KR101827320B1 - Server for call center using artificial intelligence - Google Patents

Abstract

The present invention provides a server for a call center using artificial intelligence. According to the present invention, the server comprises: a real-time text middleware (RTM) module, which is a real-time text conversion module configured to receive a call from a customer terminal, when the call comprises an advise request, control to convert the received voice of the advice request to text in real time, control to receive the answer text generated based on the advice request and convert the generated answer text to a voice answer, and transmit the generated voice answer to the customer terminal in real time; a speech-to-text (STT) module which converts the voice to text when receiving an instruction to convert the voice to text in real time from the RTM; a chatbot which transmits the answer for the advice request corresponding to the text converted by the STT module to the RTM module in the form of text; and an interactive voice response (IVR) module, which is a text-to-speech (TTS) module configured to receive the answer text received from the chatbot via the RTM module, and when receiving an instruction to receive the answer text and convert the received answer text to the voice from the RTM module, convert the received answer text to the voice in real time.

Description

{Artificial Intelligence Call Center Server}

The present invention relates to an artificial intelligence call center method, and provides a server that can artificially and intelligently operate an unattended call center using RTM (Real-Time Text Middleware).

Recently, the ARS system has been developed and widely used. However, since many people feel uncomfortable in the ARS system or voice recognition system which can not communicate manually and interactively, The cost of construction increases, but the waste of agent workforce remains.

At this time, CTI (Computer Telephony Intergration) is used for accurate connection of ARS and smooth distribution of counseling to the call center. In this connection, Korean Patent Laid-Open Publication No. 2012-0070417 (published on Jun. 29, 2012) discloses a call center PBX link device for easily linking general IP-PBX and CTI middleware of various manufacturers without protocol modification do.

However, if an artificial intelligence call center is not built even if you use CTI, if you still wander in ARS, can not find or remember a menu, and you go back to the previous level, The reliability of the company adopting the system is lowered beyond the abandonment of the system or the mistrust of the system, and the company is not using the product or service of the company.

In an embodiment of the present invention, speech is recognized as text in real time, and RTM (Real-Time Text Middleware) is employed to optimize the voice signal for conversion, thereby increasing the recognition rate and recognizing in real time, It is possible to provide an artificial intelligence call center method capable of artificial intelligent processing of accurate answers and providing a system for systematically managing call center agents. It should be understood, however, that the technical scope of the present invention is not limited to the above-described technical problems, and other technical problems may exist.

According to an aspect of the present invention, there is provided a method of transmitting a voice message, which is a received consultation message, to a user terminal in real time when an outgoing call is received from a customer terminal, RTM (Real-Time Text Middleware), which is a real-time text conversion module that controls conversion to text, receives response texts generated from consultation contents and converts them to speech, and transmits the generated speech responses to the client terminal in real- (STT), which is a module for converting speech into text, and an answer to the consultation contents corresponding to the text converted from the STT, as RTM And an answer text received from the chatbot via the RTM, and receives an answer text from the RTM When receiving the host receives a command for controlling to convert the sound, and a person (Interactive Voice Response) IVR module including a TTS (Text To Speech) for converting the response text to speech in real time.

According to any one of the above-mentioned objects of the present invention, voice is recognized as text in real time, and RTM (Real-Time Text Middleware) is adopted to optimize the voice signal for conversion, It enables to artificially process the correct answers to the query questions, and it can provide a system that systematically manages call center agents.

1 is a block diagram illustrating an artificial intelligent call center system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating an embodiment of an unattended counseling service in the artificial intelligence call center server shown in FIG. 1. FIG.
FIG. 3 is a block diagram for explaining an embodiment of providing an agentless agent consulting service and an agent consulting service in the artificial intelligence call center server shown in FIG. 1. FIG.
FIG. 4 is a block diagram illustrating the RTM of the artificial intelligent call center server shown in FIG. 1. FIG.
5 is a diagram for explaining an operation of an artificial intelligent call center system according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between . Also, when an element is referred to as "including" an element, it is to be understood that the element may include other elements as well as other elements, And does not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof.

