CN112988997A - Response method and system of intelligent customer service, computer equipment and storage medium - Google Patents
Response method and system of intelligent customer service, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112988997A CN112988997A CN202110268907.6A CN202110268907A CN112988997A CN 112988997 A CN112988997 A CN 112988997A CN 202110268907 A CN202110268907 A CN 202110268907A CN 112988997 A CN112988997 A CN 112988997A
- Authority
- CN
- China
- Prior art keywords
- information
- customer service
- current
- user
- conversation
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 230000004044 response Effects 0.000 title claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 17
- 230000006399 behavior Effects 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 14
- 230000006870 function Effects 0.000 description 7
- 238000012015 optical character recognition Methods 0.000 description 6
- 238000012790 confirmation Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000013179 statistical model Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a response method, a response system, response equipment and a response storage medium of an intelligent customer service. The response method of the intelligent customer service comprises the following steps: receiving input information input by a user, converting the input information into text information, and identifying the natural semantics of the text information; detecting a current customer service conversation stage, and updating a current conversation state according to the current customer service conversation stage; and selecting corresponding feedback information from a preset database to output and display by combining the natural semantics and the current conversation state. The customer enters the intelligent customer service dialogue interface to input information, and the intelligent customer service system receives the input information input by the customer and identifies the natural semantics of the input information. And the intelligent customer service system updates the conversation stage, and outputs and displays the matched optimal feedback information from the knowledge base according to the natural semantics and the current conversation state. In the invention, the intention of the user is accurately judged by combining the current conversation stage and the natural semantics, so that the optimal matching feedback from the knowledge base to the user can be accurately realized.
Description
Technical Field
The invention relates to the technical field of intelligent customer service, in particular to a response method and system of intelligent customer service, computer equipment and a storage medium.
Background
With the rapid development of computer technology and the continuous increase of labor cost, intelligent customer service is widely applied in the field of customer service. Most of the traditional customer service systems are composed of complex and tedious operation pages. These pages are often also mixed with more or less specialized terms, often confusing to non-professional users. The user performs the customer service information operation with a good understanding, and is likely to encounter an error or the operated content is not expected.
After receiving input information input by a user, an existing customer service system generally performs semantic recognition only according to the input information, and then selects an answer from a preset question-answer model library according to semantics to reply. However, in the process of customer service consultation or operation, users often enter different consultation and operation stages along with the depth of consultation and operation, and user intentions expressed by the users in different conversation stages often have great difference, so that the existing customer service system is difficult to perform accurate intention identification according to information input by the users in different stages, information fed back by the customer service system is difficult to meet the user requirements, and the user experience is poor.
Disclosure of Invention
The embodiment of the invention provides a response method, a response system, computer equipment and a storage medium of an intelligent customer service system, and aims to solve the problem that information fed back by the existing customer service system is difficult to meet the requirements of users.
An intelligent customer service response method comprises the following steps:
receiving input information input by a user, converting the input information into text information, and identifying the natural semantics of the text information;
detecting a current customer service conversation stage, and updating a current conversation state according to the current customer service conversation stage;
and selecting corresponding feedback information from a preset database to output and display by combining the natural semantics and the current conversation state.
Further, the step of receiving input information input by a user, converting the input information into text information, and identifying the natural semantics of the text information specifically includes:
receiving character, voice or image information input by a user;
recognizing character, voice or image information input by a user, and converting the character, voice or image information into text information;
and performing lexical analysis, syntactic analysis and/or semantic analysis on the text information, and outputting the intention classification to which the text features in the text information belong.
Further, the detecting the current customer service session stage and updating the current session state according to the current customer service session stage specifically include:
pre-dividing an intelligent customer service conversation into a plurality of customer service conversation stages;
and detecting a customer service conversation stage of the current customer service conversation, and updating the current customer service conversation stage to be in a current conversation state.
Further, the step of selecting corresponding feedback information from a preset database to output and display in combination with the natural semantics and the current conversation state specifically includes:
mapping the intention classification to a preset dialogue behavior category system;
acquiring a user intention from the conversation behavior category system in combination with the current conversation state;
and selecting corresponding feedback information from a preset database according to the user intention, and outputting and displaying the feedback information.
Further, the selecting a corresponding feedback information output display mode includes:
and displaying the feedback information in a text, voice or image mode according to the current conversation state, or displaying the feedback information in a task card triggering mode according to the current conversation state.
