A customer service interaction method and system based on large language model

Abstract

The present invention is applicable to the field of customer service interaction technology, and in particular relates to a customer service interaction method and system based on a large language model. The method comprises: constructing a general data database, establishing a voice connection with a user, recording information about the voice interaction process, and obtaining initial voice interaction data; obtaining user account information, performing data query based on the user account information, and constructing a user data database; processing the initial voice interaction data to obtain an initial voice processing result, performing a switch warning detection, and obtaining a warning detection result; performing a diversion process, synchronizing to a corresponding service device, and completing a seamless switching of real-time voice. The present invention inputs the voice interaction process into the large language model in the form of text, and predicts whether the user needs to switch to a service specialist based on the interaction process with the user. When a switch is detected, preparations are started, and when demand changes, a seamless switching of the service specialist is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of customer service interaction, and in particular relates to a customer service interaction method and system based on a large language model. Background Art

[0002] Customer service interactions refer to the process of communication between a company and its customers through various communication channels, with the aim of solving customer problems, providing product or service information, collecting feedback, or improving the customer experience.

[0003] Whether it is enterprise customer service or e-commerce customer service, when the number of business types that customer service needs to respond to is large, enterprises or businesses need to set up different service specialists to serve callers with different needs. In order to efficiently respond to a large number of customer consultation needs, enterprises or e-commerce companies generally use customer service robots to respond. Customer service robots can handle simple customer consultation requests. Because customer service robots are prone to communication difficulties, many customers are reluctant to communicate with customer service robots. Some customers find it difficult to understand their requests after interacting with customer service robots, which will lead to customer complaints. Therefore, although customer service robots have been developed for a long time, human customer service is still indispensable. Human customer service is different from customer service robots. Although using human customer service can provide a better service experience, its cost is relatively higher. During the service process of human customer service, due to various reasons, human customer service often needs to switch service specialists multiple times. Each time a service specialist is switched, the new service specialist needs to read and understand the historical conversation records, which not only wastes a lot of time but also reduces the reception efficiency of human customer service. Summary of the Invention

[0004] The purpose of the present invention is to provide a customer service interaction method based on a large language model, aiming to solve the problem that during the service process of manual customer service, manual customer service often needs to switch service specialists multiple times due to various reasons. Each time the service specialist is switched, the new service specialist needs to read and understand the historical conversation records, which not only wastes a lot of time but also reduces the reception efficiency of manual customer service.

[0005] The present invention is implemented as follows: a customer service interaction method based on a large language model, the method comprising:

[0006] Constructing a general information database, establishing a voice connection with the user, and recording information about the voice interaction process to obtain initial voice interaction data. The general information database records at least service scope data of each service specialist, and the service scope data is characterized by keywords.

[0007] Obtaining user account information, performing a data query based on the user account information, and building a user profile database based on the data query results, wherein the user profile database includes at least historical order information;

[0008] The initial voice interaction data is processed by a large language model to obtain an initial voice processing result, and a switching warning detection is performed based on the initial voice processing result to obtain a warning detection result;

[0009] Based on the early warning detection results, the real-time voice interaction records are diverted and synchronized to the corresponding service equipment. After receiving the switching instructions, the real-time voice switching is completed seamlessly. During the real-time voice conversation with the user, the user information database is processed through the large language model to provide pre-loaded data to the service specialist.

[0010] Preferably, the steps of obtaining user account information, performing data query based on the user account information, and building a user profile database according to the data query results specifically include:

[0011] Perform data query based on the user's incoming call information to obtain user account information;

[0012] Searching a general data database based on user account information to extract the user's historical orders, wherein the historical orders include completed orders and orders in progress;

[0013] The user's predicted demand for each historical order is determined based on the operations allowed to be performed on completed orders and orders in progress. Based on the predicted demand, the corresponding order information is retrieved to build a user information database.

[0014] Preferably, the steps of processing the initial voice interaction data by a large language model to obtain an initial voice processing result, performing switching warning detection according to the initial voice processing result, and obtaining a warning detection result specifically include:

[0015] The initial voice interaction data is converted into initial text data through a voice conversion tool, and the initial text data is imported into a large language model to generate initial voice processing results;

[0016] Rewriting the initial speech processing result through a large language model to generate multiple replicated speech texts, extracting keywords from the replicated speech texts to obtain multiple keywords, the keywords including event description keywords, event feature keywords, and event requirement keywords;

[0017] Perform overlap matching with each service range data to determine the service range data that best suits the current user and generate early warning detection results.

[0018] Preferably, the steps of performing diversion processing on the real-time voice interaction record based on the early warning detection result, synchronizing it to the corresponding service device, receiving the switching instruction, and completing the seamless switching of the real-time voice specifically include:

[0019] Based on the early warning detection results, the corresponding service scope is determined, an idle service device is randomly selected, and a copy of the real-time voice interaction record is synchronously imported into the corresponding service device;

[0020] receiving readiness feedback information sent from the service device, and sending a switching instruction to the service device based on the readiness feedback information;

[0021] After the switching instruction is sent, the idle service device performs voice interaction with the user according to the switching instruction, and disconnects the voice connection between the current service device and the user.