The terms "about "," substantially ", etc. used to the extent that they are used throughout the specification are used in their numerical value or in close proximity to their numerical values when the manufacturing and material tolerances inherent in the stated meanings are presented, Accurate or absolute numbers are used to help prevent unauthorized exploitation by unauthorized intruders of the referenced disclosure. The word " step (or step) "or" step "does not mean" step for. &Quot;

In this specification, the term " part " includes a unit realized by hardware, a unit realized by software, and a unit realized by using both. Further, one unit may be implemented using two or more hardware, or two or more units may be implemented by one hardware.

In this specification, some of the operations or functions described as being performed by a terminal, a device, or a device may be performed instead in a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, device or device connected to the server.

In this specification, some of the operations or functions described in the mapping or matching with the terminal are used for mapping or matching the unique number of the terminal or the identification information of the individual, which is the identification data of the terminal . ≪ / RTI >

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram illustrating an artificial intelligent call center system according to an embodiment of the present invention. 1, the artificial intelligence call center system 1 may include a customer terminal 100, an artificial intelligence call center server 300, at least one agent terminal 400, and an administrator terminal 500. However, since the artificial intelligent call center system 1 of FIG. 1 is only an embodiment of the present invention, the present invention is not limited to FIG.

At this time, the respective components of FIG. 1 are generally connected through a network 200. For example, as shown in FIG. 1, the customer terminal 100 may be connected to the artificial intelligence call center server 300 through the network 200. [ The customer terminal 100 may be directly or indirectly connected to the at least one agent terminal 400 through the network 200 through the artificial intelligence call center server 300. Also, at least one of the agent terminals 400 may be connected to the customer terminal 100 through the artificial intelligence call center server 300. The administrator terminal 500 may be connected to the at least one agent terminal 400 directly or through the network 200 and the artificial intelligence call center server 300.

Here, the network 200 refers to a connection structure capable of exchanging information between nodes such as a plurality of terminals and servers. One example of such a network 200 is a 3rd Generation Partnership Project (3GPP) network, A 5th Generation Partnership Project (5GPP) network, a World Interoperability for Microwave Access (WIMAX) network, an Internet, a LAN (Local Area Network), a Wireless LAN (Local Area Network) But are not limited to, a Wide Area Network (PAN), a Personal Area Network (PAN), a Bluetooth network, an NFC network, a satellite broadcast network, an analog broadcast network, a DMB (Digital Multimedia Broadcasting)

The customer terminal 100 may be a customer terminal using a call center. The customer terminal 100 may be a terminal for requesting a desired consultation based on a voice or a number, or inputting its own information and transmitting it to the artificial intelligence call center server 300. Also, the customer terminal 100 may be a terminal that receives an answer to his / her consultation or a question in an automatic response of the artificial intelligence call center server 300. The customer terminal 100 may be a terminal of a customer who requests a consultation with a person directly when the answer to the question or the consultation is not possible with the artificial intelligence. In addition, if the customer speaks a prohibited word, the voice recorded after the call origination is generated in the customer terminal 100 is audited, and a warning is automatically received from the artificial intelligence call center server 300, And may be a terminal of a customer transmitted to the call center server 300.

Here, the customer terminal 100 may be implemented as a computer capable of connecting to a remote server or terminal through the network 200. Here, the computer may include, for example, a set-top box, a notebook equipped with a web browser (WEB Browser), a desktop, a laptop, and the like. At this time, the customer terminal 100 may be implemented as a terminal capable of connecting to a remote server or terminal through the network 200. [ The customer terminal 100 is a wireless communication device that is guaranteed to be portable and mobility, for example, as a navigation device, a personal communication system (PCS), a global system for mobile communications (GSM), a personal digital cellular (PDC) Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication) -2000, Code Division Multiple Access (CDMA) -2000, W-Code Division Multiple Access (W-CDMA), Wibro (Wireless Broadband Internet) A handheld based wireless communication device such as a smartphone, a smartpad, a tablet PC, and the like.

The artificial intelligence call center server 300 may be a server directly or indirectly providing an app page, a web page, an application, a program, or the like for providing an artificial intelligence call center service. When receiving call origination from the customer terminal 100, the artificial intelligence call center server 300 converts the voice transmitted from the customer terminal 100 into text, And transmits the generated answer to the customer terminal 100 by controlling the generated answer to be converted into voice. In addition, the artificial intelligence call center server 300 optimizes the voice signal of an exchange or a voice section by using real-time text middleware to convert the voice signal into text, so that the voice-to- And the like. The artificial intelligence call center server 300 can store text data received from the voice-to-text conversion module in real time to show what kind of conversation is being visually performed. The chattel, AI, TTS And can be a server that plays a role of a hub capable of creating an unattended consultation call center. At this time, the artificial intelligence call center server 300 may be configured to connect the agent terminal 400 and the client terminal 100. The agent terminal 400 may process the response in real time in the agent terminal 500 ), And can be a server that can be visualized. In addition, when the inquirer terminal 400 queries the inquiries of the customer, the artificial intelligence call center server 300 outputs an answer to the inquiry in real time in the agent terminal 400 in cooperation with the knowledge management system And may be a server that minimizes the response waiting time of the customer. The artificial intelligence call center server 300 may be a server that records whether the customer inquiry, consultation or complaint received at the agent terminal 400 is resolved. In addition, the artificial intelligence call center server 300 may be a server for displaying a predetermined word or a preset word in the customer terminal 100, and outputting the word on the screen.

At this time, the artificial intelligence call center server 300 may be implemented as a computer capable of connecting to a remote server or terminal through the network 200. Here, the computer may include, for example, a notebook, a desktop, a laptop, and the like on which a WEB browser is installed.

At least one of the agent terminals 400 may be a terminal of a counselor responding to the consultation of the client terminal 100. At least one of the agent terminals 400 may be a terminal for searching a keyword for a query by voice recognition or direct search, and may be a terminal for outputting it to a screen in a state where the client can be guided. At least one of the agent terminals 400 may be a terminal that transmits interactions between the agent and the client to the artificial intelligence call center server 300 in real time so as to be interlocked with the administrator terminal 500 so that the consultation contents are text and documented. have. At least one of the agent terminals 400 may be a terminal that outputs behavior code data that is automatically output from the artificial intelligence call center server 300 to speech recognition when predetermined abuse or the like is received from the customer terminal 100 have.

Here, the at least one agent terminal 400 may be implemented as a computer capable of connecting to a remote server or terminal through the network 200. Here, the computer may include, for example, a POS terminal, a card terminal, a notebook equipped with a WEB Browser, a desktop, a laptop, and the like. At this time, at least one of the agent terminals 400 may be implemented as a terminal capable of connecting to a remote server or terminal through the network 200. [ At least one of the agent terminals 400 may be a wireless communication device with guaranteed portability and mobility, for example, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular) (PHS), a PDA (Personal Digital Assistant), an IMT (International Mobile Telecommunication) -2000, a CDMA (Code Division Multiple Access) -2000, a W-CDMA A handheld based wireless communication device such as a handheld device, a smartphone, a smartpad, a tablet PC, and the like.

The administrator terminal 500 may be a terminal that monitors the telephone call state of at least one of the agent terminals 400 and displays and updates the consultation state on a screen in real time. In addition, the manager terminal 500 can not only display the consultation contents or the answer contents converted into the text, but also the contents of the conversation when the speech or accent is out of the error range of the preset user, for example, Or if the intonation is detected, it may be a terminal that outputs it as an alarm.

At this time, the administrator terminal 500 can be implemented as a computer capable of connecting to a remote server or terminal through the network 200. [ Here, the computer may include, for example, a POS terminal, a card terminal, a notebook equipped with a WEB Browser, a desktop, a laptop, and the like. At this time, the administrator terminal 500 can be implemented as a terminal capable of connecting to a remote server or a terminal through the network 200. The administrator terminal 500 is a wireless communication device that is guaranteed to be portable and mobility, for example, as a navigation device, a personal communication system (PCS), a global system for mobile communications (GSM), a personal digital cellular (PDC) Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication) -2000, Code Division Multiple Access (CDMA) -2000, W-Code Division Multiple Access (W-CDMA), Wibro (Wireless Broadband Internet) A handheld based wireless communication device such as a smartphone, a smartpad, a tablet PC, and the like.

FIG. 2 is a block diagram for explaining an embodiment of performing an unattended counseling service in the artificial intelligence call center server shown in FIG. 1. FIG. 3 is a block diagram illustrating an unmanned counseling service in the artificial intelligence call center server shown in FIG. FIG. 4 is a block diagram illustrating an RTM of the artificial intelligent call center server shown in FIG. 1, and FIG. 5 is a block diagram illustrating an embodiment of the present invention FIG. 4 is a diagram for explaining an embodiment in which the artificial intelligence call center system according to the present invention operates.

2, an artificial intelligence call center server 300 according to an exemplary embodiment of the present invention includes a real-time text middleware (RTM) 310, an interactive voice response (IVR) 320, a speech to text , And a chatbot (340).

When receiving an outgoing call from the customer terminal 100 and receiving the contents of consultation from the customer terminal 100, the RTM 310 realizes the voice of the received consultation content in the form of text A text conversion module that receives the answer text generated from the consultation content and controls conversion to speech, and transmits the generated speech response to the customer terminal 100 in real time. Hereinafter, a detailed description of the RTM 310 will be described with reference to FIG.

At this time, the RTM 310 performs a role of CTI (Computer Telephony Integration), but operates as an AI, so that its configuration and operation process are slightly different. The common role is to efficiently manage the distribution of incoming calls to the office by combining the computer and the telephone. In addition, detailed information about customers who speak on the agent (telemarker) screen is provided in real time, so that the average call time with the customer can be shortened by several tens of seconds. As a result, the service level for the customer is increased and the call center operation is operated more efficiently . In addition, by combining digital voice processing technology, voice fax resource sharing technology between different nodes, fax image processing technology, digital switching technology, various services can be provided to both client and agent quickly, accurately and conveniently.

STT (Speech To Text) 330 may be a module for converting speech to text upon receipt of an instruction to control the RTM 310 to convert speech to text in real time. At this time, unlike voice conversion to text in an existing call center, the voice signal is optimized in the RTM 310 so as to be converted into text, so that the recognition rate can be increased.

The chatbot 340 may transmit to the RTM 310, as text, an answer to the consultation content corresponding to the converted text from the STT 330. At this time, the chatbot 340 analyzes the user's query through the artificial intelligence back-end and provides services to the application or the web (front-end). In order to process the message traffic, A computing environment may be used. In the chatbot 340, natural language processing, context recognition, and a big data analysis technique may be used to provide an appropriate answer to the user's query, which is described in Table 1 below. However, the present invention is not limited thereto.

Related Technology Main Content Pattern recognition
(Pattern Recognition) Identify shapes, texts, sounds, etc. by machine Natural language processing
(Natural Language Processing) Recognizing and processing the language that humans usually use on computers.
Information retrieval, question and answer, automatic system translation, interpretation, etc. Semantic Web
(Symantic Web) The next generation intelligent web that enables computers to understand the meaning of information resources and even logical reasoning Text mining
(Text Mining) A process or technique for finding new and useful information from unstructured textual data Context aware computing
(Context Aware Computing) Technology to provide user-centered intelligent service by informing the situation of reality in virtual space and utilizing it Deep Learning Machine learning technology based on Artificial Neural Network (ANN)

The interactive voice response (IVR) 320 receives an answer text received via the RTM 310 from the chatbot 340, receives an answer text from the RTM 310, and receives an instruction to control conversion to speech , And a module including TTS (Text To Speech) that converts the reply text to speech in real time.

At this time, the IVR 320 automatically responds to the call from the outside and starts the service. When the call is received from the outside, the IVR 320 requests the customer number or the resident registration number and the password. If the customer number and the password are checked, the IVR 320 searches the HOST for the corresponding data and transmits the customer data to the agent terminal ID specified by the ACD (Auto Call Distribute) function. If the ACD function does not have the designated agent terminal ID, it requests the VMS function to record the message. At this time, if an agent terminal is specified even during recording of a message, it is immediately connected. When a call is received, the consultant terminal 400 starts a consultation by clicking a call receiving button.

The TA (Text Analytics) 350 may be a text analysis engine that comprehensively analyzes the consultation contents using the answer text received from the chatbot 340 and the data in which the consultation contents are converted into text. That is, the TA 350 is a method of analyzing keywords in documented telephone consultation contents, mobile chat (chat) consultation and e-mail consultation. For example, in a consultation analysis, it can be a way to prevent complaints from customers by finding keywords that can cause complaints. Here, the TA 350 can extract meaningful information from a large-scale document, which differs from data mining in that the subject of analysis is unstructured document information. That is, the TA 350 combines information retrieval, data mining, machine learning, statistics, and computational linguistics. Text mining is an unstructured data type that is difficult to deal with, A natural language processing (NLP) method in which a human language is recognized and processed by a computer can be used.

In detail, document classification, document clustering, metedata extraction, information extraction, and the like are classified. The document classification is classified into a document classification And the like. Document clustering is a method of grouping documents with similar characteristics into the same cluster. This is similar to discriminant analysis and clustering, which is a method of statistics, and differs in that the subject of analysis is text rather than numbers. Normally, document classification is a method of classifying according to a subject in a state in which classification information is known in advance, and a document clustering method is performed without knowing classification information. This is called supervised learning and unsupervised learning. Data mining is also used in the same sense. Information extraction, on the other hand, is a methodology that automatically extracts information that has important meaning in a document.

The management module 360 includes an agent application (APP) that stores the consultation contents analyzed by the TA 350, the consultation contents generated by the chatbot 340, and an agent application that manages to share learned knowledge stored in a plurality of agent terminals KMS (Knowledge Mangement System), VOC (Voice of Customer) monitoring and managing in real time until the consultation or complaint received is resolved when customer's consultation or complaint is received, CRM (Customer Relationship Mangement) . ≪ / RTI >

In this case, the APP may be an intra-company consultation history storage system for the agent to process the call task, and the KMS can be used by other persons among the various personal experiences of the organization members in the enterprise, It is a system that enables users to convert and share them in a form that they can use. Even if an inexperienced person who does not have a new experience or an inexperienced person is consulted, it helps them to do their own work by sharing knowledge of an expert or career person. At this time, it is possible to accumulate and utilize intellectual assets, which are unstructured data possessed by human resources, in the enterprise.

The VOC is a customer management system that improves the customer experience by managing the process status in real time from receipt of the customer complaint received at the management system call center to the completion of the process, . At this time, VOC is a process of planning, supporting and evaluating marketing activities in accordance with customer's characteristics based on maximizing customer-centered resources by analyzing and integrating internal and external data related to customers and dividing customer data into new Customers can be actively managed and guided through such cycles as customer acquisition, customer retention, customer value enhancement, potential customer activation, and lifetime customerization. In order for CRM to be implemented, a customer integrated database (DB) must be built, and customer characteristics (purchase patterns, preferences, etc.) can be analyzed with the DB constructed, and the behavior of individual customers can be predicted and associated with various marketing channels.

Referring to FIG. 3, the unattended counseling and the counselor's counseling may be implemented in a mixed form. When consulting with the counselor is performed, a recording service for recording conversation contents may be added. In other words, there are many cases where a dispute arises as a result of the contents of the call with the customer. This function can be used to manage this as evidence data, and the agent can grasp contents such as the service attitude of the customer, have.

Referring to FIG. 4, the RTM 310 may include a main engine (RTM Engine), a gateway (RTM G / W), a database, and the like.

At this time, when the outgoing call is received from the customer terminal 100 via the PBX (Private Branch Exchange) 370, the main engine analyzes the call signal, collects RTP (Real Time Protocol) And the agent terminal can be separated and transmitted in the form of encoded data that can be recognized by the STT. At this time, the PBX adopts the accumulation program control method and the time division digital communication method, and is a device that can handle the voice waveform in the same manner as the data information by digital processing.

The gateway (RTM G / W Third Party Interface) receives the text of the client terminal 100 and the agent terminal for each channel, outputs the text received in real time to the web browser, searches the keyword for the KMS, Transmits important index information to the terminal, stores important index information in the DB, and processes the received text data. That is, the text data of the conversation contents such as recorded voice data is stored. The RTM gateway is a gateway for interworking between other systems as shown in FIG.

The database is not limited to a specific database and can store and update data input and output to the main engine and the gateway.

The web browsing module outputs the text received from the gateway and controls the output of the search result of the keyword for KMS.

At this time, the STT 330 receives the RTP-encoded encoded data from the main engine, analyzes and recognizes the encoded data, and transmits the encoded data to the gateway. The STT 330 also receives and processes the voice data and delivers the text to the main engine.

