Case allocation method and device, equipment and storage medium

Abstract

The invention discloses a case allocation method, device and equipment and a storage medium, and relates to the technical field of case allocation, and the method comprises the steps: obtaining a current case list, and determining a pre-calling case in the current case list; carrying out AI outbound calling on clients corresponding to the pre-calling cases, and determining effective contact cases according to outbound calling results; according to preset group configuration information, docking the effective arriving case to a shared case pool corresponding to each operation group; and based on a preset fusion case division strategy, determining a target processing case corresponding to each user in each shared case pool, the preset fusion case division strategy comprising at least one of a competition case grabbing strategy and an automatic case division strategy. According to the method, the effective communication efficiency with clients is improved through AI outbound, and a competition mechanism and an automatic case division algorithm are combined in a case division strategy, so that efficient allocation of case resources can be ensured, and improvement of the case processing efficiency and the completion effect is facilitated.

Description

Technical Field

[0001] The present application relates to the technical field of case allocation, and in particular to a case allocation method, device, equipment and storage medium. Background Art

[0002] When handling cases in financial scenarios, especially collection scenarios, it is usually necessary to rely on a statically constructed decision variable matrix. These variables are combined with the risk assessment and weight of the collection cases, and then allocated proportionally to each user in the collection team for processing.

[0003] However, with the rising credit default rate and the surge in the number of overdue loans, the operational pressure of the collection business is growing at an unprecedented rate. In practical applications, the traditional allocation strategy ignores the differences between individual users and the dynamic reality, making it difficult to adapt to the ever-changing economic environment and collection operation methods, affecting the processing efficiency and completion effect of collection cases. Summary of the invention

[0004] The main purpose of this application is to provide a case allocation method, device, equipment and storage medium, aiming to solve the technical problems that traditional allocation strategies are limited by manual access efficiency and lack flexibility.

[0005] To achieve the above objectives, the present application proposes a case allocation method, which includes:

[0006] obtaining a current case list and determining a pre-call case in the current case list;

[0007] Conduct AI outbound calls to customers corresponding to each of the pre-call cases, and determine effective contact cases based on the outbound call results;

[0008] Connecting the effective cases to the shared case pool corresponding to each operation group according to the preset group configuration information;

[0009] Based on a preset fusion case assignment strategy, a target case to be processed corresponding to each user is determined in each shared case pool, wherein the preset fusion case assignment strategy includes at least one of a competitive case grabbing strategy and an automatic case assignment strategy.

[0010] In one embodiment, the step of performing AI outbound calling on the customers corresponding to each of the pre-call cases and determining the effective contact cases according to the outbound calling results includes:

[0011] Obtain a preset AI outbound call configuration table, wherein the preset AI outbound call configuration table includes: a machine number and a corresponding outbound call task category;

[0012] Determine the case category information of each of the pre-call cases, and match the machine number corresponding to each of the pre-call cases in the preset AI outbound call configuration table according to the case category information;

[0013] The AI ​​robots corresponding to the machine numbers make AI outbound calls to the customers corresponding to the pre-call cases to obtain the degree of willingness of the customers to answer the calls in the pre-call cases;

[0014] If the customer's willingness to answer the call is greater than the willingness threshold, the pre-call case is determined to be a valid contact case.

[0015] In one embodiment, the step of connecting the effective contact cases to the shared case pool corresponding to each operation group according to the preset group configuration information includes:

[0016] Determine the operation groups under different case categories and the case acquisition methods corresponding to the operation groups according to the preset group configuration information, wherein the case acquisition method is at least one of a case grabbing method and a case dividing method;

[0017] According to the case category information of each of the effective reached cases, a number of corresponding operation groups are determined, and each of the effective reached cases is respectively transferred to the shared case pool of each of the operation groups.

[0018] In one embodiment, before the step of determining the target processing case corresponding to each user in each shared case pool based on the preset fusion case division strategy, the following steps are included:

[0019] Obtaining the total number of current cases in each of the shared case pools, and determining whether the total number of current cases is greater than a preset capacity threshold;

[0020] When the total number of current cases is greater than the preset capacity threshold, a competitive case grabbing strategy is triggered;

[0021] When the total number of current cases is not greater than the preset capacity threshold, the automatic case allocation strategy is triggered.

