optional implementation, in the first aspect of the present invention, the prediction basic model is a BERT pre-trained model; the prediction processing scheme includes a prediction processor, a prediction processing department, a prediction processing flow and a prediction processing time.

[0010] As an optional implementation, in the first aspect of the present invention, the step of determining the allocation processing strategies corresponding to the plurality of current complaint data according to the predicted processing scheme and the preset case allocation algorithm includes: For the plurality of current complaint data for which the processing strategies are to be determined, based on a dynamic programming algorithm and according to the corresponding prediction processing schemes, the plurality of current complaint data are grouped and calculated to obtain a plurality of data sets; For each of the data sets, calculate the mode item of the predicted processing department corresponding to each of the current complaint data in the data set to obtain the processing department corresponding to the data set; Calculate the intersection of the predicted processing flows corresponding to all the current complaint data in the data set to obtain the processing method corresponding to the data set; Calculate the average of the predicted processing times corresponding to all the current complaint data in the data set to obtain the processing time limit corresponding to the data set; The processing department, processing method and processing time limit corresponding to the data set are determined as the dispatch processing strategy corresponding to each of the current complaint data in the data set.

[0011] As an optional implementation, in the first aspect of the present invention, based on the dynamic programming algorithm, according to the corresponding prediction processing scheme, the multiple current complaint data are grouped and calculated to obtain multiple data sets, including: The objective function is set to minimize the total number of all data sets and maximize the number of current complaint data in each data set; Setting restrictions includes: The similarity of the predicted processing solutions between any two of the current complaint data in each data set is greater than a first similarity threshold; The solution similarity of the predicted processing solutions between the current complaint data respectively belonging to two different data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold; Based on a dynamic programming algorithm, according to the objective function and the limiting conditions, the multiple current complaint data are grouped and calculated to obtain multiple data sets.

[0012] A second aspect of an embodiment of the present invention discloses an intelligent complaint handling system based on historical data, the system comprising: The acquisition module is used to obtain multiple historical complaint data and corresponding acceptance and processing information; A training module, used for training a case prediction model based on the plurality of historical complaint data and corresponding acceptance and processing information; A prediction module, used for inputting a plurality of current complaint data to be predicted into the case prediction model to obtain an output prediction processing plan; A determination module is used to determine the dispatch processing strategies corresponding to the multiple current complaint data based on the predicted processing plan and the preset case dispatching algorithm; the dispatch processing strategy is used to limit the processing department, processing method and processing time limit corresponding to each current complaint data.

[0013] As an optional implementation, in the second aspect of the present invention, the historical complaint data or the current complaint data includes at least one of the complaint initiator, complaint object, complaint time, complaint content, complaint transaction type and complaint method.

[0014] As an optional implementation, in the second aspect of the present invention, the acceptance processing information includes at least one of the acceptance department, acceptance type, processing personnel, processing plan, processing results and processing time.

[0015] As an optional implementation, in the second aspect of the present invention, the specific manner in which the training module trains the case prediction model according to the plurality of historical complaint data and the corresponding acceptance and processing information includes: For each of the historical complaint data, according to the acceptance and processing information corresponding to the historical complaint data, calculate the type representation value corresponding to the historical complaint data; Determine the historical complaint data whose type characterization values ​​are greater than the characterization threshold as a positive sample data set, and determine the other historical complaint data as a negative sample data set; According to the positive sample data set and the negative sample data set, the preset prediction basic model is trained and optimized until convergence to obtain a case prediction model.

[0016] As an optional implementation, in the second aspect of the present invention, the specific manner in which the training module calculates the type characterization value corresponding to the historical complaint data according to the acceptance processing information corresponding to the historical complaint data includes: Inputting the acceptance and processing information corresponding to the historical complaint data into a preset case handling appropriateness prediction model to obtain the case handling appropriateness degree corresponding to the historical complaint data; the case handling appropriateness prediction model is trained by a training data set including a plurality of training acceptance and processing information and corresponding handling appropriateness degree annotations; Calculate a weight parameter that is inversely proportional to the processing time in the acceptance and processing information corresponding to the historical complaint data; The product of the weight parameter and the degree of proper handling of the case is calculated to obtain the type characterization value corresponding to the historical complaint data.

