Intelligent customer service interaction method, device, electronic device and storage medium

By building user behavior portraits and predicting customer service problems, intelligent customer service robots can actively push personalized services, solving the problem of inability to accurately locate customer needs in the existing technology, and improving customer service efficiency and user experience.

CN113469711BActive Publication Date: 2024-11-12阳光保险集团股份有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110819530.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-20
Publication Date
2024-11-12
Estimated Expiration
2041-07-20

AI Technical Summary

Technical Problem

Existing intelligent customer service robots cannot accurately locate customer needs and cannot provide personalized services, resulting in inefficient customer service and poor user experience.

Method used

By obtaining the user ID of the target user, building a behavioral portrait, predicting the customer service issues that the user wants to consult, and actively pushing them to the user, providing corresponding customer service solutions based on user feedback, realizing a personalized interactive process.

Benefits of technology

It improves the accuracy and efficiency of intelligent customer service, improves the user experience, and can predict and push appropriate customer service issues based on user behavior data, providing personalized services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113469711B_ABST
    Figure CN113469711B_ABST
Patent Text Reader

Abstract

The present application discloses an intelligent customer service interaction method, device, electronic device and storage medium, which relates to the field of artificial intelligence technology. The method includes: when a target user triggers customer service, obtaining the user ID of the target user; based on the user ID, obtaining the behavior portrait of the target user; based on the behavior portrait, predicting the customer service problem that the target user wants to consult; actively pushing the predicted customer service problem to the target user, and providing the target user with a corresponding customer service solution based on the feedback result of the target user. By adopting the above-mentioned intelligent customer service interaction method, device, electronic device and storage medium, it is possible to better identify the triggering intention of the target user, provide personalized interactive services for the target user, and enhance the interactive experience of the target user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an intelligent customer service interaction method, device, electronic device and storage medium. Background Art

[0002] With the continuous development of artificial intelligence technology, its research results have been applied to various industries, and can help them achieve intelligent upgrades. At present, artificial intelligence technology has been introduced into the insurance industry and has become a trend. It has made important breakthroughs in all aspects of pre-sales, sales and after-sales.

[0003] In the prior art, artificial intelligence technology is usually applied to intelligent customer service robots, and then the intelligent customer service robots are used to provide customer service to users. Here, the intelligent customer service robots use a unified multi-round dialogue process, and users need to interact with the intelligent customer service robots in multiple rounds according to the unified process.

[0004] However, although the above-mentioned intelligent customer service interaction method can release manual customer service resources and reduce labor costs, it cannot accurately locate customer needs or provide personalized services to customers. Summary of the invention

[0005] In view of this, the present application provides an intelligent customer service interaction method, device, electronic device and storage medium, the purpose of which is to provide a personalized interaction process for the target user based on the behavioral portrait of the target user and enhance the user experience of the target user.

[0006] In a first aspect, an embodiment of the present application provides an intelligent customer service interaction method, including:

[0007] When the target user triggers the customer service, the user ID of the target user is obtained;

[0008] Based on the user ID, obtain the behavior profile of the target user;

[0009] Based on behavioral profiles, predict the customer service questions that target users want to ask;

[0010] The predicted customer service issues are proactively pushed to the target users, and based on the target users' feedback, corresponding customer service solutions are provided to the target users.

[0011] Optionally, the step of obtaining a behavior portrait of the target user based on the user identifier may include: obtaining a behavior portrait of the target user from a user behavior database based on the user identifier; wherein the user behavior database stores user identifiers of multiple users and behavior portraits corresponding to each user identifier, and the user behavior database may be constructed in the following manner: for each user who triggers customer service, determining the unique user identifier corresponding to the user; for each user, constructing a behavior portrait corresponding to the user identifier of the user based on the user's historical conversation records during the use of customer service.

