Collection task allocation method and device, electronic equipment and computer program product
By obtaining customer information and using the collection strategy model and diversion model for dynamic allocation, the problem of incomplete tasks caused by fluctuations in collection tasks in financial institutions is solved, and the collection efficiency and reach rate are improved.
Patent Information
- Application Number
- CN202411870367.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-18
- Publication Date
- 2025-04-25
AI Technical Summary
When dealing with overdue loans, financial institutions face the problem of excessive fluctuations in the collection task volume caused by concentrated repayment dates, resulting in endless tasks under certain collection strategies.
By obtaining customer information of the collection task, the original collection strategy model is used to determine the original collection strategy, and when triggering the diversion conditions, the collection task is used to diversion processing to the task and dynamically allocate the final collection strategy.
It effectively alleviates the pressure of handling collection tasks, improves the collection reach rate, and ensures the complete execution of collection tasks.
Smart Images
Figure CN119886644A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of collection task allocation, and in particular to a collection task allocation method, device, electronic equipment, and computer program product. Background Art
[0002] In recent years, the rapid development of consumer finance has promoted the growth of financial institutions' credit business, but it has also led to a rise in delinquency and bad debt rates. Reducing credit delinquency risks and recovering overdue loans have become difficult problems faced by consumer finance institutions.
[0003] At present, various financial institutions are building intelligent outbound call and manual outbound call collection platforms. When a loan is overdue, it will be sent to the collection platform, and the task will be transferred to the intelligent outbound call or manual outbound call through the rule engine. However, since the repayment dates are relatively concentrated, the task volume of intelligent outbound call related functions fluctuates greatly. The maximum daily average task volume may be three times the usual task volume, which may lead to the situation where tasks under a certain collection strategy cannot be completed. Summary of the invention
[0004] The embodiments of the present application provide a collection task allocation method, device, electronic device, and computer program product to achieve dynamic allocation of collection tasks and improve the collection reach rate.
[0005] The present application embodiment adopts the following technical solutions:
[0006] In a first aspect, an embodiment of the present application provides a method for allocating collection tasks, the method comprising:
[0007] Obtain customer information for collection tasks;
[0008] Based on the customer information of the collection task, determining the original collection strategy of the collection task using the collection strategy model;
[0009] When the original collection strategy of the collection task triggers the collection task diversion condition, the collection task diversion model is used to divert the collection tasks under the original collection strategy to obtain the final collection strategy of the collection task.
[0010] Optionally, the collection strategy model is a rule matching model, the customer information includes at least one of basic customer information, account information, and overdue information, and the original collection strategy of the collection task determined by the collection strategy model based on the customer information of the collection task includes:
[0011] Preprocessing the customer information of the collection task to obtain rule parameters of the collection task;
[0012] An original collection strategy of the collection task is determined according to the rule parameters of the collection task and the rule matching model.
[0013] Optionally, when the original collection strategy of the collection task triggers the collection task diversion condition, the collection task diversion model is used to divert the collection task under the original collection strategy to obtain the final collection strategy of the collection task, which includes:
[0014] Determining the original collection task amount corresponding to each original collection strategy according to the original collection strategy of the collection task;
[0015] Determining whether the original collection strategy of the collection task triggers the collection task diversion condition according to the original collection task volume corresponding to each original collection strategy and the corresponding collection task volume threshold;
[0016] When the original collection strategy of a collection task triggers the collection task diversion condition, the collection tasks of the original collection strategy are diverted using the collection task diversion model according to the original collection task volume corresponding to the original collection strategy to obtain the final collection strategy of the collection task.
[0017] Optionally, the determining whether the original collection strategy of the collection task triggers the collection task diversion condition according to the original collection task amount corresponding to each original collection strategy and the corresponding collection task amount threshold includes:
[0018] If the original collection task volume corresponding to the original collection strategy is greater than the corresponding collection task volume threshold, determining that the original collection strategy of the collection task triggers the collection task diversion condition;
[0019] Otherwise, it is determined that the original collection strategy of the collection task does not trigger the collection task diversion condition.
