KR102492334B1 - Method and apparatus for managing a call connection between a customer terminal and an agent terminal based on usage information related to a chatbot service using a neural network - Google Patents

Abstract

Disclosed in embodiments are a method and an apparatus in which a server manages call connections between a customer terminal and an agent terminal based on usage information related to a chatbot service using a neural network through a call server. According to one embodiment, the method comprises the steps of: receiving a first connection request message requesting a connection to an agent for a call from a chatbot server which provides a chatbot service to a first customer terminal, wherein the chatbot service is provided based on an authentication procedure between the first customer terminal and the chatbot server, and the connection request message includes usage information related to the chatbot service for the first customer terminal; based on the usage information related to the chatbot service for the first customer terminal and information related to a call connection status of a plurality of agent terminals, determining a priority for the first customer terminal and the plurality of agent terminals through a decision model using a plurality of neural networks; based on the determined priority for the first customer terminal and the plurality of agent terminals, selecting a first agent terminal among the plurality of agent terminals; transmitting the usage information related to the chatbot service for the first customer terminal to the first agent terminal; and establishing a call connection between the first customer terminal and the first agent terminal. Based on the fact that the last time of the first customer terminal using the chatbot service is within a range from the establishment point of the call connection to a pre-set time, transmission of interactive voice response matching the call connection may be omitted for the first customer terminal. The method and the apparatus can enhance the convenience of the customer terminal using the chatbot service.

Description

A method and apparatus for managing a call connection between a customer terminal and an agent terminal based on usage information related to a chatbot service using a neural network RELATED TO A CHATBOT SERVICE USING A NEURAL NETWORK}

Embodiments of the present disclosure relate to a technology for managing a call connection between a customer terminal and an agent terminal, and a technique for managing a call connection between a customer terminal and an agent terminal based on usage information related to a chatbot service using a neural network It is about.

On the other hand, before smartphones became popular, most people reserved medical treatment through ARS (automatic response system) service, but in recent years, ARS service and / or chatbot service, etc. can be reserved. Here, the visible ARS service is a service in which, in addition to the existing ARS service, a page connected to the ARS voice guidance is displayed on the screen of a smartphone and synchronized with the corresponding page and the voice guidance, so that information can be received more conveniently. A chatbot service is a service provided through a computer program that processes a conversation with a human through voice or text.

At this time, if the user needs to connect to a counselor while using the chatbot service, if the user needs to connect with the counselor through the phone number to connect to the counselor, after hearing the automatic voice comment, the user must wait for the connection with the counselor. There is discomfort.

In addition, when a user uses a chatbot service based on personal information, he or she must go through the authentication process. Therefore, there is a problem in that a user can use a chatbot service after completing a complicated authentication procedure of a telecommunications company using a user terminal for self-authentication.

Therefore, when a user requests a connection to a counselor while using a chatbot service, a method of determining and managing the priority of a user terminal and an agent terminal using a neural network in order to proceed with a connection to a counselor prior to a user who has generally requested a connection to a counselor. need this In addition, when a user uses a chatbot service based on personal information, a more convenient authentication procedure is required.

KR 10-2010-00122370 A KR 10-2008-0054487 A KR 10-2022-0155065 A

Embodiments of the present disclosure may provide a method and apparatus for managing a call connection between a customer terminal and a counselor terminal based on use information related to a chatbot service using a neural network.

Technical tasks to be achieved in the embodiments are not limited to those mentioned above, and other technical tasks not mentioned will be considered by those skilled in the art from various embodiments to be described below. can

A method in which a call server manages a call connection between a customer terminal and an agent terminal based on usage information related to a chatbot service by using a neural network according to an embodiment includes providing a chatbot service to a first customer terminal. Receives a first connection request message requesting an agent call connection from a chatbot server, the chatbot service is provided based on an authentication procedure between the first customer terminal and the chatbot server, and the connection request message is sent to the first customer Using a plurality of neural networks, including usage information related to the chatbot service for a terminal, and using information related to the chatbot service for the first customer terminal and call connection status for a plurality of counselor terminals Priorities of the first customer terminal and the plurality of counselor terminals are determined through a decision model, and a first counselor is selected from among the plurality of counselor terminals based on the priorities of the first customer terminal and the plurality of counselor terminals. Selecting a terminal, transmitting usage information related to the chatbot service for the first customer terminal to the first counselor terminal, and establishing a call connection between the first customer terminal and the first counselor terminal. can do. Based on the fact that the last time the first customer terminal uses the chatbot service is within a preset time from the time the call connection is established, transmission of a preset interactive voice response matching the call connection is performed by the first customer terminal may be omitted for

According to an embodiment, the method receives a second connection request message requesting an agent call connection from a second customer terminal before the first customer terminal receives the chatbot service from the chatbot server, and the plurality of The method may further include matching the second customer terminal with the first counselor terminal among counselor terminals of the above. For example, the first customer terminal may have priority over the second customer terminal to establish a call connection with the first counselor terminal. The preset time may be determined by the following equation.

In the above equation, the W _time is the preset time, k is the number of customer terminals waiting for a call, t _i is the call waiting time of the ith customer terminal, and t _avg is the average call waiting time , wherein n _t is the number of customer terminals currently using the chatbot service, n _avg is the average number of customer terminals using the chatbot service, t _n is the number of call attempts made by the first customer terminal on the day, and the w _def may be a default value for the preset time.

According to an embodiment, an authentication procedure between the customer terminal and the chatbot server may include first authentication and second authentication. The first authentication may be performed based on matching of first personal information transmitted from the customer terminal to the chatbot server and second personal information transmitted from the call server to the chatbot server. The first personal information may be information input by a user of the customer terminal. The second personal information may be information transmitted from a server associated with a communication company to the call server through automatic caller identification. The second authentication may be performed based on matching of the first personal information and third personal information transmitted from a server related to the electronic medical record, based on completion of the first authentication. Based on completion of the first authentication and the second authentication, the chatbot service may be provided from the chatbot server to the customer terminal.

For example, a first priority for the first customer terminal may be determined through a first decision model using a first neural network based on usage information related to the chatbot service for the first customer terminal. Based on information related to call connection states of the plurality of counselor terminals, second priorities for the plurality of counselor terminals may be determined through a second decision model using a second neural network. The first counselor terminal may be selected from among the plurality of counselor terminals based on the first priority for the first customer terminal and the second priority for the plurality of counselor terminals. The first neural network may include a first input layer, one or more first hidden layers, and a first output layer. Data for learning of each neural network composed of usage information related to a plurality of chatbot services and a first priority for a correct answer customer terminal is input to the first input layer of the first neural network, and the one or more first A first output vector is output after passing through a hidden layer and a first output layer, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is input to the first loss function layer. A first loss value is output using a first loss function that compares an output vector with a first correct answer vector for each learning data, and the parameters of the first neural network are learned in a direction in which the first loss value decreases. , the first decision model may be generated. The second neural network may include a second input layer, one or more second hidden layers, and a second output layer. Information related to the call connection state of a plurality of counselor terminals and data for learning each neural network composed of second priorities for correct answer counselor terminals are input to the second input layer of the second neural network, A second output vector is output by passing through at least one second hidden layer and a second output layer, the first output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer outputs a second loss value using a second loss function that compares the second output vector with a second correct answer vector for each training data, and outputs a second loss value when the parameter of the second neural network is smaller than the second loss value The second decision model, which is learned in a losing direction, may be generated.

