Customer service request processing method and device, equipment, storage medium and program product

By combining a vectorized knowledge base with a large customer service model, the problem of low efficiency in identifying and resolving order inquiries in intelligent customer service systems has been solved, achieving efficient, one-stop processing of user needs and reducing the complexity of user operations and training difficulty.

CN121350209APending Publication Date: 2026-01-16BAIDU COM TIMES TECH (BEIJING) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511510981.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-21
Publication Date
2026-01-16

AI Technical Summary

Technical Problem

Existing intelligent customer service systems struggle to efficiently identify user intent and provide accurate solutions when handling customer inquiries, especially order-related issues, resulting in high complexity and low efficiency for users.

Method used

By introducing a vectorized knowledge base and a large customer service model, the system identifies the initial semantics and confidence level, supplements the interactive interface with additional queries until the target semantics are obtained, and determines the solution information from the application knowledge base, thus achieving a one-stop solution for user needs.

Benefits of technology

It improved the efficiency of customer service request processing, reduced the complexity of user operations, and enabled all user needs to be met in a single interactive interface, thereby improving the efficiency and quality of customer service.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121350209A_ABST
    Figure CN121350209A_ABST
Patent Text Reader

Abstract

The invention provides a customer service request processing method and device, electronic equipment, a computer readable storage medium and a computer program product, and relates to the technical field of computer technologies, in particular to the technical field of man-machine interaction, natural language processing, intelligent robots and other artificial intelligence. The method comprises the following steps: in response to the situation that associated information related to an order cannot be identified from a customer service request initiated by a user through a preset vectorization knowledge base, outputting an interactive interface for interacting with a preset customer service large model; filling an information input field of the interactive interface with the customer service request to obtain recognized initial semantics and initial confidence; in response to the condition that the initial confidence coefficient is lower than a preset confidence coefficient threshold value, initiating at least one round of supplementary inquiry to the user in the interactive interface, and complementally outputting supplementary information returned by the user in the interactive interface until target semantics with the confidence coefficient not lower than the confidence coefficient threshold value are obtained; and determining solution information corresponding to the target semantics from a preset application knowledge base, and outputting the solution information on the interactive interface. According to the method, all user requirements can be completed in the interactive interface in a one-stop manner, and the processing efficiency of the customer service request is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the fields of human-computer interaction, natural language processing, intelligent robots and other artificial intelligence technologies, and particularly to a customer service request processing method, apparatus, electronic device, computer-readable storage medium and computer program product. Background Technology

[0002] Current intelligent customer service technology relies on artificial intelligence and natural language processing to automatically handle customer inquiries and answer common questions through chatbots and virtual assistants. This reduces the burden on human customer service representatives, improves the efficiency and quality of customer service, and provides a more efficient and convenient solution for communication between businesses and customers. Today, the daily feedback issues faced by businesses mainly include order inquiries, refund progress, and general inquiries. Summary of the Invention

[0003] This disclosure provides a customer service request processing method, apparatus, electronic device, computer-readable storage medium, and computer program product that can complete all user needs in one stop within an interactive interface, thereby improving the processing efficiency of customer service requests.

[0004] In a first aspect, embodiments of this disclosure propose a customer service request processing method, comprising: responding to the inability to identify order-related association information from a user-initiated customer service request through a preset vectorized knowledge base, outputting an interactive interface for interacting with a preset customer service big model; filling the customer service request in the information input field of the interactive interface to obtain the identified initial semantics and initial confidence level; responding to the initial confidence level being lower than a preset confidence level threshold, initiating at least one round of supplementary inquiries to the user on the interactive interface, and supplementing the supplementary information returned by the user on the interactive interface until a target semantics with a confidence level not lower than the confidence level threshold is obtained; determining the solution information corresponding to the target semantics from a preset application knowledge base, and outputting the solution information on the interactive interface.

[0005] Secondly, embodiments of this disclosure propose a customer service request processing apparatus, comprising: an information identification module configured to, in response to the inability to identify order-related association information from a user-initiated customer service request through a preset vectorized knowledge base, output an interactive interface for interacting with a preset customer service big model; an information filling module configured to fill the customer service request in the information input field of the interactive interface, obtaining the identified initial semantics and initial confidence level; an inquiry initiation module configured to, in response to the initial confidence level being lower than a preset confidence level threshold, initiate at least one round of supplementary inquiries to the user on the interactive interface, and supplement the supplementary information returned by the user on the interactive interface until a target semantics with a confidence level not lower than the confidence level threshold is obtained; and an information output module configured to, determine the solution information corresponding to the target semantics from a preset application knowledge base, and output the solution information on the interactive interface.