[0020] Optionally, the original collection strategy and the final collection strategy both include multiple types. When the original collection strategy of the collection task triggers the collection task diversion condition, the collection tasks of the original collection strategy are diverted using the collection task diversion model according to the original collection task volume corresponding to the original collection strategy, and the final collection strategy of the collection task includes:
[0021] Determine the overflow task volume corresponding to the first original collection strategy and the remaining task volume threshold value of the second original collection strategy according to the original collection task volume corresponding to the original collection strategy, wherein the first original collection strategy is the original collection strategy with overflow task volume, and the second original collection strategy is the original collection strategy with remaining task volume;
[0022] According to the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy, the overflow task volume corresponding to the first original collection strategy is diverted to obtain a final collection strategy for the overflow tasks.
[0023] Optionally, determining the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy according to the original collection task volume corresponding to the original collection strategy and the task volume threshold includes:
[0024] If the original collection task volume corresponding to the original collection strategy is greater than the task volume threshold, the difference between the task volume threshold corresponding to the original collection strategy and the original collection task volume is used as the overflow task volume corresponding to the first original collection strategy;
[0025] If the original collection task volume corresponding to the original collection strategy is not greater than the task volume threshold, the difference between the original collection task volume corresponding to the original collection strategy and the task volume threshold is used as the remaining task volume corresponding to the second original collection strategy.
[0026] Optionally, the second original collection strategy includes a plurality of strategies, and the overflow task volume corresponding to the first original collection strategy is diverted according to the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy to obtain the final collection strategy for the overflow task includes:
[0027] Determining a diversion order of multiple second original debt collection strategies according to the first original debt collection strategy and multiple second original debt collection strategies;
[0028] According to the overflow task volume corresponding to the first original collection strategy, the remaining task volume corresponding to the second original collection strategy, and the diversion order of multiple second original collection strategies, the overflow task volume corresponding to the first original collection strategy is diverted to at least one second original collection strategy.
[0029] In a second aspect, an embodiment of the present application further provides a collection task allocation device, the collection task allocation device comprising:
[0030] An acquisition unit, used to acquire customer information of a collection task;
[0031] A determination unit, configured to determine an original collection strategy of the collection task using a collection strategy model based on the customer information of the collection task;
[0032] The diversion unit is used to divert the collection tasks under the original collection strategy by using the collection task diversion model when the original collection strategy of the collection task triggers the collection task diversion condition, so as to obtain the final collection strategy of the collection task.
[0033] In a third aspect, an embodiment of the present application further provides an electronic device, including:
[0034] A processor; and a memory arranged to store computer executable instructions, which, when executed, cause the processor to execute any of the aforementioned collection task allocation methods.
[0035] In a fourth aspect, an embodiment of the present application further provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements any of the aforementioned collection task allocation methods.
[0036] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the collection task allocation method of the embodiments of the present application first obtains the customer information of the collection task; then, based on the customer information of the collection task, the collection strategy model is used to determine the original collection strategy of the collection task; finally, when the original collection strategy of the collection task triggers the collection task diversion condition, the collection task diversion model is used to divert the collection task under the original collection strategy to obtain the final collection strategy of the collection task. The collection task allocation method of the embodiments of the present application is based on the customer information of the collection task, and uses the collection strategy model to assign the best collection strategy to each collection task, and then based on the task processing pressure of different collection strategies, the collection task diversion model is used to dynamically allocate the collection tasks between strategies, thereby alleviating the pressure of collecting task processing and improving the collection reach rate. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0038] Figure 1 A flowchart of a collection task allocation method in an embodiment of the present application;
[0039] Figure 2 A schematic diagram of a process for determining a collection strategy based on a rule matching model in an embodiment of the present application;
[0040] Figure 3 This is a structural schematic diagram of a collection task allocation device in an embodiment of the present application;
[0041] Figure 4 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION
[0042] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0043] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0044] The present application embodiment provides a collection task allocation method, such as Figure 1 As shown, a flow chart of a collection task allocation method in an embodiment of the present application is provided, and the collection task allocation method at least includes the following steps S110 to S130:
[0045] Step S110, obtaining customer information of the collection task.
[0046] A collection task is generated for each customer to be collected, that is, one collection task corresponds to one customer to be collected. When allocating collection tasks, it is necessary to first obtain the customer information corresponding to each collection task, which may include the customer's basic information, account information, overdue status, risk score, etc. The obtained customer information is sorted and assembled into a data structure for subsequent processing. This process must ensure the accuracy of the data to avoid failing to obtain the expected results.
