CN112653798A - Intelligent customer service voice response method and device, computer equipment and storage medium - Google Patents

Intelligent customer service voice response method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN112653798A
CN112653798A CN202011532047.4A CN202011532047A CN112653798A CN 112653798 A CN112653798 A CN 112653798A CN 202011532047 A CN202011532047 A CN 202011532047A CN 112653798 A CN112653798 A CN 112653798A
Authority
CN
China
Prior art keywords
user
response
file
semantic matching
text information
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
CN202011532047.4A
Other languages
Chinese (zh)
Inventor
李改英
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.)
Ping An Puhui Enterprise Management Co Ltd
Original Assignee
Ping An Puhui Enterprise Management 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 Ping An Puhui Enterprise Management Co Ltd filed Critical Ping An Puhui Enterprise Management Co Ltd
Priority to CN202011532047.4A priority Critical patent/CN112653798A/en
Publication of CN112653798A publication Critical patent/CN112653798A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • H04M3/5166—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing in combination with interactive voice response systems or voice portals, e.g. as front-ends
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/237—Lexical tools
    • G06F40/247—Thesauruses; Synonyms
    • 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
    • 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
    • G06Q30/01—Customer relationship services
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Signal Processing (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the application belongs to the field of artificial intelligence, is applied to the field of intelligent customer service, and relates to an intelligent customer service voice response method, an intelligent customer service voice response device, computer equipment and a storage medium, wherein the method comprises the following steps: receiving a voice conversation request, wherein the voice conversation request comprises user information and current node information; recording user voice, and converting the user voice into text information; selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with topic keywords and user categories; inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords; and determining a response file according to the semantic matching degree and the user information. And providing a pointed response according to the node information and the user information, so that the response is more suitable for the user to ask a question, and the user satisfaction is improved.

Description

Intelligent customer service voice response method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to an intelligent customer service voice response method, apparatus, computer device, and storage medium.
Background
With the development of communication technology and internet technology, telephone customer service and computer customer service replace manual customer service in customer service business, the telephone customer service needs to listen to menu prompts layer by layer, and the service can be obtained only by conducting key operation step by step according to guidance, so that poor experience is easily caused to users, and the problems of the users are not solved in time, and the loss of the users is caused. Meanwhile, the intelligent customer service provided by the computer responds uniformly, the customer problem cannot be solved generally, a large amount of service is poured into the manual seats, and valuable manual seat resources are put into labor with simplicity, repeatability and low value, so that the overall working efficiency of the call center is difficult to improve, the operation cost is high, and the customer satisfaction is also influenced.
Disclosure of Invention
The embodiment of the application aims to provide an intelligent customer service voice response method, an intelligent customer service voice response device, computer equipment and a storage medium, so as to solve the problems that the response of the intelligent customer service is not in accordance with the question of a user and the satisfaction degree of the user is low.
In order to solve the above technical problem, an embodiment of the present application provides an intelligent customer service voice response method, which adopts the following technical solutions:
receiving a voice conversation request, wherein the voice conversation request comprises user information and current node information;
recording user voice, and converting the user voice into text information;
selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with topic keywords and user categories;
inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords;
comparing the semantic matching degree with a preset threshold value, and determining the file marked with the subject keyword as a candidate file when the semantic matching degree is greater than the threshold value;
determining the category of the user according to the user information;
and comparing the class to which the user belongs with the class labeled by the candidate answer file, and determining the candidate file with the labeled user class consistent with the class to which the user belongs as the answer file.
Further, before the step of inputting the text information and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword, the method further comprises:
and comparing the text information with a preset shutdown word bank, and deleting words in the text information, which are consistent with the words in the shutdown word bank.
Further, before the step of inputting the text information and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword, the method further comprises:
comparing the text information with a preset first keyword, and when the text information contains the first keyword, sending the voice conversation request to a preset artificial seat platform;
and receiving a response returned by the artificial seat platform.
Further, before the step of inputting the text information and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword, the method further comprises:
performing word segmentation on the character information to obtain word segmentation results of the character information;
matching the word segmentation result with a preset synonym library to obtain synonyms of all the words in the text information;
and inputting the synonym and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword.
Further, after the step of comparing the category to which the user belongs with the user category labeled by the candidate answer file, and determining the candidate file with the labeled user category consistent with the category to which the user belongs as the answer file, the method further comprises the following steps:
and playing response audio according to the response file.
