Intelligent customer service method and device, electronic equipment and readable storage medium

Abstract

The invention relates to the technical field of information services, and provides an intelligent customer service method and device, electronic equipment and a readable storage medium, and the method comprises the steps: responding to a customer service request sent by a user, and confirming the user identity of the user; based on preset service classification, performing classification inquiry on the user, and determining question classification of the user; acquiring historical data of the user according to the user identity, and screening classified data from the historical data according to the question classification; based on the classification data, performing target inquiry on the user, and determining a target question of the user; according to the question attribute of the target question, customer service reply conforming to the question attribute is provided, and the question attribute comprises an explanation and description attribute and an operation processing attribute. According to the technical scheme provided by one or more embodiments of the invention, the customer service can be provided for the user with low cost and high efficiency, and customer service resources can be saved for the customer service system.

Description

Technical Field

[0001] The present disclosure relates to the technical field of information services, and in particular, to an intelligent customer service method, apparatus, electronic device, and readable storage medium. Background Art

[0002] In the driving service industry, drivers can wait in person at some places where potential customers are located and ask customers face to face whether they need a driving service, and complete the driving service offline. Drivers can also register their driver identities with the driving service company and wait for the company to assign orders to them, and complete the driving service online. For example, a passenger may apply for a driving service order to the driving service company through carriers such as applications and mini-programs, and the driving service company may assign the order to an online driver near the passenger based on a preset strategy.

[0003] Generally, the customer service system of a driving service company needs to handle both passenger requests to provide high-quality driving services for passengers and driver requests to provide high-quality management services for drivers.

[0004] However, a large amount of customer service resources in the customer service system are easily occupied by a large number of daily consultations and complaints from drivers, resulting in insufficient customer service resources invested in areas such as passenger outbound calls and follow-ups. Summary of the Invention

[0005] In view of this, one or more embodiments of the present disclosure provide an intelligent customer service method, apparatus, electronic device, and readable storage medium, which can provide customer service for users at low cost and high efficiency and save customer service resources for the customer service system.

[0006] One aspect of the present disclosure provides an intelligent customer service method, the method including: in response to a customer service request sent by a user, confirming the user identity of the user; based on a preset service classification, conducting classified inquiries on the user to determine the problem classification of the user; according to the user identity, obtaining historical data of the user, and screening out classified data from the historical data according to the problem classification; based on the classified data, conducting target inquiries on the user to determine the target problem of the user; and providing a customer service reply that conforms to the problem attribute according to the problem attribute of the target problem, where the problem attribute includes an explanation attribute and an operation processing attribute.

[0007] On the other hand, the present disclosure also provides an intelligent customer service device, which includes: an identity confirmation unit for confirming the user identity of the user in response to a customer service request sent by the user; a question classification unit for classifying and querying the user based on a preset service classification to determine the question classification of the user; a data processing unit for obtaining the historical data of the user according to the user identity and screening out classified data from the historical data according to the question classification; a question determination unit for conducting a target query on the user based on the classified data to determine the target question of the user; and a question reply unit for providing a customer service reply that conforms to the question attribute of the target question, where the question attribute includes an explanation attribute and an operation processing attribute.

[0008] On the other hand, the present disclosure also provides an electronic device, which includes a memory and a processor. The memory is used to store a computer program, and when the computer program is executed by the processor, the above-mentioned intelligent customer service method is implemented.

[0009] On the other hand, the present disclosure also provides a computer-readable storage medium, which is used to store a computer program, and when the computer program is executed by a processor, the above-mentioned intelligent customer service method is implemented.

[0010] The technical solution provided by one or more embodiments of the present disclosure can ensure that customer service is provided to the correct user by confirming the user identity, preventing information leakage or incorrect processing. Classifying and querying the user can quickly locate the type of the user's problem and improve the problem processing efficiency. Utilizing the historical data of the user can provide accurate data support for the user's problem and generate a more accurate solution. Screening out classified data from the historical data according to the question classification can reduce the data processing volume while ensuring the data validity, and can improve the data processing efficiency. Conducting a target query on the user can further clarify the specific needs of the user and avoid misunderstandings. According to the question attribute, a targeted explanation or solution can be provided for the target question, improving the user satisfaction.

