Determining method and device for arrearage payment reminding strategy and storage medium

Abstract

The invention provides an arrearage payment reminding strategy determination method and device and a storage medium, relates to the technical field of data processing, and can improve the arrearage payment reminding efficiency. The method comprises the following steps: acquiring customer information data; the customer information data comprises at least one of the following items: basic information of a customer, an ordering record of the customer, a payment record of the customer, an arrearage record of the customer, preference data of the customer and behavior data of the customer; analyzing the customer information data based on a preset algorithm, and determining an arrearage payment reminding strategy; the preset algorithms comprise a clustering algorithm, a decision tree analysis algorithm and a time sequence algorithm.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus and storage medium for determining arrears collection strategy. Background Technology

[0002] With the rapid development of the data processing field, the application of overdue payment collection strategies is becoming more and more widespread. At present, traditional overdue payment collection methods mainly involve sending overdue payment collection information or manual collection to customers with overdue payments.

[0003] As described above regarding methods for collecting overdue payments, traditional methods can collect some of the outstanding payments. However, due to the complexity and diversity of the industries and business types of customers with overdue payments, traditional methods suffer from low efficiency in collecting overdue payments from some customers. Summary of the Invention

[0004] This application provides a method, apparatus, and storage medium for determining overdue payment collection strategies, which can improve the efficiency of overdue payment collection.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, this application provides a method for determining arrears collection strategies. The method includes: acquiring customer information data; the customer information data includes at least one of the following: basic customer information, customer ordering records, customer payment records, customer arrears records, customer preference data, and customer behavior data; analyzing the customer information data based on a preset algorithm to determine arrears collection strategies; the preset algorithm includes: clustering algorithm, decision tree analysis algorithm, and time series algorithm.

[0007] The above technical solution brings at least the following beneficial effects: This application uses multiple preset algorithms to analyze various customer information data to formulate overdue payment collection strategies. The customer information data obtained by this application is comprehensive and diverse, which can fully and comprehensively determine customer-related data. Therefore, obtaining multiple customer information data can provide an accurate data foundation for subsequently determining overdue payment collection strategies. In addition, the multiple preset algorithms selected by this application have high predictive accuracy. Therefore, the overdue payment collection strategies determined by the preset algorithms have high predictive accuracy. The determined overdue payment collection strategies are consistent with the customer's identity and actual situation. By using overdue payment collection strategies that are consistent with the customer's situation to collect payments from the corresponding customers, the success rate of collection can be improved, thereby improving the efficiency of overdue payment collection.

[0008] In one possible implementation, customer information data is analyzed based on a preset algorithm to determine a debt collection strategy, including: analyzing customer information data using a clustering algorithm to determine the collection amount, collection frequency, and incentive product category, where the collection amount indicates the proportion of collections, the collection frequency indicates the number of times a collection reminder is sent to the customer within a preset time period, and the incentive product category indicates the type of product that incentivizes the customer to pay the debt; analyzing customer information data using a decision tree analysis algorithm and the incentive product category to determine incentive products, which are used to incentivize the customer to pay the debt; analyzing customer information data using a time series algorithm to determine the collection timing, where the collection timing indicates the time to send a collection reminder to the customer; and determining the collection strategy based on the collection amount, collection frequency, incentive product, and collection timing.

[0009] In one possible implementation, customer information data is analyzed based on clustering algorithms to determine collection amounts, collection frequencies, and incentive product categories. This includes: clustering customer information data to determine customer identity information; clustering customer identity information, customer arrears records, and customer payment records to determine customer credit rating; and determining collection frequencies, collection amounts, and incentive product categories based on customer credit rating.

[0010] In one possible implementation, customer information data is analyzed based on a decision tree analysis algorithm to determine incentive products, including: constructing a decision tree of incentive products and customer information data based on the decision tree analysis algorithm, customer information data, and incentive product categories; and determining incentive products based on the decision tree of incentive products and customer information data.

[0011] In one possible implementation, customer information is analyzed based on time series algorithms to determine the timing of collection, including: analyzing customer payment information, customer arrears information, and customer information based on time series algorithms to determine the timing of collection.

[0012] In one possible implementation, the method further includes: performing natural language description processing on the collection strategy based on customer classification information to determine collection notification information; and sending collection notification information to customers.

[0013] In one possible implementation, the method of sending overdue payment notices to customers includes at least one of the following: SMS, email, telephone, corporate portal notification, and program notification.

[0014] Secondly, this application provides an apparatus for determining an overdue payment collection strategy. The apparatus includes: a communication unit and a processing unit; the communication unit is used to acquire customer information data; the customer information data includes at least one of the following: basic customer information, customer order records, customer payment records, customer overdue payment records, customer preference data, and customer behavior data; the processing unit is used to analyze the customer information data based on a preset algorithm to determine an overdue payment collection strategy; the preset algorithm includes: a clustering algorithm, a decision tree analysis algorithm, and a time series algorithm.

