CN117390153A - Session content analysis method, device and storage medium applied to customer service system - Google Patents

Session content analysis method, device and storage medium applied to customer service system Download PDF

Info

Publication number
CN117390153A
CN117390153A CN202311305240.8A CN202311305240A CN117390153A CN 117390153 A CN117390153 A CN 117390153A CN 202311305240 A CN202311305240 A CN 202311305240A CN 117390153 A CN117390153 A CN 117390153A
Authority
CN
China
Prior art keywords
customer service
analysis
session content
detection
service system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311305240.8A
Other languages
Chinese (zh)
Inventor
李鹏飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Shuhe Information Technology Co Ltd
Original Assignee
Shanghai Shuhe Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Shuhe Information Technology Co Ltd filed Critical Shanghai Shuhe Information Technology Co Ltd
Priority to CN202311305240.8A priority Critical patent/CN117390153A/en
Publication of CN117390153A publication Critical patent/CN117390153A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/332—Query formulation
    • G06F16/3329—Natural language query formulation or dialogue systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0613—Third-party assisted
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

The application relates to a session content analysis method, a session content analysis device, a session content analysis computer device and a session content storage medium applied to a customer service system, wherein the session content analysis method comprises the steps of receiving session content of a user terminal; based on the large language model and the prompt engineering technology, carrying out any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis on the session content, and displaying recommended content on a front-end page of the customer service system based on an analysis result; and performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on a front-end page of the customer service system. According to the method, the session content of the customer service system can be subjected to multiple analysis guidance and multiple detection by fully utilizing a large language model and a prompt engineering technology, recommended content and detection results are displayed on a front page of the customer service system, and intelligent customer analysis service is provided for the customer service system.