Additionally, a value for the first priority for the customer terminal, which is one of the data for learning of the first neural network, may be determined by the following equation.

In the above equation, P ₁ is the value for the first priority, u _a is the age of the user of the customer terminal, and n _e is the number of preset words included in the conversation between the customer terminal and the chatbot. , wherein n _t is the number of call attempts of the customer terminal on the day, c is a value related to whether the customer terminal uses a chatbot service, and h is a value related to a medical treatment subject of the customer terminal.

Additionally, for example, a value for the second priority for the counselor terminal, which is one of the data for learning the second neural network, may be determined by the following equation.

In the above equation, P ₂ is the value for the second priority, t _c is the time during which the counselor terminal communicated with the currently connected customer terminal, f _k is the kindness level of the counselor terminal, and k _m is the number of customer terminals waiting for calls to the counselor terminal, n _s is the number of times counseling has been performed by the counselor terminal so far, t _o is the continuous working time of the counselor terminal, and d may be a default value. The t _c and the t _o are units of time, for example, may be units of minutes. The d may be a value previously stored in the call server.

According to embodiments, based on the fact that the last time the call server used the chatbot service by the customer terminal was within a preset time from the time when the call connection with the counselor terminal was established, the preset interactive voice response matching the call connection By omitting the transmission for the customer terminal, the convenience of the customer terminal using the chatbot service can be increased and users can be induced to use the chatbot service.

According to embodiments, a call server receives usage information related to a chatbot service from a chatbot server, and creates a plurality of neural networks based on the usage information related to the chatbot service and information related to call connection states of a plurality of agent terminals. Priority is determined for the customer terminal and the plurality of counselor terminals through the used decision model, and by connecting the customer terminal and the counselor terminal, the counseling service can be efficiently provided to the user in conjunction with the chatbot service. In addition, the quality of counseling service may be improved by adjusting the number of customer terminals in a call waiting state according to priority.

Effects obtainable from the embodiments are not limited to the effects mentioned above, and other effects not mentioned are clearly derived and understood by those skilled in the art based on the detailed description below. It can be.

BRIEF DESCRIPTION OF THE DRAWINGS Included as part of the detailed description to aid understanding of the embodiments, the accompanying drawings provide various embodiments and, together with the detailed description, describe technical features of the various embodiments.
1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.
2 is a diagram showing the configuration of a program according to an embodiment.
3 illustrates a system for managing a call connection between a customer terminal and a counselor terminal based on usage information related to a chatbot service using a neural network according to an embodiment.
4 is a signal exchange diagram of a method for managing a call connection between a customer terminal and an agent terminal based on use information related to a chatbot service by a call server using a neural network according to an embodiment.
5 is a diagram illustrating a method for a call server to manage a call connection between a customer terminal and an agent terminal based on use information related to a chatbot service by using a neural network according to an embodiment.
6 is a block diagram illustrating a configuration of a server according to an exemplary embodiment.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood by those skilled in the art are not described. did

Throughout the specification, when a part is said to "comprising" or "including" a certain element, it means that it may further include other elements, not excluding other elements, unless otherwise stated. do. In addition, terms such as “… unit”, “… unit”, and “module” described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, “a or an”, “one”, “the” and like terms are used herein in the context of describing various embodiments (particularly in the context of the claims below). Unless otherwise indicated or clearly contradicted by context, both the singular and the plural can be used.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent a single embodiment.

In addition, specific terms used in various embodiments are provided to help understanding of various embodiments, and the use of these specific terms may be changed into other forms without departing from the technical spirit of various embodiments. .

1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.

1 is a block diagram of an electronic device 101 within a network environment 100, according to various embodiments. Referring to FIG. 1 , in a network environment 100, an electronic device 101 communicates with an electronic device 102 through a first network 198 (eg, a short-range wireless communication network) or through a second network 199. It may communicate with at least one of the electronic device 104 or the server 108 through (eg, a long-distance wireless communication network). According to one embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108 . According to an embodiment, the electronic device 101 includes a processor 120, a memory 130, an input module 150, an audio output module 155, a display module 160, an audio module 170, a sensor module ( 176), interface 177, connection terminal 178, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196 , or the antenna module 197 may be included. In some embodiments, in the electronic device 101, at least one of these components (eg, the connection terminal 178) may be omitted or one or more other components may be added. In some embodiments, some of these components (eg, sensor module 176, camera module 180, or antenna module 197) are integrated into a single component (eg, display module 160). It can be. The electronic device 101 may also be referred to as a client, terminal, or peer.

The processor 120, for example, executes software (eg, the program 140) to cause at least one other component (eg, hardware or software component) of the electronic device 101 connected to the processor 120. It can control and perform various data processing or calculations. According to one embodiment, as at least part of data processing or operation, the processor 120 transfers instructions or data received from other components (e.g., sensor module 176 or communication module 190) to volatile memory 132. , processing commands or data stored in the volatile memory 132 , and storing resultant data in the non-volatile memory 134 . According to one embodiment, the processor 120 may include a main processor 121 (eg, a central processing unit or an application processor) or a secondary processor 123 (eg, a graphic processing unit, a neural network processing unit ( NPU: neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, when the electronic device 101 includes the main processor 121 and the auxiliary processor 123, the auxiliary processor 123 may use less power than the main processor 121 or be set to be specialized for a designated function. can The secondary processor 123 may be implemented separately from or as part of the main processor 121 .

The secondary processor 123 may, for example, take the place of the main processor 121 while the main processor 121 is in an inactive (eg, sleep) state, or the main processor 121 is active (eg, running an application). ) state, together with the main processor 121, at least one of the components of the electronic device 101 (eg, the display module 160, the sensor module 176, or the communication module 190) It is possible to control at least some of the related functions or states. According to one embodiment, the auxiliary processor 123 (eg, image signal processor or communication processor) may be implemented as part of other functionally related components (eg, camera module 180 or communication module 190). there is. According to an embodiment, the auxiliary processor 123 (eg, a neural network processing device) may include a hardware structure specialized for processing an artificial intelligence model.

AI models can be created through machine learning. Such learning may be performed, for example, in the electronic device 101 itself where the artificial intelligence model is performed, or may be performed through a separate server (eg, the server 108). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning or reinforcement learning, but in the above example Not limited. The artificial intelligence model may include a plurality of artificial neural network layers. Artificial neural networks include deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), It may be one of deep Q-networks or a combination of two or more of the foregoing, but is not limited to the foregoing examples. The artificial intelligence model may include, in addition or alternatively, software structures in addition to hardware structures.

The memory 130 may store various data used by at least one component (eg, the processor 120 or the sensor module 176) of the electronic device 101 . The data may include, for example, input data or output data for software (eg, program 140) and commands related thereto. The memory 130 may include volatile memory 132 or non-volatile memory 134 .

The program 140 may be stored as software in the memory 130 and may include, for example, an operating system 142 , middleware 144 , or an application 146 .

The input module 150 may receive a command or data to be used by a component (eg, the processor 120) of the electronic device 101 from the outside of the electronic device 101 (eg, a user). The input module 150 may include, for example, a microphone, a mouse, a keyboard, a key (eg, a button), or a digital pen (eg, a stylus pen).

