WO2022131576A1

WO2022131576A1 - Method and device for providing artificial intelligence assistant service through voice call

Info

Publication number: WO2022131576A1
Application number: PCT/KR2021/016688
Authority: WO
Inventors: 최승진
Original assignee: 주식회사 아이큐브넷
Priority date: 2020-12-16
Filing date: 2021-11-16
Publication date: 2022-06-23
Also published as: KR102426288B1; KR20220086262A

Abstract

Embodiments may provide an operation method of a first terminal performing a question-and-answer operation through a voice call. In this case, the operation method of the first terminal may comprise the steps of: receiving a voice call from a second terminal and making an automatic connection; after the automatic connection is made, receiving a first query request message from the second terminal; transmitting, to an AI server, a second query request message based on the first query request message; receiving, from the AI server, a first query response message based on the second query request message; and transferring, to the second terminal, a second query response message based on the first query response message.

Description

Method and apparatus for providing artificial intelligence assistant service through voice call

Embodiments relate to a method and apparatus for providing an artificial intelligence assistant service through a voice call. More specifically, it relates to a method of providing an artificial intelligence assistant service through a voice call based on automatic reception.

Recently, non-face-to-face services are increasing, and the use of ARS responses or automatic responses for non-face-to-face services is also increasing. However, it may not be easy for consumers to use the service to get the answer they want because the ARS response or automatic response is conducted based on a pre-determined option. For this reason, consumers often obtain a desired answer through an agent instead of an ARS response or an automatic response, but the number of agents is limited and it takes a lot of time to get the desired answer, which limits the service provision.

In consideration of the above points, the following describes a method and apparatus for providing a service using artificial intelligence so that it can flexibly respond to various requests of consumers by using artificial intelligence.

[Prior art literature]

(Patent Document 1) Korean Patent Application Publication No. 10-2018-0112349

The present specification may provide a method and apparatus for providing an artificial intelligence assistant service through a voice call.

In the present specification, the receiver terminal may provide an automatic answer based on artificial intelligence to the caller terminal through a voice call.

The present specification may generate a response through artificial intelligence based on the request of the sender terminal, and provide the generated response to the sender terminal.

The present specification may provide an artificial intelligence assistant service based on a voice call by converting it into a data call.

The problem to be solved in the present specification is not limited to the above, but may be extended to various matters that can be derived by the embodiments of the invention described below.

According to an embodiment of the present specification, it is possible to provide a method of operating a first terminal for performing a question and answer through a voice call. In this case, the method of operation of the first terminal includes the steps of receiving a voice call from the second terminal, performing automatic connection, receiving a first query request message from the second terminal after the automatic connection is performed, the first transmitting a second query request message based on the first query request message to an AI server; receiving a first query response message based on the second query request message from the AI server; and a first query response message based on the first query response message It may include transmitting the second query response message to the second terminal.

In addition, according to an embodiment of the present specification, the first query request message is transmitted to the first terminal by voice based on the voice call, and the second query request transmitted by the first terminal to the AI server The message may include at least one of text information converted by performing speech to text (STT) processing on the first query request message and voice file information generated based on the first query request message.

In addition, according to an embodiment of the present specification, the first query response message delivered by the AI server to the first terminal includes text information generated based on the second query request message and the second query request message. At least one of the voice file information generated based on the information, wherein the first terminal generates the second query response message based on the first query response message received from the AI server, and the generated second A question and answer message may be provided to the second terminal by voice based on the voice call.

In addition, according to an embodiment of the present specification, transmitting a request message for converting the voice call into a data call to the second terminal, receiving an acceptance message in response to the request message from the second terminal , and converting the voice call into the data call based on the acceptance message.

In addition, according to an embodiment of the present specification, further comprising the step of determining whether a preset time has elapsed after the automatic connection with the second terminal is performed, after the automatic connection with the second terminal is performed When the set time elapses, the request message may be transmitted to the second terminal.

In addition, according to an embodiment of the present specification, the method further comprising the step of determining, by the first terminal, whether the data call conversion is necessary based on the data processing capability, wherein the first terminal is the first terminal based on the data processing capability When it is determined that data call conversion is necessary, the request message may be transmitted to the second terminal.

In addition, according to an embodiment of the present specification, the data call is performed based on a third messenger platform, and the data call includes identification information in the third messenger platform of the first terminal and the data call of the second terminal. It may be performed based on identification information in the third messenger platform.