Description

Session content analysis method, device and storage medium applied to customer service system
Technical Field
The present invention relates to the field of customer service system session processing technologies, and in particular, to a session content analysis method, apparatus, computer device, and storage medium applied to a customer service system.
Background
Customer service plays a key role in enterprise business model, providing customers with excellent experience at various stages of product or service, while improving customer satisfaction and loyalty. However, the current customer service system faces challenges including "problem identification, problem distribution, and problem solving" in three stages, including high cost, poor effect, and low efficiency, when guiding the customer into the service flow. For example, customer service agents have difficulty in quickly and accurately identifying customer problems, and it takes a long time to select an applicable service flow and the judgment is not accurate enough, and when the service flow is executed, the service flow may deviate from the standard, resulting in situations such as irregular flow or increased communication pressure.
Disclosure of Invention
Based on the above, it is necessary to provide a session content analysis method, apparatus, computer device and storage medium for a customer service system, which can make full use of a large language model and prompt engineering technology to conduct multiple analysis, guidance and multiple detection on session content of the customer service system, display recommended content and detection results on a front page of the customer service system, provide intelligent customer analysis service for the customer service system, enable customer service agents to quickly and accurately understand customer intention in service process, make decisions and execute service process, and normalize and record service process.
A session content analysis method applied to a customer service system comprises the following steps: receiving session content of a user terminal; based on the large language model and the prompt engineering technology, carrying out any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis on the session content, and displaying recommended content on a front-end page of the customer service system based on an analysis result; and performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on a front-end page of the customer service system.
In one embodiment, any one of flow guidance analysis, knowledge guidance analysis and worksheet tutorial analysis is performed on session content based on a large language model and a prompt engineering technology, and recommended content is displayed on a front-end page of a customer service system based on an analysis result, including: carrying out flow guiding analysis on session content based on a large language model and a prompt engineering technology, identifying flow intention of the session content, identifying corresponding business query flow according to the flow intention when the flow intention is consultation business related information, and displaying the corresponding business query flow on a front-end page of a customer service system so as to guide a customer service agent and/or a user to enter the corresponding business query flow; and/or, carrying out knowledge guide analysis on the session content based on the large language model and the prompt engineering technology, identifying the knowledge intention of the session content, determining knowledge points according to the knowledge intention, and displaying the knowledge points on a front-end page of the customer service system so as to enable a user to know the knowledge points; and/or carrying out worksheet coaching analysis on the conversation content based on the large language model and the prompt engineering technology, identifying worksheet element information of the conversation content, determining worksheet elements to be filled according to the worksheet element information, and displaying the worksheet elements to be filled on a front-end page of the customer service system so that a user fills in worksheets based on the worksheet elements to be filled.
In one embodiment, any one of intent detection, emotion detection and customer service quality detection is performed based on the context of session content, and the detection result is displayed on a front-end page of a customer service system, including: performing intention detection based on the context of the session content, identifying user intention, and displaying the user intention on a front-end page of the customer service system; and/or, carrying out emotion detection based on the context of the session content, identifying the emotion state of the user, and displaying the emotion state of the user on a front-end page of the customer service system; and/or, based on the context of the session content, performing customer service quality detection on each flow of the customer service full link, identifying the customer service quality of each flow, and displaying the customer service quality of each flow on a front-end page of the customer service system.
In one embodiment, performing any one of a flow guidance analysis, a knowledge guidance analysis, and a worksheet coaching analysis on session content based on a large language model and prompt engineering techniques, includes: when detecting that the session content is any one of a problem understanding node, a problem distribution node, a problem handling node and a service evaluation node of the customer service full link, performing any one of flow guidance analysis, knowledge guidance analysis and worksheet coaching analysis on the session content based on a large-scale language model and a prompt engineering technology; any one of intent detection, emotion detection, and customer service quality of service detection is performed based on the context of the session content, including: when detecting that the session content is any one of a problem understanding node, a problem distributing node and a problem handling node of the customer service full link, performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content; and when detecting that the session content is a service evaluation node of the customer service full link, performing any one of emotion detection and customer service quality detection based on the context of the session content.
In one embodiment, receiving session content of a user terminal includes: receiving a streaming translation text input by a voice recognition module, wherein the voice recognition module is used for converting a voice stream input by a call center into the streaming translation text, and the call center receives the voice stream initiated by a user client through a media gateway; and/or receiving customer service information and/or user information sent by a customer service system, wherein the customer service system obtains the customer service information and/or the user information through an online customer service, and the online customer service receives the user information sent by a user through an application gateway; the session content of the user terminal comprises streaming translation text, customer service information and user information.
In one embodiment, displaying recommended content on a front-end page of a customer service system based on an analysis result includes: and displaying the recommended content corresponding to the analysis result of any one of the flow guide analysis, the knowledge guide analysis and the work order coaching analysis to a text conversation box of a front-end page of the customer service system through an auxiliary front-end component, so that a user can know the corresponding recommended content through the text conversation box.
In one embodiment, the displaying the detection result on the front end page of the customer service system includes: and displaying the detection result of any one of the intention detection, the emotion detection and the customer service quality detection to a front-end page of the customer service system through an auxiliary front-end component.
A session content analysis apparatus applied to a customer service system, comprising: the receiving module is used for receiving the session content of the user terminal; the analysis module is used for carrying out any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis on the session content based on the large-scale language model and the prompt engineering technology, and displaying recommended content on a front-end page of the customer service system based on an analysis result; the detection module is used for carrying out any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on a front-end page of the customer service system.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods of the embodiments described above when the computer program is executed by the processor.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the embodiments described above.
The session content analysis method, the session content analysis device, the computer equipment and the storage medium applied to the customer service system are used for receiving the session content of the user terminal, performing any one of flow guide analysis, knowledge guide analysis and job ticket tutorial analysis on the session content based on a large language model and a prompt engineering technology, displaying recommended content on a front-end page of the customer service system based on an analysis result, performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on the front-end page of the customer service system. Therefore, the session content of the customer service system can be subjected to multiple analysis, guidance and multiple detection by fully utilizing a large language model and a prompt engineering technology, recommended content and detection results are displayed on a front-end page of the customer service system, and intelligent customer analysis service is provided for the customer service system, so that customer intention can be rapidly and accurately understood by a customer service agent in the service process, decision can be made, the service process can be executed, and the service process can be recorded in a standardized manner.
Drawings
FIG. 1 is an application environment diagram of a session content analysis method applied to a customer service system in one embodiment;