Further, after the step of playing the response audio according to the response file, the method further includes:
obtaining user feedback;
constructing question-response data pairs according to the text information and the topic keywords marked on the response files, and marking actual matching results on the data pairs according to user feedback;
inputting the data pair into the NLP semantic matching model, and acquiring a prediction matching result output by the NLP semantic matching model in response to the data pair;
and adjusting parameters of each node of the NLP semantic matching model to make the predicted matching result consistent with the actual matching result.
Further, the file in the sub-file library is a text file, and the step of playing the response audio according to the response file comprises:
inputting the response file into a preset voice generation model to obtain response audio;
and playing the response audio.
In order to solve the above technical problem, an embodiment of the present application further provides an intelligent customer service voice response device, which adopts the following technical solution:
the receiving module is used for receiving a voice conversation request, and the voice conversation request comprises user information and current node information;
the conversion module is used for recording user voice and converting the user voice into character information;
the selection module is used for selecting a corresponding sub-file library from a preset response file library according to the node information, and the files in the sub-file library are marked with topic keywords and user categories;
the processing module is used for inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords;
the comparison module is used for comparing the semantic matching degree with a preset threshold value, and when the semantic matching degree is greater than the threshold value, determining the file marked with the subject keyword as a candidate file;
the classification module is used for determining the category of the user according to the user information;
and the determining module is used for comparing the category to which the user belongs with the user category labeled by the candidate answer file and determining the candidate file with the labeled user category consistent with the category to which the user belongs as the answer file.
Further, the intelligent customer service voice response device further comprises:
and the first comparison pair module is used for comparing the text information with a preset shutdown word bank and deleting words in the text information, which are consistent with the words in the shutdown word bank.
Further, the intelligent customer service voice response device further comprises:
the first forwarding sub-module is used for comparing the text information with a preset first keyword, and sending the voice conversation request to a preset artificial seat platform when the text information contains the first keyword;
and the first receiving submodule is used for receiving the response returned by the artificial seat platform.
Further, the intelligent customer service voice response device further comprises:
the first word segmentation submodule is used for segmenting the word information to obtain a word segmentation result of the word information;
the first matching sub-module is used for matching the word segmentation result with a preset synonym library to obtain synonyms of all the segmented words in the text information;
and the first processing sub-module is used for inputting the synonym and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword.
Further, the intelligent customer service voice response device further comprises:
and the playing module is used for playing the response audio according to the response file.
Further, the intelligent customer service voice response device further comprises:
the first obtaining submodule is used for obtaining user feedback;
the first labeling submodule is used for constructing a question-response data pair according to the text information and the topic key words labeled by the response file, and labeling an actual matching result of the data pair according to user feedback;
the first prediction submodule is used for inputting the data pair into the NLP semantic matching model and acquiring a prediction matching result output by the NLP semantic matching model in response to the data pair;
and the first adjusting submodule is used for adjusting the parameters of each node of the NLP semantic matching model to enable the predicted matching result to be consistent with the actual matching result.
Further, the playing module includes:
the first generation submodule is used for inputting the response file into a preset voice generation model to obtain response audio;
and the first playing submodule is used for playing the response audio.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:
a computer device comprises a memory and a processor, wherein the memory stores computer readable instructions, and the processor executes the computer readable instructions to realize the steps of the intelligent customer service voice response method.
In order to solve the above technical problem, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:
a computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the intelligent customer service voice response method as described above.
Compared with the prior art, the embodiment of the application mainly has the following beneficial effects: receiving a voice conversation request, wherein the voice conversation request comprises user information and current node information; recording user voice, and converting the user voice into text information; selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with topic keywords and user categories; inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords; comparing the semantic matching degree with a preset threshold value, and determining the file marked with the subject keyword as a candidate file when the semantic matching degree is greater than the threshold value; determining the category of the user according to the user information; and comparing the class to which the user belongs with the class labeled by the candidate answer file, and determining the candidate file with the labeled user class consistent with the class to which the user belongs as the answer file. And providing a pointed response according to the node information and the user information, so that the response is more suitable for the user to ask a question, and the user satisfaction is improved.