[0015] In one possible implementation, the determining unit is specifically used for: analyzing customer information data based on a clustering algorithm to determine the collection amount, collection frequency, and incentive product category, where the collection amount indicates the proportion of collections, the collection frequency indicates the number of times collection reminders are sent to customers within a preset time period, and the incentive product category indicates the category of products that incentivize customers to pay their debts; analyzing customer information data based on a decision tree analysis algorithm and the incentive product category to determine incentive products, which are used to incentivize customers to pay their debts; analyzing customer information data based on a time series algorithm to determine the collection timing, where the collection timing indicates the time to send collection reminders to customers; and determining a collection strategy based on the collection amount, collection frequency, incentive products, and collection timing.

[0016] In one possible implementation, the processing unit is specifically used to: cluster customer information data to determine customer identity information; cluster customer identity information, customer arrears records, and customer payment records to determine customer credit rating; and determine collection frequency, collection amount, and incentive product category based on customer credit rating.

[0017] In one possible implementation, the processing unit is specifically used to: construct a decision tree for incentive products and customer information data based on the decision tree analysis algorithm, customer information data, and incentive product categories; and determine the incentive product based on the decision tree for incentive products and customer information data.

[0018] In one possible implementation, the processing unit is also used to analyze customer payment information, customer arrears information, and customer information based on time series algorithms to determine the timing of collection.

[0019] In one possible implementation, the processing unit is further configured to perform natural language description processing on the collection strategy based on customer classification information to determine the collection notification information; the communication unit is further configured to send the collection notification information to the customer.

[0020] In one possible implementation, the method of sending overdue payment notices to customers includes at least one of the following: SMS, email, telephone, corporate portal notification, and program notification.

[0021] Thirdly, this application provides an apparatus for determining an overdue payment collection strategy, the apparatus comprising: a processor and a communication interface; the communication interface and the processor are coupled, the processor being used to run computer programs or instructions to implement the overdue payment collection strategy determination method as described in the first aspect and any possible implementation thereof.

[0022] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a terminal, cause the terminal to perform the overdue payment collection strategy determination method as described in the first aspect and any possible implementation thereof.

[0023] Fifthly, this application provides a computer program product containing instructions that, when the computer program product is run on an overdue payment collection strategy determination device, causes the overdue payment collection strategy determination device to perform the overdue payment collection strategy determination method as described in the first aspect and any possible implementation thereof.

[0024] Sixthly, this application provides a chip including a processor and a communication interface, the communication interface and the processor being coupled together, the processor being used to run computer programs or instructions to implement the overdue payment collection strategy determination method as described in the first aspect and any possible implementation thereof.

[0025] Specifically, the chip provided in this application also includes a memory for storing computer programs or instructions. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of a system for determining overdue payment collection strategies provided in an embodiment of this application;

[0027] Figure 2 This is a schematic diagram of a device for determining arrears collection strategy provided in an embodiment of this application;

[0028] Figure 3 A flowchart illustrating a method for determining arrears collection strategies, provided in an embodiment of this application;

[0029] Figure 4 A schematic diagram of another overdue payment collection strategy determination system provided in this application embodiment;

[0030] Figure 5 This is a schematic diagram of another device for determining overdue payment collection strategies provided in an embodiment of this application. Detailed Implementation

[0031] The following description, in conjunction with the accompanying drawings, details the method, apparatus, and storage medium for determining overdue payment collection strategies provided in the embodiments of this application.

[0032] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0033] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0034] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0035] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0036] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0037] In the current telecommunications service industry, operators face a widespread and increasingly serious problem: a large number of customers are in arrears on payments. This includes not only ordinary consumers but also government and enterprise clients. These clients are distributed across various industries and have diverse business types, covering multiple fundamental and innovative fields such as mobile communications, fixed networks, converged services, internet data centers (IDC), dual-line services, big data, cloud computing, the Internet of Things, and information security. In particular, government and enterprise clients, due to the complexity and diversity of their businesses, often become the hardest hit areas for arrears. These clients have long periods of arrears, and the amounts owed are huge. Some of these arrears have even evolved into long-standing unresolved debts that require legal action, which undoubtedly greatly prolongs the collection period.

[0038] With the rapid development of the data processing field, the application of overdue payment collection strategies is becoming more and more widespread. At present, traditional overdue payment collection methods mainly involve sending overdue payment collection information or manual collection to customers with overdue payments.

[0039] As described above regarding methods for collecting overdue payments, traditional methods can collect some of the outstanding payments. However, due to the complexity and diversity of the industries and business types of customers with overdue payments, traditional methods suffer from low efficiency in collecting overdue payments from some customers.