[0012] Optionally, a behavioral portrait corresponding to the user identification of each user may be constructed in the following manner: for each user, extracting the user portrait features of the user under different pre-set behavioral portrait dimensions from the historical conversation records, the behavioral portrait dimensions including the number of times the user triggers customer service, the triggering time period when the user triggers customer service, the triggering intention of the user to trigger customer service, and the business involved in the user's use of customer service; for each user, constructing a behavioral portrait corresponding to the user identification of the user based on the extracted user portrait features.

[0013] Optionally, the user portrait features of each user can be obtained in the following manner: extract the user's historical conversation records for different trigger intentions; for each trigger intention, determine the user's behavior results under the trigger intention based on the user's historical conversation records for the trigger intention; for each trigger intention, when the user's behavior result under the trigger intention indicates success, extract business keywords from the historical conversation records corresponding to the trigger intention; for each trigger intention, determine the business name of the business handled based on the extracted business keywords; count the number of triggers and trigger time periods of the user for different trigger intentions; determine the number of triggers, trigger time periods, behavior results and business names of the business handled by the user for different trigger intentions as user portrait features.

[0014] Optionally, based on the behavioral profile, the step of predicting the customer service issues that the target user wants to inquire about may include: determining a target trigger time period for the target user to trigger customer service; based on the target user's behavioral profile, determining a trigger time period that matches the target trigger time period; and predicting customer service issues based on the trigger intention with the highest number of triggers in the matching trigger time period.

[0015] Optionally, the triggering intention may include at least one of the following items: business processing, product purchase, product consultation.

[0016] Optionally, the feedback result may include any one of the following items: the user confirms that the predicted customer service problem is the customer service problem that the user wants to consult, the user denies that the predicted customer service problem is the customer service problem that the user wants to consult, and the user clearly wants to consult the customer service problem.

[0017] In a second aspect, an embodiment of the present application provides an intelligent customer service interaction device, including:

[0018] An acquisition module, used to acquire the user ID of the target user when the target user triggers the customer service;

[0019] The confirmation module is used to obtain the behavior profile of the target user based on the user ID;

[0020] The prediction module is used to predict the customer service questions that the target user wants to consult based on the behavior profile;

[0021] The interactive module is used to proactively push predicted customer service issues to target users and provide corresponding customer service solutions to target users based on their feedback.

[0022] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the intelligent customer service interaction method as described above are performed.

[0023] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent customer service interaction method are executed.

[0024] The embodiments of the present application bring the following beneficial effects:

[0025] The embodiments of the present application provide a method, device, electronic device and storage medium for intelligent customer service interaction, including: when a target user triggers customer service, obtaining the user ID of the target user; based on the user ID, obtaining the behavior profile of the target user; based on the behavior profile, predicting the customer service issues that the target user wants to consult; actively pushing the predicted customer service issues to the target user, and providing the user with corresponding customer service solutions based on the feedback results of the target user. When the target user triggers customer service, the present application can predict the customer service issues that the target user wants to consult by analyzing the behavior profile of the target user, and actively pushes them to the user, providing the target user with a personalized interaction process and improving the target user's user experience.

[0026] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the following drawings are some implementation methods of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 A flowchart of the intelligent customer service interaction method provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of the user behavior portrait dimensions provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of the structure of an intelligent customer service interaction device provided in an embodiment of the present application;

[0031] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0033] In the prior art, the intelligent customer service robot adopts a unified multi-round dialogue process. When the target user triggers the customer service, the intelligent customer service will first ask the target user the question he wants to ask, then extract key information based on the question described by the target user, and conduct the next round of inquiry based on the extracted key information. In this way, the entire interaction process is carried out in the form of intelligent customer service asking questions, target users answering, intelligent customer service asking questions again, and target users answering again until the interaction ends. For example: intelligent customer service asks: "Excuse me, what is your question?" The target user answers: "I want to send a package to Beijing." Intelligent customer service asks: "What is your mailing address?" The target user answers: "Hangzhou." Intelligent customer service asks: "Are you going to send it from Beijing to Hangzhou?" The target user answers: "Yes." Obviously, in the above multi-round interaction process, the intelligence level of intelligent customer service is low, resulting in low customer service efficiency and affecting the interactive experience of the target user.