[0022] Preferably, in the process of real-time voice communication with the user, the user profile database is processed by a large language model to provide pre-loaded data to the service specialist, including the steps of recording real-time interactive voice, converting the real-time interactive voice into real-time interactive text, analyzing the real-time interactive text by a large language model, obtaining text features mentioned in the real-time interactive text, searching the user profile database based on the text features, extracting corresponding prompt information, completing pre-loading of data based on the prompt information, obtaining pre-loaded data, and displaying the pre-loaded data to the service specialist.

[0023] Another object of the present invention is to provide a customer service interaction system based on a large language model, the system comprising:

[0024] A voice connection module is used to build a general information database, establish a voice connection with the user, record information about the voice interaction process, and obtain initial voice interaction data. The general information database records at least the service scope data of each service specialist, and the service scope data is characterized by keywords.

[0025] A database construction module is used to obtain user account information, perform data query based on the user account information, and construct a user profile database based on the data query results, wherein the user profile database includes at least historical order information;

[0026] The handover prediction module is used to process the initial voice interaction data through a large language model to obtain an initial voice processing result, and perform handover warning detection based on the initial voice processing result to obtain a warning detection result;

[0027] The seamless switching module is used to divert real-time voice interaction records based on early warning detection results, synchronize them to the corresponding service equipment, receive switching instructions, and complete seamless switching of real-time voice. During real-time voice communication with users, the user information database is processed through a large language model to provide pre-loaded data to service specialists.

[0028] Preferably, the database construction module includes:

[0029] An account information query unit, configured to query data based on the user's incoming call information to obtain the user's account information;

[0030] An order extraction unit, configured to search a general data database based on user account information to extract the user's historical orders, wherein the historical orders include completed orders and orders in progress;

[0031] The data retrieval unit is used to determine the user's predicted demand for each historical order based on the operations allowed to be executed by completed orders and orders in progress, retrieve the corresponding order data based on the predicted demand, and build a user data database.

[0032] Preferably, the handover prediction module includes:

[0033] A speech processing unit, configured to convert the initial speech interaction data into initial text data using a speech conversion tool, import the initial text data into a large language model, and generate an initial speech processing result;

[0034] A text duplication unit is used to duplicate the initial speech processing results using a large language model to generate multiple duplicate speech texts, and extract keywords from the duplicate speech texts to obtain multiple keywords, including event description keywords, event feature keywords, and event requirement keywords;

[0035] The switching early warning unit is used to match the overlap with each service range data, determine the service range data that best suits the current user, and generate early warning detection results.

[0036] Preferably, the sensorless switching module includes:

[0037] A device selection unit is used to determine the corresponding service range based on the early warning detection result, randomly select an idle service device, and synchronously import a copy of the real-time voice interaction record to the corresponding service device;

[0038] An instruction transceiver unit, configured to receive readiness feedback information sent from a service device, and send a switching instruction to the service device based on the readiness feedback information;

[0039] The voice switching unit is used to, after the switching instruction is sent, enable the idle service device to perform voice interaction with the user according to the switching instruction and disconnect the voice connection between the current service device and the user.

[0040] Preferably, in the process of real-time voice communication with the user, the user profile database is processed by a large language model to provide pre-loaded data to the service specialist, including the steps of recording real-time interactive voice, converting the real-time interactive voice into real-time interactive text, analyzing the real-time interactive text by a large language model, obtaining text features mentioned in the real-time interactive text, searching the user profile database based on the text features, extracting corresponding prompt information, completing pre-loading of data based on the prompt information, obtaining pre-loaded data, and displaying the pre-loaded data to the service specialist.

[0041] The present invention provides a customer service interaction method based on a large language model. By recording the user's voice and inputting the voice interaction process into the large language model in the form of text, the method completes the analysis of user needs and predicts whether the user needs to switch service specialists based on the interaction process with the user. When the need for switching is detected, preparations are started, and when the needs change, seamless switching of service specialists is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flowchart of a customer service interaction method based on a large language model provided by an embodiment of the present invention;

[0043] Figure 2 A flowchart of the steps of obtaining user account information, performing a data query based on the user account information, and building a user profile database based on the data query results, provided by an embodiment of the present invention;

[0044] Figure 3 A flowchart of the steps of processing initial voice interaction data using a large language model to obtain an initial voice processing result, performing handover warning detection based on the initial voice processing result, and obtaining a warning detection result, provided in an embodiment of the present invention;

[0045] Figure 4 A flowchart of the steps of performing diversion processing on real-time voice interaction records based on early warning detection results, synchronizing them to corresponding service devices, receiving switching instructions, and completing seamless switching of real-time voice according to an embodiment of the present invention;

[0046] Figure 5 An architectural diagram of a customer service interaction system based on a large language model provided by an embodiment of the present invention;

[0047] Figure 6 An architectural diagram of a database construction module provided by an embodiment of the present invention;

[0048] Figure 7 An architectural diagram of a handover prediction module provided by an embodiment of the present invention;

[0049] Figure 8 This is an architectural diagram of a senseless switching module provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0051] It is understood that the terms "first," "second," etc., used herein may be used to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script without departing from the scope of this application.