Further, before the step of selecting the corresponding feedback information output display, the method further includes:
acquiring current user identity information;
the method for selecting the corresponding feedback information output display comprises the following steps:
and feeding back the feedback information in a text, voice or image mode according to the current user identity information.
Further, after the step of selecting corresponding feedback information from a preset database to output and display in combination with the natural semantics and the current conversation state, the method further includes:
receiving demand information continuously input by a user, and identifying demand semantics of the demand information;
judging whether the conversation state of the last stage is finished according to the requirement semantics;
if the current conversation state is finished, updating the current conversation state, and matching the optimal feedback information according to the current conversation state and the required semantics to output and display; if not, the conversation state is not updated, and the feedback information is matched again according to the current conversation state and the required semantics to be output and displayed.
An intelligent customer service response system comprising:
the semantic recognition module is used for receiving input information input by a user, converting the input information into text information and recognizing the natural semantics of the text information;
the conversation management module is used for detecting the current customer service conversation stage and updating the current conversation state according to the current customer service conversation stage;
and the information feedback module is used for selecting corresponding feedback information from a preset knowledge base by combining the natural semantics and the current conversation state and outputting and displaying the feedback information.
A computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of the above-mentioned method of response of a smart customer service when executing said computer program.
A computer storage medium, in which a computer program is stored, which computer program, when being executed by a processor, realizes the steps of the above-mentioned response method for intelligent customer service.
In the response method, the response system, the computer equipment and the storage medium of the intelligent customer service, a customer enters an intelligent customer service conversation interface to input information (such as character information, picture information or voice information), and the intelligent customer service system receives the input information input by the user, converts the input information into text information and identifies the natural semantics of the input information. And the intelligent customer service system updates the conversation stage, and outputs and displays the matched optimal feedback information from the database according to the natural semantics and the current conversation state. In the invention, the current conversation state is updated while or after the natural semantics input by the user are acquired, the intention of the user is accurately judged by combining the current conversation stage and the natural semantics, and the intention of the user in the conversation stage can be accurately identified in different intelligent customer service conversation stages, so that the optimal feedback information can be accurately matched from a knowledge base to the user, the accuracy of the intention identification of the user and the accuracy of the information feedback are greatly improved, and the user experience is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a diagram of an application environment of an intelligent customer service response method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for responding by an intelligent customer service in an embodiment of the present invention;
FIG. 3 is a detailed flowchart of step S103 in FIG. 2;
FIG. 4 is a flow chart of a method for responding by an intelligent customer service in accordance with another embodiment of the present invention;
FIG. 5 is a flow chart of a method for responding by an intelligent customer service in accordance with another embodiment of the present invention;
FIG. 6 is a schematic diagram of an intelligent customer service response system in accordance with an embodiment of the present invention;
FIG. 7 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The response method of the intelligent customer service can be applied to the application environment as shown in fig. 1, wherein the computer equipment is communicated with the server through a network. The computer device may be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server may be implemented as a stand-alone server.
In an embodiment, as shown in fig. 2, an intelligent customer service response method is provided, which is described by taking the example of the method applied to the computer device and/or the server in fig. 1, and includes the following steps:
s101: receiving input information input by a user, converting the input information into text information, and identifying the natural semantics of the text information.
When the user uses the intelligent customer service system, the user can input text information, picture information or voice information in a dialog box of the customer service system, such as: inputting 'keep alive' text content, 'keep alive' voice content or shooting a insurance policy and uploading the insurance policy to a dialog box of the intelligent customer service system. The intelligent customer service system receives character information, picture information or voice information input by a user and converts the information input by the user into text information.
Specifically, when the information input by the user is voice information, the voice information is recognized as characters through the voice recognition module and text information is formed. And if the information input by the user is picture information, recognizing and extracting the character content in the picture through an OCR (optical character recognition), and organizing the character content into text information. If the user inputs the character information, the character information in the dialog box is directly extracted to form the text information.
After a user inputs character information, picture information or voice information and converts the character information, the picture information or the voice information into text information, the intelligent customer service carries out lexical analysis, syntactic analysis and semantic analysis on the text information based on statistical model methods such as SVM and the like, understands natural semantics contained in the text information, outputs intention classification to which the text information belongs, and knows the primary intention of the user.