[0017] As an optional implementation, in the second aspect of the present invention, the prediction basic model is a BERT pre-trained model; the prediction processing scheme includes a prediction processor, a prediction processing department, a prediction processing flow and a prediction processing time.

[0018] As an optional implementation, in the second aspect of the present invention, the determination module determines the specific manner of the allocation and processing strategies corresponding to the multiple current complaint data according to the predicted processing scheme and the preset case allocation algorithm, including: For the plurality of current complaint data for which the processing strategies are to be determined, based on a dynamic programming algorithm and according to the corresponding prediction processing schemes, the plurality of current complaint data are grouped and calculated to obtain a plurality of data sets; For each of the data sets, calculate the mode item of the predicted processing department corresponding to each of the current complaint data in the data set to obtain the processing department corresponding to the data set; Calculate the intersection of the predicted processing flows corresponding to all the current complaint data in the data set to obtain the processing method corresponding to the data set; Calculate the average of the predicted processing times corresponding to all the current complaint data in the data set to obtain the processing time limit corresponding to the data set; The processing department, processing method and processing time limit corresponding to the data set are determined as the dispatch processing strategy corresponding to each of the current complaint data in the data set.

[0019] As an optional implementation, in the second aspect of the present invention, the prediction module performs grouping calculations on the multiple current complaint data to obtain multiple data sets based on a dynamic programming algorithm and the corresponding prediction processing scheme, including: The objective function is set to minimize the total number of all data sets and maximize the number of current complaint data in each data set; Setting restrictions includes: The similarity of the predicted processing solutions between any two of the current complaint data in each data set is greater than a first similarity threshold; The solution similarity of the predicted processing solutions between the current complaint data respectively belonging to two different data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold; Based on a dynamic programming algorithm, according to the objective function and the limiting conditions, the multiple current complaint data are grouped and calculated to obtain multiple data sets.

[0020] The third aspect of the present invention discloses another intelligent complaint handling system based on historical data, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the method for intelligently handling complaints based on historical data disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the intelligent complaint handling method based on historical data disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can train a case prediction model based on historical complaint data and acceptance and processing information, and use the model to predict current complaint data, thereby intelligently generating a reasonable prediction and processing plan, and combining it with a preset case dispatching algorithm to optimize the dispatching and processing strategy of complaint cases, thereby improving the intelligence level and decision-making efficiency of complaint case processing, and ensuring the accuracy of case dispatching and the timeliness of processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a method for intelligently handling complaints based on historical data disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural diagram of an intelligent complaint handling system based on historical data disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural diagram of another intelligent complaint handling system based on historical data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0029] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] The present invention discloses a method and system for intelligently handling complaints based on historical data, which can train a case prediction model based on historical complaint data and acceptance processing information, and use the model to predict current complaint data, thereby intelligently generating a reasonable prediction processing plan, and combining a preset case assignment algorithm to optimize the assignment and processing strategy of complaint cases, thereby improving the intelligence level and decision-making efficiency of complaint case processing, and ensuring the accuracy of case assignment and timeliness of processing. The following are detailed descriptions.

[0031] Embodiment 1 See also Figure 1 , Figure 1 This is a flowchart of a method for intelligently accepting complaints based on historical data disclosed in an embodiment of the present invention. Figure 1 The described method for intelligently handling complaints based on historical data can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the intelligent complaint handling method based on historical data may include the following operations: 101. Obtain multiple historical complaint data and corresponding acceptance and processing information.

[0032] 102. A case prediction model is trained based on multiple historical complaint data and corresponding acceptance and processing information. 103. Input multiple current complaint data to be predicted into the case prediction model to obtain an output prediction processing plan. 104. According to the predicted processing plan and the preset case allocation algorithm, determine the allocation and processing strategies corresponding to the multiple current complaint data.

[0033] Optionally, the dispatch processing strategy is used to define the processing department, processing method and processing time limit corresponding to each current complaint data.