FIG. 2 is a flow chart of a method for analyzing session content applied to a customer service system according to an embodiment;
FIG. 3 is a partial architectural diagram of a customer service system configured with a customer service agent assistance system in one embodiment;
FIG. 4 is a schematic diagram of flow directed analysis in one embodiment of a particular application;
FIG. 5 is a schematic diagram of a customer service flow of a customer service system in one embodiment;
FIG. 6 is a partial architectural diagram of a customer service system in one embodiment;
FIG. 7 is a block diagram of a session content analysis apparatus in one embodiment;
fig. 8 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The session content analysis method applied to the customer service system is applied to an application environment shown in fig. 1. As shown in fig. 1, a customer service agent auxiliary system is configured in the customer service system, and the customer service agent auxiliary system is a software system for implementing a session content analysis method in the application. Specifically, the customer service agent auxiliary system receives session content of the user terminal, and performs guidance class processing and detection class processing on the session content. The guidance class processing comprises any one of flow guidance analysis, knowledge guidance analysis and worksheet coaching analysis on the session content based on a large language model and prompt engineering technology. And the customer service agent auxiliary system displays recommended content on a front-end page of the customer service system based on the analysis result. The detection class processing comprises any one of intention detection, emotion detection and customer service quality detection based on the context of the conversation content, and the customer service agent auxiliary system displays detection results on a front-end page of the customer service system.
In one embodiment, as shown in fig. 2, a method for analyzing session content applied to a customer service system is provided, and the method is applied to the customer service agent auxiliary system in fig. 1 for illustration, and includes the following steps:
s202, receiving session content of the user terminal.
In this embodiment, the session content of the user terminal may be voice content or text content. The voice content is accessed into a customer service seat auxiliary system of the customer service system through a telephone channel. The text content is accessed into a customer service agent auxiliary system of the customer service system through an online channel. The session content includes communication content of the user with the customer service agent.
S204, performing any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis on the session content based on the large language model and the prompt engineering technology, and displaying recommended content on a front-end page of the customer service system based on an analysis result.
In this embodiment, the guidance class process provided by the customer service agent assistance system includes a flow guidance analysis, a knowledge guidance analysis, and a worksheet guidance analysis. Specifically, the flow directs the analysis: by combining the context with a Large Language Model (LLM) and prompt engineering (Prompt Engineering, PE), flow intent in the session content is identified and the corresponding service flow is selected for standard flow processing (Standard Operation Procedure, SOP). After entering the service flow, the embedding capability of the LLM is utilized to realize the forgiving identification of the flow branches. Through iteration of SOP, standardization, high efficiency and flow of the business flow are realized. Knowledge guide analysis: based on the context, by combining LLM and PE, the accurate identification of the closed task and the content generation of the open task are improved, so that the closed task is more attached, natural, coherent and diversified. Worksheet coaching analysis: and intelligent extraction of the work order elements and structural generation of the work order description are realized by using LLM and PE. Meanwhile, the fine adjustment and prompt capability of LLM are fully exerted.
In one example, the foregoing process guidance analysis, knowledge guidance analysis, and worksheet tutorial analysis are performed on the session content based on the large language model and the prompt engineering technology, and the recommended content is displayed on a front-end page of the customer service system based on the analysis result, including: carrying out flow guiding analysis on session content based on a large language model and a prompt engineering technology, identifying flow intention of the session content, identifying corresponding business query flow according to the flow intention when the flow intention is consultation business related information, and displaying the corresponding business query flow on a front-end page of a customer service system so as to guide a customer service agent and/or a user to enter the corresponding business query flow; and/or, carrying out knowledge guide analysis on the session content based on the large language model and the prompt engineering technology, identifying the knowledge intention of the session content, determining knowledge points according to the knowledge intention, and displaying the knowledge points on a front-end page of the customer service system so as to enable a user to know the knowledge points; and/or carrying out worksheet coaching analysis on the conversation content based on the large language model and the prompt engineering technology, identifying worksheet element information of the conversation content, determining worksheet elements to be filled according to the worksheet element information, and displaying the worksheet elements to be filled on a front-end page of the customer service system so that a user fills in worksheets based on the worksheet elements to be filled.
Specifically, as shown in fig. 3, the customer continuously inputs voice or text from the terminal to the customer service agent auxiliary system. The customer service agent auxiliary system inputs all current session contents into analysis modules such as flow guidance, knowledge guidance, work order guidance and the like, recommends agents to enter the flow in the form of flow guidance, knowledge guidance, work order guidance, or checks recommended knowledge points, or helps to identify and fill work order elements, such as work order elements such as work order type, repayment mode and the like, through dialogue, and the recommended contents are displayed on a front-end page of the customer service system, as shown in fig. 3.
For example, when the customer service agent and the customer communicate with each other in voice or text, the customer service agent auxiliary system continuously analyzes all the texts sent by the customer, and extracts the flow intention of the customer. As shown in fig. 4, when analysis is carried out on sentence 2, the system analyzes that the intention of the client is "call in" and the system does not trigger any flow; when analyzing the 4 th sentence, the system analyzes that the intention of the client is "consultation overdue problem", and the system triggers the "overdue knowledge inquiry" flow to guide the seat to enter the "overdue knowledge inquiry" flow; when analyzing the 5 th sentence, the system analyzes that the intention of the client is 'doubt overdue result', and the system does not trigger any flow; when analysis of sentence 8 is completed, the system analyzes that the intention of the customer is "presumed overdue reason", and the system triggers a "repayment inquiry flow", and guides the agent and the customer to enter the "repayment inquiry flow".
Therefore, in the real-time communication between the customer service agent and the customer, real-time flow guidance, knowledge guidance and worksheet coaching can be provided for the customer, the intention of the customer can be rapidly and accurately understood, decisions can be made and service flows can be executed.
And S206, performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on a front-end page of the customer service system.
In this embodiment, the detection class process provided by the customer service agent auxiliary system includes intent detection, emotion detection, and customer service quality of service detection. Specifically, intent detection: the method mainly solves the problem of intention deduction based on context, flexibly configures intention recognition, realizes structural recognition of intention, and is convenient for strategy triggering of an application system. Emotion detection: similar to the intention recognition, the problem of emotion recognition is solved. Customer service quality detection: by prompting and fine tuning, the configuration and the use mode of the quality inspection rule are reconstructed, and GPU resources are better scheduled in terms of instantaneity, so that the instantaneity of quality inspection is realized.
In one embodiment, the detecting of any one of intent detection, emotion detection and customer service quality detection based on the context of the session content, displaying the detection result on a front-end page of the customer service system includes: performing intention detection based on the context of the session content, identifying user intention, and displaying the user intention on a front-end page of the customer service system; and/or, carrying out emotion detection based on the context of the session content, identifying the emotion state of the user, and displaying the emotion state of the user on a front-end page of the customer service system; and/or, based on the context of the session content, performing customer service quality detection on each flow of the customer service full link, identifying the customer service quality of each flow, and displaying the customer service quality of each flow on a front-end page of the customer service system.
Specifically, as shown in fig. 3, the customer continuously inputs voice or text from the terminal to the customer service agent auxiliary system. The customer service agent auxiliary system inputs all the current session contents into an intention detection, emotion detection, customer service quality detection and other analysis modules, and displays the detected intention, emotion, customer service quality and the like in the form of intention detection, emotion detection, customer service quality detection, and the like, as shown in fig. 3.