It is understood that the user may input the above text information, picture information or voice information at any stage of the dialog operation, such as: in the stage of inputting the identity information of the intelligent customer service, when the intelligent customer service system needs the user to input the identity card number, the user takes the identity card photo and uploads the identity card photo, at the moment, the intelligent customer service system receives the identity card photo input by the user, extracts the information of name, address, identity card number, year and month of birth and the like from the identity card information input by the user, and converts the information of the name, the address, the identity card number, the year and month of birth and the like into text information. Through semantic recognition, the intention of the user to input the identity card photo at the moment is classified into identity recognition, identity verification, identity information extraction and the like.
Wherein, the natural semantics is the meaning of the words or sentences in the text information.
S102: and detecting the current customer service conversation stage, and updating the current conversation state according to the current customer service conversation stage.
It is understood that step S102 may be performed before or after step S101, or may be performed simultaneously with step S101. In the present embodiment, it is preferable that the step of updating the current dialogue state is executed after the natural semantics of the input information is recognized.
Before intelligent customer service, the complete customer service process can be divided into stages in advance, such as: the customer service process is divided into a session starting stage, a selection stage, a filling stage, a payment stage, a confirmation stage and the like. And in the process of the customer service conversation, acquiring the current customer service stage, and updating the current customer service stage to be in the current conversation state.
S103: and selecting corresponding feedback information from a preset database to output and display by combining the natural semantics and the current conversation state.
And selecting the best feedback information from a preset knowledge base according to the natural semantics and the current conversation state, and outputting and displaying the feedback information, wherein the feedback information can be task cards or text contents and the like. Such as: and the current conversation state is a license plate number filling stage, the input information input by the current user is a driver license picture, text information is extracted from the driver license picture, the intention of the user is identified as the license plate number input on the driver license picture by combining the current conversation state, and at the moment, the license plate number information on the driver license picture is automatically filled to the intelligent customer service system to complete the filling operation.
As shown in fig. 3, step S103 includes the following sub-steps:
s1031: and mapping the intention classification to a preset conversation behavior category system.
S1032: and acquiring the user intention from the conversation behavior category system in combination with the current conversation state.
S1033: and selecting corresponding feedback information from a preset database according to the user intention, and outputting and displaying the feedback information.
Specifically, for example: when a user operates to an identity information filling stage on a customer service system, if the user shoots and uploads an identity card photo at the moment, the system receives the identity card photo uploaded by the user, extracts information such as name, address, identity card number, year and month of birth and the like in the identity card photo, generates text information, and classifies intentions according to the text information, such as: at this time, the intention is classified into input of identity information, authentication, input of identity card image information, and the like. Updating a conversation state while or after analyzing and classifying the intentions, wherein the conversation state is an identity information filling stage, and combining the identity information filling stage and the intention classification, the intention of the user can be judged to be the need of filling identity information in the customer service system, then the information such as name, address, identity card number, birth year and month and the like is filled in the system, the filling information is fed back, and a user modification/confirmation task is generated for the user to carry out the next operation.
When the method of the embodiment is implemented, a client enters an intelligent customer service dialogue interface to input information (such as character information, picture information or voice information), and the intelligent customer service system receives the input information input by the user, converts the input information into text information and identifies the natural semantics of the input information. And the intelligent customer service system updates the conversation stage, and outputs and displays the matched optimal feedback information from the knowledge base according to the natural semantics and the current conversation state. In the invention, the current conversation state is updated while or after the natural semantics input by the user are acquired, the intention of the user is accurately judged by combining the current conversation stage and the natural semantics, and the intention of the user in the conversation stage can be accurately identified in different intelligent customer service conversation stages, so that the optimal matching feedback from the database to the user can be accurately realized.
In the prior art, when the intelligent customer service performs information feedback, the information feedback is usually performed only according to the identified natural semantics, and analysis is not performed in combination with the current conversation state, so that it is difficult to accurately judge the user requirements and give the most accurate information feedback. In different dialog stages of the intelligent customer service, even though the input information input by the user is completely the same, the actual requirements of the user may be different in different dialog stages. Therefore, when the user intention is identified, the user intention is identified by combining the current conversation state and the natural semantics, so that the accuracy of the user intention identification and the accuracy of information feedback can be greatly improved, and the user experience is improved.
In another embodiment, as shown in fig. 4, in the response method of the intelligent customer service of this embodiment, the method includes the following steps:
s201: receiving input information input by a user, converting the input information into text information, and identifying the natural semantics of the text information.