[0034] It can be seen that the above-mentioned embodiments of the invention can train a case prediction model based on historical complaint data and acceptance and processing information, and use the model to predict current complaint data, thereby intelligently generating a reasonable prediction and processing plan, and combining it with a preset case assignment algorithm to optimize the assignment and processing strategy of complaint cases, thereby improving the intelligence level and decision-making efficiency of complaint case handling, and ensuring the accuracy of case assignment and timeliness of processing.

[0035] As an optional embodiment, in the above steps, the historical complaint data or current complaint data includes at least one of the complaint initiator, complaint object, complaint time, complaint content, complaint transaction type and complaint method.

[0036] It can be seen that through the above-mentioned optional embodiments, the content of the complaint data is limited to comprehensively characterize the complaint-related characteristics, so as to facilitate subsequent accurate processing predictions and case assignments, assist in improving the intelligence level and decision-making efficiency of complaint case handling, and ensure the accuracy of case assignment and the timeliness of processing.

[0037] As an optional embodiment, in the above steps, the acceptance processing information includes at least one of the acceptance department, acceptance type, processing personnel, processing plan, processing results and processing time.

[0038] It can be seen that through the above-mentioned optional embodiments, the content of the acceptance and processing information is limited to comprehensively characterize the processing-related characteristics of historical complaints, so as to facilitate subsequent accurate processing predictions and case assignments, assist in improving the intelligence level and decision-making efficiency of complaint case handling, and ensure the accuracy of case assignment and the timeliness of processing.

[0039] As an optional embodiment, in the above steps, training a case prediction model based on a plurality of historical complaint data and corresponding acceptance and processing information includes: For each historical complaint data, the type representation value corresponding to the historical complaint data is calculated according to the acceptance and processing information corresponding to the historical complaint data; All types of historical complaint data with characterization values ​​greater than the characterization threshold are determined as positive sample data sets, and other historical complaint data are determined as negative sample data sets; According to the positive sample data set and the negative sample data set, the preset prediction basic model is trained and optimized until convergence to obtain the case prediction model.

[0040] It can be seen that through the above-mentioned optional embodiments, the type characterization value can be calculated based on the acceptance and processing information corresponding to the historical complaint data, and the historical complaint data can be distinguished into positive sample data sets and negative sample data sets using the characterization threshold, so as to optimize the training prediction basic model and obtain the case prediction model, thereby improving the accuracy and stability of case prediction, and assisting in improving the intelligence level and decision-making efficiency of complaint case handling, and ensuring the accuracy of case assignment and the timeliness of processing.

[0041] As an optional embodiment, in the above step, calculating the type characterization value corresponding to the historical complaint data according to the acceptance and processing information corresponding to the historical complaint data includes: Inputting the acceptance and processing information corresponding to the historical complaint data into a preset case handling propriety prediction model to obtain the case handling propriety degree corresponding to the historical complaint data; optionally, the case handling propriety prediction model is trained by a training data set including a plurality of training acceptance and processing information and corresponding handling propriety degree annotations; Calculate a weight parameter that is inversely proportional to the processing time in the acceptance and processing information corresponding to the historical complaint data; Calculate the product of the weight parameter and the degree of proper case handling to obtain the type representation value corresponding to the historical complaint data.

[0042] It can be seen that through the above-mentioned optional embodiments, the degree of case handling appropriateness corresponding to historical complaint data can be predicted based on the case handling appropriateness prediction model, and the weight parameters can be calculated in combination with the processing time to determine the type characterization value in a weighted manner, thereby enhancing the accuracy of case classification, improving the case prediction model's ability to identify the rationality of complaint case handling, and optimizing case intelligent allocation and decision-making effects.

[0043] As an optional embodiment, in the above steps, the prediction basic model is a BERT pre-trained model; the prediction processing solution includes a prediction processor, a prediction processing department, a prediction processing flow and a prediction processing time.