[0052] like Figure 1 FIG. 1 is a flowchart of a customer service interaction method based on a large language model provided by an embodiment of the present invention, the method comprising:

[0053] S100, building a general information database, establishing a voice connection with the user, recording information about the voice interaction process, and obtaining initial voice interaction data. The general information database records at least service scope data of each service specialist, and the service scope data is characterized by keywords.

[0054] In this step, a general information database is constructed. Whether it is an enterprise or a merchant, a large amount of information related to the enterprise or merchant will be prepared. Taking network operators as an example, network operators have many service items and types, so the purposes of calls from different users vary greatly. It is necessary to set up service specialists of various business types, such as voice package modules, network broadband modules, product sales modules, and procurement and installation modules. Different service specialists correspond to different service types. After the user answers the call, the business segment corresponding to the service specialist connected to the current user may not match the user's needs. At this time, switching is required. When there is a change in demand, such as user A needs to complete content consultation on multiple business segments during a call, it is necessary to switch service specialists multiple times. In the existing service process, the user needs to wait during the personnel switching process to access a new service specialist. The new service specialist needs to re-understand the previous conversation information, so it may be necessary to repeatedly ask the user the same question. This problem will affect the user experience. In the present invention, all required information is stored in a general information database, and a large language model is constructed. This large language model can analyze the information input by the user to extract keywords from the voice recordings between the user and the service specialist. Then, when the user establishes a voice connection with the first service specialist, the voice interaction process between the two is recorded to obtain initial voice interaction data. The general information database records at least the service scope data of each service specialist. The service scope data is characterized by keywords. For example, a type A service specialist is used to serve customers in the network broadband sector. The keywords may include: network speed, broadband, upstream bandwidth, downstream bandwidth, lag, access device, latency, downtime, and multiple keywords. When the chat record between the user and the service specialist involves the above keywords, it indicates that the user may need to contact the service specialist of the corresponding service sector. That is, the service scope data is used to determine the service scope of each service specialist.

[0055] S200, obtaining user account information, performing data query based on the user account information, and constructing a user profile database according to the data query result, wherein the user profile database includes at least historical order information.

[0056] In this step, the user account information is obtained. When the user calls, the user's caller ID is obtained. The user data can be retrieved based on the caller ID. Each number corresponds to a user. After the user is determined, the orders generated by the user in the historical process can be retrieved, and the number of orders related to the user can be stored independently to create a temporary user information database. Then, when performing data query, you only need to search the temporary user information database, which reduces the time for data query and improves the response speed.

[0057] S300: Process the initial voice interaction data through the large language model to obtain an initial voice processing result, perform switching warning detection based on the initial voice processing result, and obtain a warning detection result.

[0058] In this step, the initial voice interaction data is processed by the large language model. The initial voice interaction data stores the voice interaction records between the user and the service specialist. The voice interaction records are converted into a text conversation format through a voice conversion tool, and the converted text is imported into the large language model. The large language model is used to analyze the conversation records between the two, thereby performing keyword extraction to obtain the initial voice processing results. Based on the matching relationship between the initial voice processing results and the service scope data corresponding to each service specialist, it is determined whether there is a changing trend in the user's needs, thereby generating an early warning detection result.

[0059] S400 diverts and processes real-time voice interaction records based on early warning detection results, synchronizes them to corresponding service devices, receives switching instructions, and completes seamless switching of real-time voice. During real-time voice communication with users, the user profile database is processed through a large language model to provide pre-loaded data to service specialists.

[0060] In this step, the real-time voice interaction records are diverted based on the early warning detection results. When the early warning detection results show that the current user may need to switch services, a copy of the conversation record between the current service specialist and the user is imported into the service device of the new service specialist, and the previous conversation is processed through the large language model to generate a conversation summary, which is displayed to the new service specialist. The new service specialist can understand the interaction information between the user and the previous service specialist based on the conversation summary. After the new service specialist is ready, feedback information is sent to the service device of the previous service specialist. At this time, the previous service specialist can complete the switching of service devices at any time. When switching, the user's voice information is directly forwarded to the service device where the new service specialist is located, and the connection between the previous service specialist and the user is disconnected, realizing a seamless switching, improving user experience, and improving reception efficiency.

[0061] like Figure 2 As shown, as a preferred embodiment of the present invention, the steps of obtaining user account information, performing data query based on the user account information, and building a user profile database according to the data query results specifically include:

[0062] S201, performing data query based on the user's incoming call information to obtain user account information.

