Classification model-oriented user electric service method and related device thereof

Abstract

The embodiment of the application belongs to the field of artificial intelligence and financial technology, is applied to the field of insurance business electric selling service, and relates to a user electric connection service method for a classification model and related equipment thereof, which comprises the following steps: performing classification training on feature fields, training a hosting model for service classification of different users; acquiring feature attribute information corresponding to the feature fields of a target user; inputting the feature attribute information into the hosting model, performing service classification on the target user, and acquiring a classification result; selecting corresponding service processing models and editing service prompt content according to the classification result and feature attribute information corresponding to identity class feature fields, and sending the service prompt content to the target user to complete the electric connection service for the target user in this time. The application uses the hosting model to perform customer service classification and identification, breaks the original single service and sale mode, intelligently contacts customers in multiple links and multiple schemes, intelligently matches the best customer service scheme, and reduces the workload of operation personnel.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and financial technology, and in particular to a user telephone service method and related equipment for a classification model. Background Technology

[0002] Traditional services typically involve companies proactively reaching out to customers, with a relatively singular purpose. Taking insurance services as an example, sales usually occur shortly before the policy expires, with services typically provided through servers or after-sales support. Outside of these periods, long-term relationships with customers are generally not established, hindering effective service. Consequently, customers often have poor experiences when they proactively contact the company, or when the company attempts to sell or provide services. Furthermore, determining the appropriate sales and service approach for different time periods and customer types is often left to the operations staff to judge, resulting in a rather crude and simplistic approach. Summary of the Invention

[0003] The purpose of this application is to propose a user telephone service method and related equipment oriented towards a classification model, so as to break the original single sales service model, intelligently contact customers through multiple links and multiple solutions, intelligently match the best customer service solution, and reduce the workload of operations personnel.

[0004] To address the aforementioned technical problems, this application provides a user telephone service method based on a classification model, employing the following technical solution:

[0005] A user telephone service method based on a classification model includes the following steps:

[0006] Based on each target feature field in the preset feature field collection table, collect feature attribute information corresponding to several users from the specified big data platform;

[0007] The feature fields are classified and trained based on the feature attribute information, decision tree algorithm and preset decision rules to train a managed model for service classification of different users;

[0008] Obtain the feature attribute information corresponding to the feature fields of the target user, wherein the feature fields of the target user include business-related feature fields and identity-related feature fields;

[0009] Input the feature attribute information corresponding to the business class feature field into the managed model, classify the target user for services, and obtain the classification result;

[0010] Select the corresponding service processing model based on the classification results, and edit the service prompt content based on the service processing model and the feature attribute information corresponding to the identity class feature field;

[0011] According to the preset prompt method, the service prompt content is sent to the target user to complete the telephone service to the target user.

[0012] Furthermore, before the step of training a managed model for service classification of different users by classifying the feature attribute information based on the feature attribute information, decision tree algorithm, and preset decision rules, the method further includes:

[0013] The feature fields are pre-filtered to remove feature fields whose feature attribute information is empty, and retain feature fields whose feature attribute information is not empty, as the filtered business feature fields.

[0014] Furthermore, the step of training a managed model for service classification of different users by classifying the feature fields based on the feature attribute information, decision tree algorithm, and preset decision rules specifically includes:

[0015] The pre-built managed model is initialized, and service classification weights are set for different business feature fields according to the service category in the initialized managed model. The service categories include business consulting services, business signing services, birthday interaction services, holiday care services, claims services, and after-sales services.

[0016] The filtered business feature fields corresponding to the several users are input into the managed model. Based on the service classification weights corresponding to the business feature fields of each user and the decision rules built into the managed model, the service category corresponding to each user is calculated, and the initial training of the managed model is completed.

[0017] Several business feature fields corresponding to verified users are obtained and input into the initially trained managed model for service category verification. If the probability of users passing the verification reaches a preset threshold, the managed model training is complete.

[0018] Furthermore, the step of calculating the service category corresponding to each user based on the service classification weights corresponding to each user's business characteristic fields and the decision rules built into the managed model, and completing the initial training of the managed model, specifically includes:

[0019] Step A: Accumulate the service classification weights of the same service category corresponding to the current user's business characteristic fields, and obtain the service classification weights and values ​​corresponding to different service categories respectively;

[0020] Step B: Compare the service category weights and values ​​corresponding to different service categories, and select the service category with the maximum service category weight and value, which is the service category corresponding to the current user;

[0021] Step C: Repeat steps A and B to obtain the service category corresponding to each user and complete the initial training of the managed model.

