Repeated appeal processing method and device, computer equipment and storage medium

Abstract

The invention discloses a repeated appeal processing method and device, computer equipment and a storage medium, which can be applied to various scenes such as product appeal and service appeal, and the method comprises the following steps: constructing a GE matrix based on the appeal frequency and the release state; based on the GE matrix, determining the type of the problem that the account repeatedly complaints; determining a problem solving priority based on the repeated appeal rate and the repeated appeal amount; and based on the problem solving priority, determining the priority corresponding to the problem type of the repeated appeal of the account, so as to determine the problem type of the repeated appeal of the account according to the priority. According to the method and the device, the problem types of the repeated appeal are divided based on two dimensions of representing the appeal times and the release state, and the priority of the problem types is determined based on the repeated appeal rate and the repeated appeal amount, so that the problem types of the repeated appeal are solved according to the corresponding priority, and the method and the device are not only suitable for various repeated appeal businesses, but also suitable for various repeated appeal businesses. And the pressure of processing personnel is reduced, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more specifically, to a method, apparatus, computer device, and storage medium for handling repeated complaints. Background Art

[0002] In recent years, various units have established dedicated departments to handle and resolve customer complaints in an effort to improve service quality and user experience. However, facing a large number of repeated complaints, such as second and third complaints, still puts pressure on staff.

[0003] At present, the handling of repeated complaints mainly relies on experience, that is, repeated complaints are handled by staff with rich work experience, or staff with rich work experience summarize and summarize the handling experience and make a repeated complaint handling book, so that staff can handle repeated complaints in accordance with the methods in the repeated complaint handling book.

[0004] However, the above methods lack systematic logical deduction and method transferability, and their scope of application is limited. Summary of the Invention

[0005] The main purpose of this application is to provide a repeated complaint processing method, device, computer equipment and storage medium, which can be applied to various repeated complaint businesses, reduce the pressure on processing personnel, and improve user experience.

[0006] To achieve the above objectives, in a first aspect, the present application provides a method for handling repeated complaints, comprising:

[0007] A GE matrix is ​​constructed based on the number of complaints and the state of relief. The GE matrix consists of nine units, each of which is used to represent the problem type under the corresponding dimension of the number of complaints and the state of relief.

[0008] Based on the GE matrix, determine the types of issues that the account has repeatedly complained about;

[0009] Determine the priority of problem solving based on the repeat complaint rate and the number of repeat complaints;

[0010] Based on the problem resolution priority, determine the priority corresponding to the problem type for which the account repeatedly appeals, so as to determine the problem type for which the account repeatedly appeals according to the priority.

[0011] In a second aspect, an embodiment of the present application provides a repeated complaint handling device, comprising:

[0012] A construction module is used to construct a GE matrix based on the number of complaints and the relief status, wherein the GE matrix is ​​composed of nine units, and each of the nine units is used to represent the problem type under the corresponding dimension of the number of complaints and the relief status;

[0013] The first determination module is used to determine the problem type of the account making repeated appeals based on the GE matrix;

[0014] The second determination module is used to determine the priority of problem solving based on the repeated complaint rate and the repeated complaint volume;

[0015] The processing module is used to determine the priority corresponding to the problem type for which the account makes repeated appeals based on the problem resolution priority, so as to determine the problem type for which the account makes repeated appeals according to the priority.

[0016] In one embodiment, the construction module is further configured to establish an initial coordinate system with the release state as the horizontal axis and the number of complaints as the vertical axis;

[0017] In the initial coordinate system, the release state is divided according to the number of releases, and the number of appeals is divided according to the number of repeated appeals to obtain the target coordinate system;

[0018] In the target coordinate system, the number of releases and the number of repeated appeals are correspondingly connected to obtain the GE matrix.

[0019] In one embodiment, the first determining module is further configured to obtain the number of repeated appeals and the release status of the account during the observation period;

[0020] Match the number of repeated appeals and the relief status of the account during the observation period with the problem types in the GE matrix to determine the problem types for which the account has made repeated appeals.

[0021] In one embodiment, the second determining module is further configured to divide the repeated complaint rate into a high repeated complaint rate and a low repeated complaint rate, wherein the high repeated complaint rate is greater than a first preset threshold and the low repeated complaint rate is lower than a second preset threshold;

[0022] Classify the number of repeated complaints into high repeated complaints and low repeated complaints, wherein the high repeated complaints are greater than a third preset threshold and the low repeated complaints are less than a fourth preset threshold;

[0023] Determine the priority for problem resolution based on high repeat complaint rate, low repeat complaint rate, high repeat complaint volume and low repeat complaint volume.

[0024] In one embodiment, the problem solving priority includes at least a first priority, a second priority, a third priority, and a fourth priority;

[0025] The second determination module is also used to set high repeated appeal rate and high repeated appeal volume as the first priority, low repeated appeal rate and high repeated appeal volume as the second priority, high repeated appeal rate and low repeated appeal volume as the third priority, and low repeated appeal rate and low repeated appeal volume as the fourth priority.

[0026] In one embodiment, the processing module is further configured to calculate the repeat complaint rate of the account during the observation period;

[0027] Get the number of repeated complaints of the account during the observation period;

[0028] Based on the account's repeated appeal rate during the observation period, the account's repeated appeal volume during the observation period, and the problem resolution priority, the priority corresponding to the problem type for which the account repeatedly appeals is determined.