[0063] In this step, data query is performed based on the user's incoming call information. The incoming call information includes the user's calling number. By querying based on the calling number, the user's identity, including the user's name and gender, etc., can be further determined.

[0064] S202: Search the general data database based on the user account information to extract the user's historical orders, where the historical orders include completed orders and orders in progress.

[0065] In this step, a search is performed in the general information database based on the user account information, and all data related to the user stored in the general information database is retrieved based on the user account information, including historical orders. Historical orders are divided into completed orders and processing orders. For completed orders, the main body of the order has been completed. For example, the user applies for broadband installation, and the installation service has been completed, and the user is in the process of normal use. Processing orders refer to orders that the user has submitted an order application but have not yet been executed.

[0066] S203, determining the user's predicted demand for each historical order based on the operations allowed to be executed by the completed orders and the orders in progress, retrieving the corresponding order information based on the predicted demand, and constructing a user information database.

[0067] In this step, the user's predicted demand for each historical order is determined based on the operations allowed for completed orders and orders in progress. Different types of orders have different allowed operations. For example, if user A purchases product B, the order has been completed and the return and exchange period has expired, the order only allows the user to issue invoices or perform after-sales operations for quality issues. For ongoing orders, exchange operations, return operations, and product consultation operations can be performed. The above-mentioned allowed operations are stored in the user information database as the predicted demand for each historical order of the user. When the user mentions the corresponding order, the service scope can be narrowed.

[0068] like Figure 3 As shown, as a preferred embodiment of the present invention, the steps of processing the initial voice interaction data by a large language model to obtain an initial voice processing result, performing switching warning detection according to the initial voice processing result, and obtaining a warning detection result specifically include:

[0069] S301, converting the initial voice interaction data into initial text data through a voice conversion tool, importing the initial text data into a large language model, and generating an initial voice processing result.

[0070] In this step, the initial voice interaction data is converted into initial text data through a voice conversion tool. The voice conversion tool is a voice recognition engine. The voice of the conversation between the user and the service specialist is input into it, and the corresponding conversation text can be output, which is the initial voice processing result.

[0071] S302, the initial speech processing result is replicated by a large language model to generate multiple replicated speech texts, and keywords are extracted from the replicated speech texts to obtain multiple keywords, including event description keywords, event feature keywords, and event requirement keywords.

[0072] In this step, the initial speech processing results are replicated using a large language model. The large language model has replication capabilities and can convert the same text into multiple communication methods with the same topic. For example, "I have a broadband connection at your home. The bandwidth was originally 300M, but it has been very unstable in the past two days. It was not stuck before, but now it often freezes." After replication, it can be "I have a network connection at your home. The network has fluctuated greatly recently, and the network speed has dropped from time to time. The bandwidth is 300M, but now it is often not reached." After multiple replications, the number of texts is increased, and multiple replicated speech texts are obtained. The large language model is used to extract keywords recorded in the replicated speech texts and classify the keywords, including event description keywords, event feature keywords, and event demand keywords. Among them, event description keywords are used to determine the nature of the event, such as broadband, mobile network, bandwidth, etc. Event feature keywords are specific features about the event, such as network lag, high latency, slow network speed, etc. Event demand keywords are the user's requirements for the event, such as on-site repair, bandwidth increase, and cancellation.

[0073] S303: Perform overlap matching with each service range data to determine the service range data that best suits the current user and generate an early warning detection result.

[0074] In this step, the overlap is matched with each service scope data. The service specialist corresponds to one service scope data. The number of times each keyword appears in each service scope data is determined by extracting the event description keywords, event feature keywords and event demand keywords. Specifically, a weight is assigned to each keyword to calculate the number of keywords that fall into each service scope data. For example, the weight of the event description keyword is 0.2, the weight of the event feature keyword is 0.3, and the weight of the event demand keyword is 0.5. If an event description keyword falls into the corresponding service scope data, it is regarded as a keyword that appears 0.2 times in the service scope data. After the statistics are completed, the number of times the keyword corresponding to each service scope data appears is determined, and the number ratio is calculated. If there are three service scope data, they are A, B, C, and D, respectively. , B and C, in the current conversation process, the number of keywords that fall into A's service scope data is P1, the number of keywords that fall into B's service scope data is P2, and the number of keywords that fall into C's service scope data is P3. Then the corresponding frequency ratios of A, B and C are P1 / (P1+P2+P3), P2 / (P1+P2+P3), and P3 / (P1+P2+P3). When the frequency ratio is greater than the preset value, it is determined that there is a service demand that falls into the corresponding service scope data. For example, the preset value is 0.7. When P3 / (P1+P2+P3), it means that the user's current demand is in the C service scope. If the user is currently communicating with the service specialist corresponding to the C service scope data, there is no switching demand. If the user is not currently communicating with the service specialist corresponding to the C service scope data, it is determined that there is a switching demand.