[0022] Furthermore, the step of inputting the feature attribute information corresponding to the business category feature field into the managed model to classify the target user into services and obtain the classification result specifically includes:

[0023] Based on the feature attribute information, identify the different business category feature fields corresponding to the target user;

[0024] Based on the different business category feature fields, the service classification weights corresponding to the different business category feature fields, and the trained hosting model, calculate the service category corresponding to the business category feature fields;

[0025] The service category is used as the classification result for the target user's service.

[0026] Furthermore, the step of selecting the corresponding service processing model based on the classification result, and editing the service prompt content based on the service processing model and the feature attribute information corresponding to the identity class feature field, specifically includes:

[0027] Different service processing models are pre-set for different service categories, wherein there is a one-to-one correspondence between the different service processing models and the different service categories;

[0028] Obtain the feature attribute information corresponding to the identity class feature field, and input the feature attribute information into the service processing model corresponding to the target user;

[0029] The output content of the service processing model is obtained as the service prompt content, wherein the service processing model has a built-in program for editing the service prompt content based on the feature attribute information corresponding to the identity class feature field.

[0030] Furthermore, the step of sending the service prompt content to the target user according to a preset prompting method to complete the telephone contact service to the target user specifically includes:

[0031] The service prompt content is obtained and sent to the target user according to a preset prompt method, wherein the prompt method includes intelligent robot phone call and intelligent SMS.

[0032] To address the aforementioned technical problems, this application also provides a user telephone service device oriented towards a classification model, employing the following technical solution:

[0033] A user telephone service device oriented towards a classification model includes:

[0034] The user feature acquisition module is trained to collect feature attribute information corresponding to several users from a specified big data platform for each target feature field in the preset feature field acquisition table.

[0035] The model training module is used to classify and train the feature fields based on the feature attribute information, decision tree algorithm and preset decision rules, so as to train a managed model for service classification of different users.

[0036] The target user feature acquisition module is used to acquire feature attribute information corresponding to the feature fields of the target user, wherein the feature fields of the target user include business-related feature fields and identity-related feature fields;

[0037] The model classification module is used to input the feature attribute information corresponding to the business class feature field into the managed model, classify the target user for services, and obtain the classification result.

[0038] The prompt content editing module is used to select the corresponding service processing model based on the classification result, and edit the service prompt content based on the service processing model and the feature attribute information corresponding to the identity class feature field;

[0039] The telephone communication module is used to send the service prompt content to the target user according to a preset prompt method, thereby completing the telephone communication service to the target user.

[0040] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0041] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the user telephone service method for a classification model described above.

[0042] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0043] A computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the steps of the user telephone service method for a classification model as described above.

[0044] Compared with the prior art, the embodiments of this application have the following main advantages:

[0045] The user telephone service method for classification models described in this application involves training a managed model for service classification of different users by classifying the feature fields based on the feature attribute information, decision tree algorithm, and preset decision rules; obtaining the feature attribute information corresponding to the feature fields of the target user; inputting the feature attribute information corresponding to the business category feature fields into the managed model to classify the target user and obtain the classification result; selecting the corresponding service processing model based on the classification result, and editing the service prompt content based on the service processing model and the feature attribute information corresponding to the identity category feature fields; and sending the service prompt content to the target user according to a preset prompt method to complete the telephone service for the target user. This application utilizes a managed model for customer service classification and identification, breaking the original single sales service model, intelligently contacting customers through multiple links and multiple solutions, intelligently matching the best customer service solution, and reducing the workload of operations personnel. Attached Figure Description

[0046] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0048] Figure 2 A flowchart of an embodiment of the user telephone service method based on a classification model according to this application;

[0049] Figure 3 yes Figure 2 A flowchart of a specific implementation of step 202 shown;

[0050] Figure 4 yes Figure 3 A flowchart of a specific implementation of step 302 shown;

[0051] Figure 5 yes Figure 2 A flowchart of a specific implementation of step 204 shown;

[0052] Figure 6 yes Figure 2 A flowchart of a specific implementation of step 205 shown;

[0053] Figure 7 A schematic diagram of a structural embodiment of a user telephone service device based on a classification model according to this application;

[0054] Figure 8 A schematic diagram of the structure of an embodiment of the computer device according to this application. Detailed Implementation

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0056] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0057] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0058] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0059] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0060] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0061] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.