[0011] The technical solution provided by one or more embodiments of the present disclosure can locate the question classification and specific question that the user wants to consult at low cost and high efficiency through two rounds of simple query dialogues. According to the question attribute, a targeted customer service reply can be provided. The technical solution provided by one or more embodiments of the present disclosure can not only automatically provide high-quality customer service replies for users, but also avoid the disadvantages of traditional customer service systems, such as too long conversations, too many query rounds, inaccurate question location, and impractical reply content. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The features and advantages of the embodiments of the present disclosure will be more clearly understood with reference to the accompanying drawings. The drawings are schematic and should not be construed as imposing any limitation on the present disclosure. In the drawings:

[0013] Figure 1 A schematic diagram of the steps of the intelligent customer service method in one embodiment of the present disclosure is shown;

[0014] Figure 2 A flowchart of the intelligent customer service method in one embodiment of the present disclosure is shown;

[0015] Figure 3 A schematic diagram of the functional modules of the intelligent customer service device in one embodiment of the present disclosure is shown;

[0016] Figure 4 A schematic diagram of the structure of an electronic device in one embodiment of the present disclosure is shown. Detailed implementation manners

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some but not all of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0018] In the related art, the customer service systems used by driving service companies for drivers mainly fall into the following three categories of modes.

[0019] Pure manual mode: Adopting the principle of discussing each case separately and simply stacking manpower. In this type of customer service mode, a large amount of customer service resources are easily occupied by complaints and consultations from the driver side, resulting in insufficient customer service resources for serving passengers. In addition, the pure manual mode has high costs and cannot achieve decreasing marginal costs.

[0020] Automatic reply mode: On the one hand, through self-developed or purchased speech recognition tools, an automatic dialogue is carried out with the driver; on the other hand, some automatic reply phrases are predefined for the driver's semantics. In this type of customer service mode, it is easy to consume a large amount of funds and have high costs when self-developing or purchasing accurate speech recognition tools. Moreover, the automatic reply phrases are difficult to accurately reply to the driver's questions and are difficult to actually solve the driver's problems and demands.

[0021] Machine learning mode: On the one hand, utilize large language models to have natural language conversations with drivers and understand drivers' questions; on the other hand, utilize pre-trained customer service models and generate customer service responses that match drivers' questions by means of deep neural networks, random forests, decision trees, etc. This type of customer service mode consumes a large amount of capital investment and R & D resource investment and is only suitable for individual large companies. In the current situation where there are many small and medium-sized companies in the driving service industry, it is difficult to promote this type of customer service mode on a large scale.

[0022] Please refer to Figure 1 , an intelligent customer service method provided by an embodiment of the present disclosure can be applied to a customer service system, can be automatically executed, and can include the following multiple steps.

[0023] S1: In response to a customer service request sent by a user, confirm the user identity of the user.

[0024] In this embodiment, by confirming the user identity, the customer service system can ensure that customer service is provided to the correct user and prevent information leakage or incorrect processing. According to the actual application scenario, the user can be a driver in the driving service industry, a driver in the online car-hailing industry, or a passenger.

[0025] In some embodiments, the step of, in response to a customer service request sent by a user, confirm the user identity of the user includes: identifying the incoming call mobile phone number of the customer service request; in the registration information, confirming the user identity corresponding to the incoming call mobile phone number; if the incoming call mobile phone number does not exist in the registration information, prompting the user to input a consulting mobile phone number; according to the consulting mobile phone number, in the registration information, confirming the user identity corresponding to the consulting mobile phone number.