[0034] In addition, in the prior art, there is also a method of realizing intelligent customer service interaction based on building a target user portrait. The main method is: establish data tags for target users, then build a user portrait based on the target user's data tags, and provide intelligent customer service interaction for the target user based on the constructed user portrait. Here, the data tags of the target user mainly include: gender, education, age, whether or not to drive frequently, family members, home address, etc. The above data tags are all data on the user attribute dimension, and cannot accurately locate the user's intention to trigger customer service. Therefore, it is not accurate enough to realize intelligent customer service interaction based on the above target user's data tags, and it is also impossible to provide accurate personalized interactive services for the target user.

[0035] Based on this, the embodiments of the present application provide an intelligent customer service interaction method, device, electronic device and storage medium. When the target user triggers customer service, by analyzing the target user's behavioral portrait, it is possible to predict the customer service issues that the target user wants to consult, and actively push them to the user, thereby providing the target user with an accurate and personalized interaction process and improving the target user's user experience.

[0036] To facilitate understanding of this embodiment, firstly, an intelligent customer service interaction method disclosed in the embodiment of the present application is introduced in detail. Figure 1 A flow chart of the intelligent customer service interaction method provided in the embodiment of the present application is as follows: Figure 1 As shown, the method comprises the following steps:

[0037] Step 101: When a target user triggers customer service, a user ID of the target user is obtained.

[0038] Specifically, each target user corresponds to a unique user ID. When the target user triggers the customer service, the user ID corresponding to the target user will be identified based on the target user's user information. Here, the user information includes: mobile phone number, name, home address, user account, and ID number. The user ID can be a mobile phone number or an ID number. The ID number of the target user can be obtained through the stored user information of the target user.

[0039] In one example, the phone number can be used as a user identifier. When a target user triggers customer service, the user information of the target user is obtained, and the phone number of the target user is determined based on the user information. Then, the user behavior portrait corresponding to the phone number is searched from the user behavior database.

[0040] Step 102: Obtain a behavior profile of the target user based on the user identifier.

[0041] Specifically, based on the user identifier, a behavior portrait of the target user is obtained from a user behavior database, wherein the user identifiers of multiple users and the behavior portraits corresponding to each user identifier are stored in the user behavior database, and the user behavior database is constructed in the following manner: for each user who triggers customer service, the unique user identifier corresponding to the user is determined respectively; for each user, based on the historical conversation records of the user in the process of using customer service, a behavior portrait corresponding to the user identifier of the user is constructed. Here, the user behavior database is a relational database, including but not limited to any of the following: MySQL, Oracle, SQLite, and the historical conversation records are stored in text form. If the user triggers customer service by making a phone call or sending a voice, the voice sent by the user is first converted into text form and then processed. It should be noted that the method of triggering customer service includes but is not limited to any of the following items: dialing a customer service phone number, entering text on the online customer service page, and entering voice on the online customer service page, which is not limited in this application.

[0042] The behavior portrait corresponding to the user ID of each user can be constructed in the following manner: for each user, the user portrait features of the user under different pre-set behavior portrait dimensions are extracted from the historical conversation records.

[0043] Figure 2 A schematic diagram of the user behavior portrait dimensions provided in the embodiment of the present application, such as Figure 2 As shown, the behavior profile dimensions include the number of times a user triggers customer service, the triggering time period when a user triggers customer service, the triggering intention of a user triggering customer service, and the business involved in the user's use of customer service. For example, the triggering intention may include but is not limited to at least one of the following items: business handling, product purchase, and product consultation.

[0044] Then, for each user, a behavior portrait corresponding to the user ID of the user is constructed based on the extracted user portrait features. Here, the user portrait features of each user can be obtained in the following way: extract the user's historical conversation records for different trigger intentions; for each trigger intention, determine the user's behavior result under the trigger intention based on the user's historical conversation records for the trigger intention; for each trigger intention, when the user's behavior result under the trigger intention indicates success, extract business keywords from the historical conversation records corresponding to the trigger intention; for each trigger intention, determine the business name of the business handled based on the extracted business keywords; count the number of triggers and trigger time periods of the user for different trigger intentions; determine the number of triggers, trigger time periods, behavior results and business names of the business handled by the user for different trigger intentions as user portrait features.