[0029] In one embodiment, the processing module is further configured to divide the observation period into a plurality of time periods;

[0030] For each of the multiple time periods, calculate the repeat complaint rate of each time period;

[0031] Summarize each time period and the repeat complaint rate of each time period to obtain the repeat complaint rate of the account during the observation period.

[0032] In one embodiment, the processing module is further configured to obtain the number of accounts that have filed repeated complaints in each time period, and the number of accounts that have filed all complaints in each time period;

[0033] The number of accounts with repeated complaints in each time period is divided by the number of complaint accounts in each time period to obtain the repeated complaint rate in each time period.

[0034] In one embodiment, the processing module is further configured to determine a target repeat complaint rate based on the repeat complaint rate of the account during the observation period;

[0035] Determine the target number of repeated complaints based on the number of repeated complaints received by the account during the observation period;

[0036] If the target repeated appeal rate and target repeated appeal volume meet any priority in the problem resolution priority, any priority will be determined as the priority corresponding to the problem type for which the account makes repeated appeals.

[0037] In one embodiment, the processing module is further configured to calculate an average of all repeated appeal rates of the account during the observation period except for the minimum repeated appeal rate and the maximum repeated appeal rate to obtain a target repeated appeal rate.

[0038] In a third aspect, an embodiment of the present application provides a device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above methods when executing the computer program.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0040] The embodiments of the present application provide a method, apparatus, computer equipment and storage medium for handling repeated complaints, including: first constructing a GE matrix based on the number of complaints and the state of relief, wherein the GE matrix is ​​composed of nine units, and each of the nine units is used to characterize the problem type under the dimension corresponding to the number of complaints and the state of relief, and then determining the problem type of repeated complaints made by the account based on the GE matrix, and then determining the problem solving priority based on the repeated complaint rate and the amount of repeated complaints, and then determining the priority corresponding to the problem type of repeated complaints made by the account based on the problem solving priority, so as to determine the problem type of repeated complaints made by the account according to the priority. The present application divides the problem types of repeated complaints based on the two dimensions of the number of complaints and the state of relief, and determines the priority of the problem type based on the repeated complaint rate and the amount of repeated complaints, so as to solve the problem types of repeated complaints according to the corresponding priority. The systematic logical deduction and method transferability are not only applicable to various repeated complaint businesses, but also reduce the pressure on processing personnel and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings that constitute part of this application are used to provide a further understanding of this application and make other features, objects and advantages of this application more apparent. The illustrative embodiment drawings of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0042] Figure 1 This is an application scenario diagram of a repeated complaint handling method provided in an embodiment of the present application;

[0043] Figure 2 This is a flowchart of a method for handling repeated complaints provided in an embodiment of the present application;

[0044] Figure 3 This is a schematic diagram of the structure of a GE matrix provided in an embodiment of the present application;

[0045] Figure 4 This is a flowchart of a complaint attribution method provided in an embodiment of the present application;

[0046] Figure 5 This is a schematic diagram of a divided problem-solving priority provided by an embodiment of the present application;

[0047] Figure 6 This is a schematic diagram of a trend of repeated complaint rates during an observation period provided in an embodiment of the present application;

[0048] Figure 7This is a flowchart of another method for handling repeated complaints provided in an embodiment of the present application;

[0049] Figure 8 This is a schematic diagram of the structure of a repeated complaint processing device provided in an embodiment of the present application;

[0050] Figure 9 It is a schematic diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only 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 making creative efforts are within the scope of protection of this application.

[0052] The terms "first," "second," "third," "fourth," and so on (if any) in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in orders other than those illustrated or described herein.

[0053] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0054] It should be understood that in the various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0055] It should be understood that in this application, "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0056] It should be understood that in this application, "multiple" means two or more. "And / or" is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "Contains A, B and C", "Contains A, B, C" means that A, B, and C are all included, "Contains A, B or C" means that one of A, B, and C is included, and "Contains A, B and / or C" means that any one, any two, or any three of A, B, and C are included.

[0057] It should be understood that, in this application, "B corresponding to A," "B corresponding to A," "A corresponds to B," or "B corresponds to A" means that B is associated with A and B can be determined based on A. Determining B based on A does not mean determining B based solely on A; B can also be determined based on A and / or other information. A and B match when the similarity between A and B is greater than or equal to a preset threshold.

[0058] Depending on the context, "if" as used herein may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting."

[0059] The data involved in this application may be data authorized by the tester or fully authorized by all parties. The collection, dissemination, and use of the data shall comply with the relevant laws, regulations, and standards of the relevant countries and regions. The implementation methods / examples of this application may be combined with each other.

[0060] The embodiments of the present application can be applied to various scenarios such as product complaint scenarios and service complaint scenarios.

[0061] The following specific embodiments are used to describe the technical solution of the present application in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0062] First, to facilitate understanding of the solution of this application, the terms in this solution are explained as follows:

[0063] GE Matrix (McKinsey Matrix): GE is commonly used for business analysis. It is generally evaluated based on two dimensions: the competitive strength of a specific business module in the market and the attractiveness of the market in which it is located. Each dimension is evaluated using three levels: high, medium, and low, forming a 3X3 matrix.

[0064] Vintage analysis, also known as aging analysis, can reflect the risk profile of customers across different aging cycles. By observing changes in risk profiles over different cycles, we can analyze changes in risk profiles and risk control strategies across these cycles. Furthermore, the vintage curve can be used to determine when delinquency rates stabilize, helping to identify the appropriate performance period.