[0047] Step S120, based on the customer information of the collection task, determine the original collection strategy of the collection task using the collection strategy model.
[0048] After obtaining the information of the customers to be collected, the collection strategy model is used to process and analyze the above customer information. This collection strategy model can evaluate and analyze customer information according to pre-defined rules and logic to determine the collection strategy for overdue customers. The collection strategy results returned by the collection strategy model may include information such as the collection method adopted, the collection frequency, and the collection team. The type of collection method can be flexibly set according to actual needs, for example, it may include intelligent voice, automatic outbound calls, non-head office manual outbound calls, head office manual outbound calls, etc.
[0049] Step S130, when the original collection strategy of the collection task triggers the collection task diversion condition, the collection task diversion model is used to divert the collection task under the original collection strategy to obtain the final collection strategy of the collection task.
[0050] Although the collection strategy model in the above steps realizes the dynamic acquisition of collection strategies, considering that there may be a situation where the collection task execution pressure of a certain collection strategy is too high, a collection task diversion step is set before the collection task is officially issued. When the collection task diversion conditions are met, the collection task diversion model can be used to convert and deploy different collection tasks according to the preset configuration. The main idea of diversion is the splitting of tasks. Before diversion, the pre-configured strategy will be loaded, and then the collection tasks that need to be diverted will be split according to the diversion strategy. After the splitting is completed, the task will be issued. Because each call will reload the diversion configuration, it is possible to flexibly adjust the task diversion situation and effectively alleviate the execution pressure of one or some collection tasks.
[0051] The collection task allocation method in the embodiment of the present application is based on the customer information of the collection task, and uses the collection strategy model to assign the best collection strategy to each collection task. Then, based on the task processing pressure of different collection strategies, the collection task diversion model is used to dynamically allocate the collection tasks between strategies, thereby alleviating the collection task processing pressure and improving the collection reach rate.
[0052] In some embodiments of the present application, the collection strategy model is a rule matching model, the customer information includes at least one of basic customer information, account information, and overdue information, and the original collection strategy of the collection task is determined based on the customer information of the collection task and the collection strategy model, including: preprocessing the customer information of the collection task to obtain the rule parameters of the collection task; and determining the original collection strategy of the collection task according to the rule parameters of the collection task and the rule matching model.
[0053] The collection strategy model of the embodiment of the present application can adopt a rule matching model, which can evaluate, decide and process the input data according to predefined rules and logic, and finally output a matching collection strategy.
[0054] like Figure 2 As shown, a flow chart of determining a collection strategy based on a rule matching model in an embodiment of the present application is provided. First, basic customer feature information (such as age, gender, work, etc.), repayment information, overdue status, etc. are obtained through various data sources, such as databases, files, API interfaces, etc., and then the obtained raw data is preprocessed, including data cleaning, format conversion, field mapping and other operations, to obtain the rule parameters required by the rule engine so that the rule engine can correctly parse and process the data. After that, the rule matching model formulates corresponding collection strategies, including collection methods, collection frequency, etc., based on the customer's overdue status, account information, risk level and other parameters.
[0055] Continue to refer Figure 2 , Figure 2An example of a process for matching collection strategies based on rule parameters and rule matching models is given in the specification. In actual situations, there are many rule parameters, which are only given as an example here. For example, the following judgment is made using the number of overdue periods as the initial matching condition:
[0056] If the number of overdue periods is greater than the preset overdue period threshold, the product type is determined. If the product type is product A, the matching collection method is manual collection by the head office. If it is not product A, the account status is further determined to be abnormal. If the account status is abnormal, the matching collection method is manual collection by the head office. If the account status is normal, the matching collection method is automatic outbound call.
[0057] If the number of overdue periods is less than or equal to the preset overdue period threshold, it is determined whether the overdue amount is greater than the preset amount threshold X. If so, the matching collection method is manual outbound call, otherwise the matching collection method is intelligent voice.
[0058] The above is the use of the rule engine to obtain a large number of customer parameters, including basic customer characteristics, loan products, loan amounts, remaining amounts, account age, overdue days, overdue amounts, local institutions, risk parameters, five-level classification and other parameters, and then use the obtained customer portrait data as input parameters into the rule engine, and output the accurately matched collection strategy to adapt to the changes of different overdue customers and different business scenarios.