[0045] Taking the above example as an example, when a user triggers customer service for the first time, the user's phone number can be used as the unique user ID corresponding to the user, and the voice conversation between the user and the intelligent customer service during the interaction process is stored in the conversation record corresponding to the user ID of the user in the user behavior database. After that, each time the user triggers customer service, the voice conversation between the user and the intelligent customer service during the interaction process is stored in the conversation record corresponding to the user ID of the user in the user behavior database to form the user's historical conversation record. In this way, for each user, a historical conversation record corresponding to the user can be constructed.

[0046] Then, according to the different triggering intentions of the users, the historical conversation records of the users are classified, and the historical conversation records of the users for different triggering intentions are extracted, and the business keywords are extracted based on the extracted historical conversation records. For example: if the user has purchased auto insurance business according to the historical conversation records with the triggering intention of product purchase, then the purchased product is the corresponding behavior result, where the behavior result includes but is not limited to any of the following items: purchase of insurance, handling of claims business, handling of renewal business, purchase of products, consultation business, not purchase of insurance, not handling of claims business, not handling of renewal business, not purchase of products, not consultation business. After determining that the user has purchased the product, the named entity recognition algorithm or information extraction algorithm in artificial intelligence can be used to extract the corresponding business keywords from the historical conversation records corresponding to the intention of product purchase, where the business keywords include but are not limited to any of the following items: purchase of auto insurance products, purchase of health insurance, purchase of accident insurance.

[0047] Taking the purchase of auto insurance products by users as an example, the business name of the business handled can be determined, such as: purchasing compulsory traffic insurance. After determining the business name of the business handled by the user, the corresponding trigger times and trigger time periods under different trigger intentions when the user triggers the customer service are counted, and the counted trigger times, trigger time periods, behavior results, and business names of the business handled are determined as user portrait features. Here, the number of triggers can be specific to the number of triggers in a certain period of time, such as: the number of triggers in July 2021, and the trigger time period can be specific to a specific time period of each day, such as: 10 am to 12 noon. Finally, all user portrait features corresponding to the user ID of the user are combined together to form a behavioral portrait corresponding to the user ID of the user.

[0048] Step 103: Based on the behavior profile, predict the customer service questions that the target user wants to consult.

[0049] In an embodiment of the present application, customer service problems can be predicted in the following manner: based on the behavior profile, the trigger intention with the highest number of triggers for the target user is determined, and the customer service problem is predicted based on the determined trigger intention.

[0050] In addition, in the embodiment of the present application, customer service problems can also be predicted in the following ways: determine the target trigger time period for the target user to trigger customer service; determine the trigger time period that matches the target trigger time period based on the behavior profile of the target user; and predict customer service problems based on the trigger intention with the highest number of triggers in the matching trigger time period. The above method of predicting customer service problems based on the trigger time period can further improve the accuracy of predicting customer service problems.

[0051] Taking the above example as an example, if the target user triggers the customer service at 11 noon, at this time, the target trigger time period can be determined as 10 to 12 o'clock based on the trigger time of the target user. Then, based on the target user's phone number, the data corresponding to the user behavior portrait of the target user in the trigger time period from 10 to 12 o'clock can be determined, and the trigger times corresponding to each trigger intention of the target user in this trigger time period can be obtained, and the trigger intention with the highest trigger times is selected as the predicted trigger intention. Assuming that the target user has the highest number of triggers corresponding to product purchases in the previous time period from 10 to 12 o'clock, the product purchase is used as the predicted trigger intention of the target user. Then, based on the trigger intention, it is determined that the target user has asked about the purchase of compulsory traffic insurance products many times in the trigger time period, and has not yet purchased compulsory traffic insurance. Therefore, the purchase of compulsory traffic insurance is used as the customer service question that the target user predicts to ask.