The sound output module 155 may output sound signals to the outside of the electronic device 101 . The sound output module 155 may include, for example, a speaker or a receiver. The speaker can be used for general purposes such as multimedia playback or recording playback. A receiver may be used to receive an incoming call. According to one embodiment, the receiver may be implemented separately from the speaker or as part of it.

The display module 160 may visually provide information to the outside of the electronic device 101 (eg, a user). The display module 160 may include, for example, a display, a hologram device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module 160 may include a touch sensor set to detect a touch or a pressure sensor set to measure the intensity of force generated by the touch.

The audio module 170 may convert sound into an electrical signal or vice versa. According to one embodiment, the audio module 170 acquires sound through the input module 150, the sound output module 155, or an external electronic device connected directly or wirelessly to the electronic device 101 (eg: Sound may be output through the electronic device 102 (eg, a speaker or a headphone).

The sensor module 176 detects an operating state (eg, power or temperature) of the electronic device 101 or an external environmental state (eg, a user state), and generates an electrical signal or data value corresponding to the detected state. can do. According to one embodiment, the sensor module 176 may include, for example, a gesture sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a bio sensor, It may include a temperature sensor, humidity sensor, or light sensor.

The interface 177 may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device 101 to an external electronic device (eg, the electronic device 102). According to one embodiment, the interface 177 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

The connection terminal 178 may include a connector through which the electronic device 101 may be physically connected to an external electronic device (eg, the electronic device 102). According to one embodiment, the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

The haptic module 179 may convert electrical signals into mechanical stimuli (eg, vibration or motion) or electrical stimuli that a user may perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 180 may capture still images and moving images. According to one embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

The power management module 188 may manage power supplied to the electronic device 101 . According to one embodiment, the power management module 188 may be implemented as at least part of a power management integrated circuit (PMIC), for example.

The battery 189 may supply power to at least one component of the electronic device 101 . According to one embodiment, the battery 189 may include, for example, a non-rechargeable primary cell, a rechargeable secondary cell, or a fuel cell.

The communication module 190 is a direct (eg, wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (eg, the electronic device 102, the electronic device 104, or the server 108). Establishment and communication through the established communication channel may be supported. The communication module 190 may include one or more communication processors that operate independently of the processor 120 (eg, an application processor) and support direct (eg, wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (eg, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (eg, : a local area network (LAN) communication module or a power line communication module). Among these communication modules, a corresponding communication module is a first network 198 (eg, a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (eg, legacy It may communicate with the external electronic device 104 through a cellular network, a 5G network, a next-generation communication network, the Internet, or a telecommunications network such as a computer network (eg, a LAN or a WAN). These various types of communication modules may be integrated as one component (eg, a single chip) or implemented as a plurality of separate components (eg, multiple chips). The wireless communication module 192 uses subscriber information (eg, International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199. The electronic device 101 may be identified or authenticated.

The wireless communication module 192 may support a 5G network after a 4G network and a next-generation communication technology, for example, NR access technology (new radio access technology). NR access technologies include high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and access of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low latency (URLLC)). -latency communications)) can be supported. The wireless communication module 192 may support a high frequency band (eg, mmWave band) to achieve a high data rate, for example. The wireless communication module 192 uses various technologies for securing performance in a high frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), and full-dimensional multiplexing. Technologies such as input/output (FD-MIMO: full dimensional MIMO), array antenna, analog beam-forming, or large scale antenna may be supported. The wireless communication module 192 may support various requirements defined for the electronic device 101, an external electronic device (eg, the electronic device 104), or a network system (eg, the second network 199). According to one embodiment, the wireless communication module 192 is a peak data rate for eMBB realization (eg, 20 Gbps or more), a loss coverage for mMTC realization (eg, 164 dB or less), or a U-plane latency for URLLC realization (eg, Example: downlink (DL) and uplink (UL) each of 0.5 ms or less, or round trip 1 ms or less) may be supported.

The antenna module 197 may transmit or receive signals or power to the outside (eg, an external electronic device). According to one embodiment, the antenna module 197 may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (eg, PCB). According to one embodiment, the antenna module 197 may include a plurality of antennas (eg, an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network such as the first network 198 or the second network 199 is selected from the plurality of antennas by the communication module 190, for example. can be chosen A signal or power may be transmitted or received between the communication module 190 and an external electronic device through the selected at least one antenna. According to some embodiments, other components (eg, a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module 197 in addition to the radiator.

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, the mmWave antenna module includes a printed circuit board, an RFIC disposed on or adjacent to a first surface (eg, a lower surface) of the printed circuit board and capable of supporting a designated high frequency band (eg, mmWave band); and a plurality of antennas (eg, array antennas) disposed on or adjacent to a second surface (eg, a top surface or a side surface) of the printed circuit board and capable of transmitting or receiving signals of the designated high frequency band. can do.

At least some of the components are connected to each other through a communication method between peripheral devices (eg, a bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and signal ( e.g. commands or data) can be exchanged with each other.

According to an embodiment, commands or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199 . Each of the external electronic devices 102 or 104 may be the same as or different from the electronic device 101 . According to an embodiment, all or part of operations executed in the electronic device 101 may be executed in one or more external electronic devices among the external electronic devices 102 , 104 , or 108 . For example, when the electronic device 101 needs to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device 101 instead of executing the function or service by itself. Alternatively or additionally, one or more external electronic devices may be requested to perform the function or at least part of the service. One or more external electronic devices receiving the request may execute at least a part of the requested function or service or an additional function or service related to the request, and deliver the execution result to the electronic device 101 . The electronic device 101 may provide the result as at least part of a response to the request as it is or additionally processed. To this end, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device 101 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an internet of things (IoT) device. Server 108 may be an intelligent server using machine learning and/or neural networks. According to one embodiment, the external electronic device 104 or server 108 may be included in the second network 199 . The electronic device 101 may be applied to intelligent services (eg, smart home, smart city, smart car, or health care) based on 5G communication technology and IoT-related technology.

The server 108 is connected to the electronic device 101 and can provide a service to the connected electronic device 101 . In addition, the server 108 may proceed with a membership sign-up procedure, store and manage various types of information of users subscribed as members, and provide various purchase and payment functions related to services. In addition, the server 108 may share execution data of service applications executed in each of the plurality of electronic devices 101 in real time so that the service can be shared among users. This server 108 may have the same configuration as a conventional web server or service server in terms of hardware. However, in terms of software, it may include a program module that is implemented through any language such as C, C++, Java, Python, Golang, or kotlin and performs various functions. In addition, the server 108 is generally connected to an unspecified number of clients and/or other servers through an open computer network such as the Internet, and receives requests from clients or other servers to perform tasks and derives and provides work results. It means a computer system and the computer software (server program) installed for it. In addition, the server 108, in addition to the above-described server program, a series of application programs operating on the server 108 and various databases (DB: Database, hereinafter referred to as It should be understood as a broad concept including DB"). Accordingly, the server 108 classifies member registration information and various information and data about games, stores them in a DB, and manages them. This DB may be implemented inside or outside the server 108 . In addition, the server 108 may be implemented using server programs that are provided in various ways according to operating systems such as Windows, Linux, UNIX, and Macintosh on general server hardware, As a representative example, a web service can be implemented using IIS (Internet Information Server) used in a Windows environment and CERN, NCSA, APPACH, TOMCAT, etc. used in a Unix environment. In addition, the server 108 may interoperate with an authentication system and a payment system for user authentication of services or payment for purchases related to services.