[0022] In one embodiment, the step of determining the target processing case corresponding to each user in each shared case pool based on the preset fusion case division strategy includes:

[0023] Upon receiving a case snatching request from a first operation user, determining whether the first operation user meets the conditions for allowing the case snatching, and the first operation user belongs to an operation group whose case acquisition method is the case snatching method;

[0024] If yes, determining the expected number of robberies of the first job user according to the robbery request;

[0025] When the expected number of robberies is not greater than a preset robbery threshold, valid cases with the expected number of robberies are obtained from the shared case pool and determined as target processing cases for the first operating user.

[0026] In one embodiment, the step of determining whether the first operation user meets the conditions for allowing the robbery includes:

[0027] Acquire the assigned cases of the first operation user, and determine the case status of each of the assigned cases, wherein the case status includes: unfinished, in progress, and completed;

[0028] When there are no unfinished assigned cases, performing authority verification on the first operation user;

[0029] It is determined whether the first operation user meets the conditions for allowing the robbery according to the permission verification result.

[0030] In one embodiment, the step of determining the target processing case corresponding to each user in each shared case pool based on the preset fusion case division strategy includes:

[0031] In response to the automatic case assignment strategy trigger instruction, obtaining the allocation weight of each second operation user, the second operation user belongs to the operation group whose case acquisition method is the case assignment method;

[0032] Based on the allocation weights, the target processing cases for each of the second operation users are determined according to preset allocation rules and in combination with all valid reached cases in the shared case pool.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a case allocation device, the device comprising:

[0034] The customer contact module is used to obtain the current case list and determine the pre-call cases in the current case list; perform AI outbound calls on the customers corresponding to each pre-call case, and determine the effective contact cases based on the outbound call results;

[0035] The case allocation module is used to connect the effectively reached cases to the shared case pool corresponding to each operation group according to the preset group configuration information; based on the preset fusion case allocation strategy, the target processing case corresponding to each user is determined in each shared case pool, and the preset fusion case allocation strategy includes at least one of the competitive case grabbing strategy and the automatic case allocation strategy.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a case allocation device, which includes: a memory, a processor, and a case allocation program stored in the memory and executable on the processor, and the case allocation program is configured to implement the steps of the case allocation method described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a case allocation program is stored, and when the case allocation program is executed by a processor, the steps of the case allocation method described above are implemented.

[0038] The present application proposes a case allocation method, which obtains the current case list and determines the pre-call cases in the current case list; makes AI outbound calls to the customers corresponding to each of the pre-call cases, and determines the effectively reached cases based on the outbound call results; connects the effectively reached cases to the shared case pool corresponding to each operation group according to the preset group configuration information; and determines the target processing cases corresponding to each user in each of the shared case pools based on the preset fusion case division strategy, and the preset fusion case division strategy includes at least one of the competitive case grabbing strategy and the automatic case division strategy. Since the present application can introduce AI outbound calls to screen effectively reached cases, some invalid reached cases are avoided to improve the user's contact efficiency with effectively reached cases. The case division strategy combines the competition mechanism and the automatic case division algorithm, which can meet the personalized case division requirements of different operation groups, increase the accuracy and efficiency of case division decisions, and ensure that the optimal algorithm can be selected for different collection scenarios, thereby improving the processing efficiency and completion effect of the case. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 This is a flow chart of the first embodiment of the case allocation method of the present application;

[0042] Figure 2 This is a flow chart of the second embodiment of the case allocation method of the present application;

[0043] Figure 3 This is a schematic diagram of the customer contact process in the case allocation method of this application;

[0044] Figure 4 This is a flow chart of the third embodiment of the case allocation method of the present application;

[0045] Figure 5 This is a schematic diagram of the execution process of the competition and robbery strategy for this application;

[0046] Figure 6 This is a schematic diagram of the module structure of the first embodiment of the case allocation device of the present application;

[0047] Figure 7 This is a schematic diagram of the structure of the equipment allocated for this application.