[0040] In view of this, this application uses multiple preset algorithms to analyze various customer information data to formulate overdue payment collection strategies. The customer information data obtained by this application is comprehensive and diverse, which can fully and comprehensively identify relevant customer data. Therefore, obtaining multiple customer information data can provide an accurate data foundation for subsequently determining overdue payment collection strategies. In addition, the multiple preset algorithms selected by this application have high predictive accuracy. Therefore, the overdue payment collection strategies determined by the preset algorithms have high predictive accuracy. The determined overdue payment collection strategies are consistent with the customer's identity and actual situation. By using overdue payment collection strategies that are consistent with the customer's situation to collect payments from the corresponding customers, the success rate of collection can be improved, thereby improving the efficiency of overdue payment collection.

[0041] The technical solutions provided in this application can be applied to various communication systems, such as New Radio (NR) communication systems using 5G, future evolution systems, or multiple communication convergence systems.

[0042] For example, Figure 1 The diagram shows a schematic of a debt collection strategy determination system 10 provided in an embodiment of this application. The debt collection strategy determination system 10 may include at least one terminal device 101 and at least one computing device 102, and the terminal device 101 may be communicatively connected to the computing device 102. Figure 1 Only one terminal device 101 and one computing device 102 are shown in the diagram.

[0043] In one possible implementation, terminal device 101 is used to send customer information data to computing device 102.

[0044] In one possible implementation, computing device 102 is used to acquire customer information data; the customer information data includes at least one of the following: basic customer information, customer order records, customer payment records, customer arrears records, customer preference data, and customer behavior data; the customer information data is analyzed based on a preset algorithm to determine an arrears collection strategy; the preset algorithm includes: clustering algorithm, decision tree analysis algorithm, and time series algorithm.

[0045] In one possible implementation, the computing device 102 and the terminal device 101 can be independent devices or they can be the same device; this application does not limit this.

[0046] In one possible implementation, terminal device 101 can be a device with wireless transceiver capabilities or a chip or chip system that can be configured in the device. Terminal device 101 includes, but is not limited to, any node among: small base stations, wireless access points, transceiver points (TRPs), transmission points (TPs), macro base stations, relay base stations, and some other access nodes.

[0047] In one possible implementation, the computing device 102 can be a high-capacity device with wireless communication capabilities (e.g., a server integrating a large number of boards), which can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted. It can also be deployed on water (such as on ships). It can also be deployed in the air (e.g., on airplanes, balloons, and satellites).

[0048] It should be noted that, Figure 1 This is just an example framework diagram. Figure 1 The number of nodes included and the names of the devices are unlimited, except for... Figure 1 In addition to the functional nodes shown, the overdue payment collection strategy determination system 10 may also include other nodes, such as core network equipment, and this application does not impose any restrictions on this.

[0049] The application scenarios of the embodiments in this application are not limited. The system architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0050] In practical implementation, Figure 1 All the equipment in the middle can be adopted Figure 2 The shown composition structure, or including Figure 2 The components shown. Figure 2This is a schematic diagram illustrating the composition of a payment collection strategy determination device 20 provided in an embodiment of this application. The payment collection strategy determination device 20 can be a computing device 102 or a chip or system-on-a-chip within the computing device 102. Alternatively, the payment collection strategy determination device 20 can be a terminal device 101 or a chip or system-on-a-chip within the terminal device 101. Figure 2 As shown, the overdue payment collection strategy determination device 20 may include a processor 201 and a bus 202.

[0051] Furthermore, the overdue payment collection strategy determination device 20 may also include a communication interface 203 and a memory 204. The processor 201, memory 204, and communication interface 203 can be connected via a bus 202.

[0052] The processor 201 can be a CPU, a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 201 can also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation.

[0053] Bus 202 is used to transmit information between the components included in the overdue payment collection strategy determination device 20.

[0054] Communication interface 203 is used to communicate with other devices or other communication networks. These other communication networks can be Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc. Communication interface 203 can be a module, circuit, communication interface, or any device capable of enabling communication.

[0055] Memory 204 is used to store instructions. These instructions can be computer programs.

[0056] The memory 204 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions; it can also be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions; it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0057] It should be noted that the memory 204 can exist independently of the processor 201 or be integrated with the processor 201. The memory 204 can be used to store instructions, program code, or some data. The memory 204 can be located inside or outside the overdue payment collection strategy determination device 20, without restriction.

[0058] In one example, processor 201 may include one or more CPUs, for example, Figure 2 CPU0 and CPU1 (not shown in the figure).

[0059] As an optional implementation, the overdue payment collection strategy determination device 20 includes multiple processors.

[0060] As an optional implementation, the overdue payment collection strategy determination device 20 also includes output devices and input devices (not shown in the figure). For example, the input device is a keyboard, mouse, microphone or joystick, etc., and the output device is a display screen, speaker, etc.

