TW202036323A - Intelligent online customer service convergence core system which can provide a reply or query to an intention generated through voice recognition and natural language processing procedures - Google Patents

Abstract

The present invention is an intelligent online customer service convergence core system. An AI processing system device processes voice or text data received by a terminal device. When the text data or voice is input to the terminal device and an AI processing system device through network connection, the customer service convergence core device determines a reply or query based on an intention generated after the data voice recognition or natural language processing. When the voice is transferred from a traditional telephone network to a voice customer service device through a private branch exchange (PBX), the customer service convergence core device determines a reply or query to an intention generated through voice recognition and natural language processing procedures for the incoming customer voice of the voice customer service device, and then retrieve a reply result from an enterprise's own system or external open data and return a reply or query to the terminal device.

Description

Intelligent online customer service convergence core system

The present invention relates to a service system, and more specifically to a core system that can provide terminal users to connect real-time intelligent online customer service through a data network or a voice network through a terminal device.

The current customer service online service (referred to as customer service) system includes telephone voice, network instant messaging, professional customer service personnel and other modes to provide users with customer services related to queries and troubleshooting.

In order to provide more friendly real-time customer service, in recent years, an intelligent system for customer service has been developed to replace human customer service. It allows users to query the system using natural language. This intelligent system can analyze the natural language input by the user, and Reply to the user. However, this type of smart customer service system currently provides IP network connection users and telephone network connection users, but cannot provide an integrated single AI machine automated processing module in a single system at the same time. It is still divided into two categories: voice and text. Channel processing, only the back-end log data provides unified data analysis processing. System administrators need to unify voice and text AI machine automation processing modules for the construction of intelligent systems. They are used throughout various channels and different channels of corpus processing. They cannot take advantage of the other party to increase the overall AI automation processing module. The correct rate and quality of service. because This requires a set of AI machine automated processing modules that integrate voice and text, which can process different data sources to increase system maintenance and management efficiency and user experience, and improve customer service quality.

Therefore, it is necessary to find an intelligent online customer service confluence core device that integrates the AI automatic processing module type to avoid the above problems.

It can be seen that the above-mentioned conventional methods still have many shortcomings and poor usability, which is not a convenient and easy-to-use design, and needs to be improved urgently.

The present invention relates to a core system that can provide terminal users to connect real-time intelligent online customer service through a data network or voice network through a terminal device, provide voice recognition, natural language processing, and generate response data and voice Or text back to the terminal device. And when the text corpus after speech recognition cannot confirm its intention through the natural language processing module, it will compare the similarity with the historical text corpus through at least two text classification methods to obtain the closest similar sentence's intention. The intention for its adoption.

Before explaining the disclosure of the present invention in detail, the terms that may be involved in the present invention are explained first.

Intent: The intent mentioned in the present invention refers to the task that the user wants to complete in application scenarios or fields such as ordering meals, ride-hailing, online shopping and other specific scenarios. It can generally be described by specific verbs. For example, in the air ticket field, there is "check Intentions such as “ticket” and “refund of ticket”. After confirming the intention, in order to complete the task, the corresponding specific information required for each intention, such as the airline of the ticket, the place of departure, and the place of arrival, must be collected during the conversation.

Historical text corpus: Historical text corpus refers to the log content generated in the process of voice customer service and text customer service dialogue. The voice customer service log content is generated by the voice of the customer service dialogue through voice recognition, natural language processing and dialogue robots The chat text corpus produced by (Chat Bot), and the text customer service chat content means that the user directly communicates with the system through text without voice, and the back-end processing is through the natural language processing module and the chat robot. In turn, historical text corpus is generated; therefore, the historical text corpus includes the text corpus log generated by the user's voice or text conversation content after the system service is used.

Historical text corpus log: The historical text corpus log refers to the conversation text content log generated in the customer service service.

Judgment of intention similarity: The judgment of intention similarity adopts at least two text classification hybrid methods, which are trained by selecting historical text content samples of intentions, and the trained classifier uses feature values such as specific keyword groups to judge similar intentions . The text classification methods used in this embodiment are Convolutional Neural Network (CNN), Word To Vector (Word2Vec), Long Short-Term Memory (LSTM) and Logistic Regression Combine at least two methods among (Logistic Regression, LR), Term Frequency-Inverse Document Frequency (TF-IDF). In order to ensure the performance of the trained model, a combination of the above three or more methods can be used to obtain the best similarity classification model by tandem combination.