The KMS receives the keyword, takes an event action, and automatically outputs a popup. The chatbot 350 receives the phrase from the RTM 310 and sends a response. The IVR 320 receives the response from the RTM 310 310, converts it into voice, and transmits the answer. It should be apparent, however, that there may be various embodiments without being limited to the above-described embodiments.

On the other hand, the artificial intelligence call center server 300 operates in cooperation with the agent terminal 400, the processing of the consultation contents is distributed to the agent terminal 400, and the voice inputted from the customer terminal 100 is stored in the KMS If there is a word matching the keyword, the search result for the word can be transmitted to the agent terminal 400 and controlled to be output in real time.

The artificial intelligence call center server 300 repeats the input voice of the customer terminal 100 and repeats the search result of the word when there is a word matching the keyword stored in the KMS among the voice of the agent who has recurred. To the terminal 400 and to be controlled so as to be output in real time. For example, when a customer makes a query, the agent can improve the accuracy of the KMS's search results by (repetitively) making the KMS correctly recognize the material.

The STT 330 can be customized by performing learning using the voice of the agent to increase the word recognition rate based on the voice of the agent.

The artificial intelligence call center server 300 operates in cooperation with the administrator terminal 500. The conversation voice of the agent who is in consultation with the customer is converted into text through the STT 330 and output . At this time, if a predetermined prohibited word is recognized from the customer terminal 100, the conversation voice may be output so as to be distinguished from the other text in the converted text. This allows the administrator to be able to recognize that the agent is in a situation of verbal abuse and take action.

The artificial intelligent call center server 300 according to an embodiment of the present invention or another server (not shown) operating in cooperation with the artificial intelligent call center server 300 may transmit an artificial intelligent call center service application, Page, web page, etc., the customer terminal 100 may install or open an artificial intelligence call center service application, a program, an app page, a web page, and the like. Also, a service program may be executed in the customer terminal 100 by using a script executed in a web browser. Here, a web browser is a program that enables a WWW (World Wide Web) service, and is a program for receiving and displaying hypertext described in hypertext mark-up language (HTML), for example, Netscape (Netscape) An Explorer, chrome, and the like. Further, the application refers to an application on the terminal, for example, an app (app) running on a mobile terminal (smart phone).

At this time, the connection of the network 200 is performed by the client terminal 100, the artificial intelligence call center server 300, at least one agent terminal 400, and the terminal connected to the network 200 by the administrator terminal 500 To create a communication object at the communication contact. The artificial intelligence call center server 300 can exchange data with each other through a communication object.

Hereinafter, an artificial intelligent call center service having the above-described configuration will be described with reference to FIG.

5, it is assumed that (a) customer terminal 100 calls 114 to ask for an airport telephone number. In this case, since it is a simple search, it can be driven as an unattended consulting service. At this time, the artificial intelligence call center server 300 can guide the airport telephone number and can also send the airport telephone number by letter. Herein, if the airport is not accurately referred to, the artificial intelligence call center server 300 may determine the location of the customer terminal 100 and inform the telephone number of the accessible airport. Further, since the airport accommodates a plurality of agencies, an additional inquiry may be made from the artificial intelligence call center server 300 to the customer terminal 100 for accurate retrieval. If the correct answer is not obtained, the telephone number of the airport at which communication is possible may be transmitted to the customer terminal 100 by letter or the like.

(b) The customer terminal 100 attempts to call the Dasan call center to report illegal parking. At this time, if the agent does not know the illegal parking report method, if the keyword illegal parking report is converted from voice to text and recognized as a keyword, the illegal parking notification method can be directly retrieved and transmitted to the agent terminal 400. In addition, the illegal parking report procedure can help guide you.

(c) In the case where the customer terminal 100 is exposed to swearing, the voice call is switched from text to text, and the artificial intelligence call center server 300 transmits a code of conduct to the agent terminal 400, ), You can send an alarm that you can hang up after several warnings.

(d) The manager may want to know how the counselor is comfortable in his / her position rather than listening to the counselor. Accordingly, the artificial intelligence call center server 300 can monitor the conversation between the agent and the client transmitted from the agent terminal 400 in real time in a conversation format (text). If a problem occurs, the artificial intelligence call center server 300, To the administrator terminal 500 to promptly recognize and handle the problem.