[0059] Of course, in addition to matching collection strategies using rule matching models, the embodiments of the present application can also use deep learning and other technologies to pre-train a collection strategy prediction model, with the input being the above-mentioned multi-dimensional customer information and the output being the optimal collection strategy corresponding to the customer.
[0060] In some embodiments of the present application, when the original collection strategy of the collection task triggers the collection task diversion condition, the collection task under the original collection strategy is diverted by using the collection task diversion model to obtain the final collection strategy of the collection task, including: determining the original collection task amount corresponding to each original collection strategy according to the original collection strategy of the collection task; determining whether the original collection strategy of the collection task triggers the collection task diversion condition according to the original collection task amount corresponding to each original collection strategy and the corresponding collection task amount threshold; when the original collection strategy of the collection task triggers the collection task diversion condition, the collection task of the original collection strategy is diverted by using the collection task diversion model according to the original collection task amount corresponding to the original collection strategy to obtain the final collection strategy of the collection task.
[0061] Before formally carrying out task diversion, it is possible to first determine whether the current collection task volume under each collection strategy has triggered the collection task diversion condition. For example, the original collection strategy corresponding to each collection task can be determined based on the collection strategy model in the aforementioned embodiment, and the total collection task volume corresponding to each original collection strategy can be counted. Then, the total collection task volume corresponding to each original collection strategy is compared with the task volume threshold corresponding to each collection strategy, so as to determine whether each collection strategy triggers the collection task diversion condition.
[0062] If the collection task diversion condition is triggered, the set diversion strategy is further used to divert the tasks that need to be diverted based on the total collection task volume under each collection strategy. Diversion means that the collection strategy of a collection task is divided from collection strategy A to collection strategy B.
[0063] In some embodiments of the present application, determining whether the original collection strategy of the collection task triggers the collection task diversion condition based on the original collection task volume corresponding to each original collection strategy and the corresponding collection task volume threshold includes: if the original collection task volume corresponding to the original collection strategy is greater than the corresponding collection task volume threshold, then determining that the original collection strategy of the collection task triggers the collection task diversion condition; otherwise, determining that the original collection strategy of the collection task does not trigger the collection task diversion condition.
[0064] When specifically judging whether the original collection strategy triggers the collection task diversion condition, the total collection task volume corresponding to each original collection strategy can be compared with the maximum task volume that each collection strategy can handle in a collection cycle (such as within a day), that is, the task volume threshold. If the total collection task volume under a certain collection strategy is greater than the corresponding collection task volume threshold, then the collection strategy triggers the collection task diversion condition, indicating that the collection strategy has a task volume overflow, and the overflow tasks need to be diverted. If it is not greater than the corresponding collection task volume threshold, then the collection strategy does not trigger the collection task diversion condition, indicating that the collection strategy does not have a task volume overflow, and the tasks under the collection strategy do not need to be diverted, but the tasks diverted from other strategies can be accepted.
[0065] The collection task volume threshold corresponding to each collection strategy can be flexibly set in combination with the actual execution capability of each collection strategy in the actual business scenario, and is not specifically limited here. By setting the collection task volume threshold, it is possible to accurately determine whether the collection tasks under each collection strategy need to be diverted.
[0066] In some embodiments of the present application, the original collection strategy and the final collection strategy both include multiple types. When the original collection strategy of a collection task triggers a collection task diversion condition, the collection task of the original collection strategy is diverted using the collection task diversion model according to the original collection task volume corresponding to the original collection strategy, and the final collection strategy for the collection task is obtained, including: determining the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy according to the original collection task volume and the task volume threshold corresponding to the original collection strategy, the first original collection strategy being the original collection strategy with an overflow task volume, and the second original collection strategy being the original collection strategy with a remaining task volume; and diverting the overflow task volume corresponding to the first original collection strategy according to the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy to obtain the final collection strategy for the overflow task.
[0067] The types of collection strategies actually covered by the original collection strategy and the final collection strategy defined in the embodiment of the present application are the same, and are only used to distinguish the source of the collection strategy corresponding to each collection task. The original collection strategy comes directly from the collection strategy model, and the final collection strategy comes from the collection task diversion model.