Drawings
In order to more clearly illustrate the solution of the present application, the drawings needed for describing the embodiments of the present application will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a smart customer service voice response method according to the present application;
FIG. 3 is a flow diagram of one embodiment of transitioning to an agent;
FIG. 4 is a schematic block diagram illustrating one embodiment of a smart customer service voice response unit in accordance with the subject application;
FIG. 5 is a schematic block diagram of one embodiment of a computer device according to the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "including" and "having," and any variations thereof, in the description and claims of this application and the description of the above figures are intended to cover non-exclusive inclusions. The terms "first," "second," and the like in the description and claims of this application or in the above-described drawings are used for distinguishing between different objects and not for describing a particular order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a web browser application, a shopping application, a search application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the intelligent customer service voice response method provided by the embodiment of the present application generally consists ofServer/terminal Terminal equipmentThe execution is carried out, and accordingly, the intelligent customer service voice response device is generally arranged inServer/terminal deviceIn (1).
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow diagram of one embodiment of a method for intelligent customer service voice response according to the present application is shown. The intelligent customer service voice response method comprises the following steps:
step S201, receiving a voice dialog request, where the voice dialog request includes user information and current node information.
In the embodiment, the electronic device (such as the one shown in fig. 1) on which the intelligent customer service voice response method operatesGarment Server/terminal device) The voice conversation request may be received through a wired connection or a wireless connection. It should be noted that the wireless connection means may include, but is not limited to, a 3G/4G connection, a WiFi connection, a bluetooth connection, a WiMAX connection, a Zigbee connection, a uwb (ultra wideband) connection, and other wireless connection means now known or developed in the future.
And voice suspension navigation is added on a human-computer interaction interface, so that a user is supported to call an intelligent customer service at any time to carry out voice conversation. Usually, when a user has a problem in applying for service, an intelligent customer service voice call request is initiated. The user initiates a voice conversation request, records a node where the user initiates the voice conversation request, and reads user information according to the user ID, wherein the user information comprises but is not limited to age, occupation and the like. The node where the user initiates the dialogue request belongs, for example, the node of the application program of the financial loan application is provided with loan qualification verification, loan amount application and the like.
Step S202, recording user voice, and converting the user voice into text information.
In this embodiment, after receiving the voice conversation request, the switch of the recording device is turned on to record and store the voice of the user. And then converting the user voice into text information. Speech to text human Speech can be converted to text using common ASR technology (Automatic Speech Recognition).
Step S203, selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with the topic keywords and the user categories.
And selecting a corresponding sub-library from a preset response file library according to the node information carried in the voice conversation request. In this embodiment, the human-computer interaction interface is provided with a plurality of nodes interacting with the user, the nodes correspond to different nodes, the problems encountered by the user are different, in order to reduce the calculation amount, the preset response document library is divided into libraries, each sub-library corresponds to one node, and the corresponding sub-library is called through node information carried in the voice conversation request. The sub-library is a series of answer documents, and each document is at least marked with applicable user categories and topic keywords of the document. The response file may be a text file or an audio file.
Step S204, inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching, and obtaining the semantic matching degree of the text information and the subject keywords.
In the embodiment, the text information converted from the user recording and the subject keywords labeled on the document are input into a pre-trained NLP semantic matching model, the matching degree between the text information and the pre-trained NLP semantic matching model is calculated, and the document with the matching degree larger than a set threshold value is taken as a candidate document.
In the training process of the NLP (natural language processing) semantic matching model, a deep neural network can express Query and Title into low-dimensional semantic vectors through massive click exposure logs of Query and Title in a search engine, the distance between the two semantic vectors is calculated through cosine distance, the weight of each node of the deep neural network is adjusted, the predicted matching result is consistent with the actual Query-Title matching result, and the NLP semantic matching model is finally obtained.
Step S205, comparing the semantic matching degree with a preset threshold, and when the semantic matching degree is greater than the threshold, determining the document marked with the subject keyword as a candidate document.
And comparing the semantic matching degree with a preset threshold, and determining the file marked with the subject keyword as a candidate file when the semantic matching degree of the text information and the subject keyword is greater than the threshold.
And step S206, determining the category of the user according to the user information.
The user information and the text information converted according to the recorded user voice determine how the intelligent customer service responds. For example, different users ask the same question, "what materials are needed for applying for loan", according to the user information, one of the users successfully applies for loan by using the application program once, the other user is a new user, the materials needed for applying for the two users are not consistent, and different response documents are prepared in advance for the same question of the users of different types in order to answer the questions of the two types of users more accurately. Making the response more appropriate to each type of client.
The category of the user is determined according to the user information, the user is determined through a rule matching algorithm, for example, the set rule is that the age is more than 30 and less than 45, the academic record is the subject, the client with the profession as an engineer is a type 1 client, and the user category is determined through comparing the user information with the set rule.
Step S207, comparing the user belonged category with the user category labeled by the candidate answer file, and determining the candidate file with the labeled user category consistent with the user belonged category as the answer file.