When the user uses the intelligent customer service system, the user can input text information, picture information or voice information in a dialog box of the customer service system, such as: inputting 'keep alive' text content, 'keep alive' voice content or shooting a insurance policy and uploading the insurance policy to a dialog box of the intelligent customer service system. The intelligent customer service system receives character information, picture information or voice information input by a user and converts the information input by the user into text information.
Specifically, when the information input by the user is voice information, the voice information is recognized as characters through the voice recognition module and text information is formed. And if the information input by the user is picture information, recognizing and extracting the character content in the picture through an OCR (optical character recognition), and organizing the character content into text information. If the user inputs the character information, the character information in the dialog box is directly extracted to form the text information.
After a user inputs character information, picture information or voice information and converts the character information, the picture information or the voice information into text information, the intelligent customer service carries out lexical analysis, syntactic analysis and semantic analysis on the text information based on statistical model methods such as SVM and the like, understands natural semantics contained in the text information, outputs intention classification to which the text information belongs, and knows the primary intention of the user.
It is understood that the user may input the above text information, picture information or voice information at any stage of the dialog operation, such as: in the stage of inputting the identity information of the intelligent customer service, when the intelligent customer service system needs the user to input the identity card number, the user takes the identity card photo and uploads the identity card photo, at the moment, the intelligent customer service system receives the identity card photo input by the user, extracts the information of name, address, identity card number, year and month of birth and the like from the identity card information input by the user, and converts the information of the name, the address, the identity card number, the year and month of birth and the like into text information. Through semantic recognition, the intention of the user to input the identity card photo at the moment is classified into identity recognition, identity verification, identity information extraction and the like.
Wherein, the natural semantics is the meaning of the words or sentences in the text information.
S202: and detecting the current customer service conversation stage, and updating the current conversation state according to the current customer service conversation stage.
It is understood that step S202 may be executed before or after step S201, or may be executed simultaneously with step S201. In the present embodiment, it is preferable that the step of updating the current dialogue state is executed after the natural semantics of the input information is recognized.
Before intelligent customer service, the complete customer service process can be divided into stages in advance, such as: the customer service process is divided into a session starting stage, a selection stage, a filling stage, a payment stage, a confirmation stage and the like. And in the process of the customer service conversation, acquiring the current customer service stage, and updating the current customer service stage to be in the current conversation state.
S203: and acquiring the identity information of the current user.
Acquiring age information, nationality information and/or address information and the like of the current user. Specifically, the age information, the nationality information, and the like of the user may be acquired from registration information or login information of the user, and the address information of the user may be acquired by positioning.
S204: and selecting corresponding feedback information from a preset database by combining the natural semantics and the current conversation state, and feeding back the feedback information in a text, voice or image mode according to the current user identity information selection.
When the information feedback display is carried out, if the nationality of the current user is China, the feedback information can be displayed by using Chinese characters, and if the nationality of the current user is British, the feedback information can be displayed by using English. If the current user is a child or an elderly person, the information can be fed back by using a voice mode or an image mode. That is, when information feedback is performed on users with different identities, the most suitable feedback mode in text, voice or images can be selected for information feedback.
When the method of the embodiment is implemented, a client enters the intelligent customer service dialogue interface to input information (such as text information, picture information or voice information), and the intelligent customer service system receives the input information input by the user and identifies the natural semantics of the input information. The intelligent customer service system updates the conversation stage to obtain the current user identity information, matches the best feedback information from the knowledge base to output and display according to natural semantics and the current conversation state, and selects to display in a text, voice or image mode according to the user identity information when outputting and displaying the feedback information so as to meet different user groups. In the invention, the current conversation state is updated while or after the natural semantics input by the user are acquired, and the intention of the user is accurately judged by combining the current conversation stage and the natural semantics, so that the optimal matching feedback can be accurately carried out from the knowledge base to the user, the display mode which can be accepted by the user is selected according to the identity information of the user, and the user experience is improved.
In another embodiment, as shown in fig. 5, in the response method of the intelligent customer service of this embodiment, the method includes the following steps:
s301: receiving input information input by a user, converting the input information into text information, and identifying the natural semantics of the text information.
When the user uses the intelligent customer service system, the user can input text information, picture information or voice information in a dialog box of the customer service system, such as: inputting 'keep alive' text content, 'keep alive' voice content or shooting a insurance policy and uploading the insurance policy to a dialog box of the intelligent customer service system. The intelligent customer service system receives character information, picture information or voice information input by a user and converts the information input by the user into text information.