[0026] Specifically, a user can send a customer service request to the customer service system by means of calling a customer service phone number, logging in to a customer service website, accessing a customer service program, etc. The incoming call mobile phone number can represent the mobile phone number used by the user to send the customer service request. For example, the mobile phone number used by the user when calling a customer service phone number, logging in to a customer service website, or accessing a customer service program.

[0027] The customer service system can save and manage the registration information of users. According to the incoming call mobile phone number of the user, the customer service system can automatically match the user identity in the registration information and quickly lock the user identity. If the incoming call mobile phone number does not exist in the registration information of the customer service system, the customer service system needs to prompt the user to input an accurate consulting mobile phone number. According to the consulting mobile phone number, the customer service system can query and obtain the user identity in the registration information. If the customer service system fails to query and obtain the user identity in the registration information according to the consulting mobile phone number, the customer service system can prompt the user that the query fails, and the customer service system can prompt the user to re-enter an accurate consulting mobile phone number. For example, the customer service system can generate a prompt message "The current consulting mobile phone number is not registered. Please re-enter the consulting mobile phone number".

[0028] In a practical application example, a customer may register their identity in the customer service system using a mobile phone number other than the incoming call mobile phone number (e.g., the user's alternate mobile phone number) and log in to the customer service system using the incoming call mobile phone number. At this time, the user needs to enter the consulting mobile phone number used for identity registration to obtain subsequent customer service.

[0029] In a practical application example, a customer may log in to the customer service system using an alternate mobile phone number or a relative or friend's mobile phone number. At this time, the user needs to enter the consulting mobile phone number used for identity registration to obtain subsequent customer service.

[0030] S2: Based on a preset business classification, conduct classified inquiries on the user to determine the problem classification of the user.

[0031] In this embodiment, the customer service system provides customer service around specific business content. For example, a customer service system of a chauffeur company may need to handle business content such as price calculation, route planning, marketing activities, recharge and withdrawal, signing and leaving, payment, and commission calculation. By updating and sorting out the existing business content, the customer service system can obtain a preset business classification. Using the preset business classification, the customer service system can conduct classified inquiries on users to confirm which problem classification the problem the user is about to consult matches among the preset business classifications.

[0032] In some embodiments, the problem classification includes but is not limited to price calculation objections, route planning objections, marketing activity problems, recharge and withdrawal problems, signing and leaving problems, payment problems, and commission calculation problems.

[0033] In a practical application example, relying on continuous business sorting and precipitation, the customer service system can ask the driver about the business classification they want to consult, obtain the driver's reply regarding the business classification, and lock in the major category of the problem the driver wants to consult this time.

[0034] S3: According to the user identity, obtain the historical data of the user, and based on the problem classification, screen out classified data from the historical data.

[0035] In this embodiment, the historical data of the user can be the user's order data and operation data within a certain historical period (e.g., within a week, within 10 days, within a month). For example, the user's recent received orders, the marketing activities the user participated in recently, the recharge and withdrawal initiated by the user recently, etc. Utilizing the user's historical data can provide accurate data support for the user's problem and generate a more precise solution.

[0036] In this embodiment, according to the problem classification, classification data related to the problem classification can be screened out from the historical data, which can reduce the amount of data processing and improve the data processing efficiency while ensuring the data validity. For example, if the problem classification is an objection to route planning, the classification data can be the order data and trip data in the recent historical data; if the problem classification is a recharge and withdrawal problem, the classification data can be the recharge and withdrawal data in the recent historical data.

[0037] S4: Based on the classification data, conduct a target inquiry on the user to determine the user's target problem.

[0038] In this embodiment, conducting a target inquiry on the user can further clarify the user's specific needs, obtain an accurate target problem, and avoid misunderstandings. Before conducting a target inquiry on the user, some candidate consultation questions can be predicted. When conducting a target inquiry on the user, it can be asked whether the user's target problem is one of these candidate consultation questions. If the target problem is one of the candidate consultation questions, the user's reply process can be simplified (for example, only reply with the serial number of the candidate consultation question), which can improve the user's reply efficiency. If the target problem does not belong to the candidate consultation questions, the target problem input by the user can be identified. The candidate consultation questions can be determined according to the abnormal data in the classification data.