[0062] It should be noted that the user telephone service method for classification models provided in this application is generally executed by a server / terminal device, and correspondingly, the user telephone service device for classification models is generally set in the server / terminal device.

[0063] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0064] Continue to refer to Figure 2 The diagram illustrates a flowchart of an embodiment of a user telephone service method based on a classification model according to this application. The user telephone service method based on a classification model includes the following steps:

[0065] Step 201: Collect feature attribute information corresponding to several users from a designated big data platform according to each target feature field in the preset feature field collection table, wherein the target feature fields include business category feature fields.

[0066] In this embodiment, the telemarketing service refers to sending business-related service push notifications to customers using electronic devices, including but not limited to robot voice calls, sending telemarketing emails to customers, and sending telemarketing text messages to customers.

[0067] In this embodiment, the designated big data platform is an insurance business information sharing platform with a pre-specified collection address. The feature field collection table includes the name information of all feature fields to be collected. The feature fields and the corresponding feature attribute information have a one-to-one correspondence. It can be understood that the feature field is the feature name and the feature attribute information is the feature attribute value.

[0068] For example, if the feature field is the customer's birthday, the corresponding feature attribute information is January 1, 2000.

[0069] In this embodiment, the business category feature fields include: customer's birthday, customer's gender, insurance expiration date, inquiry time, signing time, signing premium, whether insurance is provided free of charge, number of claims, latest claim reporting time, whether the customer is a property insurance customer, whether the customer is a health insurance customer, whether the customer is a life insurance customer, whether the customer is a credit card customer, whether the customer is a securities customer, latest gift type, latest gift time, and discount coefficient.

[0070] In this embodiment, when performing the step of collecting feature attribute information corresponding to several users from a designated big data platform based on each target feature field in the preset feature field collection table, the collected feature attribute information may be null.

[0071] By collecting feature attribute information for several users from each target feature field in the preset feature field collection table, the purpose is to provide sufficient data support for model training. On the other hand, collecting training data from the insurance business information sharing platform also ensures the authenticity of the data, eliminating the need for developers to create simulated data themselves.

[0072] Step 202: Based on the feature attribute information, decision tree algorithm and preset decision rules, classify and train the feature fields to train a managed model for classifying services for different users.

[0073] In this embodiment, before the step of training a managed model for classifying services for different users by classifying the feature attribute information according to the feature attribute information, decision tree algorithm and preset decision rules, the method further includes: pre-screening the feature fields, removing feature fields whose feature attribute information is empty, and retaining feature fields whose feature attribute information is not empty, as the screened business feature fields.

[0074] By pre-screening the feature fields before model training and removing feature fields with null values, the amount of training data is reduced on the one hand, and the training data is optimized on the other.

[0075] Continue to refer to Figure 3 , Figure 3 yes Figure 2 A flowchart of a specific implementation of step 202 shown includes:

[0076] Step 301: Initialize the pre-built managed model and set service classification weights for different business feature fields according to the service category in the initialized managed model.

[0077] The service categories include business consulting services, business signing services, birthday interaction services, holiday care services, claims services, and after-sales services.

[0078] By setting service classification weights for different business feature fields based on service categories, it is ensured that different business feature fields have corresponding weight values ​​when corresponding to different service categories, which makes it easier to predict the corresponding service category by combining the business feature fields corresponding to the user.

[0079] Step 302: Input the filtered business feature fields corresponding to the several users into the managed model, calculate the service category corresponding to each user according to the service classification weight corresponding to the business feature fields of each user and the decision rules built into the managed model, and complete the initial training of the managed model.

[0080] In this embodiment, the sum of the weights of the same business feature field corresponding to different service categories is 1. That is, assuming the business feature field is the insurance expiration date, and the service categories include business consultation service, business signing service, birthday interaction service, holiday care service, claims service, and after-sales service, the weights of the insurance expiration date corresponding to business consultation service, business signing service, birthday interaction service, holiday care service, claims service, and after-sales service can be set to 0.08, 0.3, 0.01, 0.01, 0.5, and 0.1, respectively. The sum of the weights of the business feature field insurance expiration date corresponding to these six service categories is 1.