[0048] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0050] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0051] In the collection scenario, the case handling process focuses on manpower-driven, which is limited by the efficiency of manual contact, resulting in ineffective consumption of resources (for example, there are a large number of invalid contact cases that waste user processing time). In addition, the current allocation strategy evenly distributes different cases to users in different operating groups based on preset weights, ignoring the reality of individual differences and dynamic changes. For example, each user's collection ability level and daily work status are different. At the same time, different types of cases may have unique collection cycle patterns. This static case allocation method often causes efficient users to exhaust case tasks prematurely, while less efficient colleagues are still dealing with backlogged cases. This not only delays the contact time with customers, but also hinders the overall collection efficiency.

[0052] This application uses AI outbound calls to achieve initial contact with the corresponding customers of the case, and then screens the cases based on the contact results, avoiding some invalid contact cases, thereby improving the user's contact efficiency with effective contact cases. The case division strategy combines the competition mechanism and the automatic case division algorithm, which can meet the personalized case division requirements of different operation groups, increase the accuracy and efficiency of case division decisions, and ensure that the optimal algorithm can be selected for different collection scenarios.

[0053] Based on this, the present application embodiment provides a case allocation method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the case allocation method of the present application. In this embodiment, the method includes: Steps S10 to S40:

[0054] Step S10: Obtain a current case list, and determine the pre-call case in the current case list.

[0055] It should be noted that the method of this embodiment can be applied to allocate collection cases in financial scenarios, and the execution subject of the method of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a mobile phone, a tablet, a case management server, etc., and can also be other devices that can access the case management system. The following takes the case management device (hereinafter referred to as the "management device") as an example to explain the various embodiments of this application.

[0056] It should be understood that the current case list may include several pending cases (for example, loan cases to be collected) and corresponding processing information, including: the customer's (collection object) debt type, debt amount, overdue time, communication method, etc.

[0057] It should also be noted that, considering the large differences in the nature of the customers and the amount of debt owed for different pending cases, that is, the importance of different pending cases varies, the pending cases in the current case list can be divided in advance: some pending cases can be identified as pre-call cases to be pre-contacted through AI outbound calls, and the other pending cases can be identified as manual contact cases to allow users to directly contact customers and conduct subsequent processing.

[0058] Step S20: Perform AI outbound calls to customers corresponding to each of the pre-call cases, and determine effective contact cases based on the outbound call results.

[0059] It should be understood that several AI robots that can perform customer outbound calling tasks can be maintained in the management device, and users can configure the outbound call display name, outbound call task scope, etc. of each AI robot based on different processing requirements.

[0060] It can be understood that different pre-processed cases can be matched to corresponding AI robots based on the case category of the pre-call case and the outbound call history information of each AI robot, and the AI ​​robot can make initial contact with multiple customers at the same time.

[0061] It should be noted that based on the pre-set analysis rules, the recorded key data can be analyzed in real time, and qualified pre-call cases can be identified as effective contact cases, so as to achieve preliminary screening of cases before the operating user processes them, avoiding some invalid contact tasks, such as empty numbers or numbers that are not the user's own, thereby improving the user's contact efficiency with effective customers.

[0062] In addition, pre-call cases that do not meet the conditions can also be identified as manual contact cases so that users can directly contact customers and perform subsequent processing.

[0063] Step S30: Connect the effectively reached cases to the shared case pool corresponding to each operation group according to the preset group configuration information.

[0064] It should be understood that the screened effective contact cases can be automatically imported into the shared case pool corresponding to each operation group; or the case docking information of each operation group can be pre-configured to connect the effective contact cases of a specific case category to the shared case pool corresponding to a certain operation group.

[0065] It should be noted that the entire operation team can be divided into operation groups that handle different types of cases, such as Mortgage Group A and Mortgage Group B that handle mortgage cases. For different operation groups, you can configure the type of team members, the number of team members, and the weight of case assignments, and you can also configure the importance of the cases you can accept (for example, whether to accept manual contact cases).

[0066] It is understandable that one or more operation groups may correspond to a designated shared case pool, and each user in the operation group may be responsible for handling each case in the shared case pool (including effectively reached cases and manually reached cases).

[0067] Step S40: Based on a preset fusion case assignment strategy, determine the target case to be processed for each user in each shared case pool, wherein the preset fusion case assignment strategy includes at least one of a competitive case grabbing strategy and an automatic case assignment strategy.

[0068] It should be noted that, considering that the traditional case allocation strategy ignores the uneven distribution of overdue cases (for example, loan cases have a peak in the middle of the month, but are relatively rare at the end of the month) and the dynamic changes in the collection ability of each user, different case allocation strategies can be implemented based on different case volumes.