Specifically, when the information input by the user is voice information, the voice information is recognized as characters through the voice recognition module and text information is formed. And if the information input by the user is picture information, recognizing and extracting the character content in the picture through an OCR (optical character recognition), and organizing the character content into text information. If the user inputs the character information, the character information in the dialog box is directly extracted to form the text information.
After a user inputs character information, picture information or voice information and converts the character information, the picture information or the voice information into text information, the intelligent customer service carries out lexical analysis, syntactic analysis and semantic analysis on the text information based on statistical model methods such as SVM and the like, understands natural semantics contained in the text information, outputs intention classification to which the text information belongs, and knows the primary intention of the user.
It is understood that the user may input the above text information, picture information or voice information at any stage of the dialog operation, such as: in the stage of inputting the identity information of the intelligent customer service, when the intelligent customer service system needs the user to input the identity card number, the user takes the identity card photo and uploads the identity card photo, at the moment, the intelligent customer service system receives the identity card photo input by the user, extracts the information of name, address, identity card number, year and month of birth and the like from the identity card information input by the user, and converts the information of the name, the address, the identity card number, the year and month of birth and the like into text information. Through semantic recognition, the intention of the user to input the identity card photo at the moment is classified into identity recognition, identity verification, identity information extraction and the like.
Wherein, the natural semantics is the meaning of the words or sentences in the text information.
S302: and detecting the current customer service conversation stage, and updating the current conversation state according to the current customer service conversation stage.
It is understood that step S302 may be performed before or after step S301, or may be performed simultaneously with step S301. In the present embodiment, it is preferable that the step of updating the current dialogue state is executed after the natural semantics of the input information is recognized.
Before intelligent customer service, the complete customer service process can be divided into stages in advance, such as: the customer service process is divided into a session starting stage, a selection stage, a filling stage, a payment stage, a confirmation stage and the like. And in the process of the customer service conversation, acquiring the current customer service stage, and updating the current customer service stage to be in the current conversation state.
S303: and selecting corresponding feedback information from a preset database to output and display by combining the natural semantics and the current conversation state.
And selecting the best feedback information from a preset knowledge base according to the natural semantics and the current conversation state, and outputting and displaying the feedback information, wherein the feedback information can be task cards or text contents and the like. Such as: and the current conversation state is a license plate number filling stage, the input information input by the current user is a driver license picture, text information is extracted from the driver license picture, the intention of the user is identified as the license plate number input on the driver license picture by combining the current conversation state, and at the moment, the license plate number information on the driver license picture is automatically filled to the intelligent customer service system to complete the filling operation.
Specifically, for example: when a user operates to an identity information filling stage on a customer service system, if the user shoots and uploads an identity card photo at the moment, the system receives the identity card photo uploaded by the user, extracts information such as name, address, identity card number, year and month of birth and the like in the identity card photo, generates text information, and classifies intentions according to the text information, such as: the user's intention is to input identity information, perform identity verification, input identity card image information, and the like. Updating a conversation state while or after analyzing and classifying the intentions, wherein the conversation state is an identity information filling stage, and combining the identity information filling stage and the intention classification, the user can judge that the user needs to fill the identity information in the customer service system at the moment, then filling the information such as name, address, ID card number, birth year and month and the like into the system, feeding back the filling information and generating a user modification/confirmation task, and carrying out the next operation for the user.
S304: and receiving demand information continuously input by a user, and identifying the demand semantics of the demand information.
After the information feedback at the last stage, if the user continues to input the demand information, the intelligent customer service system receives the demand information continuously input by the user, and the intelligent customer service system performs lexical analysis, syntactic analysis and semantic analysis on the demand information based on statistical model methods such as SVM and the like and identifies the demand semantics of the demand information.
S305: and judging whether the conversation state of the last stage is finished according to the requirement semantics.
And understanding the requirement semantics, and judging whether the conversation state of the previous stage is finished according to the requirement semantics. Such as: the user inputs the voice information of 'I do not need XXX, I want YYY', at the moment, the understanding that the natural semantics is 'XXX' information fed back by the intelligent customer service system last time can not meet the user requirement, and the user real requirement is 'YYY', and the conversation state of the previous stage is judged to be incomplete. And if the information input by the user is matched with the conversation state of the next stage, judging that the conversation state of the previous stage is finished.
S306: and if the current conversation state is finished, updating the current conversation state, and outputting and displaying the optimal feedback information according to the current conversation state and the requirement semantic matching.