[0006] Thirdly, embodiments of this disclosure provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the customer service request processing method as described in the first aspect.

[0007] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions that enable a computer to implement the customer service request processing method as described in the first aspect when executed.

[0008] Fifthly, embodiments of this disclosure provide a computer program product including a computer program that, when executed by a processor, can implement the steps of the customer service request processing method as described in the first aspect.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is an exemplary system architecture to which this disclosure can be applied; Figure 2 A flowchart of a customer service request processing method provided in this embodiment of the disclosure; Figure 3 A flowchart illustrating another customer service request processing method provided in this disclosure embodiment; Figure 4 A flowchart illustrating a customer service request processing method in an application scenario provided by an embodiment of this disclosure; Figure 5 A structural block diagram of a customer service request processing device provided in this disclosure embodiment; Figure 6 This is a schematic diagram of the structure of an electronic device suitable for performing a customer service request processing method, provided as an embodiment of the present disclosure. Detailed Implementation

[0011] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding; these should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description. It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0012] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0013] Figure 1 An exemplary system architecture 100 is shown, to which embodiments of the customer service request processing methods, apparatus, electronic devices, and computer-readable storage media of this disclosure may be applied.

[0014] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0015] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various applications for enabling information communication between the terminal devices 101, 102, and 103 and server 105 can be installed. These applications include web browsers, search engines, and instant messaging applications.

[0016] Terminal devices 101, 102, and 103 and server 105 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with displays, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 101, 102, and 103 are software, they can be installed in the aforementioned electronic devices, and can be implemented as multiple software programs or software modules, or as a single software program or software module; no specific limitation is made here. When server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server. When server 105 is software, it can be implemented as multiple software programs or software modules, or as a single software program or software module; no specific limitation is made here.

[0017] Server 105 can provide various services through its built-in applications. Taking a web browser-like application that can generate solution information based on customer service requests as an example, when running this web browser-like application, server 105 can achieve the following effects: In response to the inability to identify order-related information from the customer service request initiated by the user through a preset vectorized knowledge base, it outputs an interactive interface that interacts with a preset customer service big model; the customer service request is filled in the information input field of the interactive interface to obtain the identified initial semantics and initial confidence level; in response to the initial confidence level being lower than a preset confidence level threshold, at least one round of supplementary inquiries is initiated to the user in the interactive interface, and the supplementary information returned by the user is output in the interactive interface until a target semantics with a confidence level not lower than the confidence level threshold is obtained; the solution information corresponding to the target semantics is determined from the preset application knowledge base, and the solution information is output in the interactive interface.

[0018] It should be noted that the vectorized knowledge base, customer service requests, and related information can be obtained from terminal devices 101, 102, and 103 via network 104, or they can be pre-stored locally on server 105 through various means. Therefore, when server 105 detects that this data is already stored locally (e.g., when it starts processing previously retained customer service request processing tasks), it can choose to retrieve this data directly from the local storage. In this case, the exemplary system architecture 100 may not include terminal devices 101, 102, and 103 and network 104.

[0019] Since generating resolution information based on customer service requests requires significant computing resources and power, the customer service request processing methods provided in the subsequent embodiments of this disclosure are generally executed by a server 105 with strong computing power and abundant computing resources. Correspondingly, the customer service request processing device is also generally located within the server 105. However, it should also be noted that when terminal devices 101, 102, and 103 also possess sufficient computing power and resources, they can also perform the aforementioned calculations performed by the server 105 through web browsing applications installed on them, thereby outputting the same results as the server 105. Especially when multiple terminal devices with different computing capabilities exist simultaneously, but a web browsing application determines that its terminal device has strong computing power and abundant remaining computing resources, it can allow the terminal device to perform the aforementioned calculations, thereby appropriately reducing the computing pressure on the server 105. Accordingly, the customer service request processing device can also be located within terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also exclude the server 105 and the network 104.

[0020] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0021] Please refer to Figure 2 , Figure 2 A flowchart of a customer service request processing method provided in this disclosure embodiment, wherein process 200 includes the following steps: Step 201: In response to the inability to identify order-related information from the user's customer service request through the preset vectorized knowledge base, output an interactive interface that interacts with the preset customer service big model.