The first network 198 and the second network 199 are a connection structure capable of exchanging information between nodes such as terminals and servers, or a network connecting the server 108 and the electronic devices 101 and 104. means (Network). The first network 198 and the second network 199 include Internet, Local Area Network (LAN), Wireless Local Area Network (Wireless Local Area Network), Wide Area Network (WAN), Personal Area Network (PAN), and 3G , 4G, LTE, 5G, Wi-Fi, etc., but are not limited thereto. The first network 198 and the second network 199 may be closed first networks 198 and second networks 199 such as LAN and WAN, but are preferably open such as the Internet. The Internet includes protocols such as the TCP/IP protocol, TCP, and User Datagram Protocol (UDP), and various services that exist in the upper layer, such as HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), and DNS (Domain Name System). ), Simple Mail Transfer Protocol (SMTP), Simple Network Management Protocol (SNMP), Network File Service (NFS), and Network Information Service (NIS). ) structure.

A database may have a general data structure implemented in a storage space (hard disk or memory) of a computer system using a database management program (DBMS). The database may have a data storage form in which data can be freely searched for (extracted), deleted, edited, added, and the like. Databases are relational database management systems (RDBMS) such as Oracle, Informix, Sybase, and DB2, or object-oriented database management such as Gemston, Orion, and O2. It can be implemented according to the purpose of an embodiment of the present disclosure using a system (OODBMS) and XML Native Databases such as Excelon, Tamino, and Sekaiju, and its functions may have appropriate fields or elements to achieve.

2 is a diagram showing the configuration of a program according to an embodiment.

2 is a block diagram 200 illustrating a program 140 according to various embodiments. According to one embodiment, the program 140 includes an operating system 142, middleware 144, or an application 146 executable in the operating system 142 for controlling one or more resources of the electronic device 101. can include The operating system 142 may include, for example, Android™, iOS™, Windows™, Symbian™ or Tizen™. At least some of the programs 140 are, for example, preloaded in the electronic device 101 at the time of manufacture, or when used by a user, an external electronic device (eg, the electronic device 102 or 104), or a server ( 108)) can be downloaded or updated. All or part of program 140 may include a neural network.

The operating system 142 may control management (eg, allocation or reclamation) of one or more system resources (eg, process, memory, or power) of the electronic device 101 . Operating system 142 may additionally or alternatively include other hardware devices of electronic device 101 , such as input module 150 , sound output module 155 , display module 160 , audio module 170 . , sensor module 176, interface 177, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196, or It may include one or more driver programs for driving the antenna module 197.

The middleware 144 may provide various functions to the application 146 so that the function or information provided from one or more resources of the electronic device 101 may be used by the application 146 . The middleware 144 includes, for example, the application manager 201, the window manager 203, the multimedia manager 205, the resource manager 207, the power manager 209, the database manager 211, and the package manager 213. ), connectivity manager 215, notification manager 217, location manager 219, graphics manager 221, security manager 223, call manager 225, or voice recognition manager 227. can

The application manager 201 may manage the life cycle of the application 146 , for example. The window manager 203 may manage one or more GUI resources used in a screen, for example. The multimedia manager 205 identifies, for example, one or more formats necessary for reproducing media files, and encodes or decodes a corresponding media file among the media files using a codec suitable for the selected format. can be done The resource manager 207 may manage a source code of the application 146 or a memory space of the memory 130 . The power manager 209 may manage, for example, the capacity, temperature, or power of the battery 189, and determine or provide related information necessary for the operation of the electronic device 101 by using corresponding information among them. . According to an embodiment, the power manager 209 may interoperate with a basic input/output system (BIOS) (not shown) of the electronic device 101 .

The database manager 211 may create, search, or change a database to be used by the application 146, for example. The package manager 213 may manage installation or update of applications distributed in the form of package files, for example. The connectivity manager 215 may manage, for example, a wireless connection or a direct connection between the electronic device 101 and an external electronic device. The notification manager 217 may provide a function for notifying a user of occurrence of a designated event (eg, an incoming call, message, or alarm), for example. The location manager 219 may manage location information of the electronic device 101, for example. The graphic manager 221 may manage, for example, one or more graphic effects to be provided to a user or a user interface related thereto.

Security manager 223 may provide system security or user authentication, for example. The telephony manager 225 may manage, for example, a voice call function or a video call function provided by the electronic device 101 . The voice recognition manager 227 transmits, for example, the user's voice data to the server 108, and at least partially based on the voice data, a command corresponding to a function to be performed in the electronic device 101; Alternatively, text data converted at least partially based on the voice data may be received from the server 108 . According to one embodiment, the middleware 244 may dynamically delete some existing components or add new components. According to one embodiment, at least part of the middleware 144 may be included as part of the operating system 142 or may be implemented as separate software different from the operating system 142 .

The application 146 includes, for example, a home 251, a dialer 253, an SMS/MMS 255, an instant message (IM) 257, a browser 259, a camera 261, and an alarm 263. , Contacts (265), Voice Recognition (267), Email (269), Calendar (271), Media Player (273), Albums (275), Watch (277), Health (279) (e.g. exercise or blood sugar) measurement of biometric information) or environmental information 281 (eg, measurement of atmospheric pressure, humidity, or temperature information). According to an embodiment, the application 146 may further include an information exchange application (not shown) capable of supporting information exchange between the electronic device 101 and an external electronic device. The information exchange application may include, for example, a notification relay application configured to transmit designated information (eg, a call, message, or alarm) to an external electronic device, or a device management application configured to manage an external electronic device. there is. The notification relay application, for example, transmits notification information corresponding to a designated event (eg, mail reception) generated in another application (eg, the email application 269) of the electronic device 101 to an external electronic device. can Additionally or alternatively, the notification relay application may receive notification information from an external electronic device and provide the notification information to the user of the electronic device 101 .

The device management application is, for example, a power source (eg, turn-on or turn-off) of an external electronic device that communicates with the electronic device 101 or some component thereof (eg, a display module or a camera module of the external electronic device). ) or functions (eg brightness, resolution, or focus). The device management application may additionally or alternatively support installation, deletion, or update of an application operating in an external electronic device.

Throughout this specification, a neural network, a neural network, and a network function may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may be generally referred to as “nodes”. These “nodes” may also be referred to as “neurons”. A neural network includes at least two or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more “links”.

In a neural network, two or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, the input node to output node relationship can be created around the link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in a neural network, two or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values between the links, the two neural networks may be recognized as different from each other.

3 illustrates a system for managing a call connection between a customer terminal and a counselor terminal based on usage information related to a chatbot service using a neural network according to an embodiment. One embodiment of FIG. 3 may be combined with various embodiments of the present disclosure.

Referring to FIG. 3, the management system 300 for managing the call connection between the customer terminal and the agent terminal based on usage information related to the chatbot service includes a customer terminal 310, a call server 320, and a chatbot server 330. and a counselor terminal 340 .

The customer terminal 310 may receive various services related to guidance, such as an audio response system (ARS) service and an interactive voice response (IVR) service, from the call server 320 . Here, the ARS service is a service that provides pre-recorded voice information when a customer accesses the system, and the IVR service is a service that provides customized information to a customer based on information input by the customer according to the purpose of use.