[0065] Policy intervention: If a user's transaction is identified as risky during the payment process, the payment platform's backend will initiate transaction interception to prevent the user from being defrauded.

[0066] Appeal: When a user believes that their payment behavior has been unreasonably interfered with and that payment cannot be successfully made, they can file an appeal by calling, providing feedback on the official account, or making order complaints to protect their own rights and interests.

[0067] Relief: When a user's appeal is judged to be reasonable, the restrictions on the user's payment rights will be lifted.

[0068] Next, the present application solution will be described through specific embodiments with reference to the accompanying drawings.

[0069] See also Figure 1 , Figure 1 A schematic diagram of an application scenario of a repeated complaint handling method provided in an embodiment of the present application.

[0070] like Figure 1 As shown, the client 102 communicates with the server 104, wherein the client 102 sends a repeated appeal request to the server 104. After receiving the repeated appeal request, the server 104 first constructs a GE matrix based on the number of appeals and the release status, wherein the GE matrix is ​​composed of nine units, and each of the nine units is used to characterize the problem type under the corresponding dimensions of the number of appeals and the release status. Then, based on the GE matrix, the problem type of the account's repeated appeal is determined, and then based on the repeated appeal rate and the repeated appeal amount, the problem solving priority is determined. Then, based on the problem solving priority, the priority corresponding to the problem type of the account's repeated appeal is determined, so as to determine the problem type of the account's repeated appeal according to the priority.

[0071] The client 102 and the server 104 can communicate through any communication method, including but not limited to network communication, and the above-mentioned network can include but not limited to: wired network, wireless network, wherein the wired network includes: local area network, metropolitan area network and wide area network, and the wireless network includes: Bluetooth, WIFI, and other networks that realize wireless communication. The client 102 includes but is not limited to at least one of the following: mobile phone (such as Android phone, iOS phone, etc.), laptop computer, tablet computer, PDA, mobile Internet device (Mobile Internet Device, MID), PAD, desktop computer, smart TV, etc. The server 104 can be an on-site server or a remote server, wherein both the on-site server and the remote server can be implemented as independent servers or a service cluster composed of multiple servers. The above is only an example, and no limitation is made to this in this embodiment.

[0072] See also Figure 2 , Figure 2 This is a flow chart of a method for handling repeated complaints provided in an embodiment of the present application. Figure 2 As shown, this method is applied to Figure 1 The server 104 shown includes the following steps:

[0073] Step S201: Constructing a GE matrix based on the number of complaints and the release status.

[0074] The number of appeals represents the number of appeals an account has submitted regarding one or more issues within a preset timeframe. This preset timeframe can be set based on the specific situation and is not limited here. Release corresponds to an appeal, and the release status refers to the state in which an account resolves an issue and its restrictions are lifted after executing an appeal request.

[0075] The GE Matrix (also known as the McKinsey Matrix) helps companies select and position their businesses by assessing their market strengths and market attractiveness, thereby identifying their strengths and weaknesses. Its application requires first identifying strategic business units (SBUs): dividing the company's business into SBUs and conducting an internal and external environmental analysis. Next, evaluation factors and weightings are determined: key evaluation indicators for market attractiveness and corporate competitiveness are determined, along with weightings for each indicator. These indicators include the industry's development potential and profitability, the company's financial resources, human resources, technological capabilities and experience, and intangible resources and capabilities. Next, an evaluation and scoring process is performed: Based on the industry analysis results, the market attractiveness and competitiveness of each SBU are evaluated and scored, and the weighted sum is calculated to obtain a final score for each SBU's market attractiveness and competitiveness. Strategic units are then marked on the GE Matrix: each SBU is circled on the GE Matrix, with the size of the circle representing the SBU's total market size. In some cases, a sector can be used to represent the company's market share. Finally, strategies for each SBU are explained: corresponding strategies are formulated for each SBU mapped on the GE Matrix.

[0076] The GE Matrix (GE Matrix / Mckinsey Matrix) in this application contains two main dimensions: the number of complaints and the relief status. Each dimension is divided into three levels, forming a matrix of nine units in total, where each of the nine units is used to represent the problem type under the corresponding dimensions of the number of complaints and the relief status.

[0077] The GE matrix in this application uses a quantitative method to divide the number of complaints and the state of relief, which is more accurate, reasonable and applicable than the method of dividing the dimensions into three levels: low, medium and high. In addition, this application uses the two indicators of the number of complaints and the state of relief in the GE matrix to divide the problem types of repeated complaints, and refines the problem types of repeated complaints, and the refined problem types are more in line with the situation of repeated complaints. In addition, the refined problem types are solved one by one or in parallel, and the problems are accurately located, which improves the accuracy and efficiency of problem solving.

[0078] To construct a GE matrix based on the number of complaints and the release status, it is necessary to establish an initial coordinate system with the release status as the horizontal axis and the number of complaints as the vertical axis. Then, in the initial coordinate system, the release status is divided according to the number of releases, and the number of complaints is divided according to the number of repeated complaints to obtain the target coordinate system. Then, in the target coordinate system, the number of releases and the number of repeated complaints are correspondingly connected to obtain the GE matrix.