(e) On the other hand, when the customer terminal 100 calling at 114 can not perform an accurate search in the automatic answering system, and a voice for sighing or frustration is heard, the agent terminal 400 is immediately connected to the agent terminal 400, The terminal 400 may listen to the search word that the customer repeatedly tries to search for while talking, and respond to the query so that the customer does not repeatedly talk again.

(f) Also, in order to share experiences and know-how that have been worked among agents, when a situation occurs (when a specific word or keyword is recognized), the processing method and know-how can be outputted in real time through KMS.

The artificial intelligent call center method of FIGS. 2 to 5 will be described with reference to FIG. 1, which is the same as the artificial intelligent call center method. do.

The artificial intelligent call center service method according to an embodiment through the above description can also be implemented in the form of a recording medium including an application executed by a computer or a command executable by a computer such as a program module. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer readable medium may include both computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The artificial intelligent call center service method according to an embodiment of the present invention can be executed by an application installed in a terminal (which may include a program included in a platform or an operating system basically installed in the terminal) (I.e., a program) directly installed on a master terminal by a user via an application providing server such as an application store server, an application, or a web server associated with the service. In this regard, the artificial intelligent call center method according to an embodiment of the present invention described above is implemented as an application (i.e., a program) installed basically in a terminal or directly installed by a user and stored in a computer- Lt; / RTI >

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

Claims (7)

When an outgoing call is received from the customer terminal and the consultation contents are received from the customer terminal or when the agent sends a call to the customer and a call is received from the customer to the terminal, A controller for controlling the conversion of the voice as the received consultation content into text in real time, receiving the response text generated from the consultation content and converting the received response text into voice, and transmitting the generated voice response to the client terminal in real time RTM (Real-Time Text Middleware), a text conversion module;
A Speech To Text (STT) module for converting speech into text upon receiving an instruction for controlling the speech to be converted into text in real time from the RTM;
A chatbox (ChatBot) for transmitting the answer to the consultation contents corresponding to the text converted from the STT to the RTM as text;
A text to speech (TTS) unit for receiving the reply text received via the RTM from the chatbot, receiving an answer text from the RTM and converting the answer text into speech, An Interactive Voice Response (IVR) module;
TA (Text Analytics), which is a text analysis engine for synthetically analyzing consultation contents using response text received from the chatbot and data in which the consultation contents are converted into text;
An APP (Agent Application) for storing consultation contents analyzed by the TA, a consultation content created by the chatbot, a KMS (Knowledge Mangement System) for managing the learned and stored knowledge from a plurality of agent terminals, A VOC (Voice of Customer) that monitors and manages in real time until the received consultation or complaint is resolved, and a CRM (Customer Relationship Mangement) for managing the customer when the complaint is received,
Operates in cooperation with an agent terminal,
If the keyword corresponding to the keyword stored in the KMS is present among the voices input from the client terminal, the search result for the word is transmitted to the agent terminal, Respectively,
When a word matching the keyword stored in the KMS is present among the voice of the recurrent agent who repeats the input voice of the customer terminal, the search result for the word is transmitted to the agent terminal and controlled to be output in real time ,
The STT is customized by performing learning using the voice of the agent to increase the word recognition rate based on the voice of the agent,
In the RTM,
When an outgoing call is received from the customer terminal via a private branch exchange (PBX), the mobile terminal analyzes the call signal, collects RTP (Real Time Protocol), separates and encodes the selected customer terminal and the agent terminal, (RTM Engine);
The texts of the client terminal and the agent terminal are received for each channel, the text received in real time is outputted to the web browser, the keyword for the KMS as the real keyword is searched for and transmitted to the agent terminal, and the searched keyword is stored in the index DB A gateway (RTM G / W Thirdparty Interface) linked with a text file;
A database configured to store data input and output to and from the main engine and the gateway; And
And a web browsing module for outputting a text received from the gateway and outputting a keyword search result for the KMS keyword,
Wherein the STT receives RTP from the main engine, and analyzes the RTP, and transmits the analyzed RTP to the gateway when the RTP is collected in the main engine. delete delete delete delete delete delete

Images