For example, intent detection: continuously according to the input of the client, summarizing and reasoning the intention of the client such as 'calling, consulting overdue questions, questioning overdue results, presuming overdue reasons', and the like; emotion detection: gradually reasoning that the emotion of the client is no emotion, doubtful emotion, questioned emotion, worry emotion and the like; customer service quality detection: the service quality of the customer service is gradually identified as 'no violation (finishing the opening), no violation (finishing the probing), no violation (finishing the pacifying)', and the like.
Therefore, in the real-time communication between the customer service agent and the customer, the customer real-time intention and emotion of the customer and the service quality feedback of the customer to the customer service agent can be provided for the customer service agent, so that the customer service agent can adjust the service strategy in real time.
According to the session content analysis method applied to the customer service system, session content of a user terminal is received, any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis is carried out on the session content based on a large language model and a prompt engineering technology, recommended content is displayed on a front-end page of the customer service system based on an analysis result, any one of intention detection, emotion detection and customer service quality detection is carried out based on the context of the session content, and a detection result is displayed on the front-end page of the customer service system. Therefore, the session content of the customer service system can be subjected to multiple analysis, guidance and multiple detection by fully utilizing a large language model and a prompt engineering technology, recommended content and detection results are displayed on a front-end page of the customer service system, and intelligent customer analysis service is provided for the customer service system, so that customer intention can be rapidly and accurately understood by a customer service agent in the service process, decision can be made, the service process can be executed, and the service process can be recorded in a standardized manner.
In one embodiment, the analyzing any one of the flow guidance analysis, the knowledge guidance analysis and the job ticket tutorial analysis on the session content based on the large language model and the prompt engineering technology includes: when detecting that the session content is any one of a problem understanding node, a problem distribution node, a problem handling node and a service evaluation node of the customer service full link, performing any one of flow guidance analysis, knowledge guidance analysis and worksheet coaching analysis on the session content based on a large-scale language model and a prompt engineering technology; any one of intention detection, emotion detection and customer service quality detection is performed based on the context of the session content, and the method comprises the following steps: when detecting that the session content is any one of a problem understanding node, a problem distributing node and a problem handling node of the customer service full link, performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content; and when detecting that the session content is a service evaluation node of the customer service full link, performing any one of emotion detection and customer service quality detection based on the context of the session content.
Specifically, as shown in fig. 5, according to the analysis of the full-link method, the detachable customer service flow is four flows of service seeking, demand expression, demand response and evaluation feedback; then, a part of the process is split, and the demand response flow can be divided into two flows of machine solution and manual solution; and the same is true, and the separation is continuous. As shown in fig. 4, the implementation flow nodes of the flow guidance analysis, the knowledge guidance analysis, the job ticket tutorial analysis, the intention detection, the emotion detection and the customer service quality detection of the customer service agent auxiliary system are as follows:
the flow is guided: question understanding-question distribution-question handling-service evaluation;
knowledge wizard: question understanding-question distribution-question handling-service evaluation;
worksheet coaching: question understanding-question distribution-question handling-service evaluation;
and (5) intention recognition: question understanding-question distribution-question handling;
emotion guide: question understanding-question distribution-question handling-service evaluation;
customer service quality detection: question understanding-question distribution-question handling-service evaluation.
And analyzing each node of the customer service flow based on a full-link method, and setting corresponding functional modules for covering according to flow characteristics among the nodes. The scope of responsibility of each module, the purpose to be achieved, is clear.
In one embodiment, the receiving the session content of the user terminal includes: receiving a streaming translation text input by a voice recognition module, wherein the voice recognition module is used for converting a voice stream input by a call center into the streaming translation text, and the call center receives the voice stream initiated by a user client through a media gateway; and/or receiving customer service information and/or user information sent by a customer service system, wherein the customer service system obtains the customer service information and/or the user information through an online customer service, and the online customer service receives the user information sent by a user through an application gateway; the session content of the user terminal comprises streaming translation text, customer service information and user information.
Specifically, as shown in fig. 6, the user may be a question by voice call or a feedback question by an online text channel. The conversation content received by the customer service agent auxiliary system can be a text converted from voice stream to stream translation, and can also be a customer service message and/or a user message sent by the customer service system. Therefore, customer service problems of users can be processed in multiple ways through multiple channels, the system is guaranteed to be capable of deeply understanding business processes and user requirements, and therefore efficient and accurate services can be provided under different conditions. The system avoids the limitation possibly occurring when the system is designed independently, and ensures the stability and the reliability of the system in actual operation.
In one embodiment, the displaying the recommended content on the front-end page of the customer service system based on the analysis result includes: and displaying the recommended content corresponding to the analysis result of any one of the flow guide analysis, the knowledge guide analysis and the work order coaching analysis to a text conversation box of a front-end page of the customer service system through an auxiliary front-end component, so that a user can know the corresponding recommended content through the text conversation box.
In one embodiment, the displaying the detection result on the front end page of the customer service system includes: and displaying the detection result of any one of the intention detection, the emotion detection and the customer service quality detection to a front-end page of the customer service system through an auxiliary front-end component.
Specifically, the recommended content corresponding to the analysis result of any one of the flow guide analysis, the knowledge guide analysis and the work order coaching analysis is displayed to a text conversation box of a front-end page of the customer service system through the auxiliary front-end component. As shown in fig. 3, the SG component, KG component and TG component respectively display the corresponding display contents of the flow guide analysis, the knowledge guide analysis and the job ticket tutorial analysis, and display the display contents into the text conversation box, so that the end user and customer service can learn the corresponding recommended contents,
And displaying the detection result of any one of the intention detection, the emotion detection and the customer service quality detection to a front-end page of the customer service system through an auxiliary front-end component. As shown in fig. 3, the QC component, the SR component and the IR component respectively display detection results corresponding to intent detection, emotion detection and customer service quality detection, so that the customer service can learn the intent and emotion state of the user in real time, and learn the customer service quality evaluated by the system, so as to adjust the customer service in real time.
According to the session content analysis method of the embodiments, an advanced large language model (Large Language Model, LLM) is adopted for the requirements of customer service seat auxiliary systems, functions of guiding class processing and detecting class processing are configured, and more efficient and accurate service experience is achieved, so that continuously evolving customer service requirements are met.
It should be understood that, although the steps in the flowchart are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or other steps.
The application also provides a session content analysis device applied to the customer service system. As shown in fig. 7, a session content analysis device is applied to a customer service agent auxiliary system, and includes a receiving module 702, an analysis module 704 and a detection module 706. A receiving module 702, configured to receive session content of a user terminal; the analysis module 704 is configured to perform any one of flow guidance analysis, knowledge guidance analysis and worksheet tutorial analysis on the session content based on the large language model and the prompt engineering technology, and display recommended content on a front-end page of the customer service system based on an analysis result; the detection module 706 is configured to perform any one of intent detection, emotion detection, and customer service quality detection based on the context of the session content, and display the detection result on a front page of the customer service system.