The customer terminal 310 may receive a chatbot service from the chatbot server 330 through the IVR service provided by the call server 320 . Here, the chatbot service is a service provided through a computer program that processes a conversation with a human through voice or text.

For example, while the customer terminal 310 uses the chatbot service, the chatbot server 330 may transmit usage information related to the chatbot service for the customer terminal 310 to the call server 320, and the call server 320 ) may store and manage usage information related to the chatbot service for the customer terminal 310 . Here, the usage information related to the chatbot service includes personal information about the customer terminal 310 input through the chatbot service, information about a category inquired by the customer terminal 310 through the chatbot service, and information between the customer terminal 310 and the chatbot. It may contain information about the contents of the conversation. When the customer terminal 310 requests connection with the agent, the call server 320 transmits usage information related to the chatbot service for the customer terminal 310 to the agent terminal 340 that matches the customer terminal 310, and the customer The terminal 310 and the counselor terminal 340 may be directly connected. That is, the call server 320 omits the IVR service provided when the customer terminal 310 accesses the call server 320 based on the information that the customer terminal 310 uses the chatbot service, and the customer terminal 310 and The counselor terminal 340 may be connected. At this time, when the customer terminal 310 uses the chatbot service within a preset time (eg, 10 minutes), the call server 320 prioritizes the customer terminal 310 through various priority connection routing techniques. ) can be associated with Here, the priority connection routing scheme is a routing method in which a specific terminal is preferentially connected to other terminals according to preset priorities.

Also, when the customer terminal 310 and the counselor terminal 340 are connected, the call server 320 can check the current call state of the counselor terminal 340 in real time. When the agent terminal 340 is in a difficult call state such as being on a call with another terminal, the call server 320 informs the chatbot server 330 that the agent terminal 340 is in a difficult call state, and the chatbot server ( 330) may transmit a message requesting standby through the chatbot service to the customer terminal 310. Thereafter, the call server 320 notifies the chatbot server 330 that the agent terminal 340 is in a callable state, and the call server 320 can automatically connect the customer terminal 310 and the agent terminal 340 there is. At this time, the call server 320 transmits information related to the chatbot service for the customer terminal 310 to the agent terminal 340, and the agent sends the customer terminal through a customer relationship management (CRM) program installed in the agent terminal 340. Information related to the chatbot service for (310) can be checked. Through this, it is possible to induce more customers to use the chatbot service by providing favorable conditions to customers using the chatbot service by prioritizing the connection of the customer terminal using the chatbot service rather than the customer terminal that directly applied for the agent connection.

When the chatbot server 330 provides the chatbot service to the customer terminal 310, the chatbot server 330 may provide the customer terminal 310 with a simple authentication procedure for a service using personal information of the customer.

For example, the call server 320 may receive personal information (eg, phone number) of the customer terminal 310 from an external server (eg, a telecommunications company server) when making a call connection with the customer terminal 310 . Then, when the customer terminal 310 uses the chatbot service, the call server 320 may transmit the personal information of the customer terminal 310 received from the external server to the chatbot server 330 . The chatbot server 330 simply determines whether the personal information received from the customer terminal 310 through the chatbot service (eg, name, date of birth, phone number) and the personal information received from the call server 320 match. authentication process can be performed. Alternatively, for example, the personal information received from the customer terminal 310 through the chatbot service (eg, name, date of birth, phone number) matches the personal information received from the call server 320, and the chatbot server 330 A simple authentication procedure can be performed by inputting an authentication number set in advance by the customer terminal 310 .

In addition, the chatbot server 330 determines whether the personal information received from the customer terminal 310 through the chatbot service and the personal information received from the call server 320 match, as well as within the EMR (electronic medical record) server. A simple authentication procedure can be performed by determining whether the information matches the registered patient's personal information. Here, the EMR server is a server that stores and manages medical records of patients visiting the hospital in electronic form.

Therefore, the chatbot server 330 can check whether the customer terminal 310 is the person without the paid authentication service through an external server only through the simple authentication procedure described above.

4 is a signal exchange diagram of a method for managing a call connection between a customer terminal and an agent terminal based on use information related to a chatbot service by a call server using a neural network according to an embodiment. The embodiment of FIG. 4 can be combined with various embodiments of the present disclosure.

Referring to FIG. 4 , in step S401, a customer terminal may perform a call connection with a call server. Here, the call connection may be a phone connection between the customer terminal and the call server through a wireless network. That is, the customer terminal can perform a phone connection with the call server through the phone number.

In step S402, the customer terminal may request a chatbot service from the call server. For example, a customer terminal may request a chatbot service based on an IVR service provided from a call server.

In step S403, the call server may determine whether the phone number received from the external server (eg, the telecommunication company server) matches the phone number of the customer terminal registered in the call server. For example, a communication company server may transmit a phone number of a customer terminal to a call server through an automatic number identification service.

In step S404, the call server may transmit a chatbot service request message including the phone number received from the external server to the chatbot server. For example, if the phone number received from the external server and the phone number of the customer terminal registered in the call server match, the call server may transmit a chatbot service request message including the phone number received from the external server to the chatbot server. there is.

Alternatively, for example, step S403 may be omitted, and in step S404, the call server sends a chatbot service request message, including the phone number of the customer terminal received from the telecommunication company server through the automatic caller identification service, to the chatbot server. can transmit Here, the phone number received from the external server may be second personal information about the customer terminal.

In step S405, the chatbot server may provide an interface related to the chatbot service to the customer terminal.

In step S406, the customer terminal may transmit the first personal information to the chatbot server through an interface related to the chatbot service. For example, the user of the customer terminal may transmit the first personal information to the chatbot server by inputting the customer's name, date of birth, and phone number through an interface displayed on the screen of the customer terminal. The interface related to the chatbot service may include an interface for inputting personal information necessary to provide the chatbot service in addition to interfaces that provide the chatbot service. The first personal information may include the customer's name, date of birth, and phone number.

In step S407, the chatbot server may determine whether the personal information matches. The chatbot server may determine whether the phone numbers match based on the first personal information and the second personal information. For example, if the phone numbers match, the chatbot server may determine that the first authentication is completed.

In step S408, the customer terminal may perform a simple authentication procedure with the chatbot server. For example, the simple authentication procedure may be a procedure in which the customer terminal authenticates through an authentication number previously set.

Alternatively, for example, the simple authentication procedure may be replaced with steps S407 and S409, step S407 may be a first authentication procedure, and step S408 may be a second authentication procedure. That is, step S406 may be omitted.

In step S409, the chatbot server may determine whether the first personal information matches the third personal information registered in the EMR server. For example, the chatbot server may determine whether the phone numbers match based on the first personal information and the third personal information received through an interface related to the chatbot service.

In step S410, when the first personal information and the third personal information match, the chatbot server may provide a chatbot service to the customer terminal. For example, when the phone numbers match based on the first personal information and the third personal information, the chatbot server may provide a chatbot service to the customer terminal. That is, based on completion of the first authentication and the second authentication, the chatbot server may provide a chatbot service to the customer terminal.

In step S411, the customer terminal may request a chatbot server to connect to an agent through the chatbot service.