[0079] In the face of the chaotic data situation, in order to solve the problem systematically and specifically, we first need to break down the complex problem into specific sub-modules, such as Figure 3 The GE matrix shown here breaks down the problem into 3x3 submodules (units) based on the number of user complaints and the status of the user's complaint resolution. Each submodule represents a type of problem, such as strategy optimization, product optimization, or service solution optimization.

[0080] This application divides the release status and the number of appeals according to the number of times, that is, the release status is divided into "0 times (i.e. no release), 1 time (i.e. only released once), multiple times (i.e. repeated release)", and the number of appeals is divided into "1 time (i.e. only once), a small amount of repetitions, and multiple repetitions". Among them, the number of small amounts of repetitions and multiple repetitions in the number of appeals can be set according to the specific situation, such as a small amount of repetitions is less than the preset number of times, and multiple repetitions is greater than the preset number. The preset number is also set according to the specific situation.

[0081] This application divides the types of repeated complaints based on the two dimensions of the number of complaints and the status of relief, breaks down complex problems into multiple small problems, refines the problems, improves the efficiency of problem solving, reduces the pressure on processing personnel, and improves user experience.

[0082] Furthermore, the above-mentioned cross-splitting and summarizing of the problem based on the number of appeals and releases of accounts can help determine the overall progress and resolution process of the problem. However, if you need to deeply analyze the underlying reasons for repeated appeals and releases, you need to further analyze the reasons of each unit. Specifically, Figure 4 As shown, users can be classified based on their historical complaint behavior to determine whether they are new or old complaint accounts. If a new complaint account has only appealed once, then the reason for the appeal is single and unique. However, if a new complaint account appeals repeatedly, it may involve multiple issues, that is, there are multiple reasons for the appeal.

[0083] Step S202: Based on the GE matrix, determine the problem type of the account's repeated appeals.

[0084] Based on the GE matrix, it can be observed that in terms of the release status and the number of appeals, the problem types of repeated appeals made by this application account can be divided into strategy optimization, product optimization, service solution optimization, the ideal state of malicious appeals, and the ideal state of reasonable appeals.

[0085] To determine the type of issue resulting from repeated appeals based on the GE matrix, you first need to obtain the number of repeated appeals and the resolution status of the account during the observation period. Then, you need to match these numbers with the issue types in the GE matrix to determine the type of issue resulting from repeated appeals. The observation period is any time period, such as the past month.

[0086] Assume that the observation period is the past month, and you can check the repeated appeals of an account within a month. If the number of repeated appeals of an account is 1 and the number of releases is 0, you can compare it with the following: Figure 3 In the GE matrix shown, the problem types matched by the accounts belong to the ideal state of malicious appeals.

[0087] Step S203: Determine the problem resolution priority based on the repeated complaint rate and the repeated complaint volume.

[0088] The repeated appeal rate refers to the probability that an account will repeatedly appeal against a certain issue within a certain period of time, and the repeated appeal volume refers to the total number of repeated appeals made by an account against a certain issue within a certain period of time.

[0089] Problem solving priority refers to the priority for solving all problem types formed in the above GE matrix.

[0090] To determine the problem resolution priority based on the repeat complaint rate and the number of repeat complaints, the repeat complaint rate must first be divided into a high repeat complaint rate and a low repeat complaint rate, where the high repeat complaint rate is greater than the first preset threshold and the low repeat complaint rate is less than the second preset threshold. The number of repeat complaints is then divided into a high repeat complaint volume and a low repeat complaint volume, where the high repeat complaint volume is greater than the third preset threshold and the low repeat complaint volume is less than the fourth preset threshold. Finally, based on the high repeat complaint rate, the low repeat complaint rate, the high repeat complaint volume, and the low repeat complaint volume, the problem resolution priority is determined. The first, second, third, and fourth preset thresholds can be set as appropriate, such as the first and second preset thresholds being equal, and the third and fourth preset thresholds being equal.

[0091] like Figure 5 As shown, this application divides the problem solving priority into four levels according to the Boston Matrix analysis criteria, based on the two dimensions of repeated appeals volume and repeated appeals rate, from high to low: first priority, second priority, third priority and fourth priority.

[0092] Priority is given to high rates and high volumes of repeated complaints, second priority to low rates and high volumes of repeated complaints, third priority to high rates and low volumes of repeated complaints, and fourth priority to low rates and low volumes of repeated complaints. That is, when both priority 1 and priority 2 issues occur, priority 1 issues are addressed first.

[0093] Step S204: Based on the problem resolution priority, the priority corresponding to the problem type for which the account makes repeated appeals is determined, so as to determine the problem type for which the account makes repeated appeals according to the priority.

[0094] To determine the priority level corresponding to the problem type for which an account has repeatedly appealed based on the problem resolution priority, you must first calculate the account's repeated appeal rate during the observation period, then obtain the number of repeated appeals for the account during the observation period, and then determine the priority level corresponding to the problem type for which the account has repeatedly appealed based on the account's repeated appeal rate, the number of repeated appeals for the account during the observation period, and the problem resolution priority.

[0095] Calculating the repeated complaint rate of an account during the observation period includes: dividing the observation period into multiple time periods; calculating the repeated complaint rate of each time period for each of the multiple time periods; and summarizing each time period and the repeated complaint rate of each time period to obtain the repeated complaint rate of the account during the observation period.