In addition, according to an embodiment of the present specification, when the first terminal performs the data call based on the third messenger platform, transmitting a data call provision request message to the third messenger platform; The method may further include receiving an acceptance message for the data call from a third messenger platform, wherein when the acceptance message is received, the data call may be performed based on the third messenger platform.

In addition, according to an embodiment of the present specification, after the automatic connection is performed, transmitting at least one piece of related content information related to the first terminal to the second terminal; The method may further include receiving the related content information selected by the second terminal based on the information, wherein the first query request message may be generated based on the related content information selected by the second terminal.

The present specification has an effect of providing a response to the calling terminal through artificial intelligence in consideration of the contents of the called terminal through a voice call.

The present specification has the effect of providing a flexible response by analyzing the request of the sender terminal through artificial intelligence and generating and providing a response corresponding to the request.

The present specification has an effect of providing specific response information by converting an artificial intelligence assistant service based on a voice call into a data call.

1 is a diagram illustrating an example of an operating environment of a system according to an embodiment of the present specification.

2 is a block diagram illustrating an internal configuration of the computing device 200 according to an embodiment of the present specification.

3 is a diagram illustrating a method of providing a response to a request of a caller terminal through a voice call based on artificial intelligence according to an embodiment of the present specification.

4A is a diagram illustrating a method of providing a response to a request of a caller terminal according to an embodiment of the present specification.

4B is a diagram illustrating a method of providing a response to a request of a caller terminal based on related content according to an embodiment of the present specification.

4C is a diagram illustrating a method of providing a response to a request of a caller terminal based on related content according to an embodiment of the present specification.

4D is a diagram illustrating a method of providing a response to a request of a caller terminal based on related content according to an embodiment of the present specification.

5A is a diagram illustrating a method of converting a voice call into a data call according to an embodiment of the present specification.

5B is a diagram illustrating a method of converting a voice call into a data call based on a preset time according to an embodiment of the present specification.

5C is a diagram illustrating a method of converting a voice call into a data call based on artificial intelligence according to an embodiment of the present specification.

6A is a diagram illustrating a method of converting a voice call into a data call based on a third messenger platform according to an embodiment of the present specification.

6B is a diagram illustrating a method of converting a voice call into a data call based on the third messenger platform according to an embodiment of the present specification.

7A is a diagram illustrating a method of providing a response to a caller terminal according to an embodiment of the present specification.

7B is a diagram illustrating a method of providing a response to a caller terminal according to an embodiment of the present specification.

8 is a flowchart illustrating a method of providing an artificial intelligence assistant service through a voice call according to an embodiment of the present specification.

In the description of the embodiments of the present specification, if it is determined that a detailed description of a known configuration or function may obscure the gist of the embodiment of the present specification, a detailed description thereof will be omitted. In addition, in the drawings, parts not related to the description of the embodiments of the present specification are omitted, and similar reference numerals are attached to similar parts.

In the embodiments of the present specification, when a component is "connected", "coupled" or "connected" with another component, it is not only a direct connection relationship, but also an indirect relationship where another component exists in the middle. It can also include human connections. In addition, when a component is said to "include" or "have" another component, it means that another component may be further included without excluding other components unless otherwise stated. .

In the embodiment of the present specification, terms such as first, second, etc. are used only for the purpose of distinguishing one component from other components, and unless otherwise specified, do not limit the order or importance between the components. does not Accordingly, within the scope of the embodiments herein, a first component in an embodiment may be referred to as a second component in another embodiment, and similarly, a second component in an embodiment is referred to as a first component in another embodiment. can also be called

In the embodiment of the present specification, the components that are distinguished from each other are for clearly explaining each characteristic, and the components do not necessarily mean that the components are separated. That is, a plurality of components may be integrated to form one hardware or software unit, or one component may be distributed to form a plurality of hardware or software units. Accordingly, even if not specifically mentioned, such integrated or dispersed embodiments are also included in the scope of the embodiments of the present specification.

In the present specification, the network may be a concept including both wired and wireless networks. In this case, the network may mean a communication network in which data exchange between the device and the system and devices can be performed, and is not limited to a specific network.