[0061] It should be noted that the overdue payment collection strategy determination device 20 can be a desktop computer, laptop computer, network server, mobile phone, tablet computer, wireless terminal, embedded device, chip system, or other device. Figure 2 Equipment with a similar structure. Furthermore... Figure 2 The composition shown does not constitute a basis for the interpretation of this invention. Figure 1 as well as Figure 2 The limitations of each device in the process, except Figure 2 In addition to the components shown, Figure 1 as well as Figure 2 The various devices may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0062] In this embodiment of the application, the chip system may be composed of chips or may include chips and other discrete devices.

[0063] Furthermore, the actions, terms, etc., involved in the various embodiments of this application can be referenced interchangeably without limitation. The message names or parameter names in the messages exchanged between the various devices in the embodiments of this application are merely examples, and other names may be used in specific implementations without limitation.

[0064] The following is combined Figure 1 The overdue payment collection strategy determination system shown herein describes the overdue payment collection strategy determination method provided in the embodiments of this application. The actions, terminology, etc., involved in the various embodiments of this application can be referred to mutually without limitation. The message names or parameter names in the messages exchanged between various devices in the embodiments of this application are merely examples; other names can be used in specific implementations without limitation. The actions involved in the various embodiments of this application are merely examples; other names can be used in specific implementations, such as replacing "included in" with "carried in" or "carried in," etc.

[0065] like Figure 3 As shown in the figure, a method for determining arrears collection strategy is provided in an embodiment of this application. The method includes:

[0066] S301, The computing device acquires customer information data.

[0067] The customer information data includes at least one of the following: basic customer information, customer ordering records, customer payment records, customer overdue payment records, customer preference data, and customer behavior data.

[0068] For example, the computing device may obtain customer information data in the following ways: the computing device may obtain customer information data from a database; the computing device may also connect to a third-party credit platform to obtain customer information data from the third-party credit platform; or the computing device may directly read customer information data displayed by sensors through an Internet of Things protocol. This application embodiment does not limit these methods.

[0069] In one possible implementation, the computing device can perform preliminary classification of the acquired customer information data, which can be categorized into: public data, government and enterprise data, network data, and management data. Public data includes: basic customer information, order records, payment records, app preferences, behavioral data, credit data, data usage, voice data, and product data. Government and enterprise data includes: company information, industry information, order records, contract data, business opportunity data, credit data, customer relationship data, and product data. Network data includes: broadband information, data usage, and dual-line information. Management data includes: employee ID information, role information, and access control information.

[0070] S302. The computing device analyzes customer information data based on a preset algorithm to determine a debt collection strategy.

[0071] The preset algorithms include: clustering algorithm, decision tree analysis algorithm, and time series algorithm.

[0072] In one possible implementation, the above-mentioned S302 process can be as follows: The computing device analyzes customer information data based on a clustering algorithm to determine the collection amount, collection frequency, and incentive product category, wherein the collection amount indicates the proportion of collections. The collection frequency indicates the number of times collection reminders are sent to customers within a preset time period. The incentive product category indicates the category of products that incentivize customers to pay their outstanding debts. The computing device analyzes customer information data based on a decision tree analysis algorithm and the incentive product category to determine the incentive product, wherein the incentive product is used to incentivize customers to pay their outstanding debts. The computing device analyzes customer information data based on a time series algorithm to determine the collection timing, wherein the collection timing indicates the time when collection reminders are sent to customers. The computing device determines a collection strategy based on the collection amount, collection frequency, incentive product, and collection timing.

[0073] In one possible implementation, the computing device analyzes customer information data based on a clustering algorithm to determine the collection amount, collection frequency, and incentive product category. This includes: the computing device clustering customer information data to determine customer identity information, and clustering customer identity information, customer arrears records, and customer payment records to determine the customer's credit rating. Based on the customer's credit rating, the computing device determines the collection frequency, collection amount, and incentive product category.

[0074] In one possible implementation, the specific process by which the computing device clusters customer information data to determine customer identity information can be as follows: The computing device processes the customer information data to generate multiple sample points, where each sample point corresponds to the customer information data of one customer. The computing device selects K (K is a positive integer) cluster centers using the K-means clustering algorithm, and calculates the Euclidean distance between each sample point and the cluster center by substituting each sample point into a preset similarity formula. The similarity between the sample point and the cluster center is measured by the Euclidean distance between each sample point and the cluster center, and the sample point is classified into the class determined by the cluster center with the highest similarity to that sample point. The computing device updates the cluster centers iteratively based on the K-means clustering algorithm until the cluster centers no longer change. The computing device clusters the K values ​​based on the K-means clustering algorithm and calculates the sum of squares due to error (SSE) between the sample points and sample centers obtained in each clustering. The computing device plots line graphs of SSE and K values. By identifying the inflection points (also known as elbows) in the SSE and K value line graphs, the optimal K value is determined, feature value extraction is completed, and customer information data is classified according to the feature values.