In step S412, the chatbot server may transmit a first connection request message requesting an agent connection to the call server. The first connection request message may include usage information related to the chatbot service. For example, usage information related to the chatbot service includes personal information about the customer terminal entered through the chatbot service, information about the category that the customer terminal inquired through the chatbot service, and information about the conversation between the customer terminal and the chatbot. can include

In step S413, the call server determines the priority of the customer terminal through a decision model using a neural network based on usage information related to the chatbot service for the customer terminal and call connection status information for a plurality of agent terminals. there is. Here, the plurality of counselor terminals are a plurality of counselor terminals currently managed by the call server. Information related to the call connection status includes information on whether or not the agent terminal is in a call connection state with the customer terminal, information on the elapsed time after the call connection between the agent terminal and the customer terminal, and information on the customer terminal waiting for a call with respect to the agent terminal. Information, the degree of kindness to the counselor terminal, the number of consultations of the counselor terminal, and the continuous working hours of the counselor terminal may be included.

In step S414, the call server may transmit usage information related to the chatbot service to the selected counselor terminal based on the priority of the customer terminal.

In step S415, the customer terminal and the counselor terminal may perform a call connection.

For example, based on the fact that the last time the customer terminal used the chatbot service was within a preset time from the time the call connection was established, transmission of a preset interactive voice response matching the call connection to the customer terminal. may be omitted. Here, the preset interactive voice response may be a voice message pre-stored in the call server. For example, the preset interactive voice response may be a response automatically transmitted for guidance when a customer terminal connects a call with a call server.

5 is a diagram illustrating a method for a call server to manage a call connection between a customer terminal and an agent terminal based on use information related to a chatbot service by using a neural network according to an embodiment. The embodiment of FIG. 5 can be combined with various embodiments of the present disclosure.

Referring to FIG. 5 , in step S501, the call server may receive a first connection request message requesting a call connection with an agent from a chatbot server that provides a chatbot service to a first customer terminal. The chatbot service may be provided based on an authentication procedure between the first customer terminal and the chatbot server. The connection request message may include use information related to the chatbot service for the first customer terminal.

In step S502, the call server uses a decision model using a plurality of neural networks based on usage information related to the chatbot service for the first customer terminal and information related to a call connection state for a plurality of counselor terminals. Priorities of the customer terminal and the plurality of counselor terminals may be determined.

The decision model may include a first decision model and a second decision model, and the priority may include a first priority for the first customer terminal and a second priority for the plurality of counselor terminals.

For example, a first decision model using a first neural network and a second neural network based on usage information related to the chatbot service for the first customer terminal and information related to call connection states for a plurality of counselor terminals A first priority for the first customer terminal and a second priority for a plurality of counselor terminals may be determined through the used second determination model. For example, usage information related to the chatbot service includes personal information about the customer terminal entered through the chatbot service, the number of accesses to the chatbot service, information on the category that the customer terminal inquired through the chatbot service, and information between the customer terminal and the chatbot. It may contain information about the contents of the conversation. Personal information about the customer terminal may include the date of birth, name, and phone number of the user of the customer terminal. The information about the category inquired by the customer terminal through the chatbot service may include information about the category and information about the treatment subject, such as hospital guidance, treatment reservation, guidance video, user guide, and the like. Information on conversation contents between the customer terminal and the chatbot may be in the form of text data.

Information related to call connection states of a plurality of counselor terminals may be information input to the call server in real time. For example, the information related to the call connection state of a plurality of agent terminals includes information about whether or not the agent terminal is in a call connection state with the customer terminal, information about the consultation time that has elapsed after the agent terminal is connected to the customer terminal, It may include information about customer terminals waiting for a call to the counselor terminal, friendliness of the counselor terminal, information about the number of consultations of the counselor terminal, and information about continuous working hours of the counselor terminal. Here, the friendliness of the counselor terminal may be an evaluation score determined by the feedback of the customer terminal. Here, the information on the number of consultations of the counselor terminal may include the number of times the counselor terminal was connected to the customer terminal on the same day and the phone number of the connected customer terminal. Here, the continuous working time of the counselor terminal may be the time during which the user of the counselor terminal is continuously consulting with the customer without leaving the seat.

The first decision model may be a model learned by the first neural network. The first neural network may include a first input layer, one or more first hidden layers, and a first output layer. Data for learning of each neural network composed of usage information related to a plurality of chatbot services and a first priority for a correct answer customer terminal is input to the first input layer of the first neural network, and the one or more first A first output vector is output after passing through a hidden layer and a first output layer, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is input to the first loss function layer. A first loss value is output using a first loss function that compares an output vector with a first correct answer vector for each learning data, and the parameters of the first neural network are learned in a direction in which the first loss value decreases. , the first decision model may be generated.

For example, the first neural network may be a CNN model including a residual block in which one or more first hidden layers are formed by stacking six convolutional layers and a bottleneck structure based on the residual block. .

As convolutional layers are deeply stacked and learned, representative features that exist in the training data can be extracted well, so learning performance can increase. can Therefore, in the present disclosure, residual learning is introduced to reduce the influence of the gradient on the CNN model, and a bottle neck is applied to solve the problem that the speed decreases as the parameter increases as the depth of the network increases. . Here, the bottleneck structure is a structure in which the amount of computation is reduced while compressing a channel, features of a channel before being compressed are extracted from a compressed channel, and the channel is increased again. This causes loss of information, but it is possible to increase the learning speed by reducing the amount of calculation.

For example, a residual block is formed by stacking six convolutional layers, and may include a shortcut capable of adding an input value to an output value. That is, a residual block can be constructed by adding the concept of residual learning, which learns to optimize the difference between input and output, and a shortcut connection that adds the input as it is to the output.

That is, while two convolutional layers are stacked in the existing residual block, six convolutional layers are stacked in the present disclosure, thereby increasing the number of blocks for extracting useful features and information affecting final feature extraction. By making it more shareable, it is possible to increase the learning performance of the network.

Specifically, the call server may vectorize a plurality of variables through data preprocessing based on usage information related to a plurality of chatbot services. For example, the call server, based on usage information related to a plurality of chatbot services, determines whether a chatbot service is used or not, the number of preset words included in the conversation content of a customer terminal, a value for a treatment subject, and a value related to a customer terminal. A first input vector including the number of call attempts and the age of the user of the customer terminal may be determined. The call server may learn the first neural network as described above by inputting the first input vector to the first input layer of the first neural network.

Here, the value related to whether the chatbot service is used may be a value of 0 when the chatbot service is not used, and may be a value for the number of times when the chatbot service is used. The number of preset words included in the conversation content of the customer terminal may be determined through natural language processing based on information about the conversation content between the customer terminal and the chatbot. Preset words may include “quickly”, “urgently”, “complaint” and “inconvenient”. A value for each medical category may be a value corresponding to each medical category.

In addition, the first priority for the customer terminal with the correct answer, which is one of the data for learning of the first neural network, may be determined by Equation 1 below as a value for the first priority for the customer terminal.

In Equation 1, P ₁ is a value for the first priority, u _a is the age of the user of the customer terminal, and n _e is a preset word included in the conversation between the customer terminal and the chatbot , where n _t is the number of call attempts made by the customer terminal on the same day, c is a value related to whether the customer terminal uses a chatbot service, and h is a value related to a treatment subject of the customer terminal.