In one embodiment, any one of flow guidance analysis, knowledge guidance analysis and worksheet tutorial analysis is performed on session content based on a large language model and a prompt engineering technology, and recommended content is displayed on a front-end page of a customer service system based on an analysis result, including: carrying out flow guiding analysis on session content based on a large language model and a prompt engineering technology, identifying flow intention of the session content, identifying corresponding business query flow according to the flow intention when the flow intention is consultation business related information, and displaying the corresponding business query flow on a front-end page of a customer service system so as to guide a customer service agent and/or a user to enter the corresponding business query flow; and/or, carrying out knowledge guide analysis on the session content based on the large language model and the prompt engineering technology, identifying the knowledge intention of the session content, determining knowledge points according to the knowledge intention, and displaying the knowledge points on a front-end page of the customer service system so as to enable a user to know the knowledge points; and/or carrying out worksheet coaching analysis on the conversation content based on the large language model and the prompt engineering technology, identifying worksheet element information of the conversation content, determining worksheet elements to be filled according to the worksheet element information, and displaying the worksheet elements to be filled on a front-end page of the customer service system so that a user fills in worksheets based on the worksheet elements to be filled.
In one embodiment, any one of intent detection, emotion detection and customer service quality detection is performed based on the context of session content, and the detection result is displayed on a front-end page of a customer service system, including: performing intention detection based on the context of the session content, identifying user intention, and displaying the user intention on a front-end page of the customer service system; and/or, carrying out emotion detection based on the context of the session content, identifying the emotion state of the user, and displaying the emotion state of the user on a front-end page of the customer service system; and/or, based on the context of the session content, performing customer service quality detection on each flow of the customer service full link, identifying the customer service quality of each flow, and displaying the customer service quality of each flow on a front-end page of the customer service system.
In one embodiment, performing any one of a flow guidance analysis, a knowledge guidance analysis, and a worksheet coaching analysis on session content based on a large language model and prompt engineering techniques, includes: when detecting that the session content is any one of a problem understanding node, a problem distribution node, a problem handling node and a service evaluation node of the customer service full link, performing any one of flow guidance analysis, knowledge guidance analysis and worksheet coaching analysis on the session content based on a large-scale language model and a prompt engineering technology; any one of intent detection, emotion detection, and customer service quality of service detection is performed based on the context of the session content, including: when detecting that the session content is any one of a problem understanding node, a problem distributing node and a problem handling node of the customer service full link, performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content; and when detecting that the session content is a service evaluation node of the customer service full link, performing any one of emotion detection and customer service quality detection based on the context of the session content.
In one embodiment, receiving session content of a user terminal includes: receiving a streaming translation text input by a voice recognition module, wherein the voice recognition module is used for converting a voice stream input by a call center into the streaming translation text, and the call center receives the voice stream initiated by a user client through a media gateway; and/or receiving customer service information and/or user information sent by a customer service system, wherein the customer service system obtains the customer service information and/or the user information through an online customer service, and the online customer service receives the user information sent by a user through an application gateway; the session content of the user terminal comprises streaming translation text, customer service information and user information.
In one embodiment, displaying recommended content on a front-end page of a customer service system based on an analysis result includes: and displaying the recommended content corresponding to the analysis result of any one of the flow guide analysis, the knowledge guide analysis and the work order coaching analysis to a text conversation box of a front-end page of the customer service system through an auxiliary front-end component, so that a user can know the corresponding recommended content through the text conversation box.
In one embodiment, the displaying the detection result on the front end page of the customer service system includes: and displaying the detection result of any one of the intention detection, the emotion detection and the customer service quality detection to a front-end page of the customer service system through an auxiliary front-end component.
The specific definition of a session content analysis device may be referred to above as a definition of a session content analysis method, and will not be described here. Each module in the session content analysis apparatus may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server supporting the operation of a customer service agent assistance system, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface of the computer device is used for receiving session content of the user terminal, etc. The computer program is executed by a processor to implement a session content analysis method as described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application is directed, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program: receiving session content of a user terminal; based on the large language model and the prompt engineering technology, carrying out any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis on the session content, and displaying recommended content on a front-end page of the customer service system based on an analysis result; and performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on a front-end page of the customer service system.
In one embodiment, when the processor executes the computer program to perform any one of the process guidance analysis, the knowledge guidance analysis and the worksheet tutorial analysis on the session content based on the large language model and the prompt engineering technology, and display the recommended content on the front end page of the customer service system based on the analysis result, the following steps are specifically implemented: carrying out flow guiding analysis on session content based on a large language model and a prompt engineering technology, identifying flow intention of the session content, identifying corresponding business query flow according to the flow intention when the flow intention is consultation business related information, and displaying the corresponding business query flow on a front-end page of a customer service system so as to guide a customer service agent and/or a user to enter the corresponding business query flow; and/or, carrying out knowledge guide analysis on the session content based on the large language model and the prompt engineering technology, identifying the knowledge intention of the session content, determining knowledge points according to the knowledge intention, and displaying the knowledge points on a front-end page of the customer service system so as to enable a user to know the knowledge points; and/or carrying out worksheet coaching analysis on the conversation content based on the large language model and the prompt engineering technology, identifying worksheet element information of the conversation content, determining worksheet elements to be filled according to the worksheet element information, and displaying the worksheet elements to be filled on a front-end page of the customer service system so that a user fills in worksheets based on the worksheet elements to be filled.
In one embodiment, the processor executes the computer program to perform any one of the above detection of intention detection, emotion detection and customer service quality detection based on the context of the session content, and when the front end page of the customer service system displays the detection result, the following steps are specifically implemented: performing intention detection based on the context of the session content, identifying user intention, and displaying the user intention on a front-end page of the customer service system; and/or, carrying out emotion detection based on the context of the session content, identifying the emotion state of the user, and displaying the emotion state of the user on a front-end page of the customer service system; and/or, based on the context of the session content, performing customer service quality detection on each flow of the customer service full link, identifying the customer service quality of each flow, and displaying the customer service quality of each flow on a front-end page of the customer service system.