[0075] In one possible implementation, the Euclidean distance between a sample point and the cluster center satisfies the following formula 1:

[0076]

[0077] Where, x i Let y be the i-th cluster center. i Let y be the i-th sample point, n be the feature dimension, and Dist(x,y) be the Euclidean distance between sample point y and cluster center x.

[0078] In one possible implementation, the sum of squared errors satisfies the following formula 2:

[0079]

[0080] Where K is the number of clusters, p is the number of sample points in the i-th cluster Ci, and m i Let be the cluster center of the i-th cluster Ci.

[0081] In one example, the computing device can categorize customers into public and government / enterprise customers. Public customers can be further divided into campus market customers, rural market customers, cluster market customers, senior citizen market customers, etc., while government / enterprise customers can be further divided into education industry customers, healthcare industry customers, government industry customers, agriculture industry customers, financial industry customers, etc.

[0082] In another example, campus market customers can be divided into mobile network customers and broadband customers, while education industry customers can be further divided into IoT customers and big data customers. Computing devices can cluster customer information data to determine specific customer categories, thereby identifying customer identity information.

[0083] For example, a computing device uses a clustering algorithm to segment customer information data. This customer information data can be categorized into: market classification, business classification, industry classification, credit rating classification, and customer profile classification. Specifically, market classification can be divided into: campus market, rural market, clustered market, and senior citizen market, etc. Business classification can be divided into: mobile network services, fixed network services, broadband services, and innovative services, etc. Industry classification can be divided into: education industry, healthcare industry, government industry, and agriculture, etc. Credit rating classification can be divided into: Level 1, Level 2, Level 3, Level 4, and Level 5. Customer profile classification can be divided into: customer preferences, frequently used apps, data usage, and language usage, etc.

[0084] In one possible implementation, the computing device uses the K-means clustering algorithm to cluster customer identity information and the customer's payment and arrears records to determine the customer's credit rating. The credit rating is then analyzed to determine the frequency of collection, the amount of collection, and the type of incentive product for the customer.

[0085] For example, for customers with high credit ratings, the collection frequency can be once a month, and the collection amount can be 50%. If the customer completes the payment, a high-value incentive product can be given as a gift. For customers with low credit ratings, the collection frequency can be as soon as the payment is overdue, and the collection amount can be 100%. If the customer completes the payment, a low-value incentive product can be given as a gift.

[0086] In one possible implementation, the computing device analyzes customer information data based on a decision tree analysis algorithm to determine the incentive product. This includes: the computing device constructing a decision tree based on the decision tree analysis algorithm, the customer information data, and the incentive product category; and the computing device determining the incentive product based on the decision tree.

[0087] In one possible implementation, the computing device analyzes customer information data based on a decision tree analysis algorithm to determine the specific process of incentive products. This process involves the computing device determining the optimal splitting feature and constructing a decision tree for the incentive products and customer information data. Specifically, the computing device divides the customer information data into two or more subsets based on the optimal splitting feature, recursively executing this process for each subset until the termination condition of the decision tree analysis algorithm is met. The computing device calculates the information entropy before and after each split using a preset formula, and determines the information gain by the difference between the information entropy before and after the split. A smaller information entropy indicates a more ordered or concentrated subset after the split, while a larger information entropy indicates a more disordered or scattered subset after the split. The computing device uses the information gain to measure the effectiveness of using the current feature to split the sample set into subsets. Each time the computing device splits a subset, it selects the splitting method with the best effect based on the information entropy, and recursively executes this process for each child node of the decision tree until the termination condition of optimal customer-incentive product matching is met, leading to the conclusion of intelligently recommending different incentive products for different customer characteristics.

[0088] In one possible implementation, information entropy satisfies the following formula 3:

[0089]

[0090] Where D is the total number of samples, c k Let n be the number of samples in class k, and n be the number of classes of the samples.

[0091] In one possible implementation, the information gain satisfies the following formula 4:

[0092]

[0093] Where a is the current splitting feature, and V is the number of values ​​that feature a can take.

[0094] For example, based on the decision tree analysis algorithm, the computing device can determine incentive products for different customers, such as: the computing device can recommend data packages, software value-added products, and products that give away free minutes when topping up phone credit to public customers; the computing device can provide extended warranty services, product extension services, cloud computing products, big data products, etc. to government and enterprise customers.

[0095] In one possible implementation, the computing device analyzes customer information based on a time-series algorithm to determine the timing of collection, including: the computing device analyzes customer payment information, customer arrears information, and customer information based on a time-series algorithm to determine the timing of collection.

[0096] For example, if public customers are accustomed to paying their bills after receiving their salaries or after receiving payment reminders, the computing device can determine the timing of the payment reminder as when the customer receives their salary. For government and enterprise customers, they may pay their bills when a company makes a payment. By analyzing payment behavior, the computing device can determine the optimal timing for payment reminders.