[0022] In this embodiment, when the executing entity (e.g. Figure 1 When the server 105 shown cannot identify order-related information from the user-initiated customer service request using the preset vectorized knowledge base, it outputs an interactive interface for interacting with the preset customer service big model. The vectorized knowledge base is a knowledge base that uses a vector space model to represent and store information. A knowledge base is a data system that stores and organizes domain-specific knowledge for querying, reasoning, and information retrieval. Related information refers to order-related information stored in the vectorized knowledge base, including basic domain information, common order questions, and responses. The customer service big model is a model based on artificial intelligence and natural language processing technologies. It can interact with users through the interactive interface, answer questions, provide information, serve customers, and offer efficient solutions.

[0023] In this embodiment, the executing entity can obtain the customer service request initiated by the user through various methods (such as submitting a form on the front end, text input, voice input, etc.).

[0024] Step 202: Fill in the customer service request in the information input field of the interactive interface to obtain the identified initial semantics and initial confidence level.

[0025] In this embodiment, the executing entity fills in the customer service request in the information input field of the interactive interface, and obtains the identified initial semantics and initial confidence level. The initial semantics refers to the semantic information obtained by identifying the customer service request using the customer service big data model, and the initial confidence level refers to the confidence level of the semantic information output by the customer service big data model.

[0026] Step 203: In response to the initial confidence level being lower than the preset confidence level threshold, initiate at least one round of supplementary queries to the user in the interactive interface, and supplement the supplementary information returned by the user in the interactive interface until the target semantics with a confidence level not lower than the confidence level threshold is obtained.

[0027] In this embodiment, when the executing entity determines that the initial confidence level is lower than a preset confidence threshold, it initiates at least one round of supplementary inquiries to the user through the interactive interface, and outputs the supplementary information returned by the user in the interactive interface. The customer service big data model continues to identify semantic information and corresponding confidence levels based on the supplementary information until the identified confidence level is not lower than the preset confidence threshold. Then, the semantic information corresponding to that confidence level is used as the target semantics. The target semantics are ultimately input into the customer service big data model to obtain the semantic information of the corresponding solution.

[0028] Step 204: Determine the solution information corresponding to the target semantics from the preset application knowledge base, and output the solution information on the interactive interface.

[0029] In this embodiment, the executing entity inputs the target semantics obtained in step 203 into the customer service big model. The customer service big model analyzes and understands the target semantics and outputs the solution information corresponding to the target semantics. The solution information is a solution stored in a preset application knowledge base for resolving customer service issues. The application knowledge base can cover all possible issues related to the current platform and typically includes content such as frequently asked questions, account management, operation guides, product descriptions, brand introductions, user tutorials, policy terms, and return / exchange procedures.

[0030] In this embodiment, when sensitive data is present in the solution information, the solution information is anonymized before being output to the interactive interface. Common data anonymization methods such as data masking, partial hiding, data generalization, and encryption can be used to anonymize the solution information.

[0031] The customer service request processing method provided in this embodiment, when unable to identify order-related information from a user-initiated customer service request using a preset vectorized knowledge base, outputs an interactive interface for interaction with a preset customer service big data model. The customer service request is then filled into the information input field of the interactive interface to obtain the identified initial semantics and initial confidence level. When the initial confidence level is lower than a preset confidence level threshold, at least one round of supplementary inquiries is initiated to the user on the interactive interface, and the supplementary information returned by the user is output to the interactive interface until a target semantics with a confidence level not lower than the confidence level threshold is obtained. Finally, the solution information corresponding to the target semantics is determined from a preset application knowledge base and output on the interactive interface. This embodiment generates corresponding solution information for user-issued customer service requests through a customer service big data model, reducing user operation complexity and significantly improving the processing efficiency of customer service requests.

[0032] Please refer to Figure 3 , Figure 3 A flowchart of another customer service request processing method provided in this disclosure embodiment, wherein process 300 includes the following steps: Step 301: Receive customer service requests initiated by users.

[0033] In this embodiment, the executing entity can obtain the customer service request initiated by the user through various methods (such as submitting a form on the front end, text input, voice input, etc.).

[0034] Step 302: Determine whether the customer service request contains related information that is associated with the order information recorded in the vectorized knowledge base.