And after the conversation state of the last stage is judged to be finished, updating the current conversation state, entering the next conversation state, and outputting and displaying the best feedback information according to the current conversation state and the required semantic matching. The requirement semantics is identified according to the requirement information input by the user at this time.
S307: if not, the conversation state is not updated, and the feedback information is matched again according to the current conversation state and the required semantics to be output and displayed.
After the conversation state of the previous stage is judged to be not finished, the current feedback information cannot meet the user requirement, the conversation state is not updated at the moment, and the optimal feedback information is continuously matched again to be output and displayed according to the requirement semantics input again by the user in the current conversation state so as to meet the user requirement.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In an embodiment, a response system of the intelligent customer service is provided, and the response system of the intelligent customer service corresponds to the response method of the intelligent customer service in the above embodiment one to one. As shown in fig. 6, the response system of the intelligent customer service includes a semantic recognition module 601, a session management module 602, and an information feedback module 603, and the detailed description of each functional module is as follows:
the semantic recognition module 601 is configured to receive input information input by a user, convert the input information into text information, and recognize natural semantics of the text information.
The dialog management module 602 is configured to detect a current customer service dialog stage, and update a current dialog state according to the current customer service dialog stage.
And the information feedback module 603 is configured to select, from a preset database, corresponding feedback information to output and display in combination with the natural semantics and the current conversation state.
The semantic recognition module 601 specifically includes:
and the receiving unit is used for receiving the character, voice or image information input by the user.
And the identification unit is used for identifying the character, voice or image information input by the user and converting the character, voice or image information into text information.
And the analysis unit is used for performing lexical analysis, syntactic analysis and/or semantic analysis on the text information and outputting the intention classification to which the text features in the text information belong.
Further, the dialog management module 602 is specifically configured to pre-divide the intelligent customer service dialog into a plurality of customer service dialog stages;
and detecting a customer service conversation stage of the current customer service conversation, and updating the current customer service conversation stage to be in a current conversation state.
The information feedback module 603 specifically includes:
and the mapping unit is used for mapping the intention classification to a preset conversation behavior category system.
And the intention acquisition unit is used for acquiring the user intention from the conversation behavior category system by combining the current conversation state.
And the display unit is used for selecting corresponding feedback information from the preset database according to the user intention and outputting and displaying the feedback information.
Further, the information feedback module is also used for displaying the feedback information in a text, voice or image mode according to the current conversation state, or displaying the feedback information in a mode of triggering the task card according to the current conversation state.
Further, the system also comprises an identity information acquisition module.
The identity information acquisition module is used for acquiring the identity information of the current user.
The information feedback module 603 is further configured to select to feed back the feedback information in a text, voice, or image manner according to the current user identity information.
Further, the semantic identifying module 601 is further configured to receive demand information continuously input by a user, and identify demand semantics of the demand information.
The system also comprises a judging module which is used for judging whether the conversation state of the previous stage is finished according to the requirement semantics.
The dialog management module 602 is further configured to update the current dialog state if the judgment module judges that the previous-stage dialog state is completed, and output and display optimal feedback information according to the current dialog state and the requirement semantic matching; if the judging module judges that the conversation state of the last stage is not finished, the conversation state is not updated, and the feedback information is matched again to output and display according to the current conversation state and the required semantics.
For specific limitations of the response system of the intelligent customer service, reference may be made to the above limitations of the response method of the intelligent customer service, which are not described herein again. The modules in the response system of the intelligent customer service can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. 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 comprises a computer storage medium and an internal memory. The computer storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the computer storage media. The database of the computer device is used for storing data, such as feedback information, generated or obtained during execution of the response method of the intelligent customer service. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of responding to an intelligent customer service.
In one embodiment, a computer device is provided, which includes a memory, a processor and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement the steps of the response method of the intelligent customer service in the above embodiments, such as steps S101-S103 shown in fig. 2 or steps shown in fig. 3 to 5. Alternatively, the processor implements the functions of each module/unit in the embodiment of the response system of the intelligent customer service when executing the computer program, for example, the functions of each module/unit shown in fig. 6, and are not described herein again to avoid repetition.