[0068] When it is determined that a certain collection strategy has triggered the collection task diversion condition, the overflow task volume under the collection strategy, i.e., the above-mentioned first original collection strategy, can be calculated, and at the same time, the remaining task volume under other collection strategies, i.e., the above-mentioned second original collection strategy, can be calculated. According to the overflow task volume under the first original collection strategy and the remaining task volume under the second original collection strategy, the overflow tasks under the first original collection strategy are diverted to the second original collection strategy for processing, so that the overflow tasks can be executed in a timely manner, thereby ensuring the processing efficiency of the collection tasks.
[0069] In some embodiments of the present application, determining the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy based on the original collection task volume and the task volume threshold corresponding to the original collection strategy includes: if the original collection task volume corresponding to the original collection strategy is greater than the task volume threshold, then the difference between the task volume threshold corresponding to the original collection strategy and the original collection task volume is used as the overflow task volume corresponding to the first original collection strategy; if the original collection task volume corresponding to the original collection strategy is not greater than the task volume threshold, then the difference between the original collection task volume corresponding to the original collection strategy and the task volume threshold is used as the remaining task volume corresponding to the second original collection strategy.
[0070] When analyzing the task overflow of each original collection strategy, it is mainly achieved through the following methods:
[0071] The overflow task volume of the first original collection strategy = the task volume threshold of the first original collection strategy - the original collection task volume;
[0072] The remaining task volume of the second original collection strategy=the original collection task volume-the task volume threshold of the second original collection strategy.
[0073] The size of the overflow task volume reflects how much of the task needs to be diverted by the current collection strategy, and the size of the remaining task volume reflects how much of the task of other collection strategies the current collection strategy can accept. By calculating the overflow task volume and the remaining task volume, the task overflow situation and the acceptability of different collection strategies can be intuitively reflected, providing a quantitative basis for the subsequent dynamic allocation of collection tasks.
[0074] In some embodiments of the present application, the second original collection strategy includes multiple strategies, and the overflow task volume corresponding to the first original collection strategy is diverted according to the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy to obtain the final collection strategy for the overflow task, including: determining the diversion order of multiple second original collection strategies according to the first original collection strategy and multiple second original collection strategies; diverting the overflow task volume corresponding to the first original collection strategy to at least one second original collection strategy according to the overflow task volume corresponding to the first original collection strategy, the remaining task volume corresponding to the second original collection strategy and the diversion order of multiple second original collection strategies.
[0075] The principle of the collection task diversion model is as follows:
[0076] 1) If the task volume of the collection strategy A output by the collection strategy model does not reach the threshold preset in the collection task diversion model, the output of the diversion model remains the original collection strategy;
[0077] 2) If the task volume of collection strategy A on the day in the collection strategy model reaches the preset threshold in the collection task diversion model, the overflow task volume will be diverted to collection strategy B through the collection task diversion model. If the sum of the task volume to be diverted of collection strategy A and the task volume hitting collection strategy B on the day exceeds the threshold of collection strategy B in the collection task diversion model, the secondary overflow tasks of collection strategy A will continue to be diverted to collection strategy C, and so on, until the diversion is completed or the collection strategy utilization rate reaches 100%.
[0078] Therefore, the principle of the collection task diversion model is to calculate whether there is task overflow in each collection strategy task through diversion strategy and preset thresholds. If there is overflow, it means that this strategy cannot be completed on time due to the huge amount of tasks. The overflow tasks will be dynamically allocated to ensure the collection reach rate of such customer groups on the same day, thereby avoiding the situation where collection is not carried out due to overflow.