[0052] Here, since the time required to consult different customer service issues is different, different users have different free time in different time periods. Assuming that the time consumed for product consultation is longer and the time consumed for handling renewal business is shorter, in one example, if a user often triggers customer service for product consultation at around seven o'clock in the evening, it means that the user has more free time in the time period around seven o'clock, so he hopes to consult customer service issues of product consultation that take a long time in this time period, so when the user triggers customer service again in this time period, customer service issues of product consultation can be pushed first. In another example, if a user often triggers customer service at around three o'clock in the afternoon on weekdays to handle renewal business, it means that the user has less free time in the time period around three o'clock in the afternoon, so he hopes to consult customer service issues of renewal business that take less time in this time period, so when the user triggers customer service again in this time period, customer service issues of renewal business can be pushed first.

[0053] Step 104, proactively push the predicted customer service issues to the target user, and provide the target user with a corresponding customer service solution based on the target user's feedback results.

[0054] Specifically, for each predicted customer service problem, a corresponding customer service plan will be formulated in advance, and after predicting the problem that the target user wants to consult, the predicted customer service problem will be actively pushed to the target user, and the corresponding customer service plan will be provided to the user based on the feedback result of the target user. Here, the feedback result includes any of the following: the user confirms that the predicted customer service problem is the customer service problem that the user wants to consult, the user denies that the predicted customer service problem is the customer service problem that the user wants to consult, and the user clearly wants to consult the customer service problem.

[0055] Taking the above example, it has been determined that the target user wants to consult about the purchase of compulsory traffic insurance, so the customer service question is actively pushed to the target user: "Excuse me, do you want to buy compulsory traffic insurance?" Here, if the target user confirms that the customer service question is the question he wants to consult, the target user is provided with a corresponding customer service solution; if the target user denies that the customer service question is the question he wants to consult, then according to the number of times the target user triggers the voice customer service during the time period from 10 o'clock to 12 o'clock, the trigger intent with the second highest triggering number is selected from the triggering times corresponding to each triggering intention, and the customer service question that the target user wants to consult is determined according to the triggering intention, and the customer service question is actively pushed to the target user, and then the corresponding customer service solution is provided to the user according to the feedback result of the target user. It should be noted that if the target user still believes that the customer service question provided by the intelligent customer service is not the customer service question he wants to consult, the customer service question is no longer predicted, but the target user is directly asked about the customer service question he wants to consult; if the target user clearly wants to consult other customer service questions, the customer service question that the target user wants to consult is extracted from the target user's voice conversation record, and the target user is provided with a corresponding customer service solution according to the determined customer service question.

[0056] Based on the same inventive concept, an intelligent customer service interaction device corresponding to the intelligent customer service interaction method is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned intelligent customer service interaction method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0057] Figure 3 A schematic diagram of the structure of the intelligent customer service interaction device provided in the embodiment of the present application, such as Figure 3 As shown, the device includes the following modules:

[0058] An acquisition module 301 is used to acquire a user ID of a target user when the target user triggers customer service;

[0059] A confirmation module 302 is used to obtain a behavior profile of a target user based on the user identifier;

[0060] Prediction module 303, used to predict customer service questions that the target user wants to consult based on the behavior profile;

[0061] The interaction module 304 is used to actively push the predicted customer service issues to the target users, and provide the target users with corresponding customer service solutions based on the feedback results of the target users.

[0062] Optionally, the confirmation module 302, which is used to obtain the behavior portrait of the target user based on the user identifier, may include: based on the user identifier, obtaining the behavior portrait of the target user from a user behavior database; wherein the user behavior database stores user identifiers of multiple users and the behavior portraits corresponding to each user identifier, and the user behavior database may be constructed in the following manner: for each user who triggers customer service, determining the unique user identifier corresponding to the user; for each user, constructing a behavior portrait corresponding to the user identifier of the user based on the historical conversation records of the user in the process of using the customer service.