[0044] It can be seen that through the above-mentioned optional embodiments, the details of the prediction basic model are limited, the contextual features can be effectively obtained to achieve accurate prediction of the case, and the content of the prediction processing plan results is limited to facilitate subsequent accurate case assignment, assist in improving the intelligence level and decision-making efficiency of complaint case handling, and ensure the accuracy of case assignment and timeliness of processing.

[0045] As an optional embodiment, in the above steps, according to the predicted processing scheme and the preset case allocation algorithm, the allocation processing strategy corresponding to the multiple current complaint data is determined, including: For a plurality of current complaint data for which a processing strategy is to be determined, based on a dynamic programming algorithm and according to corresponding prediction processing schemes, the plurality of current complaint data are grouped and calculated to obtain a plurality of data sets; For each data set, calculate the mode item of the predicted processing department corresponding to each current complaint data in the data set, and obtain the processing department corresponding to the data set; Calculate the intersection of the predicted processing flows corresponding to all current complaint data in the data set to obtain the processing method corresponding to the data set; Calculate the average predicted processing time corresponding to all current complaint data in the data set to obtain the processing time limit corresponding to the data set; The processing department, processing method and processing time limit corresponding to the data set are determined as the dispatch processing strategy corresponding to each current complaint data in the data set.

[0046] It can be seen that through the above-mentioned optional embodiments, the current complaint data can be grouped and calculated based on the dynamic programming algorithm, the classification structure of the complaint data can be determined in an optimal way, and the main processing department, optimal processing method and reasonable processing time limit of each data set can be extracted through statistical analysis, thereby improving the accuracy and coordination of case assignment and optimizing the processing efficiency of complaint cases and resource scheduling capabilities.

[0047] As an optional embodiment, in the above steps, based on the dynamic programming algorithm, according to the corresponding prediction processing scheme, the multiple current complaint data are grouped and calculated to obtain multiple data sets, including: The objective function is set to minimize the total number of all data sets and maximize the number of current complaint data in each data set; Setting restrictions includes: The similarity of the predicted processing solutions between any two current complaint data in each data set is greater than a first similarity threshold; The similarity of the predicted processing solutions between the current complaint data respectively belonging to two different data sets is less than a second similarity threshold; optionally, the second similarity threshold is less than the first similarity threshold; Based on the dynamic programming algorithm, according to the objective function and the limiting conditions, the multiple current complaint data are grouped and calculated to obtain multiple data sets.

[0048] It can be seen that through the above-mentioned optional embodiments, it is possible to optimize the grouping method of the current complaint data by setting the objective function and limiting conditions and using the dynamic programming algorithm, so that the number of data sets is minimized and the number of complaint data in each data set is maximized, while ensuring that the complaint data processing solutions within the same data set have a high degree of similarity, while the similarity of the processing solutions between different data sets is low, thereby improving the rationality and accuracy of case classification and optimizing the balance and execution efficiency of case assignment.

[0049] Embodiment 2 See also Figure 2 , Figure 2 This is a schematic diagram of the structure of an intelligent complaint handling system based on historical data disclosed in an embodiment of the present invention. Figure 2 The intelligent complaint handling system based on historical data described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the intelligent complaint handling system based on historical data may include: The acquisition module 201 is used to acquire multiple historical complaint data and corresponding acceptance and processing information.

[0050] The training module 202 is used to train a case prediction model based on a plurality of historical complaint data and corresponding acceptance and processing information. The prediction module 203 is used to input a plurality of current complaint data to be predicted into the case prediction model to obtain an output prediction processing plan. The determination module 204 is used to determine the dispatching and processing strategies corresponding to the multiple current complaint data according to the predicted processing plan and the preset case dispatching algorithm.

[0051] Optionally, the dispatch processing strategy is used to define the processing department, processing method and processing time limit corresponding to each current complaint data.

[0052] It can be seen that the above-mentioned embodiments of the invention can train a case prediction model based on historical complaint data and acceptance and processing information, and use the model to predict current complaint data, thereby intelligently generating a reasonable prediction and processing plan, and combining it with a preset case assignment algorithm to optimize the assignment and processing strategy of complaint cases, thereby improving the intelligence level and decision-making efficiency of complaint case handling, and ensuring the accuracy of case assignment and timeliness of processing.