[0079] To further illustrate, if the collection strategy model calculates that the number of tasks that hit the intelligent voice strategy on a certain day is 70,000, the number of tasks that hit the manual phone strategy is 80,000, and the number of tasks that hit the automatic outbound call strategy is X million, the result output by the collection strategy model is input into the collection task diversion model, and the calculation logic is as follows:
[0080] 1) If the task volume that hits the intelligent voice does not exceed the intelligent voice task volume threshold in the task diversion model, the final collection strategy output is still the intelligent voice;
[0081] 2) If the number of tasks that hit the intelligent voice exceeds the intelligent voice threshold preset by the task diversion model (assuming 50,000), the overflowing intelligent voice tasks (70,000-50,000) need to be diverted. After the diversion model is applied, the strategy and amount of tasks that need to be diverted next time are obtained, such as manual calls;
[0082] 3) If the threshold of the manual telephone strategy in the task diversion model is X ten thousand, then calculate:
[0083] If (the number of intelligent voice tasks on the day - the preset threshold of intelligent voice + the number of tasks that hit the manual call on the day) <= the manual call threshold, that is: 7-5+8<=X, then the number of tasks diverted to the manual call strategy = the number of intelligent voice tasks on the day - the preset threshold of intelligent voice;
[0084] If (the number of intelligent voice tasks on the day - the preset threshold of intelligent voice + the number of manual phone tasks on the day) > the manual phone threshold, that is, 7-5+8>X, then the number of tasks diverted to the manual phone strategy = the manual phone threshold - the number of manual phone tasks on the day. The remaining ((the number of intelligent voice tasks on the day - the intelligent voice threshold) - (the manual phone threshold - the number of manual phone tasks)) intelligent voice tasks continue to repeat the above calculation rules and be diverted to other collection strategies, such as automatic broadcasting, automatic outbound calls, etc.
[0085] It should be noted that in the above-mentioned diversion process, the diversion order between the collection strategies can be used to determine which other collection strategy to divert to first. Specifically, the diversion order of other collection strategies can be determined comprehensively from the similarity between the original collection strategy and other collection strategies, the collection success rate, and the remaining task volume of other collection strategies. For example, if the original collection strategy is head office outbound calls, if the task volume of the head office outbound calls overflows, it can be diverted to non-head office manual outbound calls first. If there is still overflow after diverting to non-head office manual outbound calls, the overflow part will be further diverted to automatic outbound calls, and so on, until the diversion is completed or the collection strategy utilization rate reaches 100%.
[0086] This application realizes dynamic allocation of collection tasks through the collection strategy model and the collection task diversion model, avoiding the situation where the collection tasks for some customers are not completed due to the excessive workload of a certain collection strategy. It can effectively and comprehensively cover overdue customers and improve customer collection efficiency.
[0087] In summary, the key points of the collection task allocation method of this application mainly include:
[0088] 1) Input the overdue customer profile information including the number of overdue days, overdue amount, risk score, warning level, etc. as parameters into the collection strategy model, and accurately identify the collection strategy corresponding to the customer through the collection strategy model;
[0089] 2) Continuously monitor and track the collection strategy output by the collection strategy model, input the output results of the collection strategy model and the statistical task volume into the collection task diversion model, and the collection task diversion model outputs the diverted collection strategy through a preset smoothing threshold.
[0090] The collection task allocation method of this application has achieved at least the following technical effects:
[0091] 1) Based on the collection strategy model, the present disclosure adds a collection task diversion model. The collection task diversion model is a smooth strategy model that can be dynamically adjusted. It can use the task volume of the collection strategy and parameters such as preset thresholds to dynamically divert overflow tasks according to the expected strategy, thereby improving the collection reach and task execution efficiency;
[0092] 2) By continuously monitoring and tracking the strategy results output by the collection strategy model, the collection task diversion model can be used to divert overflow tasks in a timely manner, and the latest collection strategy can be allocated for them to avoid missing the best collection time due to the overflow part not being collected in time.
[0093] The present application embodiment also provides a collection task allocation device 300, such as Figure 3 As shown, a schematic diagram of the structure of a collection task allocation device in an embodiment of the present application is provided, and the collection task allocation device 300 at least includes: an acquisition unit 310, a determination unit 320 and a diversion unit 330, wherein:
[0094] An acquisition unit 310 is used to acquire customer information of a collection task;
[0095] A determination unit 320 is used to determine an original collection strategy of the collection task using a collection strategy model based on the customer information of the collection task;
[0096] The diversion unit 330 is used to divert the collection tasks under the original collection strategy by using the collection task diversion model to obtain the final collection strategy of the collection task when the original collection strategy of the collection task triggers the collection task diversion condition.
[0097] In some embodiments of the present application, the collection strategy model is a rule matching model, the customer information includes at least one of basic customer information, account information, and overdue information, and the determination unit 320 is specifically used to: pre-process the customer information of the collection task to obtain the rule parameters of the collection task; determine the original collection strategy of the collection task based on the rule parameters of the collection task and the rule matching model.