And comparing the class to which the user belongs with the class of the user marked by the candidate answer file, and when the marked class of the user is consistent with the class to which the user belongs, the corresponding candidate file is the answer file.
The method comprises the steps that a voice conversation request is received, wherein the voice conversation request comprises user information and current node information; recording user voice, and converting the user voice into text information; selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with topic keywords and user categories; inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords; comparing the semantic matching degree with a preset threshold value, and determining the file marked with the subject keyword as a candidate file when the semantic matching degree is greater than the threshold value; determining the category of the user according to the user information; and comparing the class to which the user belongs with the class labeled by the candidate answer file, and determining the candidate file with the labeled user class consistent with the class to which the user belongs as the answer file. And providing a pointed response according to the node information and the user information, so that the response is more suitable for the user to ask a question, and the user satisfaction is improved.
In some optional implementations of this embodiment, before step S204, the electronic device may further perform the following steps:
and comparing the text information with a preset shutdown word bank, and deleting words in the text information, which are consistent with the words in the shutdown word bank.
Since the user voice usually contains some words without specific meanings, in order to reduce the calculation amount of the subsequent step processing, the corpus cleaning is carried out on the user voice to character conversion result. Words appearing in the word stock, such as "kayian", "this", "that", etc., are filtered from the text information by matching with a preset disabled word stock.
In some optional implementations, before step S204, the electronic device may perform the following steps:
comparing the text information with a preset first keyword, and when the text information contains the first keyword, sending the voice conversation request to a preset artificial seat platform;
and receiving a response returned by the artificial seat platform.
For example, the preset first keyword is "artificial customer service", and when the user voice contains the "artificial customer service" keyword, the voice conversation request is directly sent to the artificial seat platform. A rapid channel for seeking manual service is provided for users, so that switching between intelligent customer service and manual customer service is very convenient, and user experience is improved.
In some optional implementations, before step S204, the electronic device may perform the following steps:
performing word segmentation on the character information to obtain word segmentation results of the character information;
matching the word segmentation result with a preset synonym library to obtain synonyms of all the words in the text information;
and inputting the synonym and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword.
In this embodiment, a synonym library is preset, the preset synonym library is queried according to keywords in the text information, multiple synonyms of the keywords are obtained, and the multiple synonyms are compared with the topic keywords labeled by the file to obtain the candidate file.
In some optional implementations, after step S207, the electronic device may perform the following steps:
and playing response audio according to the response file.
And playing the response file by using an audio playing module.
In some optional implementations, after step S207, the electronic device may perform the following steps:
obtaining user feedback;
constructing question-response data pairs according to the text information and the topic keywords marked on the response files, and marking actual matching results on the data pairs according to user feedback;
inputting the data pair into the NLP semantic matching model, and acquiring a prediction matching result output by the NLP semantic matching model in response to the data pair;
and adjusting parameters of each node of the NLP semantic matching model to make the predicted matching result consistent with the actual matching result.
Recording feedback of a user on the question response of the current round, forming question-response data pairs by the text information and the topic keywords marked on the response files, marking actual matching results of the data pairs according to the feedback of the user, such as user feedback satisfaction, marking the matching degree of the question-response data pairs as 1, otherwise marking the matching degree as 0, inputting the data pairs into the NLP semantic matching model, and adjusting parameters of each node to enable the matching degree output by the NLP semantic matching model to be consistent with the marked matching degree.
In some embodiments, the NLP semantic matching model is optimized by using data formed by multi-round question response, and the optimized NLP semantic matching model is used for semantic matching, so that the contact degree between response and question is improved, and the user satisfaction is improved.
In some optional implementations, when the answer file is a text file, the electronic device may perform the following steps:
inputting the response file into a preset voice generation model to obtain response audio;
and playing the response audio.
When the response file is a text file, the response file is subjected to voice conversion, and universal software can be adopted for converting characters into voice.
When the response file is a text file, the response file occupies a small storage space relative to an audio file, and can be converted into audio with different timbres through voice conversion, so that the interestingness of an intelligent client is improved.
The application is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
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 associated with computer readable instructions, which can be stored in a computer readable storage medium, and when executed, the processes of the embodiments of the methods described above can be included. The storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a Random Access Memory (RAM).