[0081] By using weights and calculations, the service category corresponding to each user is obtained, and the initial training of the managed model is completed. Only a simple decision classification mode is needed to complete the model pre-training, which facilitates model building, breaks the original single service sales model, and enables intelligent multi-stage and multi-plan customer contact, intelligently matching the best customer service solution and reducing the workload of operations personnel.

[0082] Continue to refer to Figure 4 , Figure 4 yes Figure 3 A flowchart of a specific implementation of step 302 shown includes:

[0083] Step 401: Accumulate the service classification weights of the same service category corresponding to the business feature fields of the current user, and obtain the service classification weights and values ​​corresponding to different service categories respectively;

[0084] Step 402: Compare the service category weights and values ​​corresponding to different service categories, and select the service category with the maximum service category weight and value, which is the service category corresponding to the current user.

[0085] Step 403: Repeat steps 401 and 402 to obtain the service category corresponding to each user and complete the initial training of the managed model.

[0086] Step 303: Obtain several business feature fields corresponding to the verified users and input them into the initially trained managed model for service category verification. If the probability of verified users reaches a preset threshold, the managed model training is complete.

[0087] The validation further ensured the availability of the managed model.

[0088] In this embodiment, if the probability of a user passing the verification does not reach the preset threshold, the weights of different business feature fields corresponding to different service categories are adjusted, and the new weights are used to optimize, train, and verify the managed model until the probability of a user passing the verification reaches the preset threshold, at which point the training of the managed model is complete.

[0089] Step 203: Obtain the feature attribute information corresponding to the feature fields of the target user, wherein the feature fields of the target user include business-related feature fields and identity-related feature fields.

[0090] In this embodiment, the identity feature fields include: customer name, contact information, contact address, province, city, license plate number, vehicle usage nature, vehicle model name, vehicle series, vehicle type, new vehicle replacement identifier, and old vehicle replacement identifier.

[0091] In this embodiment, both the business-type feature field and the identity-type feature field have a unique distinguishing identifier on the target big data platform.

[0092] By obtaining the identity feature fields of the target user, we can ensure that after service classification prediction, relevant services are automatically provided to the target user based on the identity feature fields and service classification.

[0093] Step 204: Input the feature attribute information corresponding to the business category feature field into the managed model, classify the target user into services, and obtain the classification result.

[0094] Continue to refer to Figure 5 , Figure 5 yes Figure 2 A flowchart of a specific implementation of step 204 shown includes:

[0095] Step 501: Identify different business category feature fields corresponding to the target user based on the feature attribute information;

[0096] Step 502: Based on the different business category feature fields, the service classification weights corresponding to the different business category feature fields, and the trained managed model, calculate the service category corresponding to the business category feature fields;

[0097] Step 503: Use the service category as the classification result for the target user's service classification.

[0098] Step 205: Select the corresponding service processing model based on the classification result, and edit the service prompt content based on the service processing model and the feature attribute information corresponding to the identity class feature field.

[0099] By combining service processing models, service providers can accurately select the appropriate service processing model based on service classification. By using the target user's identity feature fields, service providers can easily send service processing information to the target user.

[0100] Continue to refer to Figure 6 , Figure 6 yes Figure 2 A flowchart of a specific implementation of step 205 shown includes:

[0101] Step 601: Pre-set different service processing models for different service categories, wherein there is a one-to-one correspondence between the different service processing models and the different service categories;

[0102] Step 602: Obtain the feature attribute information corresponding to the identity class feature field, and input the feature attribute information into the service processing model corresponding to the target user;

[0103] Step 603: Obtain the output content of the service processing model as the service prompt content, wherein the service processing model has a built-in program for editing the service prompt content based on the feature attribute information corresponding to the identity class feature field.

[0104] Step 206: Send the service prompt content to the target user according to the preset prompt method to complete the telephone service to the target user.

[0105] In this embodiment, the step of sending the service prompt content to the target user according to a preset prompting method to complete the current telephone service to the target user specifically includes: obtaining the service prompt content and sending the service prompt content to the target user according to a preset prompting method, wherein the prompting method includes intelligent robot phone and intelligent SMS.