Embodiments described herein may have aspects that are entirely hardware, partly hardware and partly software, or entirely software. As used herein, "unit," "device," or "system," or the like, refers to hardware, a combination of hardware and software, or a computer-related entity, such as software. For example, as used herein, a part, module, device, or system is a running process, a processor, an object, an executable, a thread of execution, a program, and/or a computer. (computer), but is not limited thereto. For example, both an application running on a computer and a computer may correspond to a part, module, device, or system of the present specification.

In addition, in the present specification, the device may be a mobile device such as a smart phone, a tablet PC, a wearable device, and a head mounted display (HMD), as well as a fixed device such as a PC or home appliance having a display function. Also, as an example, the device may be an in-vehicle cluster or an Internet of Things (IoT) device. That is, in the present specification, a device may refer to devices capable of operating an application, and is not limited to a specific type. Hereinafter, for convenience of description, a device in which an application operates is referred to as a device.

In the present specification, the communication method of the network is not limited, and the connection between each component may not be connected in the same network method. The network may include not only a communication method using a communication network (eg, a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network, a satellite network, etc.) but also short-range wireless communication between devices. For example, the network may include all communication methods through which an object and an object can network, and is not limited to wired communication, wireless communication, 3G, 4G, 5G, or other methods. For example, a wired and/or network may be a Local Area Network (LAN), a Metropolitan Area Network (MAN), a Global System for Mobile Network (GSM), an Enhanced Data GSM Environment (EDGE), a High Speed Downlink Packet Access (HSDPA), W-CDMA (Wideband Code Division Multiple Access), CDMA (Code Division Multiple Access), TDMA (Time Division Multiple Access), Bluetooth, Zigbee, Wi-Fi, VoIP (Voice over) Internet Protocol), LTE Advanced, IEEE802.16m, WirelessMAN-Advanced, HSPA+, 3GPP Long Term Evolution (LTE), Mobile WiMAX (IEEE 802.16e), UMB (formerly EV-DO Rev. C), Flash-OFDM, iBurst and MBWA (IEEE 802.20) systems, HIPERMAN, Beam-Division Multiple Access (BDMA), Wi-MAX (World Interoperability for Microwave Access), and ultrasonic-based communication can refer to a communication network by one or more communication methods selected from the group consisting of However, the present invention is not limited thereto.

Components described in various embodiments do not necessarily mean essential components, and some may be optional components. Accordingly, an embodiment composed of a subset of the components described in the embodiment is also included in the scope of the embodiment of the present specification. In addition, embodiments including other components in addition to the components described in various embodiments are also included in the scope of the embodiments of the present specification.

Hereinafter, embodiments of the present specification will be described in detail with reference to the drawings.

* FIG. 1 is a diagram illustrating an example of an operating environment of a system according to an embodiment of the present specification. Referring to FIG. 1 , a user device 110 and one or

more servers

120 , 130 , 140 are connected through a network 1 . 1 is an example for explaining the invention, and the number of user devices or the number of servers is not limited as in FIG. 1 .

The user device 110 may be a fixed terminal implemented as a computer system or a mobile terminal. The user device 110 is, for example, a smart phone, a mobile phone, a navigation system, a computer, a laptop computer, a digital broadcasting terminal, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a tablet PC, a game console (game). console), a wearable device, an Internet of things (IoT) device, a virtual reality (VR) device, and an augmented reality (AR) device. In one example embodiments, the user device 110 may actually use one of a variety of physical computer systems capable of communicating with the other servers 120 - 140 over the network 1 using a wireless or wired communication scheme. can mean

Each server may be implemented as a computer device or a plurality of computer devices that communicate with the user device 110 and the network 1 to provide commands, codes, files, contents, services, and the like. For example, the server may be a system that provides each service to the user device 110 connected through the network 1 . As a more specific example, the server may provide a service (eg, information provision, etc.) targeted by the corresponding application to the user device 110 through an application as a computer program installed and driven in the user device 110 . As another example, the server may distribute the above-described file for installation and operation of the application to the user device 110 , and may provide a corresponding service by receiving user input information. As an example, below, the artificial intelligence (AI) server may be any one of the servers of FIG. 1 . In addition, the receiver terminal performing data communication with the AI server and the caller terminal performing voice call and/or data communication with the receiver terminal may be one of the users of FIG. 1 . Also, below, the third messenger platform may be any one of the servers of FIG. 1 , and is not limited to the above-described embodiment.

2 is a block diagram illustrating an internal configuration of the computing device 200 according to an embodiment of the present specification. The computing device 200 may be applied to one or more of the user devices 110-1 and 110-2 or the servers 120-140 described above with reference to FIG. 1, and each device and server may add some components or By being configured to exclude, it may have the same or similar internal configuration.