The present invention proposes an intelligent online customer service convergence core system, which includes: at least one terminal device to obtain a question request including text data or voice input by a customer; at least one AI processing system device (Artificial Intelligence) to process the data received by the terminal device Voice or text data; and a customer service convergence core device, when the text data or voice is connected through the network Connect to the terminal device and the AI processing system device, receive input data, determine a reply based on the intention generated after data speech recognition or natural language processing, or query the enterprise's own system or external open data (Open Data) to obtain the reply result, and return it Reply or query results to the terminal device; when the voice is transferred from the traditional telephone network through the Private Branch Exchange (PBX) to the voice customer service device for processing, the customer service confluence core device provides voice recognition to the customer's voice incoming from the voice customer service device , The natural language processing program, after identifying the customer's intention, obtains the required query data through the company's own system or external open data, and generates the reply data and sends it back to the terminal device by voice or text.

Among them, the intelligent online customer service convergence core system also includes a front-end device, which is connected to the customer service convergence core device through the Internet to obtain support from AI processing system devices, enterprise-owned systems, and external open data systems to respond to customer input Question request containing information.

Among them, the customer service convergence core device is connected to the AI processing system device through the network to provide voice recognition and natural language processing. After identifying the customer's intention, the necessary query data can be obtained through the company's own system or external open data. And store all text corpus in the process of processing, and classify the collected historical text corpus with intention. In order to speed up the processing of historical text data, the newly added text corpus log must be marked with frequently used keywords as the basis for search index. If there is no suitable keyword, it will be expanded by candidate keywords until there is a suitable keyword to provide corpus Label. The acquisition of keywords is based on historical text data after the word segmentation, and then the word segmentation types are counted, and the occurrence frequency is selected item by item from high to low. The preset number of keywords and content selection required for each tagging are based on history The text data is set by the number and content of keywords belonging to the same intention after manual bidding; and the source of the candidate keywords is expanded by the word segmentation of non-keywords in the segmentation category As a matter of fact, the addition of candidate keywords is based on the frequency of occurrence as the priority of selection.

Among them, the intention classification means that after the historical text corpus logs are marked with keywords, the similarity of their keywords and the number of keywords will be classified into the same group based on the intent similarity, and the classified historical text data will be classified by the intention type Classification storage, storage methods are arranged according to their similarity, each classification has its matching scene knowledge points for the natural language processing module to judge the intention.

Among them, when the text sentence after machine speech recognition cannot confirm its intention through the natural language processing module, the similarity judgment method of the aforementioned intention classification is compared with the historical text corpus to obtain the intent of the most similar sentence as The intention is to assist in the process of converting speech recognition to text. Due to the lack of recognition, this historical text corpus feedback mechanism is used to provide the correct intention judgment. This method can be used under the mixed use of voice customer service and text customer service. In machine voice and text customer service operations, errors caused by insufficient voice recognition include typos, missing characters, and historical corpus logs containing incorrect text messages that affect the generation of correct intentions; Through the intent classification similarity matching and the historical text corpus log obtained in the text customer service operation, the voice recognition error is assisted to obtain the correct intent.

Among them, the customer service convergence core device determines the query result response type according to the network connection type, including: receiving network data and selecting for voice recognition, and then performing semantic analysis of the result or directly performing semantic analysis; based on the network connection type Select a processing process; obtain the customer's intentions required by the corresponding problem through the processing process; and obtain the required query data through the company's own system or external open data according to the customer's intentions, and generate the query results.

Among them, the network connection type judgment includes an integrated data stream and customer service stream core device, which performs voice recognition and voice recognition processing on the customer's network connection type The procedure includes: obtaining the data of the data source network type through the network connection type judgment process; and judging the data according to the network type, judging whether the client conducts the remote device data connection process through the network.

Among them, when the network connection is a digital network connection, the network type judgment will be performed after the network type is confirmed, and the network transmission data will be judged. If it is text data, natural language processing will be performed. After the customer's intention, the necessary query data is obtained through the company's own system or external open data, and the reply data is generated and sent back to the terminal device by voice or text.

Among them, when the network connection is a digital network connection, the network type judgment will be performed after the network type is confirmed, and the network transmission data will be judged. If it is voice data, the speech recognition and natural language processing procedures will be performed , After identifying the customer’s intention, obtain the required query data through the company’s own system or externally open data, and generate the reply data and send it back to the terminal device by voice or text.

Among them, when the network connection is a telephone network connection, the network type judgment will perform the transmission data voice recognition and natural language processing procedures after confirming the network type, and after the customer’s intention is determined, through the enterprise Obtain the required query data from its own system or external open data, and generate response data to return to the terminal device in voice or text.

Among them, the question request is input in a text input mode or a voice input mode, and is judged by the message gateway according to the content type of the transmitted signal, and then sent to the AI processing system device to judge the customer's intention.

Among them, the customer-owned system is one of the non-public internal dedicated system groups, and the non-public internal dedicated system group includes at least one of the following: an enterprise resource planning system (ERP), a knowledge management system (KMS) , A customer relationship management system (CRM), with And an enterprise's own database system.

Among them, the emerging customer service channel is a mobile phone or a tablet computer or a personal computer or a notebook computer or a digital panel or an electronic signboard or a smart speaker and other emerging customer service channel terminal equipment.

The above detailed description is a specific description of a feasible embodiment of the present invention, but this embodiment is not used to limit the scope of the present invention. Any equivalent implementation or modification that does not deviate from the technical spirit of the present invention shall be included in this case. The scope of patents.

To sum up, this case is not only innovative in terms of spatial form, but also can improve the above-mentioned multiple functions compared with conventional articles. It should fully meet the requirements of novel and progressive statutory invention patents. An application is filed in accordance with the law, and your office is requested for approval. This invention patent application is to encourage invention, and it will be convenient.

100‧‧‧Intelligent online customer service convergence core system

110‧‧‧Emerging Customer Service Channel

112‧‧‧Smartphone

114‧‧‧Computer

116‧‧‧Smart Device

120‧‧‧Traditional Customer Service Channel

122‧‧‧Phone

132‧‧‧IP network (TCP/IP)

134‧‧‧Public switched telephone network or mobile network

140‧‧‧Voice customer service device

142‧‧‧User Private Exchange

144‧‧‧Interactive Voice Response System

146‧‧‧Media Resource Control Protocol Server

150‧‧‧Customer Service Confluence Core Device

152‧‧‧Customer Service Confluence Management Module

154‧‧‧Message Gateway

160‧‧‧AI processing system device

162‧‧‧Speech to text module

164‧‧‧Text-to-speech module

166‧‧‧Natural Language Processing Module

167‧‧‧Intention Judgment Knowledge Base

168‧‧‧Talking Robot

170‧‧‧Enterprise Own System

172‧‧‧Enterprise own system database

180‧‧‧External open data system

182‧‧‧News

184‧‧‧weather

190‧‧‧Other application systems

192‧‧‧Live Customer Service System

S200~S204‧‧‧Step Process

S300~S307‧‧‧Step Process

S400~S407‧‧‧Step Process

S501~S508‧‧‧Step Process

S601~S612‧‧‧Step Process

Figure 1 is a schematic diagram of an intelligent online customer service convergence core system according to an embodiment of the present invention

Figure 2 is a schematic diagram of a customer service process according to an embodiment of the present invention.

Figure 3 is a schematic diagram of a customer service process according to an embodiment of the present invention.

Figure 4 is a schematic diagram of a customer service process according to an embodiment of the present invention.

Fig. 5 is a schematic diagram of a customer service process according to an embodiment of the present invention.

Fig. 6 is a schematic diagram of a customer service process according to an embodiment of the present invention.

For the benefit of reviewers to understand the technical features, content and advantages of the present invention And the effects that can be achieved, the present invention is combined with the accompanying drawings, and is described in detail as follows in the form of embodiment. The figures used therein are only for illustration and auxiliary description purposes, and are not necessarily the present invention. The true proportions and precise configuration after implementation should not be interpreted in terms of the proportions and configuration relationships of the attached drawings, and the scope of rights of the present invention in actual implementation should not be interpreted.

The term "exemplary" used in the present invention means that the disclosed element or embodiment is only an example, and does not indicate any preference of the user. In addition, the same number indicates the same element in all the several figures, and unless otherwise specified in the description, the articles "a" and "above" include plural references. The words "including" and "including" used in the specification of the present invention are used to indicate the existence of specific technical features, values, method steps, operation processing, elements and components, but it does not exclude the possibility of adding more technologies Features, values, method steps, job processing, components, components, or any combination of the above.

Fig. 1 is a schematic diagram of an intelligent online customer service convergence core system according to an embodiment of the present invention. The intelligent online customer service convergence core system 100 can include an emerging customer channel 110, a traditional customer service channel 120, a public switched telephone network or mobile network 134 (Public Switched Telephone Network, PSTN), and a voice customer service device 140 (including user-specific The switch 142, an interactive voice response system 144 (Interactive Voice Response, IVR) and a media resource control protocol server 146 (Media Resource Control Protocol, MRCP)), a customer service convergence core device 150, and an AI processing system device 160. The customer service convergence core device 150 can be connected to the AI processing system device 160, the emerging customer channel 110, the traditional customer service channel 120, the voice customer service device 140, the customer-owned system 170, and the external open data system 180 through the public switched telephone network or the mobile network 134 , Other application systems 190, in which the public switched telephone network or mobile network 134 can be any type of network familiar to those skilled in the art, which can use various Any one of the communication protocols available to support data communication, including but not limited to PSTN, TCP/IP, etc., can be any combination of other networks.

The customer service convergence core device 150 is mainly responsible for providing a customer service smart service with different network connection convergence platforms. Through the interface between the customer service convergence management module 152 and different network types, it can obtain traditional customer service channels and emerging customer service channels front-end device customers For the relevant data required by the question, perform voice recognition and semantic analysis, analyze the type of intent, and then query the customer’s own system, external open data, and other application systems according to the type of intent to obtain relevant query results, and then return the query results To the customer. The customer service confluence core device 150 can be regarded as an intelligent customer service robot, which includes a pre-designed network type determination program for subsequent processing of data sources. The message gateway 154 can automatically provide the corresponding network type according to the network type source. The processing flow corresponding to the data is to conduct text or voice dialogues, obtain the questions asked by the customer, perform the required voice recognition, semantic analysis, and analyze the intent type. Then, according to the intent type, query the company's own system 170 and external open data 180 1. The other application system 190 obtains the query result, and finally sends the query result back to the customer.

The AI processing system device 160 can provide speech recognition and natural language semantic analysis services, and can analyze a natural speech after recognition and semantic analysis. For example, the AI processing system device 160 can have a natural language processing engine and a speech to text module 162 (Speech To Text, STT) and a text to speech module 164 (Text To Speech, TTS), which can be processed through the natural language processing engine The entire text content is directly analyzed, or the speech signal is converted into text through the speech-to-text module 162 and then analyzed, to obtain the semantic analysis result of the text. The AI processing system device 160 can, after obtaining the customer’s intention request, send the query request command data required by the intention to the enterprise’s own system 170, external open data 180, and other data via the IP network (TCP/IP) 132 He applies the system 190 to query to obtain query results, and finally returns the query results to the customer. When the machine speech-to-text module 162 converts the speech to text, if the text corpus cannot be confirmed by the natural language processing module 166 (Natural Language Processing, NLP) and the intention judgment knowledge base 167, it will use at least two The text classification method combination is compared with the historical text corpus for similarity, and the closest similar sentence intention is obtained as the intention for its adoption. That is, in the process of confluence processing of machine voice customer service and text customer service, the text corpus obtained through text customer service can be used to strengthen the shortcomings of insufficient recognition accuracy of the voice customer service voice-to-text module 162, and enhance the accuracy of system processing.

The emerging customer service channel 110 can be a computer or a mobile device, such as a smart phone 112, a computer 114, or a smart device 116, which can be capable of running applications. The traditional customer service channel 120 can be a phone 122. The emerging customer service channel 110 and the traditional customer service channel 120 can be used by customers or users. The customer or user can input a question request of the data to be inquired in a text input mode or a voice input mode according to the input method of the terminal device. The channel 110 and the traditional customer service channel 120 can obtain the aforementioned question request input by the customer, and transmit the aforementioned question request to the customer service convergence core device 150 or connect to the customer service convergence core device 150 through the AI processing system device 160. Customers or users can download and install their own service application developed by the customer service convergence core device 150 (for ease of understanding, hereafter referred to as-service APP), the service APP includes a graphical interface, so that customers or users can Connect to the customer service convergence core device 150 through the service APP of the emerging customer service channel 110 to interact or talk with the customer service convergence core device 150 through a graphical interface to ask questions, inquire, receive, and display the response provided by the customer service convergence core device 150 The query result of the answer to the question asked above. The 110 series of emerging customer service channels at the front desk can generate web pages, for example, e-web pages for use The user uses. Similarly, customers or users can also input the above-mentioned question request containing the above-mentioned data to be inquired by text input or voice input, and the emerging customer service channel 110 can obtain the above-mentioned question request input by the customer and send the above-mentioned question request To the customer service convergence core device 150, the emerging customer service channel 110 can also receive and display the answers or query results corresponding to the above-mentioned questions provided by the customer service convergence core device 150 and generate a page containing the answers or query results to present the query results to customers or user.

In detail, customers can use the service APP of Emerging Customer Service Channel 110 or the e-webpage generated by Emerging Customer Service Channel 110 to conduct a conversation with the customer service convergence core device 150 through text or voice input to make inquiries or inquiries. The device 150 can receive the data input by the customer through a preset dialogue process, and connect to the AI processing system device 160 via the message gateway 154 for semantic analysis and/or speech recognition (for example, through speech-to-text processing), and then recognize the customer's intention , According to the type of question, you can choose to directly reply to the customer’s answer, or interface with the back-end enterprise-owned system 170, external open data system 180 (such as news 182, weather 184) or other application systems 190 (such as real customer service system 192). The information system provides customer consultation results. In one embodiment, when the emerging customer service channel 110 is a smart phone, the customer service convergence core device 150 can make good use of the characteristics of the phone and design interactive methods such as clicks, pictures, forms, and swipes to provide customers with input related query data. And according to the screen size and operating characteristics of the mobile phone, it provides a simplified query result presentation that matches the mobile phone screen, making it more convenient for customers to conduct various queries on the mobile phone.

The enterprise-owned system 170 is a non-public internal dedicated system group, and the aforementioned non-public internal dedicated system group is used to provide inquiries about exclusive data within the enterprise. For example, the aforementioned non-public internal dedicated system group may include ERP or CRM or KMS or dialogue Robot knowledge base, etc., but the present invention is not limited to this. The aforementioned enterprise-owned system 170 may have an enterprise-owned system database 172 that stores relevant information in the enterprise. Each enterprise-owned system 170 may each have an independent enterprise-owned system database 172 or multiple enterprise-owned systems 170 may share the same enterprise-owned system database 172. The customer service convergence core device 150 can access the data stored in the enterprise-owned system database 172 through the aforementioned enterprise-owned system 170 when necessary.

Specifically, the customer service convergence core device 150 can send the data to the AI processing system device 160 through the message gateway 154 after receiving the problem request containing the data. The AI processing system device 160 receives the data, judges the data, and performs voice Recognition and semantic analysis or directly perform semantic analysis to generate a semantic analysis result, and return the semantic analysis result to the AI processing system device 160. The customer service convergence core device 150 can then determine the above-mentioned query result according to the semantic analysis result.

In one embodiment, the customer service convergence core device 150 determines the query result according to the data required by the question may include the following steps: receiving the semantic analysis result of the data; determining a question type based on the semantic analysis result; according to the question type, Choose a dialogue process; obtain the reference materials corresponding to the above-mentioned questions through the above-mentioned dialogue process; and generate the above-mentioned query results based on the above-mentioned reference materials.

Figures 2 to 6 are schematic diagrams of a customer service process according to an embodiment of the present invention.

First, in step S200, the customer or any questioner can ask the customer service convergence core device a question containing a questioning data through the service APP of the terminal device or the e-page of the front desk device (such as the company or customer service official website) or traditional phone. Request, as described in step S204, the customer service confluence core device will determine the source of the message. Or as in step S201, after the customer makes a phone call and asks the question request of the data, in step S202, send to interactive After the digital voice response system transmits the digital voice to the customer service convergence core device via the server (step S203), as described in step S204, the customer service convergence core device determines the message source channel as an emerging customer service channel or a traditional customer service channel.

When the source type of the connection channel source is judged to be an emerging customer service channel, as shown in Figure 3, step S300, first pass the signal content type judgment through the message gateway 1, and step S301, the text data input by the customer service convergence core device The AI processing system device performs voice recognition and natural language processing into text in step S302. Then, as described in step S303, the AI processing system device performs semantic analysis on the text data to understand the customer’s intentions. Then, in step S304, the enterprise-owned system, external open data, and other application systems perform query to obtain the query result and return the customer service convergence core device. The customer service convergence core device determines that the query result is text or voice (step S305), and the query result is voice At this time, in step S306, the voice is converted into text and displayed on the terminal device (step S307). When the query result is text, it is directly displayed on the terminal device (step S307).

When the source of the connection path is judged to be the traditional customer service path, as shown in Figure 4, step S400, the customer service convergence core device transmits the voice to the AI processing system device, and step S401, the AI processing system device recognizes and recognizes the voice Natural language is processed into text. In step S402, the AI processing system device performs semantic analysis on the text data to understand the customer’s intentions. Then, in step S403, the enterprise’s own system, external open data, and other application systems are used to query to obtain the query results and return them The customer service convergence core device, the customer service convergence core device converts the text of the query result into a complete sentence, and sends it to the speech synthesis module in the AI processing system device. The AI processing system device returns the synthesized response voice to the server (step S404), and then use the interactive voice system to dial the reply voice to the phone in the traditional customer service channel (step S405). In detail, the AI processing system device can generate a semantic analysis result after the semantic analysis of the question data is completed and send the semantic analysis result back to the customer service convergence core device, so that the customer service convergence core device can obtain the corresponding questions from the AI processing system device The required semantic analysis results. Then, the customer service confluence core device can understand the customer's intentions and perform context processing based on the semantic analysis results, determine a dialogue flow based on the understood customer's intentions, and select the appropriate dialogue flow to confirm the information and goals the customer wants to inquire. The dialogue process can adopt a question and answer method, and the AI processing system device can determine the content to be questioned according to the semantic analysis result. The AI processing system device can establish multiple possible dialogue flows in advance based on the customer service experience, and then select a suitable dialogue flow according to the semantic analysis results required by the question for subsequent data collection (such as step S406 to step S407).

In an embodiment, as shown in FIG. 5, in step S501, when the natural language processing module processes the customer service corpus, step S505 provides the knowledge bases of scenes required by the natural language processing module, and then adds text in step S502 Corpus, and step S503 and step S506 perform keyword group and intent pairing and add text corpus keyword labeling, and finally step S504 performs intent classification of the labelled text corpus. Intent classification refers to the historical text corpus log history After the keywords are labeled, the similar keyword types and keyword numbers will be classified into the same group based on the intent similarity judgment. The historical text data after the output classification is classified and stored according to the intent types, and the storage method is arranged according to the similarity. Each category has its matching scene knowledge points for the natural language processing module to judge the intention. The historical text corpus logs are stored according to intent classification (step S508), and a reference for matching the keyword group and intent in step S506 is provided (step S507).

As shown in Figure 6, when the machine voice customer service operation is processed in step S601, the voice recognition of the content of the customer service conversation is performed in step S602 to generate text, and then the customer service is performed in step S603. The text semantic analysis of the conversation content, step S604 generates the most similar text corpus content and intention according to the semantic analysis result. When the text sentence after machine speech recognition cannot confirm its intention through the natural language processing module, it will be classified as similar through the aforementioned intention The degree judgment method compares the similarity with the historical text corpus (step S608), and obtains the intent of the most similar sentence as its intent (steps S605, S608) to assist in the process of speech recognition to text, due to insufficient recognition Next, through this historical text corpus feedback mechanism, the judgment of the correct intention is provided (step S612). This method can be used under the mixed use of voice customer service and text customer service. In machine voice and text customer service operations, errors caused by insufficient voice recognition include typos, additions and deletions, so that the historical corpus log contains incorrect text messages that affect the generation of correct intentions; Through the intent classification similarity matching and the historical text corpus logs obtained in the text customer service operation (step S606, step S607, step S609 to step S611), the above voice recognition error is assisted to obtain the correct intent.

To sum up, this case is not only innovative in terms of technical ideas, but also has the above-mentioned multiple functions that are not available in conventional existing methods. It has fully met the requirements of novel and progressive statutory invention patents. I file an application in accordance with the law. Approval of this invention patent application to encourage invention, so that it is convenient.