[0097] In one possible implementation, the collection strategy includes the content of the collection notice, the recipients of the notice, and the timing of the collection. The content includes overdue payment information, payment incentive information, and payment methods. Overdue payment information includes the overdue product and overdue period, while incentive information includes preferential policies such as value-added products and services offered after successful payment. Payment methods include payment QR codes and payment links. Recipients of the collection notice include public customers, government and enterprise customers, and their developers and operations personnel.

[0098] As described above regarding the method for determining collection strategies, the computing device can determine a collection strategy based on the collection amount, collection frequency, incentive products, and collection timing. Furthermore, the computing device can also use the collection strategy to collect overdue payments from customers with outstanding balances. If a customer with an outstanding balance does not have an outstanding balance, the computing device can store the collection strategy. When the corresponding customer incurs an outstanding balance, the computing device can retrieve the corresponding collection strategy and use it to collect the overdue payment from that customer. The following describes in detail the process of collecting overdue payments from customers based on a collection strategy.

[0099] In one possible implementation, the process by which the computing device generates the overdue payment notification information can be as follows: the computing device performs natural language description processing on the overdue payment strategy based on customer classification information, determines the overdue payment notification information, and sends the overdue payment notification information to the customer.

[0100] For example, the payment reminders pushed to customers by the computing device, processed using natural language processing (NLP), can contain friendly, concise, and direct language, along with incentive products and preferential policies, making them easy for customers to understand, generating interest, and ultimately leading to payment. The payment reminders pushed to account managers by the computing device, also processed using NLP, can include marketing scripts, incentive products, and preferential policies, facilitating targeted outreach, maintaining customer relationships, improving customer perception, and ultimately increasing the payment reminder success rate. The payment reminders pushed to operations personnel by the computing device, also processed using NLP, can include payment reminder results, allowing operations personnel to coordinate, plan, and analyze payment reminder performance. The computing device then pushes the integrated payment reminder content to the sending module, and, based on the customer's credit rating, sends it at the optimal time for payment reminder.

[0101] In another example, the computing device can determine whether to directly send the collection strategy to the customer. If it is necessary to send the collection strategy directly to the customer, the computing device performs natural language processing on the collection strategy based on the customer classification information to determine the collection notification information and sends the collection notification information to the customer. If it is not necessary to send the collection strategy directly to the customer, the computing device performs natural language processing on the collection strategy based on the customer classification information to determine the collection plan and sends the collection plan to the account manager. The account manager can then use the collection plan to send overdue payment reminders to the corresponding customer.

[0102] In one possible implementation, the method of sending overdue payment notices to customers includes at least one of the following: SMS, email, telephone, corporate portal notification, and program notification.

[0103] For example, the methods of sending payment reminders to customers may also include at least one of the following: payment QR code, payment mini-program link, or customer manager visit.

[0104] In one possible implementation, the computing device can also record payment collection information and incentive order information after the collection notice is issued, and input the relevant data into the data collection module to optimize and update the collection strategy. Furthermore, operations personnel can regularly monitor the actual completion of collections and adjust strategies and optimize models accordingly.

[0105] In view of this, this application uses multiple preset algorithms to analyze various customer information data to formulate overdue payment collection strategies. The customer information data obtained by this application is comprehensive and diverse, which can fully and comprehensively identify relevant customer data. Therefore, obtaining multiple customer information data can provide an accurate data foundation for subsequently determining overdue payment collection strategies. In addition, the multiple preset algorithms selected by this application have high predictive accuracy. Therefore, the overdue payment collection strategies determined by the preset algorithms have high predictive accuracy. The determined overdue payment collection strategies are consistent with the customer's identity and actual situation. By using overdue payment collection strategies that are consistent with the customer's situation to collect payments from the corresponding customers, the success rate of collection can be improved, thereby improving the efficiency of overdue payment collection.

[0106] It is understood that the above-mentioned method for determining overdue payment collection strategies can be implemented by an overdue payment collection strategy determination device. To achieve the above functions, the overdue payment collection strategy determination device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, the embodiments disclosed in this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments disclosed in this application.

[0107] The embodiments disclosed in this application can divide the overdue payment collection strategy determination device generated by the above method example into functional modules. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in the embodiments disclosed in this application is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0108] For example, Figure 4 This is a schematic diagram of another overdue payment collection strategy determination system provided in an embodiment of this application. The overdue payment collection strategy determination system includes: a data acquisition module 401, a data processing module 402, a strategy generation module 403, a strategy distribution module 404, and an operation monitoring module 405.

[0109] In one possible implementation, the data acquisition module 401 is used to acquire customer information data; the customer information data includes at least one of the following: basic customer information, customer order records, customer payment records, customer arrears records, customer preference data, and customer behavior data. The acquired customer information data is then sent to the data processing module 402.