[0039] For example, in the classification data related to price calculation objections, abnormal data such as "the price after order completion is inconsistent with the pre-estimated price shown when receiving the order", "the price becomes more expensive due to not following the navigation route during the trip", and "there is a situation of filling in additional fees (fuel costs, parking fees, etc.)" can be detected. At this time, the candidate consultation questions can be "inquiry about inconsistent estimated prices", "inquiry about increased prices", "inquiry about additional fees", etc.

[0040] Another example is that in the classification data related to marketing activity problems, abnormal data such as "there are orders that do not meet the marketing activity conditions and are judged as participation failures by the system" and "there is a situation of marketing activity cheating resulting in non-payment of rewards" can be detected. At this time, the candidate consultation questions can be "inquiry about failed activity participation", "inquiry about unissued activity rewards", etc.

[0041] In some embodiments, abnormal data can be screened out from the classification data. According to the abnormal data, problem prompt words can be determined. Using the problem prompt words, a target inquiry can be conducted on the user to determine the user's target problem.

[0042] Specifically, the problem prompt words can be summary information of abnormal data such as "order cancellation", "order violation", "recharge failure", etc. Using the problem prompt words, the target problem that the user expects to consult can be quickly locked.

[0043] In a practical application example, when the customer service system uses question prompt words for targeted inquiries, the following template can be adopted: "May I ask if the question you want to consult is 'order cancellation', 'order violation', 'top-up failure'... If so, please reply with the keyword in the statement." According to the user's reply, the customer service system can lock the target question and give a targeted response.

[0044] S5: Provide a customer service reply that conforms to the question attribute of the target question, where the question attribute includes an explanatory attribute and an operation processing attribute.

[0045] In this embodiment, since the question attributes of the target questions are different, there should be certain differences in the content structure of the customer service replies. Providing a customer service reply that conforms to the question attribute can provide a targeted explanation or solution for the target question and improve user satisfaction.

[0046] In some embodiments, if the question attribute is an explanatory attribute, then provide the user with a question summary of the target question, order information involved in the target question, and an explanatory report of the target question.

[0047] In some actual application scenarios, for explanatory questions, reading the question summary and the order information that this question may involve to the driver can gain the driver's recognition of the customer service system; providing the driver with an explanatory report can help the driver obtain a detailed explanation of the target question.

[0048] In a practical application example, the customer service reply for an explanatory question can be: The order you received at XXXX time cannot participate in the order rush reward because the order type is a special offer order. Please be informed. You can check it in the list of "Home Page - Marketing Activities - Participation Failure" on the driver side.

[0049] In some embodiments, if the question attribute is an operation processing attribute, then provide the user with a question summary of the target question, order information involved in the target question, and an operation guidance report for the target question; where the operation guidance report includes operation configuration information and operation step information.

[0050] In some actual application scenarios, for operation processing questions, reading the question summary and the order information that this question may involve to the driver can gain the driver's recognition of the customer service system; providing the driver with an operation guidance report can help the driver obtain an autonomous solution to the target question, including the driver's preparation work and the driver's execution actions.

[0051] In a practical application example, the customer service reply to an explanatory question can be: The order from XX starting point to XX ending point that you received at XXXX time was determined not to be settled because it was suspected of taking a detour. You can initiate an appeal on your own in the driver app. The appeal entry is "Me - Orders - Abnormal Orders". The appeal result will be feedback within 1 working day.

[0052] In some embodiments, the method further includes: confirming with the user whether the customer service reply is a satisfactory reply; if the customer service reply is a satisfactory reply, ending the current session; if the customer service reply is an unsatisfactory reply, transferring to a human customer service and synchronizing the target question and the customer service reply to the human customer service.