[0035] In this embodiment, the executing entity determines whether the customer service request contains related information associated with the order information recorded in the vectorized knowledge base. This related information refers to order-related information stored in the vectorized knowledge base, including basic domain information, common order questions, and responses.

[0036] In this embodiment, the executing entity can convert the customer service request into a vector representation, and then calculate the similarity between the vectorized customer service request and each vector in the vectorized knowledge base. By judging whether the similarity meets the preset similarity threshold, it can be determined whether the customer service request contains related information related to the order information recorded in the vectorized knowledge base.

[0037] In this embodiment, the vectorized knowledge base is constructed as follows: Basic domain information and common query information from the application knowledge base are collected and verified using various methods to generate a common knowledge base. The information in the common knowledge base is then decomposed and vectorized. Based on the vectorized information, the vectorized knowledge base is constructed. By constructing a vectorized knowledge base, retrieval efficiency can be improved, storage space requirements reduced, and more efficient and intelligent information management and retrieval achieved.

[0038] Step 303: In response to the inability to identify order-related information from the user-initiated customer service request through the preset vectorized knowledge base, output an interactive interface that interacts with the preset customer service big model.

[0039] In this embodiment, when the executing entity cannot identify order-related information from the user-initiated customer service request using a preset vectorized knowledge base, it outputs an interactive interface for interacting with a preset customer service model. Specific operations are already described in... Figure 2 Step 201 in the illustrated embodiment is described in detail and will not be repeated here.

[0040] In this embodiment, the customer service big model is generated as follows: order information recorded in the vectorized knowledge base is used as fine-tuning training samples to fine-tune the general big language model, and the resulting big language model is used as the customer service big model. The trained customer service big model can better adapt to the needs of the customer service system, thereby enabling accurate analysis of user needs.

[0041] Step 304: Fill in the customer service request in the information input field of the interactive interface to obtain the identified initial semantics and initial confidence level.

[0042] In this embodiment, the specific operation of step 304 has been described. Figure 2 Step 202 in the illustrated embodiment is described in detail and will not be repeated here.

[0043] Step 305: In response to the initial confidence level being lower than the preset confidence level threshold, initiate at least one round of supplementary queries to the user in the interactive interface, and output the supplementary information returned by the user in the interactive interface until the target semantics with a confidence level not lower than the confidence level threshold is obtained.

[0044] In this embodiment, the specific operation of step 305 has been described. Figure 2 Step 203 in the illustrated embodiment is described in detail and will not be repeated here.

[0045] Step 306: Determine the solution information corresponding to the target semantics from the preset application knowledge base, and output the solution information on the interactive interface.

[0046] In this embodiment, the specific operation of step 306 has been described. Figure 2 Step 204 in the illustrated embodiment is described in detail.

[0047] In some optional embodiments of this example, when the target semantics are to query order information, the executing entity can query the candidate orders corresponding to the user's ID information in the vectorized knowledge base and output the candidate orders as solution information on the interactive interface. Since the vectorized knowledge base is built based on common knowledge bases in the application knowledge base, the knowledge recorded in the vectorized knowledge base is included in the application knowledge base. In this implementation, when it is determined that the target semantics are to query order information, the candidate orders corresponding to the user's ID information are quickly retrieved directly from the vectorized knowledge base and sent to the user, thereby improving the response speed to the user's customer service request.

[0048] In some optional embodiments of this example, when the target semantics are to invoke a target function, the executing entity will output a jump link or functional control that can jump to the corresponding interface of the target function as solution information on the interactive interface. The functional control may include function cards, function buttons, confirmation buttons, etc. For example, when the target semantics are to query order logistics, the executing entity can directly output a link to the order logistics query function on the interactive interface. The user can click the link to jump to the logistics query interface, or the logistics query card can be directly displayed, and the user can directly enter the order number in the logistics query card to display the current logistics information of the order. This embodiment improves the convenience of user operation by completing user needs in one stop within the interactive interface.

[0049] Step 307: In response to a customer service request containing related information, use a vectorized knowledge base to match the order information corresponding to the related information, and return the order information as the order query result to the user.

[0050] In this embodiment, when a customer service request contains related information, the executing entity uses a vectorized knowledge base to match the order information corresponding to the related information and returns the order information as the order query result to the user. Specifically, the executing entity can vectorize the related information and then return the order information in the vectorized knowledge base that has a similarity greater than a preset similarity threshold to the vectorized related information as the order query result to the user.