[0096] Calculating the repeat complaint rate for each time period includes: obtaining the number of accounts that have filed repeated complaints and the number of accounts that have filed a full complaint for each time period; and dividing the number of accounts that have filed repeated complaints by the number of accounts that have filed a complaint for each time period to obtain the repeat complaint rate for each time period. The number of accounts that have filed a full complaint for each time period is the number of accounts that have filed a full complaint for the first time period among the multiple time periods.

[0097] For example, when analyzing accounts with repeated complaints, new accounts with no historical complaint records are selected as observation objects, and their complaint performance in a future period of time (i.e., observation period or observation point) is observed to obtain the complaint behavior trajectories of different accounts during the observation period.

[0098] like Figure 6 As shown, the observation period of this new account is divided into five time periods, namely T, M1, M2, M3 and M4. Among them, T represents T days, T is an integer greater than or equal to 1, M1 represents the time period [T, T+2], totaling 3 days, M2 represents the time period [T, T+6], totaling 7 days, M3 represents the time period [T, T+14], totaling 15 days, and M4 represents the time period [T, T+29], totaling 30 days.

[0099] To calculate the repeat complaint rate for each time period, we need to divide the number of repeat complaint accounts in each time period by the total number of complaint accounts in the first time period to get the repeat complaint rate for each time period.

[0100] T+0 repeat appeal rate = number of accounts with repeated appeals on day T / number of accounts with full appeals on day T (corresponding to the value at T in each row of the table);

[0101] T+3 repeat appeal rate = number of accounts with repeated appeals within [T, T+2] days / number of accounts with full appeals on day T (corresponding to the value at M1 in each row of the table);

[0102] T+7 repeat appeal rate = number of accounts with repeat appeals within [T, T+6] days / number of accounts with full appeals on day T (corresponding to the value at M2 in each row of the table);

[0103] T+15 repeat appeal rate = number of accounts with repeated appeals within [T, T+14] days / number of accounts with full appeals on day T (corresponding to the value at M3 in each row of the table);

[0104] T+30 repeat complaint rate = number of accounts with repeated complaints within [T, T+29] days / number of accounts with full complaints on day T (corresponding to the value at M4 in each row of the table).

[0105] After calculating the repeated complaint rate of each time period, and configuring the repeated complaint rate of each time period to the corresponding time period, the following is formed: Figure 6 Repeat appeal rate for the indicated accounts during the observation period.

[0106] It should be noted that the time periods M1, M2, M3, and M4 can be fixed time intervals or non-fixed time intervals. For example, based on experience, 3 days, 7 days, 15 days, 30 days, and 90 days can be taken as the time periods respectively.

[0107] The advantage of using a fixed time period is that variables can be controlled to eliminate the lack of comparability caused by time differences. The disadvantage is that more observation points need to be set. Too many indicators will not only increase the workload of analysis, but also cause the goals to be dispersed, resulting in a "disfocus" problem. Using an experience-based observation period in a non-fixed time period can solve the "disfocus" problem, and the overall trend of changes in the repeat complaint rate can be obtained based on fewer observation values.

[0108] For a fixed time period, we can analyze the changing trends in the repeat complaint rate over different time periods, reflecting the service quality over different periods. For a fixed observation point, we can see that the repeat complaint rate increases with increasing observation time. When the growth tends to stabilize, the observation period is considered the "mature stage" of repeat complaints, meaning that repeat complaints by accounts typically occur within X days. The X-day repeat complaint rate can be used as a stable observation period to analyze the reasons for repeated complaints by accounts, where X is an integer.

[0109] After obtaining the account's repeated appeal rate during the observation period, the account's repeated appeal volume during the observation period is also required. Then, based on the account's repeated appeal rate during the observation period, the account's repeated appeal volume during the observation period, and the problem resolution priority, determine the priority corresponding to the problem type for which the account is repeatedly appealing.

[0110] Among them, based on the account's repeated complaint rate during the observation period, the account's repeated complaint volume during the observation period, and the problem resolution priority, the priority corresponding to the problem type for which the account repeatedly complains is determined, including: determining the target repeated complaint rate based on the account's repeated complaint rate during the observation period; determining the target repeated complaint volume based on the account's repeated complaint volume during the observation period; if the target repeated complaint rate and the target repeated complaint volume meet any priority in the problem resolution priority, any priority is determined as the priority corresponding to the problem type for which the account repeatedly complains.

[0111] Among them, based on the repeated complaint rate of the account during the observation period, the target repeated complaint rate is determined, including: calculating the average of all repeated complaint rates of the account during the observation period except the minimum repeated complaint rate and the maximum repeated complaint rate to obtain the target repeated complaint rate; or taking the maximum repeated complaint rate among the repeated complaint rates of the account during the observation period as the target repeated complaint rate; or taking the minimum repeated complaint rate among the repeated complaint rates of the account during the observation period as the target repeated complaint rate.

[0112] For example, assume that the observation period includes three time periods, and the repeated complaint rates of an account in the three time periods are A1, A2 and A3 respectively, and then calculate the target repeated complaint rate, where the target complaint rate can be taken as the average of the repeated complaint rates A1, A2 and A3 in the three time periods as the target repeated complaint rate.

[0113] Among them, based on the number of repeated complaints of the account during the observation period, the target number of repeated complaints is determined, including: calculating the average of all repeated complaints of the account during the observation period except the minimum number of repeated complaints and the maximum number of repeated complaints to obtain the target number of repeated complaints; or taking the maximum number of repeated complaints of the account during the observation period as the target number of repeated complaints; or taking the minimum number of repeated complaints of the account during the observation period as the target number of repeated complaints.