[0063] Optionally, the confirmation module 302 may construct a behavior portrait corresponding to the user identification of each user in the following manner: for each user, extracting the user portrait features of the user under different pre-set behavior portrait dimensions from the historical conversation records, the behavior portrait dimensions including the number of times the user triggers the customer service, the triggering time period for the user to trigger the customer service, the triggering intention of the user to trigger the customer service, and the business involved in the user's use of the customer service; for each user, constructing a behavior portrait corresponding to the user identification of the user based on the extracted user portrait features.

[0064] Optionally, the confirmation module 302 can obtain the user portrait features of each user in the following manner: extract the user's historical conversation records for different trigger intentions; for each trigger intention, determine the user's behavior result under the trigger intention based on the user's historical conversation records for the trigger intention; for each trigger intention, when the user's behavior result under the trigger intention indicates success, extract business keywords from the historical conversation records corresponding to the trigger intention; for each trigger intention, determine the business name of the business handled based on the extracted business keywords; count the number of triggers and trigger time periods of the user for different trigger intentions; determine the number of triggers, trigger time periods, behavior results and business names of the business handled by the user for different trigger intentions as user portrait features.

[0065] Optionally, the prediction module 303, which is used to predict the customer service issues that the target user wants to inquire about based on the behavioral profile, may include: determining a target trigger time period for the target user to trigger customer service; determining a trigger time period that matches the target trigger time period based on the target user's behavioral profile; and predicting customer service issues based on the trigger intention with the highest number of triggers in the matching trigger time period.

[0066] Optionally, the triggering intention may include at least one of the following items: business processing, product purchase, product consultation.

[0067] Optionally, the feedback result may include any one of the following items: the user confirms that the predicted customer service problem is the customer service problem that the user wants to consult, the user denies that the predicted customer service problem is the customer service problem that the user wants to consult, and the user clearly wants to consult the customer service problem.

[0068] Corresponds to Figure 1 The intelligent customer service interaction method in the present application embodiment also provides a structural schematic diagram of an electronic device 400, such as Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420 and a bus 430. The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 through the bus 430. When the machine-readable instructions are executed by the processor 410, the above-mentioned intelligent customer service interaction method can be executed. When the target user triggers customer service, according to the historical behavior data of the target user, such as: the trigger frequency, the distribution of the trigger time period, the intention of triggering customer service, the business handled, etc., a behavior profile of the target user is constructed, and the customer service questions that the target user wants to consult are predicted based on the behavior profile of the target user, and the customer service questions that the target user wants to consult are actively pushed to the user, so as to provide a personalized interaction process for the target user and improve the user experience of the target user.

[0069] Corresponds to Figure 1 The intelligent customer service interaction method in the embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned intelligent customer service interaction method are executed.

[0070] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned intelligent customer service interaction method can be executed. When the target user triggers customer service, the target user's historical behavior data, such as: trigger frequency, distribution of triggering time periods, intention of triggering customer service, handled business, etc., is used to construct a behavior profile of the target user, and the target user's behavior profile is used to predict the customer service issues that the target user wants to consult, and the profile is actively pushed to the user, thereby providing the target user with a personalized interaction process and improving the target user's user experience.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the above method embodiments and will not be repeated here.