[0053] Specifically, the customer service system can confirm whether the user is satisfied with the reply. If satisfied, the customer service system can end the current session and complete the current customer service. If the user is not satisfied with the customer service reply, a human customer service can be used as a backup. The customer service system can call up the human customer service and automatically display on the workbench of the human customer service the problem that the intelligent customer service has locked, as well as the progress of handling this problem. In this way, a large amount of repeated communication between the human customer service and the user can be saved, helping the human customer service quickly communicate with the user in a targeted manner.

[0054] Please refer to Figure 2 , The intelligent customer service method provided by an embodiment of the present disclosure can execute the following automated process after the driver calls in.

[0055] The first step is to quickly lock the driver's identity. Quickly query the driver information based on the incoming call number to confirm whether the driver is a registered driver. If there is no driver information corresponding to the incoming call number, ask the driver for the registered mobile phone number, and then use the registered mobile phone number to confirm that the driver is a registered driver.

[0056] The second step is to pre - sort high - probability complaint consultations. First, quickly lock the driver's basic information, including the affiliated fleet, recent received orders, recent participated marketing activities, recent initiated recharge and withdrawal, etc. Subsequently, classify the driver's basic information. High - priority information includes: recent abnormal situations of this driver, including order cancellation, order violation, recharge and withdrawal failure, marketing activity participation failure, etc. Low - priority information includes: recent normal situation data of the driver.

[0057] The third step is to quickly lock the problem classification and specific problem. The system automatically asks the driver the question to be consulted and conducts targeted classification guidance for high - priority problems: "Do you want to consult about 'order cancellation', 'order violation','recharge failure'... type of problems? Please reply with the keyword in the statement". According to the driver's reply, first lock the abnormal situation problem of this driver in the confirmed section by the driver, and conduct targeted responses.

[0058] Step 4: Automatically respond to the driver's concerns. For questions about explaining the reasons, respond to the abnormal orders in the driver's confirmation section and inform the driver that a complete report is available on the driver's end to inform the specific abnormal situation and reasons. For questions about operation processing, inform the driver of the conditions and preparations required for this type of operation processing and inform the driver that a complete report is available on the driver's end to inform the driver of the problem and the next step to be taken.

[0059] Step 5: Manual customer service is used as a guarantee for driver satisfaction. Ask the driver whether he has received a satisfactory response. If the driver is satisfied, the conversation ends. If the driver is not satisfied, the conversation is transferred to manual customer service, and the driver feedback section summary information is automatically displayed on the manual customer service interface.

[0060] In this embodiment, a hierarchical inquiry guidance model is adopted to clarify the driver's problem classification and target questions, which does not require excessive human-machine training and greatly reduces the resource consumption of preparatory work. It is especially suitable for the chauffeur industry where most of the companies are small and medium-sized.

[0061] In this implementation, the business classification of "what abnormal situations have occurred recently" is focused on. Through simple human-computer dialogue, the problems that drivers want to report can be quickly located, which not only avoids the disadvantages of long dialogues and too many questions, but also takes into account the characteristics of different businesses and fully explores the actual demands of the driver group.

[0062] In this embodiment, each abnormal problem of the designated driver service can be answered in a targeted manner. For explanation questions, the driver can be quickly informed of the reasons and put at ease. For operation and processing questions, the driver can be informed of the required execution actions and preparations at the first time. In addition, by adopting the mode of sending reports to the driver, a complete solution to the problem that the driver wants to report can be quickly given to the driver to put at ease.

[0063] In this embodiment, if the driver is not satisfied with the intelligent customer service response, the driver can be transferred to the manual customer service for additional processing. The operating system of the manual customer service can automatically link and display the driver's abnormal problem list to improve the efficiency of the manual customer service. In this way, the manual customer service is avoided from asking the driver for information again, asking the driver what questions he wants to report, and inquiring the reasons for the driver's feedback, so that the manual customer service can handle the problem efficiently and reduce the negative emotions of the driver.