It should be understood that, although the steps in the flowcharts of the figures 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 performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
With further reference to fig. 4, as an implementation of the method shown in fig. 2, the present application provides an embodiment of an intelligent customer service voice response apparatus, where the apparatus embodiment corresponds to the method embodiment shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 4, the intelligent customer service voice response device 400 according to this embodiment includes: a receiving module 401, a converting module 402, a selecting module 403, a processing module 404, a comparing module 405, a categorizing module 406, and a determining module 407. Wherein:
a receiving module 401, configured to receive a voice conversation request, where the voice conversation request includes user information and current node information;
a conversion module 402, configured to record a user voice and convert the user voice into text information;
a selecting module 403, configured to select a corresponding sub-file library from a preset response file library according to the node information, where files in the sub-file library are labeled with a topic keyword and a user category;
a processing module 404, configured to input the text information and the topic keyword into a pre-trained NLP semantic matching model for semantic matching, so as to obtain a semantic matching degree between the text information and the topic keyword;
a comparison module 405, configured to compare the semantic matching degree with a preset threshold, and when the semantic matching degree is greater than the threshold, determine that the file labeled with the topic keyword is a candidate file;
a classification module 406, configured to determine, according to the user information, a category to which the user belongs;
the determining module 407 is configured to compare the category to which the user belongs with the user category labeled by the candidate answer file, and determine that the candidate file with the labeled user category consistent with the category to which the user belongs is the answer file.
In the embodiment, a voice conversation request is received, wherein the voice conversation request comprises user information and current node information; recording user voice, and converting the user voice into text information; selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with topic keywords and user categories; inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords; comparing the semantic matching degree with a preset threshold value, and determining the file marked with the subject keyword as a candidate file when the semantic matching degree is greater than the threshold value; determining the category of the user according to the user information; and comparing the class to which the user belongs with the class labeled by the candidate answer file, and determining the candidate file with the labeled user class consistent with the class to which the user belongs as the answer file. And providing a pointed response according to the node information and the user information, so that the response is more suitable for the user to ask a question, and the user satisfaction is improved.
In some optional implementations of this embodiment, the intelligent customer service voice response device further includes:
and the first comparison pair module is used for comparing the text information with a preset shutdown word bank and deleting words in the text information, which are consistent with the words in the shutdown word bank.
In some optional implementations of this embodiment, the intelligent customer service voice response device further includes:
the first forwarding sub-module is used for comparing the text information with a preset first keyword, and sending the voice conversation request to a preset artificial seat platform when the text information contains the first keyword;
and the first receiving submodule is used for receiving the response returned by the artificial seat platform.
In some optional implementations of this embodiment, the intelligent customer service voice response device further includes: :
the first word segmentation submodule is used for segmenting the word information to obtain a word segmentation result of the word information;
the first matching sub-module is used for matching the word segmentation result with a preset synonym library to obtain synonyms of all the segmented words in the text information;
and the first processing sub-module is used for inputting the synonym and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword.
In some optional implementations of this embodiment, the intelligent customer service voice response device further includes:
and the playing module is used for playing the response audio according to the response file.
In some optional implementations of this embodiment, the intelligent customer service voice response device further includes:
the first obtaining submodule is used for obtaining user feedback;
the first labeling submodule is used for constructing a question-response data pair according to the text information and the topic key words labeled by the response file, and labeling an actual matching result of the data pair according to user feedback;
the first prediction submodule is used for inputting the data pair into the NLP semantic matching model and acquiring a prediction matching result output by the NLP semantic matching model in response to the data pair;
and the first adjusting submodule is used for adjusting the parameters of each node of the NLP semantic matching model to enable the predicted matching result to be consistent with the actual matching result.
In some optional implementations of this embodiment, the playing module includes:
the first generation submodule is used for inputting the response file into a preset voice generation model to obtain response audio;
and the first playing submodule is used for playing the response audio.
In order to solve the technical problem, an embodiment of the present application further provides a computer device. Referring to fig. 5, fig. 5 is a block diagram of a basic structure of a computer device according to the present embodiment.
The computer device 5 comprises a memory 51, a processor 52, a network interface 53 communicatively connected to each other via a system bus. It is noted that only a computer device 5 having components 51-53 is shown, but it is understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead. As will be understood by those skilled in the art, the computer device is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device, and the like.
The computer device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The computer equipment can carry out man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch panel or voice control equipment and the like.