[0053] As an optional embodiment, the historical complaint data or the current complaint data includes at least one of the complaint initiator, the complaint object, the complaint time, the complaint content, the complaint transaction type and the complaint method.

[0054] It can be seen that through the above-mentioned optional embodiments, the content of the complaint data is limited to comprehensively characterize the complaint-related characteristics, so as to facilitate subsequent accurate processing predictions and case assignments, assist in improving the intelligence level and decision-making efficiency of complaint case handling, and ensure the accuracy of case assignment and the timeliness of processing.

[0055] As an optional embodiment, the acceptance processing information includes at least one of the acceptance department, acceptance type, processing personnel, processing plan, processing results and processing time.

[0056] It can be seen that through the above-mentioned optional embodiments, the content of the acceptance and processing information is limited to comprehensively characterize the processing-related characteristics of historical complaints, so as to facilitate subsequent accurate processing predictions and case assignments, assist in improving the intelligence level and decision-making efficiency of complaint case handling, and ensure the accuracy of case assignment and the timeliness of processing.

[0057] As an optional embodiment, the training module trains a case prediction model according to a plurality of historical complaint data and corresponding acceptance and processing information, including: For each historical complaint data, the type representation value corresponding to the historical complaint data is calculated according to the acceptance and processing information corresponding to the historical complaint data; All types of historical complaint data with characterization values ​​greater than the characterization threshold are determined as positive sample data sets, and other historical complaint data are determined as negative sample data sets; According to the positive sample data set and the negative sample data set, the preset prediction basic model is trained and optimized until convergence to obtain the case prediction model.

[0058] It can be seen that through the above-mentioned optional embodiments, the type characterization value can be calculated based on the acceptance and processing information corresponding to the historical complaint data, and the historical complaint data can be distinguished into positive sample data sets and negative sample data sets using the characterization threshold, so as to optimize the training prediction basic model and obtain the case prediction model, thereby improving the accuracy and stability of case prediction, and assisting in improving the intelligence level and decision-making efficiency of complaint case handling, and ensuring the accuracy of case assignment and the timeliness of processing.

[0059] As an optional embodiment, the specific manner in which the training module calculates the type characterization value corresponding to the historical complaint data according to the acceptance and processing information corresponding to the historical complaint data includes: Inputting the acceptance and processing information corresponding to the historical complaint data into a preset case handling propriety prediction model to obtain the case handling propriety degree corresponding to the historical complaint data; optionally, the case handling propriety prediction model is trained by a training data set including a plurality of training acceptance and processing information and corresponding handling propriety degree annotations; Calculate a weight parameter that is inversely proportional to the processing time in the acceptance and processing information corresponding to the historical complaint data; Calculate the product of the weight parameter and the degree of proper case handling to obtain the type representation value corresponding to the historical complaint data.

[0060] It can be seen that through the above-mentioned optional embodiments, the degree of case handling appropriateness corresponding to historical complaint data can be predicted based on the case handling appropriateness prediction model, and the weight parameters can be calculated in combination with the processing time to determine the type characterization value in a weighted manner, thereby enhancing the accuracy of case classification, improving the case prediction model's ability to identify the rationality of complaint case handling, and optimizing case intelligent allocation and decision-making effects.

[0061] As an optional embodiment, the prediction basic model is a BERT pre-trained model; the prediction processing solution includes a prediction processor, a prediction processing department, a prediction processing flow and a prediction processing time.

[0062] It can be seen that through the above-mentioned optional embodiments, the details of the prediction basic model are limited, the contextual features can be effectively obtained to achieve accurate prediction of the case, and the content of the prediction processing plan results is limited to facilitate subsequent accurate case assignment, assist in improving the intelligence level and decision-making efficiency of complaint case handling, and ensure the accuracy of case assignment and timeliness of processing.