[0051] In some optional embodiments of this example, when the customer service request contains related information, the executing entity can also return links to relevant information corresponding to the related information in the vectorized knowledge base to the user. By clicking the links, the user can view all relevant information corresponding to the related information in the vectorized knowledge base, thereby providing the user with comprehensive feedback information.

[0052] Step 308: In response to receiving the substitute operation instruction from the user, initiate a substitute operation authorization confirmation request and record the authorization confirmation information returned by the user to the substitute authorization confirmation request.

[0053] In this embodiment, when a substitute operation instruction is received from a user, the executing entity can initiate a substitute operation authorization confirmation request and record the authorization confirmation information returned by the user to the substitute authorization confirmation request. The substitute operation instruction is an instruction used to replace certain actions or commands.

[0054] Step 309: Based on the received authorization confirmation information, perform the corresponding operation on behalf of the user in the interactive interface, and push the feedback obtained after the operation is completed to the user.

[0055] In this embodiment, the executing entity, based on the received authorization confirmation information, completes the corresponding operation on behalf of the user in the interactive interface and pushes the feedback obtained after the operation is completed to the user. This embodiment, after obtaining user authorization, can help the user perform the required operation, improving the convenience of user operation.

[0056] In this embodiment, the difference is... Figure 2 The illustrated embodiment provides a method for determining whether a customer service request contains related information about the order information recorded in the vectorized knowledge base through steps 301-302; a method for generating solution information by calling the customer service big model when the customer service request does not contain related information through steps 303-306; a method for generating order query results using the vectorized knowledge base when the customer service request contains related information through step 307; and a method for completing the corresponding operation on behalf of the user in the interactive interface when a substitute operation instruction is received through steps 308-309. There is no causal or dependency relationship between the four implementation methods, and they do not necessarily need to be applied simultaneously in one embodiment. They can be applied separately in different embodiments as needed to determine whether a customer service request contains related information about the order information recorded in the vectorized knowledge base, or to generate solution information by calling the customer service big model when the customer service request does not contain related information, or to generate order query results using the vectorized knowledge base when the customer service request contains related information, or to complete the corresponding operation on behalf of the user in the interactive interface when a substitute operation instruction is received. This embodiment exists only as a preferred embodiment that simultaneously includes four specific implementation methods.

[0057] In some optional embodiments of this example, the executing entity can also update the knowledge base based on customer service requests and target response information, then update the vectorized knowledge base based on the updated knowledge base, and train the customer service big model based on the updated vectorized knowledge base. This example improves the comprehensiveness and richness of information in the vectorized knowledge base by continuously supplementing the information stored in the knowledge base and updating the vectorized knowledge base and the customer service big model based on the supplemented knowledge base. This allows the customer service big model to better understand the user's needs and context, thereby making more accurate judgments and helping users solve more complex needs.

[0058] The customer service request processing method provided in this embodiment improves response speed by introducing a vectorized knowledge base to quickly answer customer service requests containing related information about orders recorded in the knowledge base. Furthermore, it uses a large customer service model to understand customer service requests where keyword recognition and character matching cannot easily determine the user's true intent, thus identifying the user's true intent. Simultaneously, it integrates with other functional systems to help users obtain the necessary information or perform the required operations, enabling all user needs to be met in a single interactive interface. This reduces the difficulty of customer service training and the complexity of user operations, significantly improving the efficiency of customer service request processing.

[0059] To enhance understanding, this disclosure also provides a specific implementation scheme based on a particular application scenario. Please refer to the example below. Figure 4 The process shown is 400.

[0060] In this implementation, the executing entity acquires accurate and complete basic domain information (such as transaction platform-related information) and daily classifications (such as frequently asked questions and answers) to form a knowledge base. The information in the knowledge base is then broken down into information segments, which are then vectorized to generate a vectorized knowledge base. The executing entity can use the knowledge base information to fine-tune and train a general-purpose large language model, generating a large customer service model. Furthermore, the executing entity can update and maintain the knowledge base in a timely manner based on historical interaction records, and simultaneously update both the large customer service model and the vectorized knowledge base.

[0061] Step 401: Receive customer service requests initiated by users.

[0062] Step 402: Determine whether the customer service request contains related information that is associated with the order information recorded in the vectorized knowledge base.