[0075] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of performing diversion processing on the real-time voice interaction record based on the early warning detection result, synchronizing it to the corresponding service device, receiving the switching instruction, and completing the seamless switching of the real-time voice specifically include:

[0076] S401, determining the corresponding service range based on the early warning detection result, randomly selecting an idle service device, and synchronously importing a copy of the real-time voice interaction record to the corresponding service device.

[0077] In this step, the corresponding service scope is determined based on the early warning detection results. For example, if the early warning detection results determine that the current user's needs fall from the M service scope to the N service scope, then idle service personnel within the N service scope are queried, an idle service personnel is randomly selected, and a copy of the real-time voice interaction record is synchronously imported into the corresponding service device. At this time, the service personnel corresponding to the service device can directly hear the conversation between the current service personnel and the user, and the previous conversation is processed through the large language model to generate a conversation summary, which is displayed to the new service specialist.

[0078] S402: Receive readiness feedback information sent from the service device, and send a switching instruction to the service device based on the readiness feedback information.

[0079] S403: After the switching instruction is sent, the idle service device performs voice interaction with the user according to the switching instruction, and disconnects the voice connection between the current service device and the user.

[0080] In this step, readiness feedback information is received from the service device. When the new service specialist fully understands the previous conversation information, the new service specialist sends readiness feedback information to the service device corresponding to the current service specialist. At this time, the service specialist currently connected to the user can switch services at any time. When the service switch is determined, the idle service device interacts with the user by voice according to the switching instruction, and disconnects the voice connection between the current service device and the user. The above switching process can be repeated multiple times. During the service of the service specialist, the real-time interactive voice is converted into real-time interactive text. The real-time interactive text is analyzed by a large language model to obtain text features mentioned in the real-time interactive text. Based on the text features, the user information database is searched to extract the corresponding prompt information. Based on the prompt information, the data is preloaded to obtain the preloaded data, which is then displayed to the service specialist.

[0081] like Figure 5 As shown, a customer service interaction system based on a large language model provided by an embodiment of the present invention includes:

[0082] The voice connection module 100 is used to build a general information database, establish a voice connection with the user, record information about the voice interaction process, and obtain initial voice interaction data. The general information database records at least the service scope data of each service specialist, and the service scope data is characterized by keywords.

[0083] In this system, the voice connection module 100 builds a general information database. Whether it is an enterprise or a merchant, a large amount of information related to the enterprise or merchant will be prepared. Taking network operators as an example, network operators have many service items and types. Therefore, the purposes of calls from different users vary greatly, and it is necessary to set up service specialists of various business types, such as voice package modules, network broadband modules, product sales modules, and procurement and installation modules. Different service specialists correspond to different service types. After the user answers the call, the business segment corresponding to the service specialist connected to the current user may not match the user's needs. At this time, switching is required. When there is a change in demand, such as user A needs to complete content consultation on multiple business segments during a call, it is necessary to switch service specialists multiple times. In the existing service process, the user needs to wait during the personnel switching process to connect to a new service specialist. The new service specialist needs to re-understand the previous conversation information, so it may be necessary to repeat the conversation with the user. Asking the same questions will affect the user experience. In the present invention, all required information is stored in a general information database, and a large language model is constructed. This large language model can analyze the information input by the user to extract keywords from the voice recordings between the user and the service specialist. Then, when the user establishes a voice connection with the first service specialist, the voice interaction process between the two is recorded to obtain initial voice interaction data. The general information database records at least the service scope data of each service specialist. This service scope data is characterized by keywords. For example, a type A service specialist serves customers in the network broadband sector. Their keywords may include: network speed, broadband, upstream bandwidth, downstream bandwidth, lag, access device, latency, downtime, and multiple keywords. When the chat record between the user and the service specialist contains these keywords, it indicates that the user may need to contact the service specialist of the corresponding service sector. In other words, the service scope data is used to determine the service scope of each service specialist.

[0084] The database construction module 200 is used to obtain user account information, perform data query based on the user account information, and construct a user profile database according to the data query results. The user profile database at least includes historical order information.

[0085] In this system, the database construction module 200 obtains user account information. When a user calls, the user's caller ID is obtained. User data can be retrieved based on the caller ID. Each number corresponds to a user. After the user is determined, the orders generated by the user in the historical process can be retrieved, and the number of orders related to the user can be stored independently to create a temporary user information database. Then, when performing data query, only the temporary user information database needs to be retrieved, which reduces the time for data query and improves the response speed.

[0086] The switching prediction module 300 is used to process the initial voice interaction data through a large language model to obtain an initial voice processing result, and perform switching warning detection based on the initial voice processing result to obtain a warning detection result.

[0087] In this system, the handover prediction module 300 processes the initial voice interaction data using a large language model. The initial voice interaction data stores the voice interaction records between the user and the service specialist. The voice interaction records are converted into a text conversation format using a voice conversion tool, and the converted text is imported into the large language model. The large language model is used to analyze the conversation records between the two, thereby performing keyword extraction and obtaining the initial voice processing results. Based on the matching relationship between the initial voice processing results and the service scope data corresponding to each service specialist, it is determined whether there is a trend of change in the user's needs, thereby generating an early warning detection result.