[0110] Furthermore, in one possible implementation, the data acquisition module 401 is also used to perform preliminary classification of the acquired customer information data, which can be initially classified into: public data, government and enterprise data, network data, and management data. Public data includes: basic information, order records, payment records, application (APP) preferences, behavioral data, credit data, traffic data, voice data, and product data; government and enterprise data includes: enterprise information data, industry information data, order records, contract data, business opportunity data, credit data, customer relationship data, and product data; network data includes: broadband information data, traffic information data, and dual-line information data; management data includes: employee ID information data, role information data, and permission information data.

[0111] In one possible implementation, the data processing module 402 is used to analyze customer information data based on a clustering algorithm to determine the collection amount, collection frequency, and incentive product category. The collection amount indicates the proportion of collections, the collection frequency indicates the number of times collection reminders are sent to customers within a preset time period, and the incentive product category indicates the category of products that incentivize customers to pay their debts. The module also analyzes the customer information data based on a decision tree analysis algorithm and the incentive product category to determine incentive products, which are used to incentivize customers to pay their debts. Finally, the module analyzes the customer information data based on a time series algorithm to determine the collection timing, which indicates the time to send collection reminders to customers.

[0112] Furthermore, in one possible implementation, the data acquisition module 402 is also used to segment customer information data using a clustering algorithm. The customer information data can be segmented into: market categories, business categories, industry categories, credit rating categories, and customer profile categories. Specifically, market categories can be divided into: campus markets, rural markets, clustered markets, and senior citizen markets, etc. Business categories can be divided into: mobile network services, fixed network services, broadband services, and innovative services, etc. Industry categories can be divided into: education, healthcare, government, and agriculture, etc. Credit rating categories can be divided into: Level 1, Level 2, Level 3, Level 4, and Level 5. Customer profile categories can be divided into: customer preferences, frequently used apps, data usage, and language usage, etc.

[0113] In one possible implementation, the data acquisition module 402 is also used to predict overdue payments using a decision tree analysis algorithm, determine incentive products, and send the incentive products to the strategy generation module 403.

[0114] In one possible implementation, the data acquisition module 402 is also used to determine the collection timing through a time series analysis algorithm and send the collection timing to the strategy generation module 403.

[0115] In one possible implementation, the strategy generation module 403 determines a collection strategy based on the collection amount, collection frequency, incentive product, and collection timing. The collection strategy is then sent to the strategy distribution module 404.

[0116] In one possible implementation, the strategy delivery module 404 is used to determine whether to directly deliver the collection strategy to the customer. If it is necessary to directly deliver the collection strategy to the customer, it performs natural language processing on the collection strategy based on the customer classification information to determine the collection notification information and sends the collection notification information to the customer. If it is not necessary to directly deliver the collection strategy to the customer, it performs natural language processing on the collection strategy based on the customer classification information to determine the collection plan and sends the collection plan to the account manager. The account manager then uses the collection plan to collect the overdue payment from the corresponding customer.

[0117] In one possible implementation, the operations monitoring module 405 is used to record payment information and incentive order information after the collection notice is issued. It is also used to input relevant data into the data collection module for optimizing and updating the collection strategy.

[0118] Figure 5 This is a schematic diagram of a device for determining overdue payment collection strategies, provided in an embodiment of the present invention. Figure 5 As shown, the overdue payment collection strategy determination device 50 can be used to execute... Figure 3 The method for determining overdue payment collection strategies is shown. The overdue payment collection strategy determination device 50 includes a communication unit 501 and a processing unit 502.

[0119] The communication unit 502 is used to acquire customer information data; the customer information data includes at least one of the following: basic customer information, customer order records, customer payment records, customer arrears records, customer preference data, and customer behavior data; the processing unit 502 is used to analyze the customer information data based on a preset algorithm to determine the arrears collection strategy; the preset algorithm includes: clustering algorithm, decision tree analysis algorithm, and time series algorithm.

[0120] In one possible implementation, the processing unit 501 is specifically used for: analyzing customer information data based on a clustering algorithm to determine the collection amount, collection frequency, and incentive product category, where the collection amount indicates the proportion of collections, the collection frequency indicates the number of times collection reminders are sent to customers within a preset time period, and the incentive product category indicates the category of products that incentivize customers to pay their debts; analyzing customer information data based on a decision tree analysis algorithm and the incentive product category to determine incentive products, which are used to incentivize customers to pay their debts; analyzing customer information data based on a time series algorithm to determine the collection timing, where the collection timing indicates the time to send collection reminders to customers; and determining a collection strategy based on the collection amount, collection frequency, incentive products, and collection timing.

[0121] In one possible implementation, the processing unit 502 is specifically used to: cluster customer information data to determine customer identity information; cluster customer identity information, customer arrears records, and customer payment records to determine customer credit rating; and determine collection frequency, collection amount, and incentive product category based on customer credit rating.

[0122] In one possible implementation, the processing unit 502 is specifically used to: construct a decision tree for incentive products and customer information data based on the decision tree analysis algorithm, customer information data, and incentive product categories; and determine the incentive product based on the decision tree for incentive products and customer information data.