[0069] Specifically, first, the current total number of cases in each shared case pool can be obtained, and it can be determined whether the current total number of cases is greater than the preset capacity threshold; then, when the current total number of cases is greater than the preset capacity threshold, the competitive case grabbing strategy is triggered; when the current total number of cases is not greater than the preset capacity threshold, the automatic case assignment strategy is triggered.

[0070] It is understandable that the preset capacity threshold can be set for different shared case pools to distinguish the size of the case volume. When the case volume is large, a competitive case grabbing strategy can be adopted. At this time, each user in the corresponding operation group can be prompted to actively grab cases in the shared case pool, thereby maximizing the utilization rate of collection resources; when the case volume is small, the automatic case division strategy is restored to ensure that the customers corresponding to each case can be processed in a timely manner, while ensuring the balance of user performance within the entire operation group.

[0071] This embodiment introduces AI outbound calls to screen effective contact cases, thereby avoiding some invalid contact cases and improving the user's contact efficiency with effective contact cases. The competition mechanism and automatic case division algorithm are combined in the case division strategy to meet the personalized case division requirements of different operation groups, increase the accuracy and efficiency of case division decisions, ensure that the optimal algorithm can be selected for different collection scenarios, and thus improve the processing efficiency and completion effect of cases.

[0072] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , Figure 2 This is a flowchart of the second embodiment of the case allocation method of the present application.

[0073] In this embodiment, in order to specifically illustrate how to reach customers of each pending case through AI outbound calling combined with manual work, step S20 specifically includes: steps S201 to S204:

[0074] Step S201: Obtain a preset AI outbound call configuration table, wherein the preset AI outbound call configuration table includes: a machine number and a corresponding outbound call task category.

[0075] It should be understood that the preset AI outbound call configuration table can maintain the configuration information of each AI robot, including: AI robot configuration items such as machine number, outbound call display name, outbound call task category and outbound call task range.

[0076] Step S202: Determine the case category information of each of the pre-call cases, and match the machine number corresponding to each of the pre-call cases in the preset AI outbound call configuration table according to the case category information.

[0077] It should be understood that the case category of the pre-call case corresponding to each AI robot can be determined based on the outbound call history records of each AI robot. The case category may not be unique, and there may be overlapping case categories corresponding to each AI robot.

[0078] It is understandable that the case category of the pre-call case can be matched in the preset AI outbound call configuration table to determine the machine number corresponding to one or more AI robots suitable for handling the case category.

[0079] Step S203: The AI ​​robots corresponding to the machine numbers make AI outbound calls to the customers corresponding to the pre-call cases to obtain the degree of customer willingness to answer the calls for the pre-call cases.

[0080] It is understandable that the corresponding AI robot can be determined by the machine number, and then the initial contact with each customer can be achieved based on the AI ​​robot. In AI contact, key data in the process of calling or talking with customers can be recorded, such as: outbound call status (whether the customer is connected), whether the caller is a customer pre-stored in the processing information of the pre-call case, outbound call rounds, and the customer's willingness to repay obtained by analysis.

[0081] Step S204: If the customer's willingness to answer the call is greater than the willingness threshold, the pre-call case is determined to be a valid contact case.

[0082] It should be understood that the willingness threshold can be used to distinguish whether the customer is willing to answer the call at the current moment. If the quantified value of the customer's willingness to answer the call is greater than the willingness threshold, it means that the customer is willing to answer the call. The pre-call case corresponding to the customer is regarded as an effective contact case, so that the subsequent manual direct contact with the customer can execute the subsequent case processing process (i.e., the collection process).

[0083] It should also be noted that if the quantitative value of the customer's willingness to answer the call is less than the willingness threshold, it means that the customer's willingness to answer the call is low, and the pre-call case corresponding to the customer can be regarded as an invalid contact case.

[0084] Furthermore, invalid contact cases can be divided into three types: the customer did not answer, the caller was not the customer, and the customer hung up after answering. In this way, the invalid contact cases corresponding to the customer hung up after answering are determined as manual contact cases, so that the user can directly contact the customer and conduct subsequent processing; invalid contact cases corresponding to other types are determined as pending verification cases to facilitate the review of case processing information.