[0063] As an optional embodiment, the determination module determines the specific manner of the allocation processing strategy corresponding to the multiple current complaint data according to the predicted processing scheme and the preset case allocation algorithm, including: For a plurality of current complaint data for which a processing strategy is to be determined, based on a dynamic programming algorithm and according to corresponding prediction processing schemes, the plurality of current complaint data are grouped and calculated to obtain a plurality of data sets; For each data set, calculate the mode item of the predicted processing department corresponding to each current complaint data in the data set, and obtain the processing department corresponding to the data set; Calculate the intersection of the predicted processing flows corresponding to all current complaint data in the data set to obtain the processing method corresponding to the data set; Calculate the average predicted processing time corresponding to all current complaint data in the data set to obtain the processing time limit corresponding to the data set; The processing department, processing method and processing time limit corresponding to the data set are determined as the dispatch processing strategy corresponding to each current complaint data in the data set.

[0064] It can be seen that through the above-mentioned optional embodiments, the current complaint data can be grouped and calculated based on the dynamic programming algorithm, the classification structure of the complaint data can be determined in an optimal way, and the main processing department, optimal processing method and reasonable processing time limit of each data set can be extracted through statistical analysis, thereby improving the accuracy and coordination of case assignment and optimizing the processing efficiency of complaint cases and resource scheduling capabilities.

[0065] As an optional embodiment, the prediction module performs grouping calculations on the multiple current complaint data to obtain multiple data sets based on a dynamic programming algorithm and a corresponding prediction processing scheme, including: The objective function is set to minimize the total number of all data sets and maximize the number of current complaint data in each data set; Setting restrictions includes: The similarity of the predicted processing solutions between any two current complaint data in each data set is greater than a first similarity threshold; The similarity of the predicted processing solutions between the current complaint data respectively belonging to two different data sets is less than a second similarity threshold; optionally, the second similarity threshold is less than the first similarity threshold; Based on the dynamic programming algorithm, according to the objective function and the limiting conditions, the multiple current complaint data are grouped and calculated to obtain multiple data sets.

[0066] It can be seen that through the above-mentioned optional embodiments, it is possible to optimize the grouping method of the current complaint data by setting the objective function and limiting conditions and using the dynamic programming algorithm, so that the number of data sets is minimized and the number of complaint data in each data set is maximized, while ensuring that the complaint data processing solutions within the same data set have a high degree of similarity, while the similarity of the processing solutions between different data sets is low, thereby improving the rationality and accuracy of case classification and optimizing the balance and execution efficiency of case assignment.

[0067] Embodiment 3 See also Figure 3 , Figure 3 It is another intelligent complaint handling system based on historical data disclosed in an embodiment of the present invention. Figure 3 The intelligent complaint handling system based on historical data is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the intelligent complaint handling system based on historical data may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; Among them, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the intelligent complaint handling method based on historical data described in Example 1.

[0068] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for intelligently handling complaints based on historical data described in the first embodiment.

[0069] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the method for intelligently handling complaints based on historical data described in Example 1.

[0070] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0072] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0073] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0074] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. 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 processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] 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.

[0076] 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.

[0077] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0078] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0079] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0081] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0082] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0083] Finally, it should be noted that the intelligent complaint handling method and system based on historical data disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligently handling complaints based on historical data, characterized in that: The method comprises: Obtain multiple historical complaint data and corresponding acceptance and processing information; Training a case prediction model based on the plurality of historical complaint data and corresponding acceptance and processing information; Inputting a plurality of current complaint data to be predicted into the case prediction model to obtain an output prediction processing plan; According to the predicted processing plan and the preset case dispatching algorithm, the dispatching processing strategies corresponding to the multiple current complaint data are determined; the dispatching processing strategies are used to limit the processing department, processing method and processing time limit corresponding to each current complaint data.

2. The intelligent complaint handling method based on historical data according to claim 1 is characterized in that: The historical complaint data or the current complaint data includes at least one of the complaint initiator, the complaint object, the complaint time, the complaint content, the complaint matter type and the complaint method.

3. The intelligent complaint handling method based on historical data according to claim 1 is characterized in that: The acceptance processing information includes at least one of the acceptance department, acceptance type, processing personnel, processing plan, processing results and processing time.