In one embodiment, when the processor executes the computer program to implement the step of performing any one of the flow guidance analysis, the knowledge guidance analysis and the worksheet tutorial analysis on the session content based on the large language model and the prompt engineering technology, the following steps are specifically implemented: when detecting that the session content is any one of a problem understanding node, a problem distribution node, a problem handling node and a service evaluation node of the customer service full link, performing any one of flow guidance analysis, knowledge guidance analysis and worksheet coaching analysis on the session content based on a large-scale language model and a prompt engineering technology; any one of intent detection, emotion detection, and customer service quality of service detection is performed based on the context of the session content, including: when detecting that the session content is any one of a problem understanding node, a problem distributing node and a problem handling node of the customer service full link, performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content; and when detecting that the session content is a service evaluation node of the customer service full link, performing any one of emotion detection and customer service quality detection based on the context of the session content.
In one embodiment, when the processor executes the computer program to implement the steps of receiving the session content of the user terminal, the following steps are specifically implemented: receiving a streaming translation text input by a voice recognition module, wherein the voice recognition module is used for converting a voice stream input by a call center into the streaming translation text, and the call center receives the voice stream initiated by a user client through a media gateway; and/or receiving customer service information and/or user information sent by a customer service system, wherein the customer service system obtains the customer service information and/or the user information through an online customer service, and the online customer service receives the user information sent by a user through an application gateway; the session content of the user terminal comprises streaming translation text, customer service information and user information.
In one embodiment, when the processor executes the computer program to implement the step of displaying the recommended content on the front-end page of the customer service system based on the analysis result, the following steps are specifically implemented: and displaying the recommended content corresponding to the analysis result of any one of the flow guide analysis, the knowledge guide analysis and the work order coaching analysis to a text conversation box of a front-end page of the customer service system through an auxiliary front-end component, so that a user can know the corresponding recommended content through the text conversation box.
In one embodiment, when the processor executes the computer program to implement the step of displaying the detection result on the front end page of the customer service system, the following steps are specifically implemented: and displaying the detection result of any one of the intention detection, the emotion detection and the customer service quality detection to a front-end page of the customer service system through an auxiliary front-end component.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of: receiving session content of a user terminal; based on the large language model and the prompt engineering technology, carrying out any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis on the session content, and displaying recommended content on a front-end page of the customer service system based on an analysis result; and performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on a front-end page of the customer service system.
In one embodiment, the computer program is executed by the processor to perform any one of the process guidance analysis, the knowledge guidance analysis and the worksheet tutorial analysis on the session content based on the large language model and the prompt engineering technology, and when the recommended content is displayed on the front end page of the customer service system based on the analysis result, the following steps are specifically implemented: carrying out flow guiding analysis on session content based on a large language model and a prompt engineering technology, identifying flow intention of the session content, identifying corresponding business query flow according to the flow intention when the flow intention is consultation business related information, and displaying the corresponding business query flow on a front-end page of a customer service system so as to guide a customer service agent and/or a user to enter the corresponding business query flow; and/or, carrying out knowledge guide analysis on the session content based on the large language model and the prompt engineering technology, identifying the knowledge intention of the session content, determining knowledge points according to the knowledge intention, and displaying the knowledge points on a front-end page of the customer service system so as to enable a user to know the knowledge points; and/or carrying out worksheet coaching analysis on the conversation content based on the large language model and the prompt engineering technology, identifying worksheet element information of the conversation content, determining worksheet elements to be filled according to the worksheet element information, and displaying the worksheet elements to be filled on a front-end page of the customer service system so that a user fills in worksheets based on the worksheet elements to be filled.
In one embodiment, the computer program is executed by the processor to perform any one of the above-mentioned intent detection, emotion detection and customer service quality detection based on the context of the session content, and when the front end page of the customer service system shows the detection result, the following steps are specifically implemented: performing intention detection based on the context of the session content, identifying user intention, and displaying the user intention on a front-end page of the customer service system; and/or, carrying out emotion detection based on the context of the session content, identifying the emotion state of the user, and displaying the emotion state of the user on a front-end page of the customer service system; and/or, based on the context of the session content, performing customer service quality detection on each flow of the customer service full link, identifying the customer service quality of each flow, and displaying the customer service quality of each flow on a front-end page of the customer service system.
In one embodiment, when the computer program is executed by the processor to perform the step of performing any one of the flow guidance analysis, the knowledge guidance analysis and the worksheet guidance analysis on the session content based on the large language model and the prompt engineering technology, the following steps are specifically implemented: when detecting that the session content is any one of a problem understanding node, a problem distribution node, a problem handling node and a service evaluation node of the customer service full link, performing any one of flow guidance analysis, knowledge guidance analysis and worksheet coaching analysis on the session content based on a large-scale language model and a prompt engineering technology; any one of intent detection, emotion detection, and customer service quality of service detection is performed based on the context of the session content, including: when detecting that the session content is any one of a problem understanding node, a problem distributing node and a problem handling node of the customer service full link, performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content; and when detecting that the session content is a service evaluation node of the customer service full link, performing any one of emotion detection and customer service quality detection based on the context of the session content.
In one embodiment, when the computer program is executed by the processor to implement the steps of receiving session content of the user terminal, the following steps are specifically implemented: receiving a streaming translation text input by a voice recognition module, wherein the voice recognition module is used for converting a voice stream input by a call center into the streaming translation text, and the call center receives the voice stream initiated by a user client through a media gateway; and/or receiving customer service information and/or user information sent by a customer service system, wherein the customer service system obtains the customer service information and/or the user information through an online customer service, and the online customer service receives the user information sent by a user through an application gateway; the session content of the user terminal comprises streaming translation text, customer service information and user information.
In one embodiment, when the computer program is executed by the processor to implement the step of displaying the recommended content on the front-end page of the customer service system based on the analysis result, the following steps are specifically implemented: and displaying the recommended content corresponding to the analysis result of any one of the flow guide analysis, the knowledge guide analysis and the work order coaching analysis to a text conversation box of a front-end page of the customer service system through an auxiliary front-end component, so that a user can know the corresponding recommended content through the text conversation box.
In one embodiment, when the computer program is executed by the processor to implement the step of displaying the detection result on the front end page of the customer service system, the following steps are specifically implemented: and displaying the detection result of any one of the intention detection, the emotion detection and the customer service quality detection to a front-end page of the customer service system through an auxiliary front-end component.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile 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 a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims (10)