[0085] Further, in order to specifically explain how to connect the effectively reached cases to different shared case pools, step S30 specifically includes: steps S301 to S302:

[0086] Step S301: Determine the subordinate operation groups under different case categories and the case acquisition methods corresponding to each operation group according to the preset group configuration information, wherein the case acquisition method is at least one of a case grabbing method and a case dividing method.

[0087] Step S302: Determine a number of corresponding operation groups according to the case category information of each of the effective reached cases, and transfer each of the effective reached cases to the shared case pool of each of the operation groups respectively.

[0088] It should be understood that since there can be multiple operation groups handling the same case category, when the AI ​​robot screens out a number of valid contact cases belonging to each case category, it is possible to first determine which operation groups can subsequently process the valid contact cases screened by each AI robot.

[0089] Next, the shared case pool corresponding to these operation groups can be determined, and then each valid case can be connected to the shared case pool so that users of each operation group can handle the case in a timely manner. In addition, the shared case pool can also be pre-connected with cases manually reached.

[0090] It should also be noted that since the cases in the shared case pool can be provided to one or more operation groups for processing, the case acquisition methods corresponding to each operation group are the case grabbing method and the case division method. If different case division strategies are triggered based on the case volume in the shared case pool in the future, it is necessary to ensure that among the several operation groups corresponding to each shared case pool, there is at least one operation group whose case acquisition method is the case grabbing method, and one operation group whose case acquisition method is the case division method. This ensures that under different case volumes, there is at least one operation group that can subsequently process the cases in the shared case pool.

[0091] In addition, you can refer to Figure 3 The customer contact process that combines AI technology and manual implementation in the case allocation method of this application is explained. Figure 3 This is a schematic diagram of the customer contact process in this application case allocation method.

[0092] exist Figure 3 In the process, the AI ​​outbound call configuration information can be determined first to determine the case category that each AI robot is suitable for executing, and then AI outbound calls can be executed to connect with different customers. Next, the willingness of each customer to answer the call can be determined based on the AI ​​outbound call results. Finally, the effective reached cases can be determined based on the customer's willingness to access the shared case pool of different operation groups in combination with the combined configuration information, so as to facilitate the subsequent determination of the target processing cases corresponding to each user in each of the shared case pools based on the competitive case grabbing strategy and the automatic case distribution strategy.

[0093] This embodiment obtains a preset AI outbound call configuration table, and the preset AI outbound call configuration table includes: a machine number and a corresponding outbound call task category; determines the case category information of each of the pre-call cases, and matches the machine number corresponding to each of the pre-call cases in the preset AI outbound call configuration table according to the case category information; uses the AI ​​robots corresponding to each of the machine numbers to make AI outbound calls to the customers corresponding to each of the pre-call cases, and obtains the customer's willingness to answer the call for each of the pre-call cases; if the customer's willingness to answer the call is greater than the willingness threshold, the pre-call case is determined to be an effectively reached case. This embodiment integrates the dual advantages of AI intelligence and manual collection at the customer reach layer, with independent AI outbound calls and manual collection operating in parallel, greatly improving the user's accurate reach and interaction efficiency with customers; at the same time, it provides seamless human-machine collaboration functions, greatly improving the success rate of users contacting and influencing customers, thereby increasing the repayment probability of collection cases.

[0094] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those of the first and second embodiments can be referred to the above description, and will not be described in detail later. Figure 4 , Figure 4 This is a flowchart of the third embodiment of the case allocation method of the present application.

[0095] In this embodiment, in order to illustrate the specific implementation process of different case division strategies triggered by the case volume in the shared case pool, step S40 includes: steps S401 to S403:

[0096] Step S401: upon receiving a case snatching request from a first operating user, determining whether the first operating user meets the conditions for allowing the case snatching, and the first operating user belongs to an operating group whose case acquisition method is the case snatching method.

[0097] It should be understood that when the total number of current cases is greater than the preset capacity threshold, that is, when the competitive case grabbing strategy is triggered, information can be sent to each user in the operation group corresponding to the shared case pool to prompt each user to start the case grabbing.

[0098] Specifically, when a case snatching request is received from the first job user, the assigned cases of the first job user can be obtained first, and the case status of each assigned case can be determined, and the case status includes: unfinished, in progress and completed; when there are no unfinished assigned cases, the first job user is subject to a permission check; and whether the first job user meets the conditions for allowing case snatching is determined based on the permission check result.