The memory 51 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 51 may be an internal storage unit of the computer device 5, such as a hard disk or a memory of the computer device 5. In other embodiments, the memory 51 may also be an external storage device of the computer device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the computer device 5. Of course, the memory 51 may also comprise both an internal storage unit of the computer device 5 and an external storage device thereof. In this embodiment, the memory 51 is generally used for storing an operating system installed in the computer device 5 and various application software, such as computer readable instructions of an intelligent customer service voice response method. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 52 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device 5. In this embodiment, the processor 52 is configured to execute computer readable instructions stored in the memory 51 or process data, for example, execute computer readable instructions of the intelligent customer service voice response method.
The network interface 53 may comprise a wireless network interface or a wired network interface, and the network interface 53 is generally used for establishing communication connections between the computer device 5 and other electronic devices.
Receiving a voice conversation request, wherein the voice conversation request comprises user information and current node information; recording user voice, and converting the user voice into text information; selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with topic keywords and user categories; inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords; comparing the semantic matching degree with a preset threshold value, and determining the file marked with the subject keyword as a candidate file when the semantic matching degree is greater than the threshold value; determining the category of the user according to the user information; and comparing the class to which the user belongs with the class labeled by the candidate answer file, and determining the candidate file with the labeled user class consistent with the class to which the user belongs as the answer file. And providing a pointed response according to the node information and the user information, so that the response is more suitable for the user to ask a question, and the user satisfaction is improved.
The present application further provides another embodiment, which is to provide a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the intelligent customer service voice response method as described above.
Receiving a voice conversation request, wherein the voice conversation request comprises user information and current node information; recording user voice, and converting the user voice into text information; selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with topic keywords and user categories; inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords; comparing the semantic matching degree with a preset threshold value, and determining the file marked with the subject keyword as a candidate file when the semantic matching degree is greater than the threshold value; determining the category of the user according to the user information; and comparing the class to which the user belongs with the class labeled by the candidate answer file, and determining the candidate file with the labeled user class consistent with the class to which the user belongs as the answer file. And providing a pointed response according to the node information and the user information, so that the response is more suitable for the user to ask a question, and the user satisfaction is improved.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
It is to be understood that the above-described embodiments are merely illustrative of some, but not restrictive, of the broad invention, and that the appended drawings illustrate preferred embodiments of the invention and do not limit the scope of the invention. This application is capable of embodiments in many different forms and is provided for the purpose of enabling a thorough understanding of the disclosure of the application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to one skilled in the art that the present application may be practiced without modification or with equivalents of some of the features described in the foregoing embodiments. All equivalent structures made by using the contents of the specification and the drawings of the present application are directly or indirectly applied to other related technical fields and are within the protection scope of the present application.

Claims (10)

1. An intelligent customer service voice response method is characterized by comprising the following steps:
receiving a voice conversation request, wherein the voice conversation request comprises user information and current node information;
recording user voice, and converting the user voice into text information;
selecting a corresponding sub-file library from a preset response file library according to the node information, wherein the files in the sub-file library are marked with topic keywords and user categories;
inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords;
comparing the semantic matching degree with a preset threshold value, and determining the file marked with the subject keyword as a candidate file when the semantic matching degree is greater than the threshold value;
determining the category of the user according to the user information;
and comparing the class to which the user belongs with the class labeled by the candidate answer file, and determining the candidate file with the labeled user class consistent with the class to which the user belongs as the answer file.
2. The intelligent customer service voice response method according to claim 1, wherein before the step of inputting the text information and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword, the method further comprises:
and comparing the text information with a preset shutdown word bank, and deleting words in the text information, which are consistent with the words in the shutdown word bank.
3. The intelligent customer service voice response method according to claim 1, wherein before the step of inputting the text information and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword, the method further comprises:
comparing the text information with a preset first keyword, and when the text information contains the first keyword, sending the voice conversation request to a preset artificial seat platform;
and receiving a response returned by the artificial seat platform.
4. The intelligent customer service voice response method according to claim 1, wherein before the step of inputting the text information and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword, the method further comprises:
performing word segmentation on the character information to obtain word segmentation results of the character information;
matching the word segmentation result with a preset synonym library to obtain synonyms of all the words in the text information;
and inputting the synonym and the subject keyword into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keyword.
5. The intelligent customer service voice response method according to claim 1, wherein after the step of comparing the category to which the user belongs with the user category labeled by the candidate response file, determining the candidate file with the labeled user category consistent with the category to which the user belongs as the response file, further comprises:
and playing response audio according to the response file.
6. The intelligent customer service voice response method according to claim 5, further comprising, after the step of playing response audio according to the response file:
obtaining user feedback;
constructing question-response data pairs according to the text information and the topic keywords marked on the response files, and marking actual matching results on the data pairs according to user feedback;
inputting the data pair into the NLP semantic matching model, and acquiring a prediction matching result output by the NLP semantic matching model in response to the data pair;
and adjusting parameters of each node of the NLP semantic matching model to make the predicted matching result consistent with the actual matching result.
7. The intelligent customer service voice response method according to claim 5, wherein the files in the sub-file library are text files, and the step of playing the response audio according to the response files comprises:
inputting the response file into a preset voice generation model to obtain response audio;
and playing the response audio.
8. An intelligent customer service voice response device, comprising:
the receiving module is used for receiving a voice conversation request, and the voice conversation request comprises user information and current node information;
the conversion module is used for recording user voice and converting the user voice into character information;
the selection module is used for selecting a corresponding sub-file library from a preset response file library according to the node information, and the files in the sub-file library are marked with topic keywords and user categories;
the processing module is used for inputting the text information and the subject keywords into a pre-trained NLP semantic matching model for semantic matching to obtain the semantic matching degree of the text information and the subject keywords;
the comparison module is used for comparing the semantic matching degree with a preset threshold value, and when the semantic matching degree is greater than the threshold value, determining the file marked with the subject keyword as a candidate file;
the classification module is used for determining the category of the user according to the user information;
and the determining module is used for comparing the category to which the user belongs with the user category labeled by the candidate answer file and determining the candidate file with the labeled user category consistent with the category to which the user belongs as the answer file.
9. A computer device comprising a memory having computer readable instructions stored therein and a processor that when executed performs the steps of the intelligent customer service voice response method of any one of claims 1 to 7.
10. A computer readable storage medium having computer readable instructions stored thereon which, when executed by a processor, implement the steps of the intelligent customer service voice response method according to any one of claims 1 to 7.
CN202011532047.4A 2020-12-22 2020-12-22 Intelligent customer service voice response method and device, computer equipment and storage medium Pending CN112653798A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011532047.4A CN112653798A (en) 2020-12-22 2020-12-22 Intelligent customer service voice response method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011532047.4A CN112653798A (en) 2020-12-22 2020-12-22 Intelligent customer service voice response method and device, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112653798A true CN112653798A (en) 2021-04-13

Family

ID=75359269

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011532047.4A Pending CN112653798A (en) 2020-12-22 2020-12-22 Intelligent customer service voice response method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112653798A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113053394A (en) * 2021-04-27 2021-06-29 广州小鹏汽车科技有限公司 Voice processing method, server, voice processing system and storage medium
CN113299294A (en) * 2021-05-26 2021-08-24 中国平安人寿保险股份有限公司 Task type dialogue robot interaction method, device, equipment and storage medium
CN113468306A (en) * 2021-06-30 2021-10-01 西安乾阳电子科技有限公司 Voice conversation method, device, electronic equipment and storage medium
CN113506550A (en) * 2021-07-29 2021-10-15 北京花兰德科技咨询服务有限公司 Artificial intelligent reading display and display method
CN113515705A (en) * 2021-07-27 2021-10-19 平安普惠企业管理有限公司 Response information generation method, device, equipment and computer readable storage medium
CN113656566A (en) * 2021-08-18 2021-11-16 中国平安人寿保险股份有限公司 Intelligent dialogue processing method and device, computer equipment and storage medium
CN113658684A (en) * 2021-08-11 2021-11-16 挂号网（杭州）科技有限公司 Consultation result generation method and device, electronic equipment and storage medium
CN113658684B (en) * 2021-08-11 2024-05-31 挂号网（杭州）科技有限公司 Consultation result generation method and device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103051815A (en) * 2012-11-29 2013-04-17 东莞宇龙通信科技有限公司 Call forwarding method and system
CN105721728A (en) * 2016-02-16 2016-06-29 上海斐讯数据通信技术有限公司 Call forwarding method based on WiFi and intelligent terminal
CN107708078A (en) * 2017-09-13 2018-02-16 捷开通讯(深圳)有限公司 Mobile terminal and its call transferring method, storage device