[0098] In some embodiments of the present application, the diversion unit 330 is specifically used to: determine the original collection task volume corresponding to each original collection strategy according to the original collection strategy of the collection task; determine whether the original collection strategy of the collection task triggers the collection task diversion condition according to the original collection task volume corresponding to each original collection strategy and the corresponding collection task volume threshold; when the original collection strategy of the collection task triggers the collection task diversion condition, divert the collection task of the original collection strategy according to the original collection task volume corresponding to the original collection strategy using the collection task diversion model to obtain the final collection strategy of the collection task.
[0099] In some embodiments of the present application, the diversion unit 330 is specifically used to: if the original collection task volume corresponding to the original collection strategy is greater than the corresponding collection task volume threshold, then determine that the original collection strategy of the collection task triggers the collection task diversion condition; otherwise, determine that the original collection strategy of the collection task does not trigger the collection task diversion condition.
[0100] In some embodiments of the present application, the original collection strategy and the final collection strategy both include multiple types, and the diversion unit 330 is specifically used to: determine the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy according to the original collection task volume and the task volume threshold corresponding to the original collection strategy, the first original collection strategy is the original collection strategy with overflow task volume, and the second original collection strategy is the original collection strategy with remaining task volume; according to the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy, the overflow task volume corresponding to the first original collection strategy is diverted to obtain the final collection strategy for the overflow task.
[0101] In some embodiments of the present application, the diversion unit 330 is specifically used to: if the original collection task volume corresponding to the original collection strategy is greater than the task volume threshold, then the difference between the task volume threshold corresponding to the original collection strategy and the original collection task volume is used as the overflow task volume corresponding to the first original collection strategy; if the original collection task volume corresponding to the original collection strategy is not greater than the task volume threshold, then the difference between the original collection task volume corresponding to the original collection strategy and the task volume threshold is used as the remaining task volume corresponding to the second original collection strategy.
[0102] In some embodiments of the present application, the second original collection strategy includes multiple strategies, and the diversion unit 330 is specifically used to: determine the diversion order of multiple second original collection strategies according to the first original collection strategy and the multiple second original collection strategies; and divert the overflow task volume corresponding to the first original collection strategy to at least one second original collection strategy according to the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy and the diversion order of the multiple second original collection strategies.
[0103] It can be understood that the above-mentioned collection task allocation device can implement each step of the collection task allocation method provided in the above-mentioned embodiment. The relevant explanations about the collection task allocation method are applicable to the collection task allocation device and will not be repeated here.
[0104] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.
[0105] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0106] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0107] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a collection task dispatching device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:
[0108] Obtain customer information for collection tasks;
[0109] Based on the customer information of the collection task, determining the original collection strategy of the collection task using the collection strategy model;
[0110] When the original collection strategy of the collection task triggers the collection task diversion condition, the collection task diversion model is used to divert the collection tasks under the original collection strategy to obtain the final collection strategy of the collection task.
[0111] The above application Figure 1The method performed by the collection task dispatching device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0112] The present application also provides a computer program product, including a computer program or an instruction, which is implemented when the computer program or the instruction is executed by a processor. Figure 1 The collection task allocation method in the illustrated embodiment is specifically used to execute:
[0113] Obtain customer information for collection tasks;
[0114] Based on the customer information of the collection task, determining the original collection strategy of the collection task using the collection strategy model;
[0115] When the original collection strategy of the collection task triggers the collection task diversion condition, the collection task diversion model is used to divert the collection tasks under the original collection strategy to obtain the final collection strategy of the collection task.
[0116] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0117] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0118] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0120] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0121] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0122] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0123] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0125] The above is only the embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A collection task allocation method, characterized in that: The collection task allocation method includes: Obtain customer information for collection tasks; Based on the customer information of the collection task, determining the original collection strategy of the collection task using the collection strategy model; When the original collection strategy of the collection task triggers the collection task diversion condition, the collection task diversion model is used to divert the collection tasks under the original collection strategy to obtain the final collection strategy of the collection task.
2. The collection task allocation method according to claim 1 is characterized in that: The collection strategy model is a rule matching model, the customer information includes at least one of basic customer information, account information, and overdue information, and the original collection strategy of the collection task determined by the collection strategy model based on the customer information of the collection task includes: Preprocessing the customer information of the collection task to obtain rule parameters of the collection task; An original collection strategy of the collection task is determined according to the rule parameters of the collection task and the rule matching model.