1. A session content analysis method applied to a customer service system, the method comprising:
receiving session content of a user terminal;
any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis is carried out on the session content based on a large language model and a prompt engineering technology, and recommended content is displayed on a front-end page of a customer service system based on analysis results;
And performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on a front-end page of a customer service system.
2. The method according to claim 1, wherein the performing any one of flow guidance analysis, knowledge guidance analysis and worksheet tutorial analysis on the session content based on the large language model and the prompt engineering technology, and displaying recommended content on a front-end page of the customer service system based on the analysis result, includes:
performing flow guiding analysis on the session content based on a large language model and a prompt engineering technology, identifying the flow intention of the session content, identifying a corresponding service inquiry flow according to the flow intention when the flow intention is related information of consultation service, and displaying the corresponding service inquiry flow on a front-end page of a customer service system so as to guide a customer service agent and/or a user to enter the corresponding service inquiry flow;
and/or the number of the groups of groups,
carrying out knowledge guide analysis on the session content based on a large language model and a prompt engineering technology, identifying knowledge intention of the session content, determining knowledge points according to the knowledge intention, and displaying the knowledge points on a front-end page of a customer service system so that a user can know the knowledge points;
And/or the number of the groups of groups,
and carrying out worksheet coaching analysis on the conversation content based on a large language model and a prompt engineering technology, identifying worksheet element information of the conversation content, determining worksheet elements to be filled according to the worksheet element information, and displaying the worksheet elements to be filled on a front-end page of a customer service system so that a user fills worksheets based on the worksheet elements to be filled.
3. The method according to claim 2, wherein the detecting any one of intention detection, emotion detection, and customer service quality detection based on the context of the session content, displaying the detection result on a front-end page of a customer service system, includes:
based on the context of the session content, carrying out intention detection, identifying user intention, and displaying the user intention on a front-end page of a customer service system;
and/or the number of the groups of groups,
carrying out emotion detection based on the context of the session content, identifying the emotion state of the user, and displaying the emotion state of the user on a front-end page of a customer service system;
and/or the number of the groups of groups,
and detecting the service quality of each process of the customer service full link based on the context of the session content, identifying the service quality of the customer service of each process, and displaying the service quality of the customer service of each process on a front-end page of a customer service system.
4. The method of claim 3, wherein the performing any one of a flow guide analysis, a knowledge guide analysis, and a worksheet tutorial analysis on the session content based on a large language model and a prompt engineering technique comprises:
when detecting that the session content is any one of a problem understanding node, a problem distributing node, a problem handling node and a service evaluating node of a customer service full link, performing any one of flow guiding analysis, knowledge guiding analysis and worksheet coaching analysis on the session content based on a large-scale language model and a prompt engineering technology;
any one of intention detection, emotion detection and customer service quality detection is performed based on the context of the session content, and the method comprises the following steps:
when detecting that the session content is any one of a problem understanding node, a problem distributing node and a problem handling node of a customer service full link, performing any one of intention detection, emotion detection and customer service quality detection based on the context of the session content;
and when detecting that the session content is a service evaluation node of a customer service full link, performing any one of emotion detection and customer service quality detection based on the context of the session content.
5. The method according to claim 1, wherein the receiving session content of the user terminal comprises:
receiving a streaming translation text input by a voice recognition module, wherein the voice recognition module is used for converting a voice stream input by a call center into the streaming translation text, and the call center receives the voice stream initiated by a user client through a media gateway;
and/or the number of the groups of groups,
receiving customer service information and/or user information sent by a customer service system, wherein the customer service system obtains the customer service information and/or user information through an online customer service, and the online customer service receives the user information sent by a user through an application gateway;
the session content of the user terminal comprises the streaming translation text, the customer service message and the user message.
6. The method of claim 1, wherein the presenting recommended content on the front-end page of the customer service system based on the analysis result comprises:
and displaying recommended content corresponding to the analysis result of any one of the flow guide analysis, the knowledge guide analysis and the work order tutorial analysis to a text conversation box of a front-end page of the customer service system through an auxiliary front-end component, so that a user can obtain the corresponding recommended content through the text conversation box.
7. The method of claim 1, wherein the displaying the detection result on the front-end page of the customer service system comprises:
and displaying the detection result of any one of the intention detection, the emotion detection and the customer service quality detection to a front-end page of a customer service system through an auxiliary front-end component.
8. A session content analysis apparatus applied to a customer service system, the apparatus comprising:
the receiving module is used for receiving the session content of the user terminal;
the analysis module is used for carrying out any one of flow guide analysis, knowledge guide analysis and worksheet tutorial analysis on the session content based on the large language model and the prompt engineering technology, and displaying recommended content on a front-end page of the customer service system based on an analysis result;
the detection module is used for carrying out any one of intention detection, emotion detection and customer service quality detection based on the context of the session content, and displaying a detection result on a front-end page of a customer service system.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 7 when the computer program is executed by the processor.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 7.
CN202311305240.8A 2023-10-10 2023-10-10 Session content analysis method, device and storage medium applied to customer service system Pending CN117390153A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311305240.8A CN117390153A (en) 2023-10-10 2023-10-10 Session content analysis method, device and storage medium applied to customer service system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311305240.8A CN117390153A (en) 2023-10-10 2023-10-10 Session content analysis method, device and storage medium applied to customer service system