[0088] The seamless switching module 400 is used to divert the real-time voice interaction records based on the early warning detection results, synchronize them to the corresponding service equipment, receive switching instructions, and complete the seamless switching of real-time voice. During the real-time voice conversation with the user, the user information database is processed through the large language model to provide pre-loaded data to the service specialist.

[0089] In this system, the seamless switching module 400 diverts the real-time voice interaction records based on the early warning detection results. When the early warning detection results show that the current user may need to switch services, a copy of the conversation record between the current service specialist and the user is imported into the service device of the new service specialist, and the previous conversation is processed through the large language model to generate a conversation summary, which is displayed to the new service specialist. The new service specialist can understand the interaction information between the user and the previous service specialist based on the conversation summary. After the new service specialist is ready, feedback information is sent to the service device of the previous service specialist. At this time, the previous service specialist can complete the switching of service devices at any time. When switching, the user's voice information is directly forwarded to the service device where the new service specialist is located, and the connection between the previous service specialist and the user is disconnected, realizing seamless switching, improving user experience, and improving reception efficiency.

[0090] like Figure 6 As shown, as a preferred embodiment of the present invention, the database construction module 200 includes:

[0091] The account information query unit 201 is used to perform data query based on the user's incoming call information to obtain the user's account information.

[0092] In this module, the account information query unit 201 performs data query based on the user's incoming call information, which includes the user's calling number. By querying based on the calling number, the user's identity, including the user's name and gender, can be further determined.

[0093] The order extraction unit 202 is used to search the general information database based on the user account information and extract the user's historical orders, which include completed orders and orders in progress.

[0094] In this module, the order extraction unit 202 searches the general information database based on the user account information, and retrieves all data related to the user stored in the general information database based on the user account information, including historical orders. Historical orders are divided into completed orders and processing orders. For completed orders, the main body of the order has been completed. For example, the user applies for broadband installation, and the installation service has been completed, and the user is in normal use. The processing order refers to an order that the user has submitted an order application but has not yet been executed.

[0095] The data retrieval unit 203 is used to determine the user's predicted demand for each historical order based on the operations allowed to be executed by the completed orders and the orders in progress, retrieve the corresponding order data based on the predicted demand, and build a user data database.

[0096] In this module, the data retrieval unit 203 determines the user's predicted demand for each historical order based on the operations allowed for completed orders and orders in progress. Different types of orders have different allowed operations. For example, if user A purchases product B, the order has been completed and the return and exchange period has expired, then the order only allows the user to perform invoice issuance operations or after-sales operations for quality issues. For ongoing orders, exchange operations, return operations, and product consultation operations can be performed. The above-mentioned allowed operations are stored in the user data database as the predicted demand for each historical order of the user. When the user mentions the corresponding order, the service scope can be narrowed.

[0097] like Figure 7 As shown, as a preferred embodiment of the present invention, the handover prediction module 300 includes:

[0098] The speech processing unit 301 is used to convert the initial speech interaction data into initial text data through a speech conversion tool, import the initial text data into the large language model, and generate an initial speech processing result.

[0099] In this module, the speech processing unit 301 converts the initial speech interaction data into initial text data through a speech conversion tool. The speech conversion tool is a speech recognition engine. The speech of the conversation between the user and the service specialist is input into it, and the corresponding conversation text can be output, which is the initial speech processing result.

[0100] The text duplication unit 302 is used to duplicate the initial speech processing results through a large language model to generate multiple duplicate speech texts, extract keywords from the duplicate speech texts, and obtain multiple keywords, including event description keywords, event feature keywords, and event requirement keywords.

[0101] In this module, the text replication unit 302 replicates the initial speech processing result through the large language model. The large language model has replication capabilities and can convert the same text into multiple communication methods with the same topic, such as "I have a broadband at your house. It was originally said to have a 300M bandwidth, but it has been very unstable in the past two days. It was not stuck before, but now it often freezes." After replication, it can be "I have a network at your house. The network has fluctuated greatly recently, and the network speed has dropped from time to time. The bandwidth is 300M, but now it is often not reached." After multiple replications, the number of texts is increased, and multiple replicated voice texts are obtained. The large language model is used to extract the keywords recorded in the replicated voice texts and classify the keywords, including event description keywords, event feature keywords, and event demand keywords. Among them, the event description keywords are used to determine the nature of the event, such as broadband, mobile network, bandwidth, etc. The event feature keywords are specific features about the event, such as network freeze, high latency, slow network speed, etc. The event demand keywords are the needs proposed by the user for the event, such as on-site repair, bandwidth increase, cancellation, etc.

[0102] The switching warning unit 303 is used to perform overlap matching with each service range data, determine the service range data that is most suitable for the current user, and generate a warning detection result.