100‧‧‧Intelligent online customer service convergence core system

110‧‧‧Emerging Customer Service Channel

112‧‧‧Smartphone

114‧‧‧Computer

116‧‧‧Smart Device

120‧‧‧Traditional Customer Service Channel

122‧‧‧Phone

132‧‧‧IP network (TCP/IP)

134‧‧‧Public switched telephone network or mobile network

140‧‧‧Voice customer service device

142‧‧‧User Private Exchange

144‧‧‧Interactive Voice Response System

146‧‧‧Media Resource Control Protocol Server

150‧‧‧Customer Service Confluence Core Device

152‧‧‧Customer Service Confluence Management Module

154‧‧‧Message Gateway

160‧‧‧AI processing system device

162‧‧‧Speech to text module

164‧‧‧Text-to-speech module

166‧‧‧Natural Language Processing Module

167‧‧‧Intention Judgment Knowledge Base

168‧‧‧Talking Robot

170‧‧‧Enterprise Own System

172‧‧‧Enterprise own system database

180‧‧‧External open data system

182‧‧‧News

184‧‧‧weather

190‧‧‧Other application systems

192‧‧‧Live Customer Service System

Claims (7)

An intelligent online customer service convergence core system, which at least includes: a terminal device that obtains text data or voice input by a user; an AI processing system device that processes text data received by the terminal device or Voice; a customer service convergence core device, the customer service convergence core device will determine a reply or query based on the text data or voice input from the network according to the intent generated after data voice recognition or natural language processing, and after obtaining the reply or query result, Return the reply or query result to the terminal device; a voice customer service device, when the voice is transferred from the traditional telephone network to the voice customer service device via the private exchange, the customer service convergence core device connects the customer to the voice customer service device Voice recognition and natural language processing procedures are used to determine the response or query after the intention of the customer is determined, and the response or query result is obtained, and the response or query result is returned to the terminal device; a company owns data The database provides the customer service convergence core device to obtain the reply or query result through the enterprise's own database, and the text data generated for the reply or query is sent back to the terminal device by voice; and the text language after machine voice recognition If the material cannot be confirmed through the customer service convergence core device, it will compare at least two text classification methods with the historical text corpus for similarity to obtain the intent of the closest similar sentence as the intent of adoption. For example, the intelligent online customer service convergence core system described in the first item of the scope of patent application further includes a front-end device, which is connected to the customer service convergence core device through the network to obtain an AI processing system, an enterprise-owned system or an external opening The support of the data system to obtain the reply or query result. For example, the intelligent online customer service convergence core system described in item 3 of the scope of patent application, wherein the customer service convergence core device determines the type of response or query result after determining the network connection type. For example, the intelligent online customer service convergence core system described in item 4 of the scope of patent application, wherein when the network connection type is judged by the customer service convergence core device as a digital network connection, the network transmission data is judged, and it is text When data, perform natural language processing. After identifying the user's intention, obtain the required response or query result through the company's own system or external open data, and generate voice or text response data, which is returned to the terminal device . For example, the intelligent online customer service convergence core system described in item 4 of the scope of patent application, in which when the network connection type is judged by the customer service convergence core device as a digital network connection, the network transmission data is judged, and it is voice When data, perform voice recognition and natural language processing procedures. After identifying the user’s intention, obtain the required reply or query result through the company’s own system or external open data, and generate voice or text reply data, which is returned to The terminal device. For example, the intelligent online customer service convergence core system described in item 4 of the scope of patent application, wherein when the network connection type is judged by the customer service convergence core device as a telephone network connection, the transmission data voice recognition and natural language processing procedures are performed After the user's intention is determined, the required response or query result is obtained through the company's own system or external open data, and the response data in the form of voice or text is generated and returned to the terminal device. For example, the intelligent online customer service convergence core device described in item 4 of the scope of patent application further includes a historical text corpus storage database, which synchronously stores the text corpus in the transmission process. The collected historical text corpus is classified and stored by the intention type to speed up the processing of the historical text data. According to the intent similarity judgment, the keyword types and the number of keywords will be classified into the same group to produce classified historical text The data is classified and stored according to the type of intention The degree is sorted, and the classification keywords are searched in multiple ways. Each category is provided with a corresponding scene knowledge point for the natural language processing module to perform intent judgment. For example, the intelligent online customer service convergence core system described in item 7 of the scope of patent application, when the text sentence after voice recognition cannot confirm the intention through the customer service convergence core device, it will judge the similarity of the intention classification in the historical text corpus storage database Comparing the similarity with historical text corpus to obtain the intention of the most similar sentence.

Images