[0106] By setting preset prompts and intelligently classifying customers for services, the system can match the best service classification model for the current customer and provide intelligent telemarketing services.

[0107] This application trains a managed model for classifying services for different users by classifying the feature fields based on the aforementioned feature attribute information, decision tree algorithm, and preset decision rules; obtains the feature attribute information corresponding to the feature fields of the target user; inputs the feature attribute information corresponding to the business category feature fields into the managed model to classify the target user and obtain the classification result; selects the corresponding service processing model based on the classification result, and edits the service prompt content based on the service processing model and the feature attribute information corresponding to the identity category feature fields; sends the service prompt content to the target user according to the preset prompt method, completing the telephone service for the target user. This application uses a managed model for customer service classification and identification, breaking the original single sales service model, intelligently contacting customers through multiple links and multiple solutions, intelligently matching the best customer service solution, and reducing the workload of operations personnel.

[0108] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0109] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0110] In this embodiment, a managed model can be used for customer service classification and identification, breaking the original single sales model, enabling intelligent multi-stage and multi-plan customer contact, intelligent matching of the best customer service plan, and reducing the workload of operations personnel.

[0111] Further reference Figure 7 As a response to the above Figure 2 The implementation of the method shown in this application provides an embodiment of a user telephone service device oriented towards a classification model. This device embodiment is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0112] like Figure 7As shown, the user telephone service device 700 for classification models described in this embodiment includes: a user feature acquisition module 701, a model training module 702, a target user feature acquisition module 703, a model classification module 704, a prompt content editing module 705, and a telephone transmission module 706. Wherein:

[0113] The user feature acquisition module 701 is used to collect feature attribute information corresponding to several users from a specified big data platform according to each target feature field in the preset feature field acquisition table. The target feature fields include business category feature fields.

[0114] The model training module 702 is used to perform classification training on the feature fields based on the feature attribute information, decision tree algorithm and preset decision rules, and train a managed model for service classification of different users;

[0115] The target user feature acquisition module 703 is used to acquire feature attribute information corresponding to the feature fields of the target user, wherein the feature fields of the target user include business-related feature fields and identity-related feature fields;

[0116] The model classification module 704 is used to input the feature attribute information corresponding to the business class feature field into the managed model, classify the target user for services, and obtain the classification result.

[0117] The prompt content editing module 705 is used to select the corresponding service processing model according to the classification result, and edit the service prompt content according to the service processing model and the feature attribute information corresponding to the identity class feature field;

[0118] The telephone communication sending module 706 is used to send the service prompt content to the target user according to a preset prompt method, thereby completing the telephone communication service to the target user.

[0119] This application trains a managed model for classifying services for different users by classifying the feature fields based on the aforementioned feature attribute information, decision tree algorithm, and preset decision rules; obtains the feature attribute information corresponding to the feature fields of the target user; inputs the feature attribute information corresponding to the business category feature fields into the managed model to classify the target user and obtain the classification result; selects the corresponding service processing model based on the classification result, and edits the service prompt content based on the service processing model and the feature attribute information corresponding to the identity category feature fields; sends the service prompt content to the target user according to the preset prompt method, completing the telephone service for the target user. This application uses a managed model for customer service classification and identification, breaking the original single sales service model, intelligently contacting customers through multiple links and multiple solutions, intelligently matching the best customer service solution, and reducing the workload of operations personnel.

[0120] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0121] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0122] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0123] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected via a system bus. It should be noted that only the computer device 8 with components 81-83 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), digital digital processors (DSPs), embedded devices, etc.

[0124] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0125] The memory 81 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 81 may be an internal storage unit of the computer device 8, such as the hard disk or memory of the computer device 8. In other embodiments, the memory 81 may also be an external storage device of the computer device 8, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD) card, flash card, etc. of the computer device 8. Of course, the memory 81 may also include both the internal storage unit and the external storage device of the computer device 8. In this embodiment, the memory 81 is typically used to store the operating system and various application software installed on the computer device 8, such as computer-readable instructions for a user telephone service method oriented towards a classification model. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or will be output.