[0123] In one possible implementation, the processing unit 502 is further configured to analyze the customer's payment information, the customer's arrears information, and customer information based on a time series algorithm to determine the timing for collection.

[0124] In one possible implementation, the processing unit 502 is further configured to perform natural language description processing on the collection strategy based on customer classification information to determine the collection notification information; the communication unit 502 is further configured to send the collection notification information to the customer.

[0125] In one possible implementation, the method of sending overdue payment notices to customers includes at least one of the following: SMS, email, telephone, corporate portal notification, and program notification.

[0126] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0127] This disclosure also provides a computer-readable storage medium storing instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the overdue payment collection strategy determination method provided in the embodiments of this disclosure.

[0128] This disclosure also provides a computer program product containing instructions that, when run on an electronic device, causes the electronic device to execute the overdue payment collection strategy determination method provided in the above-described embodiments of this disclosure.

[0129] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires; portable computer disks; hard disks; random access memory (RAM); read-only memory (ROM); erasable programmable read-only memory (EPROM); registers; hard disks; optical fibers; portable compact disc read-only memory (CD-ROM); optical storage devices; magnetic storage devices; or any suitable combination thereof; or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may reside in an application-specific integrated circuit (ASIC). In the embodiments of this application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0130] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining a debt collection strategy, characterized in that, The method includes: Obtain customer information data; the customer information data includes at least one of the following: the customer's basic information, the customer's order records, the customer's payment records, the customer's outstanding payment records, the customer's preference data, and the customer's behavioral data; The customer information data is analyzed based on a preset algorithm to determine the overdue payment collection strategy; the preset algorithm includes: clustering algorithm, decision tree analysis algorithm, and time series algorithm.

2. The method according to claim 1, characterized in that, The step of analyzing the customer information data based on a preset algorithm to determine the overdue payment collection strategy includes: Based on the clustering algorithm, customer information data is analyzed to determine the collection amount, collection frequency, and incentive product category. The collection amount is used to indicate the collection ratio, the collection frequency is used to indicate the number of times to send collection reminders to the customer within a preset time period, and the incentive product category is used to indicate the category of products that incentivize the customer to pay off the debt. The customer information data is analyzed based on the decision tree analysis algorithm and the category of the incentive product to determine the incentive product, which is used to incentivize the customer to pay off the debt. The customer information data is analyzed based on the time series algorithm to determine the collection timing, which indicates the time to send a collection reminder to the customer. The collection strategy is determined based on the collection amount, the collection frequency, the incentive product, and the collection timing.

3. The method according to claim 2, characterized in that, The analysis of customer information data based on clustering algorithms to determine the collection amount, collection frequency, and incentive product category includes: Cluster customer information data to determine customer identity information; Cluster the customer's identity information, the customer's outstanding payment records, and the customer's payment records to determine the customer's credit rating; Based on the customer's credit rating, the collection frequency, the collection amount, and the incentive product category are determined.

4. The method according to claim 2, characterized in that, The step of analyzing customer information data based on a decision tree analysis algorithm to determine the incentive product includes: Based on the decision tree analysis algorithm, the customer information data, and the incentive product category, a decision tree for the incentive product and customer information data is constructed. The incentive product is determined based on the decision tree of the incentive product and customer information data.

5. The method according to claim 2, characterized in that, The analysis of customer information based on time series algorithms to determine the timing of collection includes: The time series algorithm is used to analyze the customer's payment information, the customer's outstanding payment information, and customer information to determine the timing of the collection.

6. The method according to claim 1 or 2, characterized in that, The method further includes: Based on the customer classification information, the collection strategy is described using natural language processing to determine the collection notification information; Send the aforementioned payment reminder message to the customer.

7. The method according to claim 6, characterized in that, The methods for sending the overdue payment notice to customers include at least one of the following: SMS, email, telephone, corporate portal notification, and program notification.

8. A device for determining overdue payment collection strategies, characterized in that, The device for determining the overdue payment collection strategy includes an acquisition unit and a processing unit; The acquisition unit is used to acquire customer information data; the customer information data includes at least one of the following: basic customer information, customer ordering records, customer payment records, customer overdue payment records, customer preference data, and customer behavior data; The processing unit analyzes the customer information data based on a preset algorithm to determine a debt collection strategy. The preset algorithms include: clustering algorithm, decision tree analysis algorithm, and time series algorithm.

9. A device for determining overdue payment collection strategies, characterized in that, include: A processor and a communication interface; the communication interface is coupled to the processor, the processor being used to run computer programs or instructions to implement the method for determining overdue payment collection strategies as described in any one of claims 1-7.

10. A computer-readable storage medium storing instructions, characterized in that, When the computer executes the instruction, the computer performs the overdue payment collection strategy determination method as described in any one of claims 1-7.

Images