4. The intelligent complaint handling method based on historical data according to claim 1 is characterized in that: The training of a case prediction model based on the plurality of historical complaint data and the corresponding acceptance and processing information includes: For each of the historical complaint data, according to the acceptance and processing information corresponding to the historical complaint data, calculate the type representation value corresponding to the historical complaint data; Determine the historical complaint data whose type characterization values ​​are greater than the characterization threshold as a positive sample data set, and determine the other historical complaint data as a negative sample data set; According to the positive sample data set and the negative sample data set, the preset prediction basic model is trained and optimized until convergence to obtain a case prediction model.

5. The intelligent complaint handling method based on historical data according to claim 4 is characterized in that: The calculating, according to the acceptance and processing information corresponding to the historical complaint data, the type characterization value corresponding to the historical complaint data includes: Inputting the acceptance and processing information corresponding to the historical complaint data into a preset case handling appropriateness prediction model to obtain the case handling appropriateness degree corresponding to the historical complaint data; the case handling appropriateness prediction model is trained by a training data set including a plurality of training acceptance and processing information and corresponding handling appropriateness degree annotations; Calculate a weight parameter that is inversely proportional to the processing time in the acceptance and processing information corresponding to the historical complaint data; The product of the weight parameter and the degree of proper handling of the case is calculated to obtain the type characterization value corresponding to the historical complaint data.

6. The intelligent complaint handling method based on historical data according to claim 4 is characterized in that: The prediction basic model is a BERT pre-trained model; the prediction processing solution includes a prediction processor, a prediction processing department, a prediction processing flow and a prediction processing time.

7. The intelligent complaint handling method based on historical data according to claim 6 is characterized in that: The step of determining the allocation and processing strategies corresponding to the plurality of current complaint data according to the predicted processing scheme and the preset case allocation algorithm includes: For the plurality of current complaint data for which the processing strategies are to be determined, based on a dynamic programming algorithm and according to the corresponding prediction processing schemes, the plurality of current complaint data are grouped and calculated to obtain a plurality of data sets; For each of the data sets, calculate the mode item of the predicted processing department corresponding to each of the current complaint data in the data set to obtain the processing department corresponding to the data set; Calculate the intersection of the predicted processing flows corresponding to all the current complaint data in the data set to obtain the processing method corresponding to the data set; Calculate the average of the predicted processing times corresponding to all the current complaint data in the data set to obtain the processing time limit corresponding to the data set; The processing department, processing method and processing time limit corresponding to the data set are determined as the dispatch processing strategy corresponding to each of the current complaint data in the data set.

8. The intelligent complaint handling method based on historical data according to claim 7 is characterized in that: Based on the dynamic programming algorithm, according to the corresponding prediction processing scheme, the multiple current complaint data are grouped and calculated to obtain multiple data sets, including: The objective function is set to minimize the total number of all data sets and maximize the number of current complaint data in each data set; Setting restrictions includes: The similarity of the predicted processing solutions between any two of the current complaint data in each data set is greater than a first similarity threshold; The solution similarity of the predicted processing solutions between the current complaint data respectively belonging to two different data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold; Based on a dynamic programming algorithm, according to the objective function and the limiting conditions, the multiple current complaint data are grouped and calculated to obtain multiple data sets.

9. An intelligent complaint handling system based on historical data, characterized in that: The system comprises: The acquisition module is used to obtain multiple historical complaint data and corresponding acceptance and processing information; A training module, used for training a case prediction model based on the plurality of historical complaint data and corresponding acceptance and processing information; A prediction module, used for inputting a plurality of current complaint data to be predicted into the case prediction model to obtain an output prediction processing plan; A determination module is used to determine the dispatch processing strategies corresponding to the multiple current complaint data based on the predicted processing plan and the preset case dispatching algorithm; the dispatch processing strategy is used to limit the processing department, processing method and processing time limit corresponding to each current complaint data.

10. An intelligent complaint handling system based on historical data, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intelligent complaint handling method based on historical data as described in any one of claims 1-8.

Images