[0126] In some embodiments, the processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 82 is typically used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to execute computer-readable instructions stored in the memory 81 or to process data, such as executing computer-readable instructions for the user telephone service method oriented towards the classification model.

[0127] The network interface 83 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 8 and other electronic devices.

[0128] The computer device proposed in this embodiment belongs to the field of artificial intelligence technology. This application trains a managed model for classifying services for different users by classifying the feature fields based on the aforementioned feature attribute information, decision tree algorithm, and preset decision rules; it obtains the feature attribute information corresponding to the feature fields of the target user; it inputs the feature attribute information corresponding to the business category feature fields into the managed model to classify the target user and obtain the classification result; it selects the corresponding service processing model based on the classification result, and edits the service prompt content based on the service processing model and the feature attribute information corresponding to the identity category feature fields; it sends the service prompt content to the target user according to a preset prompt method, completing the telephone service for the target user. This application utilizes a managed model for customer service classification and identification, breaking the original single sales service model, intelligently contacting customers through multiple links and multiple solutions, intelligently matching the best customer service solution, and reducing the workload of operations personnel.

[0129] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by a processor to cause the processor to perform the steps of the user telephone service method for the classification model described above.

[0130] The computer-readable storage medium proposed in this embodiment belongs to the field of artificial intelligence technology. This application trains a managed model for classifying services for different users by classifying the feature fields based on the aforementioned feature attribute information, decision tree algorithm, and preset decision rules; obtains the feature attribute information corresponding to the feature fields of the target user; inputs the feature attribute information corresponding to the business category feature fields into the managed model to classify the target user and obtain classification results; selects the corresponding service processing model based on the classification results, and edits service prompt content based on the service processing model and the feature attribute information corresponding to the identity category feature fields; sends the service prompt content to the target user according to a preset prompt method, completing the telephone service for the target user. This application utilizes a managed model for customer service classification and identification, breaking the original single sales service model, intelligently contacting customers through multiple links and multiple solutions, intelligently matching the best customer service solution, and reducing the workload of operations personnel.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0132] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A user telephone service method oriented towards a classification model, characterized in that, Includes the following steps: Based on each target feature field in the preset feature field collection table, collect feature attribute information corresponding to several users from the specified big data platform; Based on the aforementioned feature attribute information, decision tree algorithm, and preset decision rules, the feature fields are classified and trained to generate a managed service model that classifies services for different users. Before the step of training a managed model for service classification of different users by classifying and training the feature attribute information based on the feature attribute information, decision tree algorithm, and preset decision rules, the method further includes: The feature fields are pre-filtered to remove feature fields whose feature attribute information is empty, and retain feature fields whose feature attribute information is not empty, as the filtered business feature fields. The step of training a managed service model for different users by classifying and training the feature fields based on the feature attribute information, decision tree algorithm, and preset decision rules specifically includes: The pre-built managed model is initialized, and service classification weights are set for different business feature fields according to the service category in the initialized managed model. The service categories include business consulting services, business signing services, birthday interaction services, holiday care services, claims services, and after-sales services. The filtered business feature fields corresponding to the aforementioned users are input into the managed model. Based on the service classification weights corresponding to each user's business feature fields and the decision rules built into the managed model, the service category corresponding to each user is calculated, completing the initial training of the managed model. Specifically, the initial training includes: Step A: Accumulate the service classification weights of the same service category corresponding to the current user's business characteristic fields, and obtain the service classification weights and values ​​corresponding to different service categories respectively; Step B: Compare the service category weights and values ​​corresponding to different service categories, and select the service category with the maximum service category weight and value as the service category corresponding to the current user; Step C: Repeat steps A and B to obtain the service category corresponding to each user and complete the initial training of the managed model; Several business feature fields corresponding to verified users are obtained and input into the initially trained managed model for service category verification. If the probability of users passing the verification reaches a preset threshold, the managed model training is complete. Obtain the feature attribute information corresponding to the feature fields of the target user, wherein the feature fields of the target user include business-related feature fields and identity-related feature fields; Input the feature attribute information corresponding to the business class feature field into the managed model, classify the target user for services, and obtain the classification result; Select the corresponding service processing model based on the classification results, and edit the service prompt content based on the service processing model and the feature attribute information corresponding to the identity class feature field; According to the preset prompt method, the service prompt content is sent to the target user to complete the telephone service to the target user. The telephone service refers to sending business-related service push to the target user using an electronic device.