[0063] Specifically, the vectorized knowledge base stores all order information and related information on the trading platform. At this point, it is necessary to determine whether the customer service request initiated by the user explicitly includes related information (such as order number, order date, transaction user, etc.).

[0064] Step 403: If the customer service request contains related information to the order information recorded in the vectorized knowledge base, return the link between the order information corresponding to the related information and the relevant information in the vectorized knowledge base corresponding to the related information to the user.

[0065] Specifically, when a customer service request contains related information about an order, the executing entity can directly return the order information corresponding to the related information stored in the vectorized knowledge base to the user, and can also return the links to related information in the vectorized knowledge base that correspond to the related information to the user.

[0066] Step 404: If the customer service request does not contain any related information to the order information recorded in the vectorized knowledge base, the user interface of the preset customer service big model is invoked to identify the customer service request and obtain the initial semantics and initial confidence.

[0067] Specifically, when the customer service request does not contain any related information about the order, it means that there is a lack of key information in the customer service request. The order information corresponding to the customer service request cannot be found directly from the vectorized knowledge base. At this time, the interactive interface of the preset customer service big model is called to identify the customer service request and obtain the initial semantics of the customer service request and the initial confidence level corresponding to the initial semantics.

[0068] Step 405: Determine whether the initial confidence level is lower than the preset confidence threshold.

[0069] Step 406: If the initial confidence level is lower than the preset confidence level threshold, initiate at least one round of supplementary queries to the user, and continue to identify based on the supplementary information returned by the user until the target semantics with a confidence level not lower than the confidence level threshold is obtained.

[0070] Specifically, if the initial confidence level is lower than the preset confidence level threshold, it means that there are still semantic ambiguities in the customer service request, such as unclear references, logical confusion, and missing information. The currently identified semantic information is unreliable. Therefore, it is necessary to ask the user for supplementary information and continue to identify the target semantics with a confidence level not lower than the confidence level threshold.

[0071] Step 407: Determine the solution information corresponding to the target semantics from the preset application knowledge base, and output the solution information on the interactive interface.

[0072] Step 408: When the target semantics is to query order information, query the candidate orders corresponding to the user's ID information in the vectorized knowledge base, and output the candidate orders as solution information on the interactive interface.

[0073] Step 409: When the target semantics is to call the target function, the jump link or function control that can jump to the corresponding interface of the target function will be output as the solution information on the interactive interface.

[0074] Step 410: When a substitute operation instruction is received from the user, initiate a substitute operation authorization confirmation request and record the authorization confirmation information returned by the user to the substitute authorization confirmation request.

[0075] For example, when a user sends a request to confirm receipt on behalf of another user, the executing entity sends a request to the user authorizing the system to confirm receipt on behalf of the user, and records the authorization confirmation information returned by the user for the request to confirm receipt on behalf of another user.

[0076] Step 411: Based on the received authorization confirmation information, perform the corresponding operation on behalf of the user in the interactive interface, and push the feedback obtained after the operation is completed to the user.

[0077] For example, when a user decides that the system will confirm receipt on their behalf, the system will complete the confirmation process on their behalf in the interactive interface and push the feedback received upon completion of the confirmation to the user.

[0078] The customer service request processing method provided in this embodiment quickly answers customer service requests containing related information about orders recorded in the vectorized knowledge base by introducing a vectorized knowledge base. It also understands customer service requests that cannot be easily determined by keyword recognition or character matching by using a large customer service model, thus determining the user's true intent. At the same time, it integrates with other functional systems to help users obtain the information or perform the required operations, enabling all user needs to be met in one stop within an interactive interface. This reduces the difficulty of customer service training and the complexity of user operations, and greatly improves the efficiency of customer service request processing.

[0079] Further reference Figure 5 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a customer service request processing device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0080] like Figure 5As shown, the customer service request processing device 500 of this embodiment may include: an information identification module 501, an information filling module 502, an inquiry initiation module 503, and an information output module 504. The information identification module is configured to, in response to the inability to identify order-related information from a user-initiated customer service request using a preset vectorized knowledge base, output an interactive interface that interacts with a preset customer service model. The information filling module is configured to fill the customer service request into the information input field of the interactive interface, obtaining the identified initial semantics and initial confidence level. The inquiry initiation module is configured to, in response to the initial confidence level being lower than a preset confidence level threshold, initiate at least one round of supplementary inquiries to the user on the interactive interface, and output the supplementary information returned by the user on the interactive interface until a target semantics with a confidence level not lower than the confidence level threshold is obtained. The information output module is configured to determine the solution information corresponding to the target semantics from a preset application knowledge base and output the solution information on the interactive interface.