[0099] Step S402: If yes, then determine the expected number of robberies of the first job user according to the robbery request.

[0100] Step S403: When the expected number of robberies is not greater than the preset robbery threshold, valid cases with the expected number of robberies are obtained from the shared case pool and determined as target processing cases for the first operating user.

[0101] It should be noted that in order to prevent cases from piling up at a certain user's place, an upper limit on the number of cases a user can snatch can be set, so that the user randomly obtains a certain number of cases as target processing cases according to a preset snatching threshold.

[0102] You can refer to this Figure 5 The execution process of the competition strategy for this application is explained. Figure 5 This is a schematic diagram of the execution flow of the competitive robbery strategy for this application.

[0103] exist Figure 5 In the process, upon receiving a case snatching request from an operator (the first operation task), it is first verified whether the operator has any unfinished collection cases; if the operator does not have any unfinished collection cases, it is further verified whether the operator has the authority to snatch the cases (for example, whether the case acquisition method of the operation group to which the operator belongs is the case snatching method, and whether the operation group corresponds to the shared case pool); when the authority verification is passed, a certain number of cases can be obtained from the shared case pool based on the set upper limit on the number of snatched cases; finally, the case is bound to the operator, and a successful snatching prompt message is returned to the operator.

[0104] By adopting a case-grabbing competition strategy, we can ensure efficient allocation of resources, stimulate the competitive vitality of the team, and maximize the efficiency of debt collection. At the same time, each user can take cases according to their own ability level and real-time work status, prevent case backlogs, and improve debt collection results in a smarter and more humane way.

[0105] Furthermore, step S40 further includes steps S401' to S402':

[0106] Step S401': in response to the automatic case assignment strategy triggering instruction, obtaining the allocation weight of each second operation user, the second operation user belonging to the operation group whose case acquisition method is the case assignment method.

[0107] It should be understood that when the total number of current cases is greater than the preset capacity threshold, the automatic case distribution strategy execution instruction can be triggered to prompt each user in the operation group corresponding to the shared case pool to stop snatching cases.

[0108] It can be understood that the allocation weight can be a fixed weight of each user in each operating group when participating in the case allocation pre-configured in the preset group configuration information, or it can be a weight updated in real time based on the outstanding balance of each second-operating user. For example, if the outstanding balance of user A is 100,000 and the outstanding balance of user B is 500,000, then the allocation weight of user A can be updated to be higher than the allocation weight of user B.

[0109] Step S402': Based on the allocation weights, according to preset allocation rules and in combination with all valid access cases in the shared case pool, the target processing cases for each of the second operation users are determined.

[0110] It should be noted that the preset allocation rule may be a detailed rule set based on different sub-case categories in different case categories.

[0111] For example, for first-hand housing loan cases and second-hand housing loan cases, which are both housing loan cases, considering the differences in the difficulty of debt collection, the corresponding difficulty levels can be pre-set based on the debt collection difficulty. Therefore, when allocating cases, it can be ensured that the difficulty levels of cases allocated to different second operation users are the same or similar, avoiding the concentration of cases with higher or lower difficulty levels allocated to a certain user.

[0112] In the specific implementation, common allocation algorithms such as the greedy algorithm can be used to comprehensively consider the allocation weights and preset allocation rules, and allocate all cases in the shared case pool to the second job user, thereby ensuring the fairness of case allocation when the case volume is low, ensuring that each user has appropriate tasks that are suitable for their capabilities, and improving the overall case processing efficiency.

[0113] In this embodiment, during periods of high caseload, a competitive case grabbing strategy is adopted to maximize the utilization of collection resources; when the caseload is low, the automatic case allocation strategy is restored to ensure that customers can receive timely and effective collection services while maintaining the performance balance of the collection team. Compared with the singleness of existing case allocation strategies, it can take into account the diversity of collection scenarios and the dynamic differences in users' collection capabilities, which is conducive to further improving the execution efficiency of case processing.