2. The user telephone service method for a classification model according to claim 1, characterized in that, The step of inputting the feature attribute information corresponding to the business class feature field into the managed model, classifying the target user for services, and obtaining the classification result specifically includes: Based on the feature attribute information, identify the different business category feature fields corresponding to the target user; Based on the different business category feature fields, the service classification weights corresponding to the different business category feature fields, and the trained hosting model, calculate the service category corresponding to the business category feature fields; The service category is used as the classification result for the target user's service.

3. The user telephone service method for a classification model according to claim 1, characterized in that, The steps of selecting the corresponding service processing model based on the classification result and editing the service prompt content based on the service processing model and the feature attribute information corresponding to the identity class feature field specifically include: Different service processing models are pre-set for different service categories, wherein there is a one-to-one correspondence between the different service processing models and the different service categories; Obtain the feature attribute information corresponding to the identity class feature field, and input the feature attribute information into the service processing model corresponding to the target user; The output content of the service processing model is obtained as the service prompt content, wherein the service processing model has a built-in program for editing the service prompt content based on the feature attribute information corresponding to the identity class feature field.

4. The user telephone service method for a classification model according to claim 1, characterized in that, The step of sending the service prompt content to the target user according to a preset prompt method to complete the telephone contact service to the target user specifically includes: The service prompt content is obtained and sent to the target user according to a preset prompt method, wherein the prompt method includes intelligent robot phone call and intelligent SMS.

5. A user telephone service device oriented towards a classification model, characterized in that, include: The user feature acquisition module is trained to collect feature attribute information corresponding to several users from a specified big data platform for each target feature field in the preset feature field acquisition table. The model training module is used to perform classification training on the feature fields based on the feature attribute information, decision tree algorithm, and preset decision rules, thereby training a managed model for service classification of different users. Before training a managed service model for different users by classifying and training the feature attribute information based on the feature attribute information, decision tree algorithm, and preset decision rules, the method further includes: The feature fields are pre-filtered to remove feature fields whose feature attribute information is empty, and retain feature fields whose feature attribute information is not empty, as the filtered business feature fields. The step of classifying and training the feature fields based on the feature attribute information, decision tree algorithm, and preset decision rules to train a managed service model for different users specifically includes: The pre-built managed model is initialized, and service classification weights are set for different business feature fields according to the service category in the initialized managed model. The service categories include business consulting services, business signing services, birthday interaction services, holiday care services, claims services, and after-sales services. The filtered business feature fields corresponding to the aforementioned users are input into the managed model. Based on the service classification weights corresponding to each user's business feature fields and the decision rules built into the managed model, the service category corresponding to each user is calculated, completing the initial training of the managed model. Specifically, the initial training includes: Step A: Accumulate the service classification weights of the same service category corresponding to the current user's business characteristic fields, and obtain the service classification weights and values ​​corresponding to different service categories respectively; Step B: Compare the service category weights and values ​​corresponding to different service categories, and select the service category with the maximum service category weight and value as the service category corresponding to the current user; Step C: Repeat steps A and B to obtain the service category corresponding to each user and complete the initial training of the managed model; Several business feature fields corresponding to verified users are obtained and input into the initially trained managed model for service category verification. If the probability of users passing the verification reaches a preset threshold, the managed model training is complete. The target user feature acquisition module is used to acquire feature attribute information corresponding to the feature fields of the target user, wherein the feature fields of the target user include business-related feature fields and identity-related feature fields; The model classification module is used to input the feature attribute information corresponding to the business class feature field into the managed model, classify the target user for services, and obtain the classification result. The prompt content editing module is used to select the corresponding service processing model based on the classification result, and edit the service prompt content based on the service processing model and the feature attribute information corresponding to the identity class feature field; The telephone communication module is used to send the service prompt content to the target user according to a preset prompt method, thereby completing the telephone communication service to the target user. The telephone communication service refers to sending service-related push notifications to the target user using an electronic device.

6. A computer device comprising a memory and a processor, the memory storing computer-readable instructions, wherein the processor, when executing the computer-readable instructions, implements the steps of the user telephone service method for a classification model as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the user telephone service method for a classification model as described in any one of claims 1 to 4.

Images