[0081] The specific processing of the aforementioned information recognition module 501, information filling module 502, query initiation module 503, and information output module 504, and the resulting technical effects, can be found in the following references: Figure 2 The relevant descriptions of steps 201-204 in the corresponding embodiments will not be repeated here.

[0082] In some optional implementations of this embodiment, the customer service request processing device 500 may further include: a request receiving module 505, configured to receive a customer service request initiated by a user; an information judgment module 506, configured to determine whether the customer service request contains related information related to order information recorded in a vectorized knowledge base; an information matching module 507, configured to, in response to the customer service request containing related information, use the vectorized knowledge base to match the order information corresponding to the related information, and return the order information as an order query result to the user; a link referencing module 508, configured to, in response to the customer service request containing related information, referencing a link to the relevant information in the vectorized knowledge base corresponding to the related information and returning it to the user; an authorization initiation module 509, configured to, in response to receiving a substitute operation instruction from the user, initiate a substitute operation authorization confirmation request, and record the authorization confirmation information returned by the user to the substitute authorization confirmation request; and a feedback push module 510, configured to, based on the received authorization confirmation information, complete the corresponding operation on behalf of the user in the interactive interface, and push the feedback obtained after completing the corresponding operation to the user.

[0083] In some optional implementations of this embodiment, the information output module 504 includes: an information query unit configured to query candidate orders corresponding to the user's ID information in a vectorized knowledge base in response to the target semantics of querying order information, wherein the knowledge recorded in the vectorized knowledge base is included in the application knowledge base; an order output unit configured to output candidate orders as solution information on the interactive interface; and a control output unit configured to output jump links or function controls that can jump to the interface corresponding to the target function as solution information on the interactive interface in response to the target semantics of calling the target function.

[0084] In some optional implementations of this embodiment, the vectorized knowledge base in the information recognition module 501 is constructed in the following way: basic domain information and common query information are collected and verified according to various methods to generate a common knowledge base; the information in the common knowledge base is split and vectorized to construct a vectorized knowledge base.

[0085] In some optional implementations of this embodiment, the customer service big model in the information recognition module 501 is trained in the following way: the order information recorded in the vectorized knowledge base is used as the fine-tuning training sample to fine-tune the general big language model, and the big language model obtained after fine-tuning is used as the customer service big model.

[0086] In some optional implementations of this embodiment, the customer service request processing device 500 may further include: an update module 511, configured to update a common knowledge base based on the customer service request and the target response information; update a vectorized knowledge base based on the updated common knowledge base; and train a large customer service model based on the updated vectorized knowledge base.

[0087] This embodiment exists as a device embodiment corresponding to the above method embodiment. The customer service request processing device provided in this embodiment introduces a vectorized knowledge base to quickly answer customer service requests containing related information about order information recorded in the vectorized knowledge base. It also uses a customer service big data model to understand customer service requests that cannot be easily determined by keyword recognition or character matching to determine the user's true intent, and at the same time, it connects with other functional systems to help users obtain the required information or perform the required operations. This enables all user needs to be completed in one stop in an interactive interface, reducing the difficulty of customer service training and the complexity of user operations, and greatly improving the processing efficiency of customer service requests.

[0088] According to embodiments of this disclosure, this disclosure also provides an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the customer service request processing method described in any of the above embodiments.

[0089] According to embodiments of this disclosure, this disclosure also provides a readable storage medium storing computer instructions that enable a computer to implement the customer service request processing method described in any of the above embodiments when executed.

[0090] According to embodiments of this disclosure, this disclosure also provides a computer program product that, when executed by a processor, can implement the customer service request processing method described in any of the above embodiments.

[0091] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0092] like Figure 6 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded into random access memory (RAM) 603 from storage unit 608. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0093] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0094] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a customer service request processing method. For example, in some embodiments, the customer service request processing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the customer service request processing method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the customer service request processing method by any other suitable means (e.g., by means of firmware).

[0095] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0097] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0098] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0099] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0100] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and Virtual Private Server (VPS) services, such as high management difficulty and weak business scalability.