For example, the higher the value of the first priority, the higher the priority. As the age of the user of the customer terminal is closer to the middle, by increasing the value of the first priority, guidance may be provided more quickly to a user of the age who mainly uses medical appointments. For example, by increasing the value for the first priority as the number of preset words included in the conversation between the customer terminal and the chatbot or the number of call attempts of the customer terminal on the same day increases, urgent or dissatisfied Guidance to the user can proceed more quickly. For example, the value for the first priority may be adjusted by reflecting the characteristics of the treatment course by setting different values for the treatment course for each treatment course. For example, a customer terminal that has not used the chatbot service determines a small value for the priority, and the higher the number of times the chatbot service is used, the higher the value for the first priority, thereby providing the user of the customer terminal with the chatbot service. use can be encouraged. In this way, an appropriate priority may be determined in consideration of the characteristics and circumstances of the customer terminal.

The second neural network may include a second input layer, one or more second hidden layers, and a second output layer. Information related to the call connection state of a plurality of counselor terminals and data for learning each neural network composed of second priorities for correct answer counselor terminals are input to the second input layer of the second neural network, A second output vector is output by passing through at least one second hidden layer and a second output layer, the first output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer outputs a second loss value using a second loss function that compares the second output vector with a second correct answer vector for each training data, and outputs a second loss value when the parameter of the second neural network is smaller than the second loss value The second decision model, which is learned in a losing direction, may be generated.

For example, the second neural network may be a CNN model including a residual block in which one or more second hidden layers are formed by stacking six convolutional layers and a bottleneck structure based on the residual block. .

Specifically, the call server may vectorize a plurality of variables through data preprocessing based on information related to call connection states of a plurality of counselor terminals. For example, the call server, based on information related to the call connection status of a plurality of agent terminals, the time during which the agent terminal made a call with the currently connected customer terminal, the degree of kindness to the agent terminal, and the customer terminal waiting for the agent terminal A second input vector including the number of, the number of consultations of the counselor terminal, and the continuous working hours of the counselor terminal may be determined. The call server may learn the second neural network as described above by inputting the second input vector to the second input layer of the second neural network.

In addition, the second priority for the counselor terminal with the correct answer, which is one of the data for learning of the second neural network, may be determined by Equation 2 below as a value for the second priority for the counselor terminal.

In Equation 2, P ₂ is a value for the second priority, t _c is the time during which the counselor terminal communicated with the currently connected customer terminal, f _k is the kindness level of the counselor terminal, k _m is the number of customer terminals waiting for calls to the agent terminal, n _s is the number of counseling sessions of the agent terminal so far, t _o is the continuous working time of the agent terminal, and d can be a default value there is. The t _c and the t _o are units of time, for example, may be units of minutes. The d may be a value previously stored in the call server.

For example, the higher the value of the second priority, the higher the priority. As the values of t _c and f _k are larger, the value for the second priority of the counselor terminal may be increased. For example, as the k _m , the n _s , and the t _o have smaller values, the value for the second priority of the counselor terminal may be increased.

That is, the longer the duration of the call with the currently connected customer terminal, the higher the possibility that the counseling will end, so the value for the second priority may have a larger value. In addition, as the friendliness of the counselor terminal is high and the number of consultations of the counselor terminal indicating the degree of fatigue of the counselor is low, more stable counseling can be performed with the user of the customer terminal who has urgent or complaints, so the value for the second priority can have a large value. In addition, since it is difficult to preferentially match counselor terminals with a large number of terminals on call waiting, and counselor terminals with long continuous working hours require break time, the value for the second priority may have a small value. In this way, an appropriate priority may be determined in consideration of the characteristics and circumstances of the counselor terminal.

In step S503, the call server may select a first counselor terminal from among the plurality of counselor terminals based on priorities for the first customer terminal and the plurality of counselor terminals.

The call server may select a first counselor terminal having a value for a second priority corresponding to a value for a first priority for the first customer terminal from among a plurality of counselor terminals. That is, the call server may match the customer terminal and the counselor terminal in the order of highest priority. For example, when the first priority for the first customer terminal is the highest priority, the call server selects an agent terminal having a second priority corresponding to the highest priority among a plurality of agent terminals as a first agent. terminal can be selected.

For example, if there are customer terminals having the same value for the first priority, the call server may first connect a customer terminal having a larger value related to whether or not the chatbot service is used to the counselor terminal. If the values related to whether or not the chatbot service is used are the same, the call server may first connect a customer terminal having a greater number of call attempts on the same day to the counselor terminal. If the customer terminals have the same number of call attempts on the same day, the call server may first connect a customer terminal having a larger value in the number of preset words included in the conversation between the customer terminal and the chatbot to the counselor terminal. When all three criteria described above are the same, the call server may select a customer terminal at random and connect the selected customer terminal to the counselor terminal.

For example, when an agent terminal having the same second priority exists, the call server may first connect the agent terminal in a call waiting state to the customer terminal. If the call state of the counselor terminals is the same, the call server may first connect the counselor terminal having a larger number of customer terminals waiting for a call to the customer terminal. If the number of customer terminals waiting for a call is the same, the call server may first connect an agent terminal having a smaller continuous working time value with the customer terminal. If the continuous working hours have the same value, the call server may randomly select an agent terminal and connect the selected agent terminal to the customer terminal.

In step S504, the call server may transmit use information related to the chatbot service for the first customer terminal to the first counselor terminal.

In step S505, a call connection between the first customer terminal and the first counselor terminal may be established.

Based on the fact that the last time the first customer terminal uses the chatbot service is within a preset time from the time the call connection is established, transmission of a preset interactive voice response matching the call connection is performed by the first customer terminal may be omitted for That is, since the first customer terminal has already been fully informed through the chatbot service, a preset interactive voice response transmitted while being matched with the counselor terminal can be omitted for the first customer terminal.

According to an embodiment, before the first customer terminal receives the chatbot service from the chatbot server, the call server, before the first customer terminal receives the chatbot service from the chatbot server, the second customer A second connection request message requesting an agent call connection may be received from the terminal. The call server may match the second customer terminal to the first counselor terminal among the plurality of agent terminals. The first customer terminal may have priority over the second customer terminal to establish a call connection with the first counselor terminal. That is, a customer terminal that does not use the chatbot service, that is, a second customer terminal may have a lower priority than a first customer terminal that is a customer terminal that uses the chatbot service.

For example, the preset time may be determined by Equation 3 below.

In Equation 3, the W _time is the preset time, k is the number of call waiting customer terminals, t _i is the call waiting time of the ith customer terminal, and t _avg is the average call waiting time, n _t is the number of customer terminals currently using the chatbot service, n _avg is the average number of customer terminals using the chatbot service, and t _n is the number of call attempts made by the first customer terminal on the day; The w _def may be a basic value for the preset time.

For example, the unit of the preset time may be a minute unit. Here, the number of call attempts by the first customer terminal on the same day may be the number of accesses to the call server. Call waiting time of the customer terminal may be determined based on information related to call connection states of a plurality of counselor terminals. The average call waiting time is an average of call waiting times for customer terminals for a preset period (eg, 6 months), and may be pre-stored in the call server. The average number of customer terminals using the chatbot service is an average value of the number of customer terminals using the chatbot service for a preset period of time, and may be pre-stored in the call server.

For example, by reducing the preset time as the call waiting time of the customer terminal in call waiting is longer than the average call waiting time, if the first customer terminal is a customer terminal that has been using the chatbot service for a relatively long time, it is excluded from priority. First, the call waiting time of the customer terminal waiting for a call can be reduced.