In an embodiment, a computer storage medium is provided, where a computer program is stored on the computer storage medium, and when executed by a processor, the computer program implements the steps of the response method for intelligent customer service in the foregoing embodiments, for example, steps S101 to S103 shown in fig. 2 or steps shown in fig. 3 to fig. 5, which are not repeated herein to avoid repetition. Alternatively, the computer program, when executed by the processor, implements the functions of each module/unit in the above-mentioned response system for intelligent customer service, for example, the functions of each module/unit shown in fig. 6, and are not described herein again to avoid repetition.
In an alternative embodiment, it is also possible to: and uploading the result of the response method of the intelligent customer service to a block chain.
Specifically, the corresponding digest information is obtained based on the result of the response method of the intelligent customer service, and specifically, the digest information is obtained by hashing the result of the response method of the intelligent customer service, for example, by using the sha256s algorithm. Uploading summary information to the blockchain can ensure the safety and the fair transparency of the user. The user can download the summary information from the blockchain to verify whether the result of the response method of the intelligent customer service is tampered. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media used in embodiments provided herein may 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 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), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. An intelligent customer service response method is characterized by comprising the following steps:
receiving input information input by a user, converting the input information into text information, and identifying the natural semantics of the text information;
detecting a current customer service conversation stage, and updating a current conversation state according to the current customer service conversation stage;
and selecting corresponding feedback information from a preset database to output and display by combining the natural semantics and the current conversation state.
2. The method for responding to an intelligent customer service of claim 1, wherein the step of receiving input information input by a user, converting the input information into text information, and identifying the natural semantics of the text information comprises:
receiving character, voice or image information input by a user;
recognizing character, voice or image information input by a user, and converting the character, voice or image information into text information;
and performing lexical analysis, syntactic analysis and/or semantic analysis on the text information, and outputting the intention classification to which the text features in the text information belong.
3. The response method of intelligent customer service according to claim 1 or 2, wherein the step of detecting the current customer service session stage and updating the current session state according to the current customer service session stage specifically comprises:
pre-dividing an intelligent customer service conversation into a plurality of customer service conversation stages;
and detecting a customer service conversation stage of the current customer service conversation, and updating the current customer service conversation stage to be in a current conversation state.
4. The response method of intelligent customer service according to claim 2, wherein the step of selecting corresponding feedback information from the preset database to output and display in combination with the natural semantics and the current conversation state specifically comprises:
mapping the intention classification to a preset dialogue behavior category system;
acquiring a user intention from the conversation behavior category system in combination with the current conversation state;
and selecting corresponding feedback information from a preset database according to the user intention, and outputting and displaying the feedback information.
5. The method for responding to an intelligent customer service of claim 1, wherein the selecting the corresponding feedback information output display mode comprises:
and displaying the feedback information in a text, voice or image mode according to the current conversation state, or displaying the feedback information in a task card triggering mode according to the current conversation state.
6. A method of responding to an intelligent customer service as recited in claim 5, wherein prior to said step of selecting a corresponding feedback information output display, said method further comprises:
acquiring current user identity information;
the method for selecting the corresponding feedback information output display comprises the following steps:
and feeding back the feedback information in a text, voice or image mode according to the current user identity information.
7. The method of responding to intelligent customer service of claim 1, wherein after the step of selecting corresponding feedback information output display from a preset database in combination with natural semantics and current dialog state, the method further comprises:
receiving demand information continuously input by a user, and identifying demand semantics of the demand information;
judging whether the conversation state of the last stage is finished according to the requirement semantics;
if the current conversation state is finished, updating the current conversation state, and matching the optimal feedback information according to the current conversation state and the required semantics to output and display; if not, the conversation state is not updated, and the feedback information is matched again according to the current conversation state and the required semantics to be output and displayed.
8. An intelligent customer service response system, comprising:
the semantic recognition module is used for receiving input information input by a user, converting the input information into text information and recognizing the natural semantics of the text information;
the conversation management module is used for detecting the current customer service conversation stage and updating the current conversation state according to the current customer service conversation stage;
and the information feedback module is used for selecting corresponding feedback information from a preset database to output and display by combining the natural semantics and the current conversation state.
9. Computer arrangement comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor realizes the steps of the method for responding to an intelligent customer service according to any of claims 1 to 7 when executing the computer program.