[0114] For example, assume that the observation period includes three time periods, and the number of repeated complaints of an account in the three time periods is B1, B2 and B3 respectively, and then calculate the target repeated complaint rate, where the target complaint rate can be taken as the average of the repeated complaint rates B1, B2 and B3 in the three time periods as the target repeated complaint rate.

[0115] After obtaining the target repeat complaint rate and target repeat complaint volume, the obtained target repeat complaint rate and target repeat complaint volume can be compared with the repeat complaint rate and repeat complaint volume of any priority level in the four levels of problem resolution. When the obtained target repeat complaint rate and target repeat complaint volume meet the repeat complaint rate and repeat complaint volume of any priority level, any priority level can be used as the priority level corresponding to the problem type for which the account has made repeated complaints. Specifically, if the high repeat complaint rate of the first priority level is above 80% and the high repeat complaint volume is above 82%, and the obtained target repeat complaint rate is 85% and the target repeat complaint volume is 90%, it means that it meets the first priority level, and the first priority level can be used as the priority level corresponding to the problem type for which the account has made repeated complaints.

[0116] See also Figure 7 , Figure 7 This is a flow chart of another method for handling repeated complaints provided in an embodiment of the present application. Figure 7 As shown, the following steps are included:

[0117] An important part of reducing the overall number of complaints is to deal with and resolve the problem of repeated user complaints. Ideally, reasonable complaints should ensure a smooth complaint-relief process. Unreasonable complaints are allowed to be repeated, but the account will not be released.

[0118] Therefore, in the face of the current situation of repeated complaints and repeated relief, it is urgent to inventory the data, sort out the processes, identify the bottlenecks in the chain governance, and promote solutions.

[0119] The specific analysis plan can be divided into the following three steps:

[0120] Complex problem modularization: A GE matrix is ​​constructed based on the number of appeals and the status of relief. The GE matrix consists of nine cells, each of which is used to represent the problem type under the corresponding dimensions of the number of appeals and the status of relief. The problem type of repeated appeals by the account is then determined based on the GE matrix.

[0121] Indicator-driven, problem-quantified: Analyze the repeated complaints of accounts during the observation period and determine the changing trend of the repeated complaint rate;

[0122] Multi-dimensional analysis and solution serialization: Based on the repeated complaint rate and repeated complaint volume, the problem resolution priority is determined. Based on the problem resolution priority, the priority corresponding to the problem type for which the account repeatedly complains is determined, so as to solve the problem type for which the account repeatedly complains according to the priority.

[0123] An embodiment of the present application provides a method for handling repeated complaints, including: first constructing a GE matrix based on the number of complaints and the status of relief, wherein the GE matrix is ​​composed of nine units, and each of the nine units is used to characterize the problem type under the corresponding dimension of the number of complaints and the status of relief, and then determining the problem type of repeated complaints made by the account based on the GE matrix, and then determining the problem solving priority based on the repeated complaint rate and the amount of repeated complaints, and then determining the priority corresponding to the problem type of repeated complaints made by the account based on the problem solving priority, so as to determine the problem type of repeated complaints made by the account according to the priority. The present application divides the problem types of repeated complaints based on the two dimensions of the number of complaints and the status of relief, and determines the priority of the problem type based on the repeated complaint rate and the amount of repeated complaints, so as to solve the problem types of repeated complaints according to the corresponding priority. The systematic logical deduction and method transferability are not only applicable to various repeated complaint businesses, but also reduce the pressure on processing personnel and improve user experience.

[0124] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0125] The following are device embodiments of the present application. For details not fully described therein, please refer to the corresponding method embodiments described above.

[0126] Figure 8 A schematic diagram of the structure of a repeated complaint processing device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown. The repeated complaint processing device includes a construction module 801, a first determination module 802, a second determination module 803, and a processing module 804. The details are as follows:

[0127] A construction module 801 is used to construct a GE matrix based on the number of complaints and the relief status, wherein the GE matrix is ​​composed of nine cells, each of which is used to represent the problem type under the corresponding dimension of the number of complaints and the relief status;

[0128] A first determination module 802 is configured to determine the problem type of repeated appeals made by an account based on the GE matrix;

[0129] The second determination module 803 is used to determine the problem resolution priority based on the repeated complaint rate and the repeated complaint volume;

[0130] The processing module 804 is used to determine the priority corresponding to the problem type for which the account makes repeated appeals based on the problem resolution priority, so as to determine the problem type for which the account makes repeated appeals according to the priority.

[0131] In one embodiment, the construction module 801 is further configured to establish an initial coordinate system with the release state as the horizontal axis and the number of complaints as the vertical axis;

[0132] In the initial coordinate system, the release state is divided according to the number of releases, and the number of appeals is divided according to the number of repeated appeals to obtain the target coordinate system;

[0133] In the target coordinate system, the number of releases and the number of repeated appeals are correspondingly connected to obtain the GE matrix.

[0134] In one embodiment, the first determining module 802 is further configured to obtain the number of repeated appeals and the release status of the account during the observation period;

[0135] Match the number of repeated appeals and the relief status of the account during the observation period with the problem types in the GE matrix to determine the problem types for which the account has made repeated appeals.