[0101] According to the technical solution of this disclosure, by introducing a vectorized knowledge base, customer service requests containing related information about order information recorded in the vectorized knowledge base can be quickly answered. Furthermore, a large customer service model is used to understand customer service requests where the user's true intent cannot be determined simply through keyword recognition and character matching, thus determining the user's true intent. Simultaneously, it integrates with other functional systems to help users obtain the required information or perform the required operations, enabling all user needs to be met in one interactive interface. This reduces the difficulty of customer service training and the complexity of user operations, significantly improving the efficiency of customer service request processing.

[0102] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0103] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A customer service request processing method, comprising: in response to being unable to identify associated information related to an order from a customer service request initiated by a user through a preset vectorized knowledge base, outputting an interaction interface for interacting with a preset customer service large model; filling in the customer service request in the information input field of the interaction interface to obtain identified initial semantics and an initial confidence level; in response to the initial confidence level being lower than a preset confidence threshold, initiating at least one round of supplementary inquiries to the user in the interaction interface, and supplementally outputting the supplementary information returned by the user in the interaction interface until target semantics with a confidence level not lower than the confidence threshold is obtained; determining solving information corresponding to the target semantics from a preset application knowledge base, and outputting the solving information in the interaction interface.

2. The method of claim 1, further comprising: receiving the customer service request initiated by the user; determining whether the customer service request contains associated information related to order information recorded in the vectorized knowledge base; in response to the customer service request containing the associated information, matching order information corresponding to the associated information using the vectorized knowledge base, and returning the order information as an order query result to the user.

3. The method of claim 2, further comprising: in response to the customer service request containing the associated information, returning a link to the relevant information corresponding to the associated information in the vectorized knowledge base to the user.

4. The method of claim 1, wherein, The determining solving information corresponding to the target semantics from a preset application knowledge base, and outputting the solving information in the interaction interface comprises: in response to the target semantics being query order information, querying candidate orders corresponding to the user's number information in the vectorized knowledge base, wherein the knowledge recorded in the vectorized knowledge base is contained in the application knowledge base; outputting the candidate orders as the solving information in the interaction interface.

5. The method of claim 1, wherein, The determining solving information corresponding to the target semantics from a preset application knowledge base, and outputting the solving information in the interaction interface further comprises: in response to the target semantics being a call to a target function, outputting a jump link or function control capable of jumping to the interface corresponding to the target function as the solving information in the interaction interface.

6. The method of claim 1, further comprising: in response to receiving a substitute operation instruction transmitted by the user, initiating a substitute operation authorization confirmation request, and recording authorization confirmation information returned by the user to the substitute authorization confirmation request; based on the received authorization confirmation information, completing corresponding operations in the interaction interface on behalf of the user, and pushing feedback obtained after completing the corresponding operations to the user.

7. The method of claim 1, wherein, The vectorized knowledge base is constructed in the following manner: collect and verify basic field information and common inquiry information in various ways to generate a common knowledge base; split and vectorize the information in the common knowledge base to construct the vectorized knowledge base.

8. The method of claim 7, wherein, The customer service large model is trained in the following manner: The order information recorded in the vectorized knowledge base is taken as a fine-tuning training sample to fine-tune a general large language model, and the large language model obtained after fine-tuning is taken as the customer service large model.

9. The method of any one of claims 1-8, comprising: updating the common knowledge base according to the customer service request and the target reply information; updating the vectorized knowledge base based on the updated common knowledge base; training the customer service large model based on the updated vectorized knowledge base.

10. A customer service request processing apparatus, comprising: an information identification module configured to output an interaction interface for interacting with a preset customer service large model in response to being unable to identify associated information related to an order from a customer service request initiated by a user through a preset vectorized knowledge base; an information filling module configured to fill the customer service request in an information input field of the interaction interface to obtain identified initial semantics and an initial confidence level; an inquiry initiation module configured to initiate at least one round of supplementary inquiry to the user through the interaction interface in response to the initial confidence level being lower than a preset confidence threshold, and output the returned supplementary information of the user in the interaction interface until target semantics with a confidence level not lower than the confidence threshold is obtained; an information output module configured to determine solution information corresponding to the target semantics from a preset application knowledge base, and output the solution information in the interaction interface.

11. An electronic device, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the customer service request processing method of any one of claims 1-9.

12. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the customer service request processing method of any one of claims 1-9.

13. A computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the steps of the customer service request processing method of any one of claims 1-9.