10. A computer storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for responding to an intelligent customer service according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110268907.6A CN112988997A (en) | 2021-03-12 | 2021-03-12 | Response method and system of intelligent customer service, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110268907.6A CN112988997A (en) | 2021-03-12 | 2021-03-12 | Response method and system of intelligent customer service, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112988997A true CN112988997A (en) | 2021-06-18 |
Family
ID=76335073
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110268907.6A Pending CN112988997A (en) | 2021-03-12 | 2021-03-12 | Response method and system of intelligent customer service, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112988997A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113360626A (en) * | 2021-07-02 | 2021-09-07 | 北京容联七陌科技有限公司 | Multi-scene mixed question-answer recommendation method for intelligent customer service robot |
CN113590778A (en) * | 2021-06-30 | 2021-11-02 | 上海一谈网络科技有限公司 | Intelligent customer service intention understanding method, device, equipment and storage medium |
CN114706965A (en) * | 2022-03-22 | 2022-07-05 | 广州营客信息科技有限公司 | AI intelligent customer service system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160162978A1 (en) * | 2014-12-08 | 2016-06-09 | Alibaba Group Holding Limited | Method and system for providing conversation quick phrases |
CN109783624A (en) * | 2018-12-27 | 2019-05-21 | 联想(北京)有限公司 | Answer generation method, device and the intelligent conversational system in knowledge based library |
CN112365892A (en) * | 2020-11-10 | 2021-02-12 | 杭州大搜车汽车服务有限公司 | Man-machine interaction method, device, electronic device and storage medium |
-
2021
- 2021-03-12 CN CN202110268907.6A patent/CN112988997A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160162978A1 (en) * | 2014-12-08 | 2016-06-09 | Alibaba Group Holding Limited | Method and system for providing conversation quick phrases |
CN109783624A (en) * | 2018-12-27 | 2019-05-21 | 联想(北京)有限公司 | Answer generation method, device and the intelligent conversational system in knowledge based library |
CN112365892A (en) * | 2020-11-10 | 2021-02-12 | 杭州大搜车汽车服务有限公司 | Man-machine interaction method, device, electronic device and storage medium |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113590778A (en) * | 2021-06-30 | 2021-11-02 | 上海一谈网络科技有限公司 | Intelligent customer service intention understanding method, device, equipment and storage medium |
CN113360626A (en) * | 2021-07-02 | 2021-09-07 | 北京容联七陌科技有限公司 | Multi-scene mixed question-answer recommendation method for intelligent customer service robot |
CN114706965A (en) * | 2022-03-22 | 2022-07-05 | 广州营客信息科技有限公司 | AI intelligent customer service system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112988997A (en) | Response method and system of intelligent customer service, computer equipment and storage medium | |
EP3855324A1 (en) | Associative recommendation method and apparatus, computer device, and storage medium | |
CN111695439A (en) | Image structured data extraction method, electronic device and storage medium | |
CN109766072B (en) | Information verification input method and device, computer equipment and storage medium | |
CN109033058B (en) | Contract text verification method, apparatus, computer device and storage medium | |
CN110442697B (en) | Man-machine interaction method, system, computer equipment and storage medium | |
CN110929125A (en) | Search recall method, apparatus, device and storage medium thereof | |
WO2022041825A1 (en) | Method and apparatus for converting image into webpage, and computer device and storage medium | |
CN111783471A (en) | Semantic recognition method, device, equipment and storage medium of natural language | |
CN112380240A (en) | Data query method, device and equipment based on semantic recognition and storage medium | |
WO2022126978A1 (en) | Invoice information extraction method and apparatus, computer device and storage medium | |
CN112925898B (en) | Question-answering method and device based on artificial intelligence, server and storage medium | |
CN112434501A (en) | Work order intelligent generation method and device, electronic equipment and medium | |
CN112559526A (en) | Data table export method and device, computer equipment and storage medium | |
CN111859862B (en) | Text data labeling method and device, storage medium and electronic device | |
CN113886577A (en) | Text classification method, device, equipment and storage medium | |
CN115994232B (en) | Online multi-version document identity authentication method, system and computer equipment | |
CN111985467A (en) | Chat record screenshot processing method and device, computer equipment and storage medium | |
CN114528851B (en) | Reply sentence determination method, reply sentence determination device, electronic equipment and storage medium | |
CN111368709A (en) | Picture text recognition method, device and equipment and readable storage medium | |
CN111209488B (en) | Information sharing method and device | |
CN114943306A (en) | Intention classification method, device, equipment and storage medium | |
CN113901821A (en) | Entity naming identification method, device, equipment and storage medium | |
CN114780602A (en) | Data tracing analysis method and device, computer equipment and storage medium | |
CN114429634A (en) | Identity authentication information filling method, system, device and storage medium |
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 |