Publications (1)

Publication Number Publication Date
CN117390153A true CN117390153A (en) 2024-01-12

Family

ID=89469370

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311305240.8A Pending CN117390153A (en) 2023-10-10 2023-10-10 Session content analysis method, device and storage medium applied to customer service system

Country Status (1)

Country Link
CN (1) CN117390153A (en)

Similar Documents

Publication Publication Date Title
KR102431754B1 (en) Apparatus for supporting consultation based on artificial intelligence
CN110378749B (en) Client similarity evaluation method and device, terminal equipment and storage medium
CN110110038B (en) Telephone traffic prediction method, device, server and storage medium
US9569743B2 (en) Funnel analysis
US11226991B2 (en) Interest tag determining method, computer device, and storage medium
KR20200092499A (en) Method and apparatus for counseling support using interactive artificial intelligence technology
US20040002868A1 (en) Method and system for the processing of voice data and the classification of calls
CN112235470B (en) Incoming call client follow-up method, device and equipment based on voice recognition
CN109635086A (en) A kind of knowledge recommendation method and device applied to knowledge platform
US20040042591A1 (en) Method and system for the processing of voice information
CN116432665B (en) Dialogue model construction method, text generation method, device, system and equipment
CN117390153A (en) Session content analysis method, device and storage medium applied to customer service system
Ramos et al. Automated enterprise-level analysis of archimate models
CN116860938A (en) Voice question-answering construction method, device and medium based on large language model
US20040006464A1 (en) Method and system for the processing of voice data by means of voice recognition and frequency analysis
CN113645357B (en) Call quality inspection method, device, computer equipment and computer readable storage medium
CN108717851A (en) A kind of audio recognition method and device
US7343288B2 (en) Method and system for the processing and storing of voice information and corresponding timeline information
CN111565254B (en) Call data quality inspection method and device, computer equipment and storage medium
CN115033677A (en) Event processing method, device, equipment and medium based on conversation robot
CN114117207A (en) System, method, electronic device and storage medium for preventing fraud
CN110852799A (en) User screening method and device based on intention label, electronic equipment and medium
CN110928845B (en) Online document export method and device, computer equipment and readable storage medium
DE10020831A1 (en) Interactive information interrogation method using mobile telephone has speech information analysed at mobile radio service device for providing required data response
US20230025114A1 (en) System and method for automated processing of natural language using deep learning model encoding

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination