CN117424960A

CN117424960A - Intelligent voice service method, device, terminal equipment and storage medium

Info

Publication number: CN117424960A
Application number: CN202311422819.2A
Authority: CN
Inventors: 孙旭; 张瑾; 刘玉蓉; 严昊; 杨明
Original assignee: China Merchants Bank Co Ltd
Current assignee: China Merchants Bank Co Ltd
Priority date: 2023-10-27
Filing date: 2023-10-27
Publication date: 2024-01-19

Abstract

The application discloses an intelligent voice service method, an intelligent voice service device, terminal equipment and a storage medium, and relates to the field of intelligent service, wherein the method comprises the following steps: receiving a service request instruction sent by a user side, wherein the service request instruction comprises target service network point information and service requirements; and if the target service network point information is one of a plurality of available service network point information in the service end, providing voice service for the service requirement through a preset intelligent system. The invention not only can ensure the quality of processing the user incoming call, but also improves the efficiency of processing the user incoming call.

Description

Intelligent voice service method, device, terminal equipment and storage medium

Technical Field

The present invention relates to the field of intelligent services, and in particular, to an intelligent voice service method, apparatus, terminal device, and storage medium.

Background

With the development and progress of society, the user inquiry and business handling modes are gradually transferred from offline to online, while banks are important components in the financial service industry, and receive a large number of clients 'calls about inquiry and business handling every day, and in this context, an efficient and intelligent call handling mode is needed to handle a large number of clients' calls.

The current method for processing the incoming call of the customer is centralized processing, when the customer needs to communicate with the bank, the customer needs to dial a unified service number to contact a customer service center of the bank, and a worker in the customer service center processes the incoming call of the customer, but the incoming call processing method still has the problems that the incoming call processing quality cannot be guaranteed and the incoming call processing efficiency is low.

Disclosure of Invention

The invention mainly aims to provide an intelligent voice service method, an intelligent voice service device, terminal equipment and a storage medium, which can ensure the quality of processing the incoming calls of users and improve the processing efficiency.

In order to achieve the above object, the present invention provides an intelligent voice service method, comprising:

receiving a service request instruction sent by a user side, wherein the service request instruction comprises target service network point information and service requirements;

and if the target service network point information is one of a plurality of available service network point information in the service end, providing voice service for the service requirement through a preset intelligent system.

Optionally, if the target service node information is one of a plurality of available service node information in the service end, the step of providing the voice service for the service requirement through the preset intelligent system includes:

Acquiring information of a plurality of available service network points based on a preset operation management system;

transmitting the plurality of available service network point information to an operator server through the operation management system;

and judging whether the target service network point information is one of the plurality of available service network point information or not through the operator server.

Optionally, the step of providing the voice service for the service requirement through a preset intelligent system includes:

carrying out semantic analysis on the service requirements in the service request instruction through a preset semantic analysis system to obtain a semantic analysis result and sending the semantic analysis result to a navigation system;

based on the navigation system, inquiring available services in a preset navigation knowledge base according to the semantic analysis result to obtain available service inquiry results;

and outputting the service-available query result to the user side through a preset interactive voice response system.

carrying out semantic analysis on the service requirements in the service request instruction through a preset semantic analysis system to obtain a semantic analysis result, wherein the semantic analysis result comprises a service object;

Judging whether the service providing object in the semantic analysis result is an artificial object or not;

if the service providing object in the semantic analysis result is judged to be an artificial object, the service request instruction is routed to the artificial object through a preset soft switching platform, and the artificial object processes the service request instruction;

if the service object provided in the semantic analysis result is judged to be a non-artificial object, the semantic analysis result is sent to a navigation system through a preset soft exchange platform, and the navigation system processes the semantic analysis result.

Optionally, the step of routing the service request instruction to the artificial object through a preset soft switch platform includes:

and sending the service request instruction to an artificial object corresponding to the target service site information for processing through a preset soft switching platform according to the target service site information in the service request instruction.

Optionally, the step of processing the semantic analysis result by the navigation system includes:

acquiring a service speaking procedure and service knowledge information based on a preset navigation knowledge base;

inquiring related service telephone operation flow and service knowledge information in the navigation knowledge base through the navigation system according to the semantic analysis result to obtain a service-available inquiry result;

Optionally, the step of performing semantic analysis on the service requirement in the service request instruction through a preset semantic analysis system to obtain a semantic analysis result includes:

performing voice recognition on the service requirement through a preset semantic analysis system to obtain a voice recognition result;

converting the voice recognition result into text information to obtain service demand text information;

and analyzing the service demand text information to obtain a semantic analysis result.

The embodiment of the application also provides an intelligent voice service device, which comprises:

the data receiving module is used for receiving a service request instruction sent by a user terminal, wherein the service request instruction comprises target service network point information and service requirements;

and the voice service module is used for providing voice service for the service requirement through a preset intelligent system if the target service network point information is one of a plurality of available service network point information in the service end.

The embodiment of the application also provides a terminal device, which comprises a memory, a processor and an intelligent voice service program stored on the memory and capable of running on the processor, wherein the intelligent voice service program realizes the steps of the intelligent voice service method when being executed by the processor.

The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores an intelligent voice service program, and the intelligent voice service program realizes the steps of the intelligent voice service method when being executed by a processor.

The intelligent voice service method, the intelligent voice service device, the intelligent voice service terminal and the intelligent voice service storage medium are provided by the embodiment of the application, and the service request instruction sent by the user terminal is received, wherein the service request instruction comprises target service network point information and service requirements; and if the target service network point information is one of a plurality of available service network point information in the service end, providing voice service for the service requirement through a preset intelligent system. Because the service request instruction sent by the user terminal comprises the target service site information, and the service terminal stores a plurality of pieces of available service site information, when the service terminal receives the service request instruction from the user terminal, the service terminal can identify the target service site information in the service request instruction, and if the target service site information is identified as one of the plurality of pieces of available service site information, the service request instruction can be further processed through a preset intelligent system, and in this way, the user can establish contact with the service terminal by inputting any piece of available service site information, thereby ensuring the quality of processing the incoming call of the user and improving the processing efficiency.

Drawings

FIG. 1 is a schematic diagram of functional modules of a terminal device to which an intelligent voice service device of the present application belongs;

FIG. 2 is a flow chart of a first exemplary embodiment of an intelligent voice service method of the present application;

FIG. 3 is a flow chart of a second exemplary embodiment of the intelligent voice service method of the present application;

FIG. 4 is a flow chart of a third exemplary embodiment of a smart voice service method of the present application;

FIG. 5 is a flow chart of a fourth exemplary embodiment of an intelligent voice service method of the present application;

FIG. 6 is a flowchart of a sixth exemplary embodiment of an intelligent voice service method of the present application;

FIG. 7 is a flow chart of a seventh exemplary embodiment of a smart voice service method of the present application;

FIG. 8 is a schematic diagram of an overall flow of the intelligent voice service method of the present application;

fig. 9 is a flowchart of an overall system deployment architecture of the intelligent voice service method of the present application.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The main solutions of the embodiments of the present application are: receiving a service request instruction sent by a user side, wherein the service request instruction comprises target service network point information and service requirements; and if the target service network point information is one of a plurality of available service network point information in the service end, providing voice service for the service requirement through a preset intelligent system. Because the service request instruction sent by the user terminal comprises the target service site information, and the service terminal stores a plurality of pieces of available service site information, when the service terminal receives the service request instruction from the user terminal, the service terminal can identify the target service site information in the service request instruction, and if the target service site information is identified as one of the plurality of pieces of available service site information, the service request instruction can be further processed through a preset intelligent system, and in this way, the user can establish contact with the service terminal by inputting any piece of available service site information, thereby ensuring the quality of processing the incoming call of the user and improving the processing efficiency.

In this embodiment, as society develops and advances, more and more users choose to consult or transact business in a call mode, and banks are an important component in the financial service industry, and receive a large number of calls from customers every day, so that the requirements for the banks to process the calls from the users are higher and higher, and the current common ways of processing the calls from the customers for centralized processing are not capable of guaranteeing the call processing quality and the call processing efficiency.

Based on this, the embodiment of the application proposes a solution, when the service end receives the service request instruction sent by the user end, the target service node information in the service request instruction is identified, if the target service node information in the service request instruction is identified as one of a plurality of available service node information in the service end, the connection between the user end and the service end is established, so that the service request instruction is processed through the intelligent system in the service end, in this way, the user can establish the connection with the service end by inputting any available service node information, thereby guaranteeing the quality of processing the incoming call of the user and improving the processing efficiency.

Specifically, referring to fig. 1, fig. 1 is a schematic diagram of functional modules of a terminal device to which an intelligent voice service device of the present application belongs. The intelligent voice service device can be a device which is independent of the terminal equipment and can perform data processing, and can also be carried on the terminal equipment in a form of hardware or software.

In this embodiment, the terminal device to which the intelligent voice service apparatus belongs at least includes an output module 110, a processor 120, a memory 130, and a communication module 140.

The memory 130 stores an operating system and an intelligent voice service program, and receives a service request instruction sent by a user side, where the service request instruction includes target service website information and a service requirement, and the service request instruction is stored in the memory 130. The output module 110 may be a display screen, a speaker, etc. The communication module 140 may include a WIFI module, a mobile communication module, a bluetooth module, and the like, and communicates with an external device or a server through the communication module 140.

Wherein the intelligent voice service program in the memory 130 when executed by the processor performs the steps of:

receiving a service request instruction sent by a user side, wherein the service request instruction comprises target service network point information and service requirements; and if the target service network point information is one of a plurality of available service network point information in the service end, providing voice service for the service requirement through a preset intelligent system.

Further, the intelligent voice service program in the memory 130 when executed by the processor also implements the following steps:

According to the scheme, the service request instruction sent by the user terminal is received, and the service request instruction comprises target service network point information and service requirements; and if the target service network point information is one of a plurality of available service network point information in the service end, providing voice service for the service requirement through a preset intelligent system. Because the service request instruction sent by the user terminal comprises the target service site information, and the service terminal stores a plurality of pieces of available service site information, when the service terminal receives the service request instruction from the user terminal, the service terminal can identify the target service site information in the service request instruction, and if the target service site information is identified as one of the plurality of pieces of available service site information, the service request instruction can be further processed through a preset intelligent system, and in this way, the user can establish contact with the service terminal by inputting any piece of available service site information, thereby ensuring the quality of processing the incoming call of the user and improving the processing efficiency.

Referring to fig. 2, fig. 2 is a schematic flow chart of a first exemplary embodiment of the intelligent voice service method of the present application.

An embodiment of the present invention provides an intelligent voice service method, including:

step S10, receiving a service request instruction sent by a user terminal, wherein the service request instruction comprises target service network point information and service requirements;

the user side refers to a device with a certain communication function, which can contact with a service provider, and the device can include: a fixed terminal or a mobile terminal having a voice call function.

Communication functions refer to the ability to transfer information between one or more devices in some manner (e.g., voice, image, data, etc.).

The communication functions may include:

and (3) voice call: through the two-way conversation of voice signal, make people can carry out real-time voice communication through equipment.

A service request instruction refers to a command or instruction for issuing a specific service request that may be used to interact with a device, system or application to obtain a desired service.

Specifically, the service request instruction sent by the user side includes target service network point information and service requirements.

The target service site information refers to information for identifying and locating a specific telephone device or object, and may be a telephone number of the target service site.

The service requirement refers to the requirement of a user on a specific service or operation, and the requirement describes the service, the operation performed or the required response which the user wants to acquire from the service end, so that the incoming call of the user can be better processed by knowing the service requirement of the user, and the processing efficiency and quality are improved.

Specifically, taking a banking service requirement as an example, the service requirement may include:

inquiring account information: the user needs to query the balance of his bank account, transaction records, interest income, etc.

Loan application and repayment: the user needs to apply for loans or transact loan repayment, such as personal loans, house loans, credit card repayment, etc.

Financial and investment services: the user needs to consult information about investment products, purchase funds, stocks, etc. and perform related trading operations.

Bank card loss reporting and compensation: the user needs to report that the bank card is lost or stolen and request to report the loss and re-transact the bank card.

Counseling service: the user needs to consult bank related questions such as exchange rate inquiry, interest rate change, account opening flow, etc.

Account setup and management: the user needs to set or change account management operations such as account passwords, contact modes, account binding and the like.

According to the service demands of the users, as the society develops and advances, the demands of the users for services become more and more, so as to save the time of consulting or transacting services, most of the users choose to consult or transact services in a call mode, and the current mode of processing the calls of the users is centralized processing, so that the call processing quality and the call processing efficiency are not guaranteed.

Therefore, this embodiment proposes that when the service end receives the service request instruction sent from the user end, the target service node information in the service request instruction is identified, if the target service node information in the service request instruction is identified as one of a plurality of available service node information in the service end, the connection between the user end and the service end is established, so that the service request instruction is processed through the intelligent system in the service end, in this way, the user can establish the connection with the service end by inputting any available service node information, thereby ensuring the quality of processing the incoming call of the user and improving the processing efficiency.

Further, the user can input any available service network point information to establish contact with the server, so that the way of establishing contact between the user and the server is greatly expanded, and the success rate of establishing contact between the user and the server is improved.

Specifically, the method for sending the service request instruction to the service end by the user end may include:

telephone call: the user can dial the telephone number of the available service network point, and the service request instruction is transmitted in a voice mode, so that the telephone call is a direct and real-time communication mode, and the method is suitable for the situation that the problem needs to be solved rapidly or manual operation needs to be carried out.

Step S30, if the target service network point information is one of a plurality of available service network point information in the server, providing voice service for the service requirement through a preset intelligent system;

the available service network point information refers to network point information capable of providing service for the user terminal, and the available service network point information can be a network point telephone number capable of providing service for the user terminal.

And after the service end receives the service request instruction sent by the user end, identifying target service network point information in the service request instruction.

Wherein, the method of identifying can include:

Database matching: the server can set a database containing the available service node information, and after receiving the service request instruction sent by the user, the server can judge whether the target service node information exists in the database by querying the database.

Internal mapping table: the server may use an internal mapping table or configuration file to associate the available service node information with a specific identifier (such as ID, code, etc.), and after receiving a service request instruction sent by the user, the server may search for the corresponding service node information according to the specified identifier, and perform matching.

Algorithm matching: the server may use an algorithm to match the target service node information, for example, a string matching algorithm, a fuzzy matching algorithm, etc., and compare the target service node information in the request instruction sent by the user terminal with the preset available service node information, so as to determine the similarity or the matching degree between them, and finally obtain a conclusion according to the similarity or the matching degree.

Network request authentication: the server can initiate a network request to the target service network node, verify whether the network request exists or is available, and determine whether the network request is the available service network node by checking the response status code, the return result and other information of the target service network node.

Wherein, intelligent system can be:

robot customer service system: the robot customer service system is a customer service system based on natural language processing and artificial intelligence technology, can process questions sent by users and give corresponding answers, and has the advantages of realizing 24-hour uninterrupted service and simultaneously processing a large number of user requests.

Knowledge base system: the knowledge base system is a system for standardizing, classifying, modeling and delivering the expertise, experience and flow in a company or organization to a computer for management, can provide more accurate, rapid and consistent service answers, and is suitable for processing some common user problems and standard operation flows.

Big data analysis system: the big data analysis system is to analyze and mine massive user data through various data mining algorithms and visualization technologies to find out information such as behavior characteristics and preferences of users, optimize customer service flows and improve user experience, and is usually required to be used together with other customer service systems.

Voice services refer to customer services provided through voice technology, which may include:

Voice self-service: the user selects options through a voice menu or a voice recognition system to finish operations such as inquiring of some common problems, inquiring of accounts, inquiring of balances and the like, and intervention of manual customer service is not needed.

Manual voice service: for some complex problems or situations requiring manual intervention, customer service voice service can provide manual service, and users communicate with customer service personnel through telephones to answer the problems, provide assistance, process complaints and the like.

In order to understand the service request instruction sent by the user side, the voice information of the user needs to be identified, wherein the identification mode can apply the following technology:

speech recognition technology: speech recognition technology is used to convert a customer's speech information into text information so that the system can understand and handle the customer's needs, and the accuracy and efficiency of speech recognition technology is critical to providing good speech services.

The voice synthesis technology comprises the following steps: under the scene of providing information, prompt, notification and the like for clients, the voice synthesis technology can convert text information into voice output, and the natural and smooth voice interaction effect is realized.

According to the intelligent voice service method, a service request instruction sent by a user side is received, wherein the service request instruction comprises target service website information and service requirements; and if the target service network point information is one of a plurality of available service network point information in the service end, providing voice service for the service requirement through a preset intelligent system. Because the service request instruction sent by the user terminal comprises the target service site information, and the service terminal stores a plurality of pieces of available service site information, when the service terminal receives the service request instruction from the user terminal, the service terminal can identify the target service site information in the service request instruction, and if the target service site information is identified as one of the plurality of pieces of available service site information, the service request instruction can be further processed through a preset intelligent system, and in this way, the user can establish contact with the service terminal by inputting any piece of available service site information, thereby ensuring the quality of processing the incoming call of the user and improving the processing efficiency.

Referring to fig. 3, fig. 3 is a schematic flow chart of a second exemplary embodiment of the intelligent voice service method of the present application.

Based on the first embodiment, a second embodiment of the present application is presented, which differs from the first embodiment in that:

in this embodiment, in step S30, if the target service node information is one of a plurality of available service node information in the server, before providing the voice service for the service requirement through the preset intelligent system, the method further includes:

step S20, based on a preset operation management system, acquiring information of a plurality of available service network points;

the server is provided with an operation management system, and the purpose of the server is to acquire and store available service site information for the subsequent operator server to identify, wherein the available service site information can be a plurality of service site information.

The method for acquiring the information of the available service network points can comprise the following steps:

manual input: an operator of the operation management system can manually input information such as contact phones of available service sites, and the method is suitable for the situation that the number of the available service sites is small, but accuracy and timeliness are required to be paid attention.

Database query: the operation management system can maintain a database containing the information of available service sites, and operators can acquire related information by querying the database, so that the method is suitable for the situation that the number of available service sites is large, and operations such as adding, deleting, modifying and checking the information can be performed through the management of the database, and the data statistics and analysis can be conveniently performed in the later stage.

Web crawler: the operation management system can use web crawler technology to crawl the information of available service sites on a specific website or platform, and integrate and screen. The method can quickly acquire a large amount of information, but attention is paid to factors such as legal and moral problems, compliance risks and the like.

API interface: the operation management system uses the API interface provided by the available service network point to acquire the information such as contact telephone, and the like, and the method is suitable for the service network point with cooperative relationship, so that the accuracy and timeliness of the data can be improved.

Geographic location identification: if the available service sites contain geographical location information, the operation management system may utilize geographical location identification techniques, such as IP address resolution, GPS positioning, etc., to obtain information such as contact phones for the available service sites.

By comprehensively utilizing the method, the operation management system can effectively acquire information such as contact phones of available service network points, integrate and manage the information, and the specific selection mode depends on the actual situation and the requirement of the operation management system.

Step S21, the operation management system sends the information of the plurality of available service network points to an operator server;

after the operation management system acquires the plurality of pieces of available service node information, the plurality of pieces of available service node information are sent to the operator server for subsequent identification of the target service node information by the operator server.

The manner in which the operation management system sends the information of the plurality of available service sites to the operator server may include:

file transfer: the operation management system can save the available service network point information in a file, and then upload the file to an operator server through an FTP (file transfer protocol) or other file transfer modes, and a program on the operator server can read the file and analyze the information in the file.

API interface: the operator server provides a corresponding API interface, and the operation management system sends the available service network point information to the operator server by calling the interface.

Database synchronization: the operation management system can establish connection with a database on an operator server and transmit the available service site information in the past in a database synchronization mode, and a program on the operator server can periodically check the update of the source database so as to synchronize the latest available service site information.

Web service call: the operation management system can send a Web service calling request to the operator server through a hypertext transfer protocol or a hypertext transfer security protocol, and can transmit the available service network point information to the operator server as a request parameter. The Web service on the operator server can parse the parameters and process the parameters after receiving the request.

The above may be selected in any manner depending on the particular technical architecture and interface provided by the operator server. Meanwhile, in order to ensure the security and integrity of data transmission, encryption, authentication and other measures can be considered to protect the data transmission process.

The encryption mode can be symmetric encryption or asymmetric encryption, and the authentication mode can be token authentication or digital certificate authentication.

Step S22, judging whether the target service network point information is one of the plurality of available service network point information or not through the operator server;

when the operator receives a plurality of pieces of available service node information from the operation management system, the operator judges the target service node information in the received service request instruction sent by the user terminal, judges whether the target service node information is one of the plurality of pieces of available service node information, and provides a judging basis for whether the subsequent service terminal processes the service request instruction.

For example, when the target service node information included in the service request instruction sent by the user side is a and the available service node information received by the operator server from the operation management system is A, B, C, D, the operator server determines that the target service node information is one of the plurality of available service node information, and then the service request instruction sent by the user side can be processed through the intelligent system.

Specifically, the method for judging whether the two information are the same may include:

character string comparison: and comparing the character strings of the target service network point information with one of the available service network point information character by character, and if each character is the same, considering that the two character strings are consistent.

Hash comparison: and respectively generating hash values of the target service node information and one of the available service node information, comparing whether the two hash values are the same, if so, considering the target service node information as one of the available service node information, and if not, considering that the available service node information does not contain the target service node information, wherein the design of a hash algorithm should ensure that the hash values generated by different information have no conflict as far as possible.

Digital comparison: for some simple digital information, numerical comparison can be directly performed to determine whether the two digital information are equal.

By comprehensively utilizing the judging mode, whether the target service network point information is one of the available service network point information can be judged more comprehensively, and the specific mode needs to be selected and designed according to the system requirements and the available resources in actual identification comparison.

According to the intelligent voice service method, a plurality of pieces of available service network point information are obtained through a preset operation management system; transmitting the plurality of available service network point information to an operator server through the operation management system; and judging whether the target service node information is one of the plurality of available service node information or not through the operator server, processing a service request instruction sent by the user terminal through the intelligent system when judging that the target service node information is one of the plurality of available service node information, and sending the target service node information to the operator server for identification through the operation management system, so that the accuracy rate of identification of the target service node information by the service terminal is enhanced, and the efficiency of answering the user call is improved.

Referring to fig. 4, fig. 4 is a schematic flow chart of a third exemplary embodiment of the intelligent method of the present application.

Based on the second embodiment, a third embodiment of the present application is presented, which differs from the second embodiment in that:

in this embodiment, for step S30, if the target service node information is one of a plurality of available service node information in the server, the voice service is provided for the service requirement through a preset intelligent system for refinement, where the refinement step may include:

Step S31, carrying out semantic analysis on the service requirements in the service request instruction through a preset semantic analysis system, obtaining a semantic analysis result and sending the semantic analysis result to a navigation system;

after the operator server judges that the target service site information in the service request instruction is one of the available service site information, the service end needs to further process the service request instruction through a semantic analysis system in the intelligent system.

The semantic analysis system refers to a system for understanding text semantics by using natural language processing and machine learning technology, and can be used for extracting meaningful information from text and interpreting, classifying or converting the meaningful information into a structural representation form.

Specifically, the service request instruction includes a service requirement of the user.

Because the user communicates with the server side mainly in a call form, before the intelligent system performs semantic analysis on the service requirement of the user, call voice of the user needs to be immediately converted into characters, so that the intelligent system can better analyze the information expressed by the voice of the user, and the intelligent system can conveniently process the service requirement of the user later.

Specifically, the speech-to-text method may include:

Text conversion is carried out on the user voice through an ASR model: ASR (Automatic Speech Recognition) refers to automatic speech recognition, a technique for converting human speech into text, by analyzing the acoustic features and language model of speech signals, to convert the speech into corresponding text. Wherein the ASR model refers to a model for automatic speech recognition, the ASR model may include a hidden markov model and a mixed gaussian model.

Deep learning-based speech recognition converts speech into text: the end-to-end learning and optimization are carried out on the acoustic and language modeling through the convolutional neural network, the cyclic neural network, the attention mechanism, the language model and other technologies, so that the voice is converted into the words.

After converting the voice into the text, carrying out semantic analysis on the obtained text information.

Specifically, the manner of semantic analysis may include:

rule-based semantic analysis: based on a manually defined rule set, matching is performed through technologies such as regular expressions, grammar analysis and the like, so that user intention is identified and corresponding functions are realized.

Semantic analysis of statistical learning: the semantic information is acquired through learning, mining and modeling of a large amount of data, and tasks such as natural language processing and intention recognition are realized.

Hybrid semantic analysis: based on the combination of the methods, the information and the technology in all aspects are comprehensively utilized to realize more accurate and comprehensive semantic analysis.

When the method is applied specifically, a proper semantic analysis method is needed to be selected according to specific conditions, and semantic analysis results are obtained after semantic analysis is carried out on the obtained text information.

The semantic analysis result may include the following information:

user intention information: the purpose or intention of the incoming call of the user is analyzed, such as inquiring account balance, handling account transfer, applying loan and the like, which can help the intelligent system to accurately understand the requirement of the user and facilitate the subsequent provision of corresponding services.

User emotion analysis information: and deducing the emotional state of the user, such as anger, anxiety, satisfaction and the like, by analyzing the converted text information, and correspondingly processing the emotional state of the user so as to improve the user experience.

Key information: the key information such as account numbers, passwords, transaction amounts and the like is obtained through analyzing the converted text information, so that the intelligent system can be helped to process the business of the user more quickly and accurately.

Problem contact identification information: identifying keywords or contacts involved in a user's problem, such as a product, a service, a channel, etc., may subsequently provide more targeted services and recommendations to the user via the contact identification information.

The above is information that the semantic analysis result may contain, and reasonably utilizing the semantic analysis result may provide better response in the subsequent process of servicing the user.

And sending the semantic analysis result obtained by analysis to a navigation system for a subsequent navigation system to inquire related information according to the semantic analysis result.

Step S32, based on the navigation system, inquiring available services in a preset navigation knowledge base according to the semantic analysis result to obtain available service inquiring results;

the navigation system is a system responsible for scheduling various information such as meaning corpus, call flow, FAQ and the like in the knowledge base, and service information related to semantic analysis results can be better queried in the knowledge base through the navigation system.

In particular, FAQ (Frequently Asked Questions) refers to frequently asked questions, and as will be appreciated, FAQ is a collection of questions and answers to a topic that better aids people in understanding and solving the questions.

The navigation knowledge base refers to a data set stored and managed in the intelligent system, and contains various information for supporting the operation and service provision of the intelligent system, so as to provide a data base for the user to rapidly and accurately provide the service.

The information in the navigation knowledge base may include:

user information: including basic information of the user, such as name, identification number, contact information, etc., which is used to identify the user's identity, authenticate the user's identity, and provide personalized services.

FAQ: questions frequently asked by the user, which may be common questions about account operation, product introduction, transaction flow, etc., and corresponding solutions are stored, and by storing the questions and answers in a navigation knowledge base, the intelligent system can answer the user's questions more quickly.

Product and service information: including details of various products and services offered by banks, such as loan products, credit card products, financial products, etc., which can be used to introduce and recommend products and services to users that suit their needs.

Operational guidelines and procedures: the operation guidelines and procedures to be followed by the user in the process of using the banking service, such as the registration procedure of the internet banking, the password resetting method and the like, are stored, and the guidelines can help the user to complete various operations correctly and smoothly.

Customer feedback records: the interaction history of the user and the intelligent customer service, the questions and feedback contents of the user and the answer and processing results of the intelligent customer service are recorded, and the records can be used for improving the answer accuracy and service quality of the intelligent customer service system.

Other relevant data: depending on the particular bank requirements, the database may also include other customer service related data such as account balance information, transaction records, complaint handling, etc.

And the navigation system queries related information in a navigation knowledge base according to the semantic analysis result and prepares for feedback to the user side.

For example, when the navigation system queries the navigation knowledge base for answers or flows of related questions according to the semantic analysis result, the method can be implemented by the following steps:

the user asks: when the semantic analysis result analysis shows that the problems or requirements set by the user are as follows: "I want to know how to apply for credit cards. "

Problem classification: the navigation system classifies questions posed by the user, determines which domain or topic the questions belong to, e.g., categorizes the user questions as "credit card applications".

Navigation knowledge base query: the navigation system can classify the credit card application, inquire related questions and answers in a navigation knowledge base, and the navigation system can inquire by adopting the keyword of the application.

And (3) obtaining an answer: once the navigation system queries the relevant questions and answers, the navigation system returns the answers to the interactive voice response system so that the interactive voice response system can output the answers to the user side.

After the steps, the service inquiry result corresponding to the service requirement of the user can be formed.

The navigation system is matched with the navigation database for use, so that the requirements of users can be processed more efficiently, the answer standards of answers can be ensured to be uniform and consistent, and the experience of the users is enhanced.

Step S33, outputting the service-available query result to a user side through a preset interactive voice response system;

after the navigation system queries the relevant answers or processes in the navigation database, the relevant answers or processes are output to the user side in a visual mode through the interactive voice response system.

The interactive voice response system is an automatic telephone interaction system, and the system can interact with a caller and process information in a voice guidance or key input mode.

The available service query result queried by the navigation system through the navigation knowledge base is often text information which cannot be directly presented at the user side, so that voice conversion is required before the navigation system outputs the text information to the user side.

The Text-to-Speech (TTS) technique may be used for converting Text into Speech.

The TTS refers to a technology of converting text into voice, and the TTS technology can be used to convert input text information into audible voice output according to a voice synthesis mode, so that the generated voice output becomes more humanized, and natural and smooth voice can be generated for users to listen through simulating voice characteristics, intonation and speech speed of human beings, so that the TTS technology is widely applied to the fields of voice broadcasting systems, intelligent navigation, voice readers and the like, and a computer can read the text like a human body.

The converted voice information is output to the user side through the interactive voice response system, and the user can interact with the service side according to the voice information, wherein the interaction mode can be a key type mode or a voice type mode or other modes.

According to the intelligent voice service method, a preset semantic analysis system is used for carrying out semantic analysis on service requirements in the service request instruction, so that a semantic analysis result is obtained and sent to a navigation system; based on the navigation system, inquiring available services in a preset navigation knowledge base according to the semantic analysis result to obtain available service inquiry results; the service-available query result is output to the user side through the preset interactive voice response system, the time for the navigation system to query the service-available is shortened through the matched use of the navigation system and the navigation database, interaction is carried out between the navigation system query and the user side through the interactive voice response system after the navigation system query is completed, the result obtained through query is output, and the interactivity of the user and the intelligent system is improved so as to provide better use experience for the user.

Referring to fig. 5, fig. 5 is a flowchart illustrating a fourth exemplary embodiment of the intelligent voice service method of the present application.

Based on the second embodiment, a fourth embodiment of the present application is presented, which differs from the second embodiment in that:

Step S301, carrying out semantic analysis on service requirements in the service request instruction through a preset semantic analysis system to obtain a semantic analysis result, wherein the semantic analysis result comprises a service object;

specifically, the semantic analysis result includes a service object.

A service object refers to a party providing a service, for example, a user indicates which entity needs to be served during the process of interacting with the intelligent system, and then the entity that needs to be served can be understood as an object of the service user, i.e. a service object.

The service object can be determined by carrying out semantic analysis on the service requirement in the user service request instruction, and after determining who the user needs to be provided with the service, the service object can be transferred to the corresponding service object for subsequent processing.

Wherein the service object may be an artificial object or a non-artificial object.

Step S302, judging whether the service object provided in the semantic analysis result is an artificial object or not;

the judging mode can be detected through keywords.

Step S303, if the service providing object in the semantic analysis result is an artificial object, routing the service request instruction to the artificial object through a preset soft switching platform, and processing the service request instruction by the artificial object;

Step S304, if the service object provided in the semantic analysis result is judged to be a non-artificial object, the semantic analysis result is sent to a navigation system through a preset soft exchange platform, and the navigation system processes the semantic analysis result;

when the operator server judges that the target service site information is one of a plurality of available service site information, the operator server sends a service request instruction sent by a user side to a soft switching platform, and the soft switching platform processes the service request instruction.

The service request sent by the user can be smoothly accessed into the intelligent system from the operator server by constructing the whole network link.

The method for constructing the network link may include:

a wired network: physical cabling devices are used including ethernet, optical fiber, etc. This approach can provide higher speed and stability, suitable for scenes requiring large bandwidth and high reliability.

Wireless network: data transmission is performed using wireless technology, such as Wi-Fi, bluetooth, mobile communication, etc. The method is convenient and flexible, and is suitable for mobile equipment or scenes with wider coverage range.

Network device configuration: by setting network equipment such as a router, a switch and the like, the normal operation and the safety of the whole system are ensured.

The soft switching platform is a communication system for a call center and a customer service center, and is a contact center based on Internet protocol.

Specifically, the soft switch platform plays a role in distributing user service request instructions in the service end, and distributes the user service request instructions to manual or non-manual processing according to the service objects required by the user and judged by the intelligent system.

For example, when a user dials a customer service number of a website, the intelligent system firstly inquires whether the user needs an artificial object to serve the user in a voice mode, and the intelligent system analyzes the requirement of the user for providing the service object according to the answer of the user and sends a user service request instruction to the corresponding object for processing.

And the operator server sends the service request instruction sent by the user terminal to the soft switching platform, wherein the sending mode can be relayed through the SIP.

SIP trunking refers to the use of the SIP protocol to connect transmission links between two or more communication systems, which can convert telephone calls into IP network-based data streams and transmit over a network, which serves as a bridge between two different telephone systems so that telephone calls can be connected and routed across different networks.

Specifically, when the service object provided in the semantic analysis result is judged to be an artificial object, the soft switch platform routes the corresponding service request instruction to the artificial object.

Wherein, the artificial object can be a staff of a website customer service center or a staff for processing related business.

The protocols used in routing to the artifacts may be the SIP protocol and the HTTP protocol.

The SIP protocol is a communication protocol, through which a voice call can be established and terminated, and media parameters are transmitted, and when a user request instruction is routed to a manual customer service call, the SIP protocol can be used to conveniently establish a call connection, and voice transmission is performed, so that real-time voice communication is realized.

The HTTP protocol is a common network communication protocol, through which information interaction and request response can be performed between different systems, and when a user request instruction is routed to a manual service call, relevant information (such as a call number, a user identity, etc.) from a call can be transferred to a background service by using the HTTP protocol, so that scheduling and forwarding of the corresponding manual service call are realized.

Specifically, when the service object provided in the semantic analysis result is judged to be a non-artificial object, the soft switching platform routes the semantic analysis result to the navigation system, and the non-artificial object processes the service request instruction of the user according to the semantic analysis result.

The non-artificial object may be a system or software with a certain analysis and communication capability, such as an intelligent device like an intelligent response robot.

According to the intelligent voice service method provided by the embodiment of the application, the preset semantic analysis system is used for carrying out semantic analysis on the service requirements in the service request instruction to obtain a semantic analysis result, wherein the semantic analysis result comprises a service object; judging whether the service providing object in the semantic analysis result is an artificial object or not; if the service providing object in the semantic analysis result is judged to be an artificial object, the service request instruction is routed to the artificial object through a preset soft switching platform, and the artificial object processes the service request instruction; if the service object provided in the semantic analysis result is judged to be a non-artificial object, the semantic analysis result is sent to a navigation system through a preset soft exchange platform, and the navigation system processes the semantic analysis result. When a user interacts with the intelligent system, the intelligent system firstly judges a main body for serving the user so as to distribute service request instructions of the user later, and after the main body for providing the service is determined, the service request instructions are distributed through the soft switching platform according to the main body for providing the service correspondingly.

Based on the fourth embodiment, a fifth embodiment of the present application is presented, which differs from the fourth embodiment in that:

in this embodiment, in step S303, if it is determined that the service providing object in the semantic analysis result is an artificial object, the service request instruction is routed to the artificial object through a preset soft switch platform, and the artificial object processes the service request instruction to refine, where the step of refining may include:

step S3031, according to the target service node information in the service request instruction, the service request instruction is sent to an artificial object corresponding to the target service node information for processing through a preset soft switching platform;

when the service object provided in the semantic analysis result is judged to be an artificial object, the soft switch platform routes the corresponding service request instruction to the artificial object.

Wherein, the distributed artificial object refers to a target service node corresponding to the target service node information in the service request instruction.

For example, when the user dials the customer service number of the a site and the intelligent system expresses that the user needs to be served by the artificial object, the soft switch platform routes the corresponding service request instruction to the a site, and the staff of the a site serves the user.

According to the intelligent voice service method provided by the embodiment of the application, the service request instruction is sent to the artificial object corresponding to the target service node information for processing through the preset soft switching platform according to the target service node information in the service request instruction, and the service request instruction can be distributed according to any service node contacted by the user, so that the problems of long user occupation and waiting time caused by processing the incoming call of the user by means of a single service node are greatly reduced.

Referring to fig. 6, fig. 6 is a flowchart illustrating a sixth exemplary embodiment of an intelligent voice service method according to the present application.

Based on the fifth embodiment, a sixth embodiment of the present application is presented, which differs from the fifth embodiment in that:

in this embodiment, for step S304, if it is determined that the service object provided in the semantic analysis result is a non-artificial object, the semantic analysis result is sent to a navigation system through a preset soft exchange platform, and the navigation system refines the processing of the semantic analysis result, where the refining step may include:

step S3041, based on a preset navigation knowledge base, acquiring a service speaking procedure and service knowledge information;

When the service object provided in the semantic analysis result is judged to be a non-artificial object, the semantic analysis result is required to be sent to a navigation system for processing.

Before the navigation system processes the service request instruction of the user, the navigation knowledge base needs to acquire the service speaking process and service knowledge information so that the subsequent navigation system can query relevant service information in the navigation knowledge base according to the semantic analysis result.

The service speaking process refers to a series of dialogue steps and oral expression modes which can be designed and specified in advance in order to provide efficient, consistent and standardized service in the process of interacting with user service, and is a standardized dialogue template used in an intelligent system or a manual customer service based on the requirements of specific industries, products or services.

Service knowledge information refers to information about products, processes, policies, etc. for solving problems, providing solutions or support.

Specifically, the service knowledge information may include:

knowledge about product: such as product functions, characteristics, methods of use, operational flows, technical parameters, application scenarios, etc.

Business process related knowledge: such as approval of business, such as account opening, loan, financial, investment, etc., transaction, rules of transaction, notes, application of materials, etc.

Policy regulations and compliance require related knowledge: such as policies, regulations and requirements in the financial industry governing policies, anti-money laundering, anti-fraud, information security, etc.

Knowledge about common problem solutions: for example, for common customer questions, questions or complaints, corresponding solutions and processing methods are preset in the knowledge base.

Customer service skill related knowledge: such as specialized customer service skills and experience, such as how to communicate effectively, how to solve complex problems, how to deal with customer complaints, etc.

The manner in which the navigation knowledge base obtains the service session flow and the service knowledge information may include:

presetting rules and processes: the common service dialects and processing flows are pre-written and stored in the navigation knowledge base, and when the navigation system needs to extract the service dialects and processing flows related to the semantic analysis result, the navigation knowledge base can provide the corresponding service dialects and processing flows for the navigation system by matching the user problems with preset rules.

Text mining and information extraction: important service knowledge information is extracted from documents, notices, common problems and other materials of banks, is arranged and added into a navigation knowledge base, and can automatically acquire and update contents in the navigation knowledge base through text mining and information extraction technology.

Manual editing and maintenance: editing and maintaining a navigation knowledge base according to business requirements and latest policies of banks by professional team or manual customer service, and updating, supplementing and correcting the knowledge base in real time so as to ensure accuracy and real-time performance of service speech and service knowledge.

Automatic learning and machine learning: the historical user dialogue data is analyzed and mined by utilizing a machine learning algorithm and a natural language processing technology, common problems and solutions are extracted from the historical user dialogue data, and the knowledge base content is further updated and perfected.

The method can help the navigation knowledge base to acquire a large amount of service speaking flows and service knowledge information by combining with methods such as preset rules, text mining, manual editing and the like, and high-quality customer service is provided.

Because the business management requirements and local language expression habits of different areas are different, the navigation knowledge base in the intelligent system can be built according to the total branch, the total navigation knowledge base covers the general management requirements of the whole row, and the navigation knowledge bases of the branches and the network points (branches) can build personalized contents according to local differences.

The total branch three-level navigation knowledge base can be used for carrying out targeted training by combining artificial intelligence capability, so that the purpose of better understanding the customer expression intention in different places is achieved, and the management requirements of different branches are more personalized.

Step S3042, according to the semantic analysis result, inquiring related service conversation process and service knowledge information in the navigation knowledge base through the navigation system to obtain a service-available inquiry result;

the semantic analysis result contains the problem or service requirement of the user, the navigation system can inquire the service call flow and service knowledge information related to the content in the navigation knowledge base according to the problem requirement of the user in the semantic analysis result, and the inquired service call flow and service knowledge information are processed to obtain the service inquiry result.

The processing may be to remove redundant information, check information, modify error information, etc.

Step S3043, outputting the service-available query result to the user terminal through a preset interactive voice response system;

According to the intelligent voice service method provided by the embodiment of the application, the navigation knowledge base provides data for the navigation system by acquiring the service call flow and the service knowledge information, the navigation system queries the related service call flow and the service knowledge information in the navigation knowledge base according to the semantic analysis result to obtain the service query result, and finally the service query result is output to the user side through the preset interactive voice response system.

Referring to fig. 7, fig. 7 is a schematic flow chart of a seventh exemplary embodiment of an intelligent voice service method of the present application.

Based on the third or sixth embodiment, a seventh embodiment of the present application is presented, which differs from the third or sixth embodiment in that:

in this embodiment, in step S301, a preset semantic analysis system performs semantic analysis on a service requirement in the service request instruction, so as to obtain a semantic analysis result, and the step of refining includes:

step S3001, performing voice recognition on the service requirement through a preset semantic analysis system to obtain a voice recognition result;

because the user communicates with the server side mainly in the form of a call, before the intelligent system performs semantic analysis on the service requirement of the user, the voice of the user needs to be recognized.

Before the voice of the user is recognized, the voice data of the user can be preprocessed, so that the accuracy of subsequent voice recognition is improved.

The manner of preprocessing the voice data of the user may include:

and (3) voice cleaning: the voice cleaning aims at removing errors and repeated factors in voice, and checking the accuracy of the voice. As a first step in speech preprocessing, speech scrubbing is an important ring to ensure the production of good quality speech data.

Phoneme labeling: in short, the phoneme label is to label the phonetic components such as phonetic symbols and pronunciation, and the phoneme is used as the minimum phonetic unit to disassemble the voice into different segments, so that the voice data can be finished more precisely and accurately.

Preprocessing the voice of the user to obtain preprocessing information which can be used for voice recognition by the semantic analysis system, and performing voice analysis on the preprocessing information through the semantic analysis system after the preprocessing information is obtained.

The voice can be analyzed through natural language processing, machine learning and other technologies, and a voice recognition result is obtained.

Step S3002, converting the voice recognition result into text information to obtain service demand text information;

and converting the obtained voice recognition result into text information to obtain the text information of the service requirement.

Wherein the speech recognition result can be converted into text information by means of an ASR (Automatic Speech Recognition ) model.

ASR models refer to models for automatic speech recognition, and may include hidden markov models and mixed gaussian models.

And step S3003, analyzing the service demand text information to obtain a semantic analysis result.

After the service demand text information is obtained, the user intention is analyzed through the intelligent system.

The analysis method can comprise the following steps:

lexical analysis: the text is subjected to word segmentation, part-of-speech tagging and other processing, and the text is divided into basic language units, so that a foundation is provided for subsequent semantic analysis.

Syntax analysis: the sentence is analyzed for the syntactic structure, and the relations among the subjects, predicates, objects and other components in the sentence are identified so as to understand the syntactic structure of the sentence.

Semantic role labeling: key components (e.g., actions, actors, recipients, etc.) in the sentence are identified and their semantic roles in the sentence are labeled to capture semantic information of the sentence.

Named entity identification: named entities in the text that have a particular meaning, such as person names, place names, time, organization, etc., are identified to extract key information.

And (5) intention recognition: the purpose or intent of the text is analyzed to understand the services or operations required by the user in the expression.

Text classification: the text is classified according to its content characteristics, and the text is classified into different categories for further processing or analysis.

Through the method, the semantics of the text information can be deeply understood, and higher-level understanding and processing of the text are realized so as to understand the intention of a user, and a data base is established for the subsequent service.

According to the intelligent voice service method, voice recognition is carried out on the service requirement through a preset semantic analysis system, and a voice recognition result is obtained; converting the voice recognition result into text information to obtain service demand text information; and analyzing the service demand text information to obtain a semantic analysis result. The user intention can be better understood by analyzing the service demand text information obtained by preprocessing the user voice and converting the text, so that the subsequent soft exchange platform can distribute the service according to the intention of the user, and the efficiency and quality of processing the service demand of the user are greatly improved.

Referring to fig. 8, fig. 8 is an overall flow chart of the intelligent voice service method of the present application.

As shown in fig. 8, the intelligent voice service method of the present application may be divided into the following parts: user, robotic response, manual response, and response summary.

The whole service flow of the intelligent voice service method can be divided into the following important steps:

step 1: when the user dials a website, the incoming call of the user is routed to the intelligent system, and the intelligent voice customer service robot in the intelligent system processes the incoming call of the user.

Step 2: when the intelligent voice customer service robot can completely solve the questions of the user, the processing of the incoming call of the user can be considered to be completed, and finally the use experience of the user can be collected in a short message mode, so that the intelligent voice customer service robot is improved subsequently.