[0136] In one embodiment, the second determining module 803 is further configured to classify the repeated complaint rate into a high repeated complaint rate and a low repeated complaint rate, wherein the high repeated complaint rate is greater than a first preset threshold and the low repeated complaint rate is lower than a second preset threshold;

[0137] Classify the number of repeated complaints into high repeated complaints and low repeated complaints, wherein the high repeated complaints are greater than a third preset threshold and the low repeated complaints are less than a fourth preset threshold;

[0138] Determine the priority for problem resolution based on high repeat complaint rate, low repeat complaint rate, high repeat complaint volume and low repeat complaint volume.

[0139] In one embodiment, the problem solving priority includes at least a first priority, a second priority, a third priority, and a fourth priority;

[0140] The second determination module 803 is also used to set high repeated complaint rate and high repeated complaint volume as the first priority, low repeated complaint rate and high repeated complaint volume as the second priority, high repeated complaint rate and low repeated complaint volume as the third priority, and low repeated complaint rate and low repeated complaint volume as the fourth priority.

[0141] In one embodiment, the processing module 804 is further configured to calculate the repeat complaint rate of the account during the observation period;

[0142] Get the number of repeated complaints of the account during the observation period;

[0143] Based on the account's repeated appeal rate during the observation period, the account's repeated appeal volume during the observation period, and the problem resolution priority, the priority corresponding to the problem type for which the account repeatedly appeals is determined.

[0144] In one embodiment, the processing module 804 is further configured to divide the observation period into a plurality of time periods;

[0145] For each of the multiple time periods, calculate the repeat complaint rate of each time period;

[0146] Summarize each time period and the repeat complaint rate of each time period to obtain the repeat complaint rate of the account during the observation period.

[0147] In one embodiment, the processing module 804 is further configured to obtain the number of accounts that have filed repeated complaints in each time period, and the number of accounts that have filed all complaints in each time period;

[0148] The number of accounts with repeated complaints in each time period is divided by the number of complaint accounts in each time period to obtain the repeated complaint rate in each time period.

[0149] In one embodiment, the processing module 804 is further configured to determine a target repeat complaint rate based on the repeat complaint rate of the account during the observation period;

[0150] Determine the target number of repeated complaints based on the number of repeated complaints received by the account during the observation period;

[0151] If the target repeated appeal rate and target repeated appeal volume meet any priority in the problem resolution priority, any priority will be determined as the priority corresponding to the problem type for which the account makes repeated appeals.

[0152] In one embodiment, the processing module 804 is further configured to calculate the average of all repeated appeal rates of the account during the observation period except for the minimum repeated appeal rate and the maximum repeated appeal rate to obtain a target repeated appeal rate.

[0153] An embodiment of the present application provides a repeated complaint processing device, which can be used to: first construct a GE matrix based on the number of complaints and the relief status, wherein the GE matrix is ​​composed of nine units, and each of the nine units is used to characterize the problem type under the corresponding dimension of the number of complaints and the relief status, and then determine the problem type of the account's repeated complaints based on the GE matrix, and then determine the problem resolution priority based on the repeated complaint rate and the repeated complaint volume, and then determine the priority corresponding to the problem type of the account's repeated complaint based on the problem resolution priority, so as to determine the problem type of the account's repeated complaint according to the priority. The present application divides the problem types of repeated complaints based on the two dimensions of the number of complaints and the relief status, and determines the priority of the problem type based on the repeated complaint rate and the repeated complaint volume, so as to solve the problem types of repeated complaints according to the corresponding priority. The systematic logical deduction and method transferability are not only applicable to various repeated complaint businesses, but also reduce the pressure on processing personnel and improve user experience.

[0154] This application Figure 9 A schematic diagram of a computer device is provided. Figure 9 As shown, the computer device 9 of this embodiment includes: a processor 901, a memory 902, and steps of the repeated complaint handling method embodiment stored in the memory 902 and executable on the processor 901, such as Figure 2 Alternatively, when the processor 901 executes the computer program 903, the functions of the modules / units in the above-mentioned embodiments of the repeated complaint handling apparatus are realized, for example Figure 8 Functionality of modules / units 801 to 804 shown.

[0155] The present application also provides a readable storage medium, which stores a computer program. When the computer program is executed by a processor, it is used to implement the repeated complaint handling method provided by the various embodiments described above.

[0156] Among them, the readable storage medium can be a computer storage medium or a communication medium. Communication media include any medium that facilitates the transmission of computer programs from one place to another. Computer storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application-specific integrated circuit (ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the readable storage medium can also exist in a communication device as discrete components. The readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0157] The present application also provides a program product, comprising execution instructions stored in a readable storage medium. At least one processor of a device can read the execution instructions from the readable storage medium, and at least one processor executes the execution instructions to cause the device to implement the repeated complaint handling methods provided in the various embodiments described above.

[0158] In the embodiments of the above-mentioned devices, it should be understood that the processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in this application may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0159] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 application.

Claims

1. A method for handling repeated complaints, characterized in that: include: Constructing a GE matrix based on the number of complaints and the relief status, wherein the GE matrix is ​​composed of nine units, each of the nine units is used to represent the problem type under the corresponding dimension of the number of complaints and the relief status; Based on the GE matrix, determine the type of problem that the account has repeatedly complained about; Determine the priority of problem solving based on the repeat complaint rate and the number of repeat complaints; Based on the problem resolution priority, the priority corresponding to the problem type for which the account makes repeated appeals is determined, so as to determine the problem type for which the account makes repeated appeals according to the priority.