CN107798032A (en) * 2017-02-17 2018-03-13 平安科技（深圳）有限公司 Response message treating method and apparatus in self-assisted voice session
CN111090726A (en) * 2019-12-04 2020-05-01 中国南方电网有限责任公司 NLP-based electric power industry character customer service interaction method
CN111739519A (en) * 2020-06-16 2020-10-02 平安科技（深圳）有限公司 Dialogue management processing method, device, equipment and medium based on voice recognition

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103051815A (en) * 2012-11-29 2013-04-17 东莞宇龙通信科技有限公司 Call forwarding method and system
CN105721728A (en) * 2016-02-16 2016-06-29 上海斐讯数据通信技术有限公司 Call forwarding method based on WiFi and intelligent terminal
CN107798032A (en) * 2017-02-17 2018-03-13 平安科技（深圳）有限公司 Response message treating method and apparatus in self-assisted voice session
CN107708078A (en) * 2017-09-13 2018-02-16 捷开通讯(深圳)有限公司 Mobile terminal and its call transferring method, storage device
CN111090726A (en) * 2019-12-04 2020-05-01 中国南方电网有限责任公司 NLP-based electric power industry character customer service interaction method
CN111739519A (en) * 2020-06-16 2020-10-02 平安科技（深圳）有限公司 Dialogue management processing method, device, equipment and medium based on voice recognition

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113053394A (en) * 2021-04-27 2021-06-29 广州小鹏汽车科技有限公司 Voice processing method, server, voice processing system and storage medium
CN113053394B (en) * 2021-04-27 2024-01-09 广州小鹏汽车科技有限公司 Speech processing method, server, speech processing system, and storage medium
CN113299294A (en) * 2021-05-26 2021-08-24 中国平安人寿保险股份有限公司 Task type dialogue robot interaction method, device, equipment and storage medium
CN113468306A (en) * 2021-06-30 2021-10-01 西安乾阳电子科技有限公司 Voice conversation method, device, electronic equipment and storage medium
CN113515705A (en) * 2021-07-27 2021-10-19 平安普惠企业管理有限公司 Response information generation method, device, equipment and computer readable storage medium
CN113506550A (en) * 2021-07-29 2021-10-15 北京花兰德科技咨询服务有限公司 Artificial intelligent reading display and display method
CN113658684A (en) * 2021-08-11 2021-11-16 挂号网（杭州）科技有限公司 Consultation result generation method and device, electronic equipment and storage medium
CN113658684B (en) * 2021-08-11 2024-05-31 挂号网（杭州）科技有限公司 Consultation result generation method and device, electronic equipment and storage medium
CN113656566A (en) * 2021-08-18 2021-11-16 中国平安人寿保险股份有限公司 Intelligent dialogue processing method and device, computer equipment and storage medium

Similar Documents

Publication Publication Date Title
CN112685565B (en) Text classification method based on multi-mode information fusion and related equipment thereof
CN112653798A (en) Intelligent customer service voice response method and device, computer equipment and storage medium
CN111368043A (en) Event question-answering method, device, equipment and storage medium based on artificial intelligence
WO2021121198A1 (en) Semantic similarity-based entity relation extraction method and apparatus, device and medium
CN110825956A (en) Information flow recommendation method and device, computer equipment and storage medium
CN112863683A (en) Medical record quality control method and device based on artificial intelligence, computer equipment and storage medium
CN112507116A (en) Customer portrait method based on customer response corpus and related equipment thereof
CN113486170B (en) Natural language processing method, device, equipment and medium based on man-machine interaction
CN112632244A (en) Man-machine conversation optimization method and device, computer equipment and storage medium
CN112528654A (en) Natural language processing method and device and electronic equipment
CN112084752A (en) Statement marking method, device, equipment and storage medium based on natural language
CN112836521A (en) Question-answer matching method and device, computer equipment and storage medium
CN115438149A (en) End-to-end model training method and device, computer equipment and storage medium
CN112669876A (en) Emotion recognition method and device, computer equipment and storage medium
CN114817478A (en) Text-based question and answer method and device, computer equipment and storage medium
CN117312535A (en) Method, device, equipment and medium for processing problem data based on artificial intelligence
CN112995414A (en) Behavior quality inspection method, device, equipment and storage medium based on voice call
CN117275466A (en) Business intention recognition method, device, equipment and storage medium thereof
US20230206007A1 (en) Method for mining conversation content and method for generating conversation content evaluation model
CN115878768A (en) NLP-based vehicle insurance service call-back clue recommendation method and related equipment thereof
CN113256395B (en) Product recommendation method, device, equipment and storage medium based on recommendation graph network
CN115238077A (en) Text analysis method, device and equipment based on artificial intelligence and storage medium
CN112364649B (en) Named entity identification method and device, computer equipment and storage medium
CN114637831A (en) Data query method based on semantic analysis and related equipment thereof
CN114238574B (en) Intention recognition method based on artificial intelligence and related equipment thereof

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