[0064] The technical solutions provided by one or more embodiments of the present disclosure can ensure that customer service is provided to the correct user by verifying the user's identity, preventing information leakage or incorrect processing. Classifying and interrogating the user can quickly locate the type of the user's problem and improve the problem-solving efficiency. Utilizing the user's historical data can provide accurate data support for the user's problem and generate more precise solutions. According to the problem classification, screening out the classified data from the historical data can reduce the amount of data processing while ensuring the data validity, and can improve the data processing efficiency. Conducting targeted interrogation of the user can further clarify the specific needs of the user and avoid misunderstandings. According to the problem attributes, providing targeted explanations or solutions for the target problem can improve user satisfaction.

[0065] The technical solutions provided by one or more embodiments of the present disclosure can locate the problem classification and specific problem that the user wants to consult at low cost and high efficiency through two rounds of simple interrogation dialogues. According to the problem attributes, targeted customer service responses can be provided. The technical solutions provided by one or more embodiments of the present disclosure can not only automatically provide high-quality customer service responses for users, but also avoid the disadvantages of traditional customer service systems, such as too long conversations, too many interrogation rounds, inaccurate problem location, and impractical response content.

[0066] Please refer to Figure 3 , the present disclosure also provides an intelligent customer service device, and the device includes:

[0067] An identity confirmation unit 100, configured to confirm the user identity of the user in response to a customer service request sent by the user;

[0068] A problem classification unit 200, configured to classify and interrogate the user based on a preset service classification to determine the problem classification of the user;

[0069] A data processing unit 300, configured to obtain the historical data of the user according to the user identity, and screen out the classified data from the historical data according to the problem classification;

[0070] A problem determination unit 400, configured to conduct targeted interrogation of the user based on the classified data to determine the target problem of the user;

[0071] A problem response unit 500, configured to provide a customer service response that conforms to the problem attributes of the target problem, where the problem attributes include an explanation attribute and an operation processing attribute.

[0072] In one embodiment, the identity confirmation unit 100 is specifically configured to identify the incoming call mobile phone number of the customer service request; confirm the user identity corresponding to the incoming call mobile phone number in the registration information; if the incoming call mobile phone number does not exist in the registration information, prompt the user to enter the consulting mobile phone number; and confirm the user identity corresponding to the consulting mobile phone number in the registration information according to the consulting mobile phone number.

[0073] In one embodiment, the problem classification includes at least one of objections to price calculation, objections to route planning, marketing activity problems, recharge and withdrawal problems, signing and leaving problems, payment problems, and commission calculation problems.

[0074] In one embodiment, the problem determination unit 400 is specifically configured to screen abnormal data in the classification data; determine a problem prompt word according to the abnormal data; and use the problem prompt word to conduct a target inquiry on the user to determine the target problem of the user.

[0075] In one embodiment, the problem reply unit 500 is specifically configured to, if the problem attribute is an explanation attribute, provide the user with a problem summary of the target problem, order information involved in the target problem, and an explanation report of the target problem.

[0076] In one embodiment, the problem reply unit 500 is specifically configured to, if the problem attribute is an operation processing attribute, provide the user with a problem summary of the target problem, order information involved in the target problem, and an operation guidance report of the target problem; wherein, the operation guidance report includes operation configuration information and operation step information.

[0077] In one embodiment, the device further includes a return visit unit 600. The return visit unit 600 is configured to confirm with the user whether the customer service reply is a satisfactory reply; if the customer service reply is a satisfactory reply, end the current session; if the customer service reply is an unsatisfactory reply, transfer to an artificial customer service and synchronize the target problem and the customer service reply to the artificial customer service.