For example, as the number of terminals currently using the chatbot service is greater than the average number of customer terminals using the chatbot service, the preset time is reduced, so that if the first customer terminal is a customer terminal that has been using the chatbot service for a relatively long time, It is possible to reduce the call waiting time of the customer terminal that does not use the chatbot service by excluding it from priority.

For example, since the first customer terminal is likely to be in an uncomfortable situation even when the first customer terminal has not used the chatbot service for a relatively long time by increasing the preset time as the number of call attempts of the first customer terminal increases on the same day, , the first customer terminal may be preferentially connected to the counselor terminal.

Therefore, if the priority is set high for the customer terminal using the chatbot service within a fixed time, the characteristics and situation of the customer terminal cannot be reflected, so the call server sets the preset time according to the characteristics and situation of the customer terminal By changing, it is possible to flexibly adjust the priority of the customer terminal.

According to an embodiment, an authentication procedure between the customer terminal and the chatbot server may include first authentication and second authentication. The first authentication may be performed based on matching of first personal information transmitted from the customer terminal to the chatbot server and second personal information transmitted from the call server to the chatbot server. The first personal information may be information input by a user of the customer terminal. The second personal information may be information transmitted from a server associated with a communication company to the call server through automatic caller identification.

The second authentication may be performed based on matching of the first personal information and third personal information transmitted from a server related to the electronic medical record, based on completion of the first authentication. Based on completion of the first authentication and the second authentication, the chatbot service may be provided from the chatbot server to the customer terminal.

6 is a block diagram illustrating a configuration of a server according to an exemplary embodiment. One embodiment of FIG. 6 may be combined with various embodiments of the present disclosure.

As shown in FIG. 6 , the server 660 may be the aforementioned call server or chatbot server. The server 600 may include a processor 610 , a communication unit 620 and a memory 630 . However, not all components shown in FIG. 6 are essential components of the server 600 . The server 600 may be implemented with more components than those shown in FIG. 6, or the server 600 may be implemented with fewer components than those shown in FIG. For example, the server 600 according to some embodiments may further include a user input interface (not shown), an output unit (not shown), etc. in addition to the processor 610, the communication unit 620, and the memory 630. .

Processor 610, typically controls the overall operation of the server (600). The processor 610 may include one or more processors to control other elements included in the server 600 . For example, the processor 610 may generally control the communication unit 620 and the memory 630 by executing programs stored in the memory 630 . Also, the processor 610 may perform the functions of the server 600 described in FIGS. 3 to 5 by executing programs stored in the memory 630 .

The communication unit 620 may include one or more components that allow the server 600 to communicate with other devices (not shown) and servers (not shown). The other device (not shown) may be a computing device such as the server 600 or a sensing device, but is not limited thereto. The communication unit 620 may receive a user input from another electronic device or data stored in an external device from an external device through a network.

For example, the communication unit 620 may transmit/receive a message for establishing a connection with at least one device. The communication unit 620 may transmit information generated by the processor 610 to at least one device connected to the server. The communication unit 620 may receive information from at least one device connected to the server. The communication unit 620 may transmit information related to the received information in response to information received from at least one device.

The memory 630 may store programs for processing and controlling the processor 610 . For example, the memory 630 may store information input to a server or information received from another device through a network. Also, the memory 630 may store data generated by the processor 610 . The memory 630 may store information input to or output from the server 600 .

The memory 630 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg SD or XD memory, etc.), RAM (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk , an optical disk, and at least one type of storage medium.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (5)

A method in which a call server manages a call connection between a customer terminal and an agent terminal based on usage information related to a chatbot service using a neural network, the method comprising:
Receiving a first connection request message requesting a call connection with an agent from a chatbot server that provides a chatbot service to a first customer terminal;
The chatbot service is provided based on an authentication procedure between the first customer terminal and the chatbot server,
The connection request message includes usage information related to the chatbot service for the first customer terminal,
The first customer terminal and the plurality of counselors through a decision model using a plurality of neural networks based on usage information related to the chatbot service for the first customer terminal and information related to a call connection state for a plurality of counselor terminals Determining a priority for a terminal;
selecting a first counselor terminal from among the plurality of counselor terminals based on priorities of the first customer terminal and the plurality of counselor terminals;
Transmitting use information related to the chatbot service for the first customer terminal to the first counselor terminal; and
Establishing a call connection between the first customer terminal and the first counselor terminal,
Based on the fact that the last time the first customer terminal uses the chatbot service is within a preset time from the time the call connection is established, transmission of a preset interactive voice response matching the call connection is performed by the first customer terminal which is omitted for
Way.
According to claim 1,
Receiving a second connection request message requesting a call connection with an agent from a second customer terminal before the first customer terminal receives the chatbot service from the chatbot server; and
Further comprising matching the second customer terminal to the first counselor terminal among the plurality of counselor terminals,
The first customer terminal takes precedence over the second customer terminal to establish a call connection with the first counselor terminal;
The preset time is determined by the following equation,

In the above equation, the Wtime is the preset time, k is the number of customer terminals waiting for a call, ti is the call waiting time of the ith customer terminal, tavg is the average call waiting time, and the nt is the number of customer terminals currently using the chatbot service, navg is the average number of customer terminals using the chatbot service, tn is the number of call attempts made by the first customer terminal on the day, and wdef is the number of call attempts made at the preset time which is the default value for
Way.
According to claim 1,
The authentication procedure between the customer terminal and the chatbot server includes first authentication and second authentication,
The first authentication is performed based on matching of first personal information transmitted from the customer terminal to the chatbot server and second personal information transmitted from the call server to the chatbot server,
The first personal information is information input by a user of the customer terminal,
The second personal information is information transmitted to the call server through automatic caller identification from a server related to a communication company,
Way.
According to claim 3,
The second authentication is performed based on matching of the first personal information and third personal information transmitted from a server related to the electronic medical record based on completion of the first authentication,
Based on the completion of the first authentication and the second authentication, the chatbot service is provided from the chatbot server to the customer terminal.
Way.
According to claim 2,
A first priority for the first customer terminal is determined through a first decision model using a first neural network based on usage information related to the chatbot service for the first customer terminal;
A second priority for the plurality of counselor terminals is determined through a second decision model using a second neural network based on information related to call connection states of the plurality of counselor terminals,
The first counselor terminal is selected from among the plurality of counselor terminals based on a first priority for the first customer terminal and a second priority for the plurality of counselor terminals;
The first neural network includes a first input layer, one or more first hidden layers and a first output layer;
Data for learning of each neural network composed of usage information related to a plurality of chatbot services and a first priority for a correct answer customer terminal is input to the first input layer of the first neural network, and the one or more first A first output vector is output after passing through a hidden layer and a first output layer, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is input to the first loss function layer. A first loss value is output using a first loss function that compares an output vector with a first correct answer vector for each learning data, and the parameters of the first neural network are learned in a direction in which the first loss value decreases. The first decision model is created,
The second neural network includes a second input layer, one or more second hidden layers, and a second output layer;
Information related to the call connection state of a plurality of counselor terminals and data for learning each neural network composed of second priorities for correct answer counselor terminals are input to the second input layer of the second neural network, A second output vector is output by passing through at least one second hidden layer and a second output layer, the first output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer outputs a second loss value using a second loss function that compares the second output vector with a second correct answer vector for each training data, and outputs a second loss value when the parameter of the second neural network is smaller than the second loss value The second decision model, which is learned in a losing direction, is generated.
Way.

Images