Step 3: when the intelligent voice customer service robot can not completely answer the user questions or the user requests to transfer into the artificial object for service, the user calls are distributed to related personnel for processing, the related personnel comprise network staff and related business answering personnel, the user calls are finished after the user questions are answered, and the related personnel are used for finishing the answering data, so that the follow-up optimization training of the intelligent voice customer service robot is facilitated, and the answering capacity of the follow-up intelligent voice customer service robot is improved.

Specifically, the method can conduct deep analysis on data converted from manual or answering failure due to problems such as customer refusal, overtime and the like, ensure retrospective mining of reasons affecting user experience, optimize process construction and speaking design, and form a closed-loop service optimal solution.

The intelligent voice service method can be divided into the following functional modules:

traffic transfer: when the user dials the website telephone number, the website telephone number needs to be verified, and after the verification is passed, the incoming call route of the user is transferred to the intelligent system.

And a robot response interaction module: when the user call is routed to the intelligent system, the robot response interaction module is started to process the user service request instruction.

Traffic distribution module: when the robot response interaction module cannot process the user demand, the soft switching platform distributes the user incoming call information, and the distributed object can be a service website worker or a related service response worker dialed by the user.

Traffic waiting module: when the soft switching platform distributes the user incoming call information, the user incoming call information can be queued due to the fact that the number of people is large, and the telephone traffic waiting module can better manage queuing of the user incoming call, optimize queuing sequence and improve user experience.

And a response agent interaction module: when the soft exchange platform distributes the user incoming call information to related staff for processing, the staff solves the user questions.

And the auxiliary short message module is used for: the related staff can be assisted by the form of short messages to answer the questions of the user.

And the data reflux training module: after the intelligent voice customer service robot can not completely answer the user questions or related staff answers the user questions, the dialogue is recorded and arranged, so that the intelligent voice customer service robot can be optimized and trained subsequently, and the answering capacity of the intelligent voice customer service robot is improved.

Referring to fig. 9, fig. 9 is a flow chart of an overall system deployment architecture of the intelligent voice service method of the present application.

The overall system deployment architecture flow of the intelligent voice service method can be divided into the following important steps:

step 1: the operation management system sends the acquired registered available service site telephone number to an operator Yun Zongji, when the user dials a site telephone, the operation Shang Yun switchboard identifies the site telephone number dialed by the user, and identifies whether the site telephone number dialed by the user is the registered available service site telephone number.

Step 2: when the operation Shang Yun switchboard judges that the network point telephone number dialed by the user is the registered available service network point telephone number, the incoming call information of the user is routed to the soft switching platform through the SIP relay.

Step 3: the soft exchange platform distributes the user incoming call information to a voice navigation system or related staff for processing through a route according to the user incoming call intention analyzed by the intelligent voice customer service robot.

Where the Speech navigation system employs ASR/TTS technology, ASR and TTS are abbreviations for Speech recognition (Automatic Speech Recognition) and Speech synthesis (Text-to-Speech), the ASR/TTS technology may help the Speech navigation system recognize user requirements.

In addition, the voice navigation system also comprises a navigation system and a navigation knowledge base, wherein data transmission is carried out between the navigation system and the navigation knowledge base through an HTTP protocol, and the navigation system can search answers or flow speech operation of related solution questions in the navigation knowledge base according to user requirements identified by the voice navigation system.

Specifically, the soft switching platform routes the incoming call information of the user to relevant staff for processing through SIP and HTTP protocols,

among them, SIP (Session Initiation Protocol) is a communication protocol for setting up, modifying and terminating multimedia sessions, which is mainly used for real-time communication such as voice telephony and video conferencing.

HTTP (Hypertext Transfer Protocol) is a protocol for transferring hypertext documents between a browser and a server, primarily for accessing and transferring web interfaces, pictures, videos.

In addition, the embodiment of the application also provides an intelligent voice service device, which comprises:

The principle and implementation process of the intelligent voice service are implemented in this embodiment, please refer to the above embodiments, and the description is omitted here.

In addition, the embodiment of the application also provides a terminal device, which comprises a memory, a processor and an intelligent voice service program stored on the memory and capable of running on the processor, wherein the intelligent voice service program realizes the steps of the intelligent voice service method when being executed by the processor.

Because the intelligent voice service program is executed by the processor and adopts all the technical schemes of all the embodiments, the intelligent voice service program has at least all the beneficial effects brought by all the technical schemes of all the embodiments and is not described in detail herein.

In addition, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores an intelligent voice service program, and the intelligent voice service program realizes the steps of the intelligent voice service method when being executed by a processor.

Compared with the prior art, the intelligent voice service method, the intelligent voice service device, the intelligent voice service terminal device and the intelligent voice service storage medium provided by the embodiment of the application are characterized in that the service request instruction sent by the user side is received, and the service request instruction comprises target service website information and service requirements; and if the target service network point information is one of a plurality of available service network point information in the service end, providing voice service for the service requirement through a preset intelligent system. Because the service request instruction sent by the user terminal comprises the target service site information, and the service terminal stores a plurality of pieces of available service site information, when the service terminal receives the service request instruction from the user terminal, the service terminal can identify the target service site information in the service request instruction, and if the target service site information is identified as one of the plurality of pieces of available service site information, the service request instruction can be further processed through a preset intelligent system, and in this way, the user can establish contact with the service terminal by inputting any piece of available service site information, thereby ensuring the quality of processing the incoming call of the user and improving the processing efficiency.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.

The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims

1. An intelligent voice service method, wherein the method is applied to a service end, and the method comprises the following steps:

2. The intelligent voice service method according to claim 1, wherein if the target service node information is one of a plurality of available service node information in a service end, the step of providing the voice service for the service requirement through a preset intelligent system comprises:

3. The intelligent voice service method according to claim 2, wherein the step of providing voice service for the service requirement through a preset intelligent system comprises:

4. The intelligent voice service method according to claim 2, wherein the step of providing voice service for the service requirement through a preset intelligent system comprises:

5. The intelligent voice service method according to claim 4, wherein the step of routing the service request instruction to the artificial object through a preset soft switching platform comprises:

6. The intelligent voice service method according to claim 5, wherein the navigation system performs the processing of the semantic analysis result comprising:

7. The intelligent voice service method according to claim 3 or 6, wherein the step of performing semantic analysis on the service requirement in the service request instruction by a preset semantic analysis system to obtain a semantic analysis result comprises:

8. An intelligent voice service device, characterized in that the intelligent voice service device comprises:

9. A terminal device, characterized in that it comprises a memory, a processor and an intelligent voice service program stored on the memory and executable on the processor, which intelligent voice service program, when executed by the processor, implements the steps of the intelligent voice service method according to any of claims 1-7.

10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon an intelligent voice service program, which when executed by a processor, implements the steps of the intelligent voice service method according to any of claims 1-7.