[0114] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the case allocation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0115] In addition, the present application also provides a case allocation device, referring to Figure 6 , Figure 6 Schematic diagram of the module structure of the first embodiment of the case allocation device of this application; Figure 6 As shown, the device comprises:

[0116] The customer contact module 601 is used to obtain a current case list and determine a pre-call case in the current case list; perform an AI outbound call on the customer corresponding to each pre-call case, and determine a valid contact case based on the outbound call result;

[0117] The case allocation module 602 is used to connect the effectively reached cases to the shared case pool corresponding to each operation group according to the preset group configuration information; based on the preset fusion case assignment strategy, determine the target processing cases corresponding to each user in each shared case pool, and the preset fusion case assignment strategy includes at least one of the competitive case grabbing strategy and the automatic case assignment strategy.

[0118] Furthermore, the customer contact module 601 is also used to obtain a preset AI outbound call configuration table, which includes: a machine number and a corresponding outbound call task category; determining the case category information of each of the pre-call cases, and matching the machine number corresponding to each of the pre-call cases in the preset AI outbound call configuration table according to the case category information; making an AI outbound call to the customer corresponding to each of the pre-call cases through the AI ​​robot corresponding to each of the machine numbers, and obtaining the customer's willingness to answer the call for each of the pre-call cases; if the customer's willingness to answer the call is greater than the willingness level threshold, determining that the pre-call case is an effective contact case.

[0119] Furthermore, the case allocation module 602 is also used to determine the subordinate operation groups under different case categories according to the preset group configuration information, and the case acquisition method corresponding to each operation group, and the case acquisition method is at least one of the case grabbing method and the case dividing method; determine the corresponding several operation groups according to the case category information of each of the effective contact cases, and transfer each of the effective contact cases to the shared case pool of each of the operation groups respectively.

[0120] Furthermore, the case allocation module 602 is also used to obtain the current total number of cases in each shared case pool and determine whether the current total number of cases is greater than a preset capacity threshold; when the current total number of cases is greater than the preset capacity threshold, trigger the competitive case grabbing strategy; when the current total number of cases is not greater than the preset capacity threshold, trigger the automatic case assignment strategy.

[0121] Furthermore, the case allocation module 602 is also used to determine whether the first operating user meets the conditions for allowing case robbery when receiving a case robbery request from the first operating user, and the first operating user belongs to an operation group whose case acquisition method is the case robbery method; if so, determine the expected number of cases to be robberied by the first operating user according to the case robbery request; when the expected number of cases to be robberied is not greater than a preset case robbery threshold, obtain the expected number of valid reached cases in the shared case pool, and determine them as the target processing cases for the first operating user.

[0122] Furthermore, the case assignment module 602 is also used to obtain the assigned cases of the first job user and determine the case status of each assigned case, the case status including: unfinished, in progress and completed; when there are no unfinished assigned cases, perform a permission check on the first job user; and determine whether the first job user meets the conditions for allowing case snatching based on the permission check result.

[0123] Furthermore, the case assignment module 602 is also used to obtain the assignment weight of each second operation user in response to the automatic case assignment strategy trigger instruction, and the second operation user belongs to the operation group whose case acquisition method is the case assignment method; based on the assignment weight, according to the preset assignment rules and combined with all the valid reached cases in the shared case pool, the target processing case of each second operation user is determined.

[0124] This embodiment introduces AI outbound calls to screen effective contact cases, thereby avoiding some invalid contact cases and improving the user's contact efficiency with effective contact cases. The competition mechanism and automatic case division algorithm are combined in the case division strategy to meet the personalized case division requirements of different operation groups, increase the accuracy and efficiency of case division decisions, ensure that the optimal algorithm can be selected for different collection scenarios, and thus improve the processing efficiency and completion effect of cases.

[0125] Other embodiments or specific implementations of the case allocation device described in this application can refer to the above-mentioned method embodiments and will not be repeated here.

[0126] The present application also provides a case allocation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the case allocation method in the above-mentioned embodiment one.

[0127] Reference below Figure 7 , Figure 7 The schematic diagram of the structure of the case allocation device of the present application. The case allocation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7The case allocation device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0128] like Figure 7 As shown, the case allocation device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the case allocation device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the case allocation device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a case allocation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0129] The present application also provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, the computer-readable program instructions being used to execute the case allocation method in the above-mentioned embodiment.