3. The collection task allocation method according to claim 1 is characterized in that: In the case where the original collection strategy of the collection task triggers the collection task diversion condition, the collection task diversion model is used to divert the collection task under the original collection strategy, and the final collection strategy of the collection task is obtained, including: Determining the original collection task amount corresponding to each original collection strategy according to the original collection strategy of the collection task; Determining whether the original collection strategy of the collection task triggers the collection task diversion condition according to the original collection task volume corresponding to each original collection strategy and the corresponding collection task volume threshold; When the original collection strategy of a collection task triggers the collection task diversion condition, the collection tasks of the original collection strategy are diverted using the collection task diversion model according to the original collection task volume corresponding to the original collection strategy to obtain the final collection strategy of the collection task.
4. The collection task allocation method according to claim 3 is characterized in that: The determining, based on the original collection task volume corresponding to each original collection strategy and the corresponding collection task volume threshold, whether the original collection strategy of the collection task triggers the collection task diversion condition includes: If the original collection task volume corresponding to the original collection strategy is greater than the corresponding collection task volume threshold, determining that the original collection strategy of the collection task triggers the collection task diversion condition; Otherwise, it is determined that the original collection strategy of the collection task does not trigger the collection task diversion condition.
5. The collection task allocation method according to claim 3 is characterized in that: The original collection strategy and the final collection strategy both include multiple types. When the original collection strategy of the collection task triggers the collection task diversion condition, the collection tasks of the original collection strategy are diverted using the collection task diversion model according to the original collection task volume corresponding to the original collection strategy, and the final collection strategy of the collection task includes: Determine the overflow task volume corresponding to the first original collection strategy and the remaining task volume threshold value of the second original collection strategy according to the original collection task volume corresponding to the original collection strategy, wherein the first original collection strategy is the original collection strategy with overflow task volume, and the second original collection strategy is the original collection strategy with remaining task volume; According to the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy, the overflow task volume corresponding to the first original collection strategy is diverted to obtain a final collection strategy for the overflow tasks.
6. The collection task allocation method according to claim 5 is characterized in that: The step of determining the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy according to the original collection task volume corresponding to the original collection strategy and the task volume threshold comprises: If the original collection task volume corresponding to the original collection strategy is greater than the task volume threshold, the difference between the task volume threshold corresponding to the original collection strategy and the original collection task volume is used as the overflow task volume corresponding to the first original collection strategy; If the original collection task volume corresponding to the original collection strategy is not greater than the task volume threshold, the difference between the original collection task volume corresponding to the original collection strategy and the task volume threshold is used as the remaining task volume corresponding to the second original collection strategy.
7. The collection task allocation method according to claim 5, characterized in that: The second original collection strategy includes a plurality of strategies, and the overflow task volume corresponding to the first original collection strategy is diverted according to the overflow task volume corresponding to the first original collection strategy and the remaining task volume corresponding to the second original collection strategy to obtain the final collection strategy for the overflow task, including: Determining a diversion order of multiple second original debt collection strategies according to the first original debt collection strategy and multiple second original debt collection strategies; According to the overflow task volume corresponding to the first original collection strategy, the remaining task volume corresponding to the second original collection strategy, and the diversion order of multiple second original collection strategies, the overflow task volume corresponding to the first original collection strategy is diverted to at least one second original collection strategy.
8. A collection task allocation device, characterized in that: The collection task allocation device comprises: An acquisition unit, used to acquire customer information of a collection task; A determination unit, configured to determine an original collection strategy of the collection task using a collection strategy model based on the customer information of the collection task; The diversion unit is used to divert the collection tasks under the original collection strategy by using the collection task diversion model when the original collection strategy of the collection task triggers the collection task diversion condition, so as to obtain the final collection strategy of the collection task.
9. An electronic device, comprising: processor; And a memory arranged to store computer executable instructions, which, when executed, cause the processor to execute any one of the collection task allocation methods of claims 1 to 7.
10. A computer program product, comprising a computer program or instructions, wherein when the computer program or instructions are executed by a processor, the method for allocating collection tasks according to any one of claims 1 to 7 is implemented.