[0103] In this module, the switching warning unit 303 performs overlap matching with each service scope data. A service specialist corresponds to one service scope data. The number of times each keyword appears in each service scope data is determined by extracting the event description keywords, event feature keywords, and event demand keywords. Specifically, a weight is assigned to each keyword to calculate the number of keywords that fall into each service scope data. For example, the weight of the event description keyword is 0.2, the weight of the event feature keyword is 0.3, and the weight of the event demand keyword is 0.5. If an event description keyword falls into the corresponding service scope data, it is regarded as a keyword that appears 0.2 times in the service scope data. After the statistics are completed, the number of times the keyword corresponding to each service scope data appears is determined, and the ratio of the number of times is calculated. If there are three service scope data, They are A, B and C respectively. During the current conversation, the number of keywords that fall into the service scope data of A is P1, the number of keywords that fall into the service scope data of B is P2, and the number of keywords that fall into the service scope data of C is P3. Then the corresponding frequency ratios of A, B and C are P1 / (P1+P2+P3), P2 / (P1+P2+P3), and P3 / (P1+P2+P3). When the frequency ratio is greater than the preset value, it is determined that there is a service demand that falls into the corresponding service scope data. For example, the preset value is 0.7. When P3 / (P1+P2+P3), it means that the user's current demand is in the service scope of C. If the user is currently communicating with the service specialist corresponding to the service scope data of C, there is no switching demand. If the user is not currently communicating with the service specialist corresponding to the service scope data of C, it is determined that there is a switching demand.

[0104] like Figure 8 As shown, as a preferred embodiment of the present invention, the senseless switching module 400 includes:

[0105] The device selection unit 401 is used to determine the corresponding service range based on the early warning detection result, randomly select an idle service device, and synchronously import a copy of the real-time voice interaction record to the corresponding service device.

[0106] In this module, the device selection unit 401 determines the corresponding service scope based on the early warning detection result. If the early warning detection result determines that the current user's needs fall from the M service scope to the N service scope, then the idle service personnel within the N service scope are queried, and an idle service personnel is randomly selected. A copy of the real-time voice interaction record is synchronously imported into the corresponding service device. At this time, the service personnel corresponding to the service device can directly hear the conversation between the current service personnel and the user, and the previous conversation is processed through the large language model to generate a conversation summary, which is displayed to the new service specialist.

[0107] The instruction transceiver unit 402 is configured to receive readiness feedback information sent from the service device, and send a switching instruction to the service device based on the readiness feedback information.

[0108] The voice switching unit 403 is configured to, after the switching instruction is sent, enable the idle service device to perform voice interaction with the user according to the switching instruction and disconnect the voice connection between the current service device and the user.

[0109] In this module, readiness feedback information is received from the service device. When the new service specialist fully understands the previous conversation information, the new service specialist sends readiness feedback information to the service device corresponding to the current service specialist. At this time, the service specialist currently connected to the user can switch services at any time. When the service switch is determined, the idle service device interacts with the user through voice according to the switching instruction, and disconnects the voice connection between the current service device and the user. The above switching process can be repeated multiple times. During the service of the service specialist, the real-time interactive voice is converted into real-time interactive text. The real-time interactive text is analyzed by a large language model to obtain the text features mentioned in the real-time interactive text. The user information database is searched based on the text features to extract the corresponding prompt information. The data is preloaded based on the prompt information to obtain the preloaded data, which is then displayed to the service specialist.

[0110] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0111] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0112] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0113] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A customer service interaction method based on a large language model, characterized in that: The method comprises: Constructing a general information database, establishing a voice connection with the user, and recording information about the voice interaction process to obtain initial voice interaction data. The general information database records at least service scope data of each service specialist, and the service scope data is characterized by keywords. Obtaining user account information, performing a data query based on the user account information, and building a user profile database based on the data query results, wherein the user profile database includes at least historical order information; The initial voice interaction data is processed by a large language model to obtain an initial voice processing result, and a switching warning detection is performed based on the initial voice processing result to obtain a warning detection result; Based on the early warning detection results, the real-time voice interaction records are diverted and synchronized to the corresponding service equipment. After receiving the switching instructions, the real-time voice switching is completed seamlessly. During the real-time voice conversation with the user, the user information database is processed through the large language model to provide pre-loaded data to the service specialist.

2. The customer service interaction method based on a large language model according to claim 1, characterized in that: The steps of obtaining user account information, performing data query based on the user account information, and building a user profile database based on the data query results specifically include: Perform data query based on the user's incoming call information to obtain user account information; Searching a general data database based on user account information to extract the user's historical orders, wherein the historical orders include completed orders and orders in progress; The user's predicted demand for each historical order is determined based on the operations allowed to be performed on completed orders and orders in progress. Based on the predicted demand, the corresponding order information is retrieved to build a user information database.