[0130] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0131] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A case allocation method, characterized in that: The method comprises: obtaining a current case list and determining a pre-call case in the current case list; Conduct AI outbound calls to customers corresponding to each of the pre-call cases, and determine effective contact cases based on the outbound call results; Connecting the effective cases to the shared case pool corresponding to each operation group according to the preset group configuration information; Based on a preset fusion case assignment strategy, a target case to be processed corresponding to each user is determined in each shared case pool, wherein the preset fusion case assignment strategy includes at least one of a competitive case grabbing strategy and an automatic case assignment strategy.

2. The method according to claim 1, characterized in that The step of making AI outbound calls to customers corresponding to each of the pre-call cases and determining effective contact cases based on the outbound call results includes: Obtain a preset AI outbound call configuration table, wherein the preset AI outbound call configuration table includes: a machine number and a corresponding outbound call task category; Determine the case category information of each of the pre-call cases, and match the machine number corresponding to each of the pre-call cases in the preset AI outbound call configuration table according to the case category information; The AI ​​robots corresponding to the machine numbers make AI outbound calls to the customers corresponding to the pre-call cases to obtain the degree of willingness of the customers to answer the calls in the pre-call cases; If the customer's willingness to answer the call is greater than the willingness threshold, the pre-call case is determined to be a valid contact case.

3. The method according to claim 2, characterized in that The step of connecting the effective access cases to the shared case pool corresponding to each operation group according to the preset group configuration information includes: Determine the operation groups under different case categories and the case acquisition methods corresponding to the operation groups according to the preset group configuration information, wherein the case acquisition method is at least one of a case grabbing method and a case dividing method; According to the case category information of each of the effective reached cases, a number of corresponding operation groups are determined, and each of the effective reached cases is respectively transferred to the shared case pool of each of the operation groups.

4. The method according to claim 1, characterized in that Before the step of determining the target processing cases corresponding to each user in each shared case pool based on the preset fusion case division strategy, the method includes: Obtaining the total number of current cases in each of the shared case pools, and determining whether the total number of current cases is greater than a preset capacity threshold; When the total number of current cases is greater than the preset capacity threshold, a competitive case grabbing strategy is triggered; When the total number of current cases is not greater than the preset capacity threshold, the automatic case allocation strategy is triggered.

5. The method according to claim 4, characterized in that The step of determining the target processing cases corresponding to each user in each shared case pool based on the preset fusion case division strategy includes: Upon receiving a case snatching request from a first operation user, determining whether the first operation user meets the conditions for allowing the case snatching, and the first operation user belongs to an operation group whose case acquisition method is the case snatching method; If yes, determining the expected number of robberies of the first job user according to the robbery request; When the expected number of robberies is not greater than a preset robbery threshold, valid cases with the expected number of robberies are obtained from the shared case pool and determined as target processing cases for the first operating user.

6. The method according to claim 5, characterized in that The step of determining whether the first operation user meets the conditions for allowing the robbery includes: Acquire the assigned cases of the first operation user, and determine the case status of each of the assigned cases, wherein the case status includes: unfinished, in progress, and completed; When there are no unfinished assigned cases, performing authority verification on the first operation user; It is determined whether the first operation user meets the conditions for allowing the robbery according to the permission verification result.

7. The method according to claim 4, characterized in that The step of determining the target processing cases corresponding to each user in each shared case pool based on the preset fusion case division strategy includes: In response to the automatic case assignment strategy trigger instruction, obtaining the allocation weight of each second operation user, the second operation user belongs to the operation group whose case acquisition method is the case assignment method; Based on the allocation weights, the target processing cases for each of the second operation users are determined according to preset allocation rules and in combination with all valid reached cases in the shared case pool.

8. A case allocation device, characterized in that: The device comprises: The customer contact module is used to obtain the current case list and determine the pre-call cases in the current case list; perform AI outbound calls on the customers corresponding to each pre-call case, and determine the effective contact cases based on the outbound call results; The case allocation module is used to connect the effectively reached cases to the shared case pool corresponding to each operation group according to the preset group configuration information; based on the preset fusion case allocation strategy, the target processing case corresponding to each user is determined in each shared case pool, and the preset fusion case allocation strategy includes at least one of the competitive case grabbing strategy and the automatic case allocation strategy.

9. A case allocation device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the case allocation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the case allocation method according to any one of claims 1 to 7 are implemented.

Images