[0078] Each unit described in the above embodiments can be specifically implemented by a computer chip or by a product with a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0079] For the convenience of description, when describing the above devices, they are described as various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0080] Please refer to Figure 4 , the present disclosure also provides an electronic device, which includes a memory and a processor. The memory is used to store a computer program, and when the computer program is executed by the processor, the above-mentioned intelligent customer service method is implemented.

[0081] The present disclosure also provides a computer-readable storage medium, which is used to store a computer program, and when the computer program is executed by a processor, the above-mentioned intelligent customer service method is implemented.

[0082] Among them, the processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. chips, or a combination of the above types of chips.

[0083] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory, that is, the methods in the above method embodiments are implemented.

[0084] The memory can include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by the processor, etc. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise internal network, a local area network, a mobile communication network, and combinations thereof.

[0085] Those skilled in the art can understand that to implement all or part of the processes in the above method embodiments, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disc, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memories.

[0086] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the embodiments of the device, equipment, and storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0087] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

[0088] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations fall within the scope defined by the appended claims.

Claims

1. An intelligent customer service method, characterized in that: The method comprises: In response to a customer service request sent by a user, confirm the user identity of the user; Based on the preset business classification, the user is asked a classified inquiry to determine the problem classification of the user; According to the user identity, historical data of the user is obtained, and according to the problem classification, classified data is filtered out from the historical data; Based on the classified data, performing a target query on the user to determine the target problem of the user; According to the problem attributes of the target problem, a customer service response that conforms to the problem attributes is provided, wherein the problem attributes include explanation attributes and operation processing attributes.

2. The method according to claim 1, characterized in that The step of confirming the user identity of the user in response to the customer service request sent by the user includes: Identify the incoming mobile phone number of the customer service request; In the registration information, confirm the user identity corresponding to the incoming mobile phone number; If the incoming phone number does not exist in the registration information, the user is prompted to enter the consultation phone number; According to the consulting mobile phone number, in the registration information, the user identity corresponding to the consulting mobile phone number is confirmed.

3. The method according to claim 1, characterized in that The problem classification includes at least one of price calculation objections, route planning objections, marketing activity issues, recharge and withdrawal issues, contract signing and resignation issues, payment issues, and commission calculation issues.

4. The method according to claim 1, characterized in that: The step of performing a target query on the user based on the classified data to determine the target question of the user includes: Screening abnormal data from the classified data; Determine a question prompt word according to the abnormal data; The question prompt words are used to conduct a target inquiry on the user to determine the target question of the user.

5. The method according to claim 1, characterized in that The providing a customer service response that matches the problem attributes according to the problem attributes of the target problem includes: If the question attribute is an explanation attribute, a question summary of the target question, order information related to the target question, and an explanation report of the target question are provided to the user.

6. The method according to claim 1, characterized in that The providing a customer service response that matches the problem attributes according to the problem attributes of the target problem includes: If the problem attribute is an operation processing attribute, providing the user with a problem summary of the target problem, order information related to the target problem, and an operation guidance report of the target problem; The operation guidance report includes operation configuration information and operation step information.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Confirm with the user whether the customer service reply is a satisfactory reply; If the customer service reply is satisfactory, the current session ends; If the customer service reply is unsatisfactory, the call will be transferred to manual customer service, and the target question and the customer service reply will be synchronized to the manual customer service.

8. An intelligent customer service device, characterized in that: The device comprises: An identity confirmation unit, configured to confirm the user identity of the user in response to a customer service request sent by the user; A question classification unit, configured to perform classified inquiries on the user based on preset business classifications to determine the question classification of the user; A data processing unit, configured to obtain historical data of the user according to the user identity, and filter out classified data from the historical data according to the problem classification; A question determination unit, configured to perform a target inquiry on the user based on the classification data to determine a target question of the user; The question reply unit is used to provide a customer service reply that conforms to the question attributes according to the question attributes of the target question, wherein the question attributes include explanation attributes and operation processing attributes.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images