2. The method for handling repeated complaints according to claim 1, wherein: The GE matrix is ​​constructed based on the number of complaints and the release status, including: An initial coordinate system is established with the release state as the horizontal axis and the number of complaints as the vertical axis; In the initial coordinate system, the release state is divided according to the number of releases, and the number of appeals is divided according to the number of repeated appeals, to obtain a target coordinate system; In the target coordinate system, the number of releases and the number of repeated appeals are correspondingly connected to obtain the GE matrix.

3. The method for handling repeated complaints according to claim 1, wherein: Determining the types of issues causing repeated appeals based on the GE matrix includes: Obtain the number of repeated appeals and the release status of the account during the observation period; The number of repeated appeals and the release status of the account during the observation period are matched with the problem types in the GE matrix to determine the problem types of the repeated appeals by the account.

4. The method for handling repeated complaints according to claim 1, wherein: The priority of problem solving is determined based on the rate and volume of repeated complaints, including: Dividing the repeated complaint rate into a high repeated complaint rate and a low repeated complaint rate, wherein the high repeated complaint rate is greater than a first preset threshold and the low repeated complaint rate is lower than a second preset threshold; Dividing the repeated complaints into a high repeated complaints volume and a low repeated complaints volume, wherein the high repeated complaints volume is greater than a third preset threshold value and the low repeated complaints volume is lower than a fourth preset threshold value; The problem resolution priority is determined based on the high repeated appeal rate, the low repeated appeal rate, the high repeated appeal volume, and the low repeated appeal volume.

5. The repeated complaint handling method according to claim 4, characterized in that: The problem solving priorities include at least a first priority, a second priority, a third priority, and a fourth priority; The determining the problem resolution priority based on the high repeated appeal rate, the low repeated appeal rate, the high repeated appeal volume, and the low repeated appeal volume includes: Taking the high repeated appeal rate and the high repeated appeal volume as the first priority, The low repeated appeal rate and the high repeated appeal amount are set as the second priority, the high repeated appeal rate and the low repeated appeal amount are set as the third priority, and the low repeated appeal rate and the low repeated appeal amount are set as the fourth priority.

6. The method for handling repeated complaints according to claim 4, wherein: Determining the priority level corresponding to the problem type for which the account has made repeated appeals based on the problem resolution priority level includes: Calculate the account's repeat complaint rate during the observation period; Obtain the number of repeated complaints of the account during the observation period; Based on the repeated complaint rate of the account during the observation period, the number of repeated complaints of the account during the observation period, and the problem resolution priority, the priority corresponding to the problem type for which the account has made repeated complaints is determined.

7. The method for handling repeated complaints according to claim 6, wherein: The calculation of the account's repeated complaint rate during the observation period includes: Divide the observation period into multiple time periods; For each time period in the multiple time periods, calculating a repeat complaint rate for each time period; Each time period and the repeat complaint rate of each time period are summarized to obtain the repeat complaint rate of the account during the observation period.

8. The method for handling repeated complaints according to claim 7, wherein: The calculating of the repeated complaint rate in each time period includes: Obtain the number of accounts that have filed repeated complaints in each time period, and the number of accounts that have filed all complaints in each time period; The number of accounts that repeatedly appeal in each time period is divided by the number of appeal accounts in each time period to obtain the repeat appeal rate in each time period.

9. The method for handling repeated complaints according to claim 7, wherein: Determining the priority corresponding to the problem type for which the account repeatedly appeals based on the account's repeated appeal rate during the observation period, the number of repeated appeals during the observation period, and the problem resolution priority includes: Determine a target repeat complaint rate based on the repeat complaint rate of the account during the observation period; Determining a target number of repeated complaints based on the number of repeated complaints received by the account during the observation period; If the target repeated appeal rate and the target repeated appeal volume meet any priority of the problem resolution priorities, the any priority is determined as the priority corresponding to the problem type for which the account makes repeated appeals.

10. The repeated complaint handling method according to claim 9, characterized in that: Determining a target repeat complaint rate based on the repeat complaint rate of the account during the observation period includes: The target repeat complaint rate is obtained by calculating the average of all repeat complaint rates of the account during the observation period except the minimum repeat complaint rate and the maximum repeat complaint rate.

11. A repeated complaint handling device, characterized in that: include: A construction module is used to construct a GE matrix based on the number of complaints and the relief status, wherein the GE matrix is ​​composed of nine units, and each of the nine units is used to represent the problem type under the corresponding dimension of the number of complaints and the relief status; A first determination module is configured to determine the problem type of repeated appeals made by an account based on the GE matrix; The second determination module is used to determine the priority of problem solving based on the repeated complaint rate and the repeated complaint volume; The processing module is used to determine the priority corresponding to the problem type of repeated appeals made by the account based on the problem resolution priority, so as to determine the problem type of repeated appeals made by the account according to the priority.

12. A computer device, characterized in that: comprising a memory, and one or more processors communicatively connected to the memory; The memory stores instructions that can be executed by the one or more processors, and the instructions are executed by the one or more processors to enable the one or more processors to implement the repeated complaint handling method according to claims 1 to 10.

13. A computer-readable storage medium, characterized in that The method comprises a program or an instruction, which, when executed on a computer, implements the repeated complaint handling method according to claims 1 to 10.

Images