3. The customer service interaction method based on a large language model according to claim 1, characterized in that: The steps of processing the initial voice interaction data using the large language model to obtain an initial voice processing result, performing switching warning detection based on the initial voice processing result, and obtaining a warning detection result specifically include: The initial voice interaction data is converted into initial text data through a voice conversion tool, and the initial text data is imported into a large language model to generate initial voice processing results; Rewriting the initial speech processing result through a large language model to generate multiple replicated speech texts, extracting keywords from the replicated speech texts to obtain multiple keywords, the keywords including event description keywords, event feature keywords, and event requirement keywords; Perform overlap matching with each service range data to determine the service range data that best suits the current user and generate early warning detection results.

4. The customer service interaction method based on a large language model according to claim 1, characterized in that: The steps of performing diversion processing on the real-time voice interaction record based on the early warning detection result, synchronizing it to the corresponding service device, receiving the switching instruction, and completing the seamless switching of the real-time voice specifically include: Based on the early warning detection results, the corresponding service scope is determined, an idle service device is randomly selected, and a copy of the real-time voice interaction record is synchronously imported into the corresponding service device; receiving readiness feedback information sent from the service device, and sending a switching instruction to the service device based on the readiness feedback information; After the switching instruction is sent, the idle service device performs voice interaction with the user according to the switching instruction, and disconnects the voice connection between the current service device and the user.

5. The customer service interaction method based on a large language model according to claim 1, characterized in that: The step of processing the user profile database through the large language model during real-time voice communication with the user and providing preloaded data to the service specialist includes: recording the real-time interactive voice, converting the real-time interactive voice into real-time interactive text, analyzing the real-time interactive text through the large language model to obtain text features mentioned in the real-time interactive text, searching the user profile database based on the text features to extract corresponding prompt information, completing preloading of data based on the prompt information, obtaining preloaded data, and displaying the preloaded data to the service specialist.

6. A customer service interaction system based on a large language model, characterized in that: The system comprises: A voice connection module is used to build a general information database, establish a voice connection with the user, record information about the voice interaction process, and obtain initial voice interaction data. The general information database records at least the service scope data of each service specialist, and the service scope data is characterized by keywords. A database construction module is used to obtain user account information, perform data query based on the user account information, and construct a user profile database based on the data query results, wherein the user profile database includes at least historical order information; The handover prediction module is used to process the initial voice interaction data through a large language model to obtain an initial voice processing result, and perform handover warning detection based on the initial voice processing result to obtain a warning detection result; The seamless switching module is used to divert real-time voice interaction records based on early warning detection results, synchronize them to the corresponding service equipment, receive switching instructions, and complete seamless switching of real-time voice. During real-time voice communication with users, the user information database is processed through a large language model to provide pre-loaded data to service specialists.

7. The customer service interaction system based on a large language model according to claim 6, characterized in that: The database construction module includes: An account information query unit, configured to query data based on the user's incoming call information to obtain the user's account information; An order extraction unit, configured to search a general data database based on user account information to extract the user's historical orders, wherein the historical orders include completed orders and orders in progress; The data retrieval unit is used to determine the user's predicted demand for each historical order based on the operations allowed to be executed by completed orders and orders in progress, retrieve the corresponding order data based on the predicted demand, and build a user data database.

8. The customer service interaction system based on a large language model according to claim 6, characterized in that: The switching prediction module includes: A speech processing unit, configured to convert the initial speech interaction data into initial text data using a speech conversion tool, import the initial text data into a large language model, and generate an initial speech processing result; A text duplication unit is used to duplicate the initial speech processing results using a large language model to generate multiple duplicate speech texts, and extract keywords from the duplicate speech texts to obtain multiple keywords, including event description keywords, event feature keywords, and event requirement keywords; The switching early warning unit is used to match the overlap with each service range data, determine the service range data that best suits the current user, and generate early warning detection results.

9. The customer service interaction system based on a large language model according to claim 6, characterized in that: The sensorless switching module includes: A device selection unit is used to determine the corresponding service range based on the early warning detection result, randomly select an idle service device, and synchronously import a copy of the real-time voice interaction record to the corresponding service device; An instruction transceiver unit, configured to receive readiness feedback information sent from a service device, and send a switching instruction to the service device based on the readiness feedback information; The voice switching unit is used to, after the switching instruction is sent, enable the idle service device to perform voice interaction with the user according to the switching instruction and disconnect the voice connection between the current service device and the user.

10. The customer service interaction system based on a large language model according to claim 6, characterized in that: In the process of real-time voice communication with the user, the user data database is processed by the large language model to provide the service specialist with pre-loaded data, including: recording the real-time interactive voice, converting the real-time interactive voice into real-time interactive text, analyzing the real-time interactive text through the large language model, and obtaining Take the text features mentioned in the real-time interactive text and search the user information database based on the text features. Extract the corresponding prompt information, complete the preloading of data based on the prompt information, and obtain the preloaded data. Display preloaded data to service specialists.

Images