[0072] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0073] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0075] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0076] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0077] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An intelligent customer service interaction method, characterized in that: Intelligent customer service interaction methods include: When a target user triggers customer service, obtaining a user ID of the target user; Based on the user identifier, obtaining a behavior profile of the target user, where the behavior profile is constructed based on historical conversation records of the user for different triggering intentions; Based on the behavior profile, predict the customer service questions that the target user wants to consult; Actively push the predicted customer service issues to the target users, and provide corresponding customer service solutions to the target users based on the feedback results of the target users; The predicting, based on the behavior profile, of the customer service questions that the target user wants to consult includes: Determine a target triggering time period triggered by the target user corresponding to the customer service at the current moment; Based on the behavior profile of the target user, determining a trigger time period that matches the target trigger time period; Predict customer service issues based on the trigger intent with the highest number of triggers in the matching trigger time period; The method further comprises: For each user, extract the user portrait features of the user under different pre-set behavior portrait dimensions from the historical conversation records. The behavior portrait dimensions include the number of times the user triggers customer service, the triggering time period when the user triggers customer service, the triggering intention of the user to trigger customer service, and the business involved in the user's use of customer service. The triggering intention includes at least one of the following items: business handling, product purchase, and product consultation; For each user, a behavior profile corresponding to the user ID of the user is constructed based on the extracted user profile features; The user profile features of each user are extracted in the following way: Extract the user's historical conversation records for different trigger intents; For each trigger intent, determine the user's behavior result under the trigger intent based on the user's historical conversation records for the trigger intent; For each trigger intent, when the user's behavior result under the trigger intent indicates success, extract the business keyword from the historical conversation record corresponding to the trigger intent; For each triggering intent, determine the business name of the business to be handled based on the extracted business keywords; Count the number of times users trigger different trigger intents and the trigger time periods; The number of times a user triggers different trigger intentions, the trigger time period, the behavior results, and the business name of the business handled are determined as user portrait features.

2. The intelligent customer service interaction method according to claim 1, characterized in that: The step of obtaining the behavior portrait of the target user based on the user identifier includes: Based on the user identifier, obtaining a behavior profile of the target user from a user behavior database; The user behavior database stores user IDs of multiple users and behavior portraits corresponding to each user ID. The user behavior database is constructed in the following manner: For each user who triggers the customer service, determining a unique user identifier corresponding to the user; For each user, a behavior profile corresponding to the user ID of the user is constructed based on the historical conversation records of the user in the process of using customer service.

3. The intelligent customer service interaction method according to claim 1, characterized in that: The feedback result includes any one of the following items: the user confirms that the predicted customer service issue is the customer service issue that the user wants to consult, the user denies that the predicted customer service issue is the customer service issue that the user wants to consult, and the user clearly states that he wants to consult.

4. An intelligent customer service interaction device, characterized in that: include: An acquisition module is used to acquire a user ID of a target user when the target user triggers customer service; A confirmation module, used to obtain a behavior profile of the target user based on the user identifier, wherein the behavior profile is constructed based on the historical conversation records of the user for different triggering intentions; A prediction module, used to predict the customer service questions that the target user wants to consult based on the behavior profile; An interactive module, used to actively push the predicted customer service issues to the target user, and provide the target user with a corresponding customer service solution based on the feedback results of the target user; The prediction module is specifically used for: Determine a target triggering time period triggered by the target user corresponding to the customer service at the current moment; Based on the behavior profile of the target user, determining a trigger time period that matches the target trigger time period; Predict customer service issues based on the trigger intent with the highest number of triggers in the matching trigger time period; The acquisition module is further used for: For each user, extract the user portrait features of the user under different pre-set behavior portrait dimensions from the historical conversation records. The behavior portrait dimensions include the number of times the user triggers customer service, the triggering time period when the user triggers customer service, the triggering intention of the user to trigger customer service, and the business involved in the user's use of customer service. The triggering intention includes at least one of the following items: business handling, product purchase, and product consultation; For each user, a behavior profile corresponding to the user ID of the user is constructed based on the extracted user profile features; The acquisition module extracts the user portrait features of each user in the following way: Extract the user's historical conversation records for different trigger intents; For each trigger intent, determine the user's behavior result under the trigger intent based on the user's historical conversation records for the trigger intent; For each trigger intent, when the user's behavior result under the trigger intent indicates success, extract the business keyword from the historical conversation record corresponding to the trigger intent; For each triggering intent, determine the business name of the business to be handled based on the extracted business keywords; Count the number of times users trigger different trigger intents and the trigger time periods; The number of times a user triggers different trigger intentions, the trigger time period, the behavior results, and the business name of the business handled are determined as user portrait features.

5. An electronic device, characterized in that: It includes a processor, a memory and a bus, the memory stores machine-readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the intelligent customer service interaction method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the intelligent customer service interaction method as described in any one of claims 1 to 3 are executed.