Referring to FIG. 2 , the computing device 200 may include a memory 210 , a processor 220 , a communication module 230 , and a transceiver 240 . The memory 210 is a non-transitory computer-readable recording medium, and is a non-volatile, high-capacity, non-volatile memory such as random access memory (RAM), read only memory (ROM), disk drive, solid state drive (SSD), and flash memory. It may include a permanent mass storage device. Here, a non-volatile mass storage device such as a ROM, an SSD, a flash memory, a disk drive, etc. may be included in the above-described device or server as a separate permanent storage device distinct from the memory 210 . In addition, the memory 210 stores an operating system and at least one program code (eg, a browser installed and driven on the user device 110 , or an application installed on the user device 110 to provide a specific service). can be These software components may be loaded from a computer-readable recording medium separate from the memory 210 . The separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD/CD-ROM drive, and a memory card.

In another embodiment, the software components may be loaded into the memory 210 through the communication module 230 instead of a computer-readable recording medium. For example, the at least one program is a computer program installed by files provided through the network 1 by a file distribution system (eg, the above-described server) that distributes the installation files of developers or applications (eg, a computer program) It may be loaded into the memory 210 based on the above-described application).

The processor 220 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. The instructions may be provided to the processor 220 by the memory 210 or the communication module 230 . For example, the processor 220 may be configured to execute a received instruction according to a program code stored in a recording device such as the memory 210 .

The communication module 230 may provide a function for the user device 110 and the server 120 -140 to communicate with each other via the network 1, and the device 110 and/or the server 120 - 140, respectively. It may provide a function for communicating with other electronic devices.

The transceiver 240 may be a means for interfacing with an external input/output device (not shown). For example, the external input device may include devices such as a keyboard, mouse, microphone, and camera, and the external output device may include devices such as a display, a speaker, and a haptic feedback device.

As another example, the transceiver 240 may be a means for an interface with a device in which functions for input and output are integrated into one, such as a touch screen.

Also, in other embodiments, the computing device 200 may include more components than those of FIG. 2 according to the properties of the applied device. For example, when the computing device 200 is applied to the user device 110, it is implemented to include at least some of the above-described input/output devices, or a transceiver, a global positioning system (GPS) module, a camera, various sensors, It may further include other components such as a database and the like. As a more specific example, when the user device is a smartphone, various types of acceleration sensors, gyro sensors, camera modules, various physical buttons, buttons using a touch panel, input/output ports, vibrators for vibration, etc. included in the smartphone are generally included. It may be implemented to include more components.

In the following, each of the terminals and servers may be devices that communicate with other terminals or servers based on FIG. 2 . That is, the terminal and the server described below may be subjects that are connected through a mutual network based on FIG. 1 and perform communication, and each terminal and the server have a memory, a processor, a communication module, and a transceiver based on FIG. 2 . and other configurations and may be a computing device that operates. Hereinafter, descriptions are made based on a terminal and a server for convenience of description, but the configurations may include various configurations as a computing device, and may not be limited to a specific computing device.

For example, in order to provide an ARS response (or automatic response) in an existing smart phone, a voice call (or voice call) may be received, and a service may be provided based on a predetermined item through the ARS response server. At this time, companies that have many stores and customers, such as card companies or home appliance companies, and companies that sell a lot of products can build and provide a server for ARS response. There may be limitations in building In consideration of the above, a method for performing automatic reception in the user terminal will be described below. Furthermore, when the user terminal performs automatic reception, a method for the user terminal to provide a flexible answer according to a request rather than a preset item through the AI server will be described. That is, the following describes a method in which the receiver terminal provides an artificial intelligence assistant service that flexibly responds to various requests and responses of the sender terminal by using artificial intelligence.

The receiver terminal 320 may set automatic reception of a voice call delivered from the caller terminal 310 . For example, the receiver terminal 320 may be a carrier terminal, and may be a smartphone or other device. That is, the receiver terminal 320 is not implemented as a specific server, and may be a commonly used mobile device and may not be limited to a specific device. In addition, the caller terminal 310 may be a device of a user who wants to receive a service from a service provider. That is, the sender terminal 310 may be a device of a customer who wants to receive a service from a service provider based on the receiver terminal 320 .

In this case, referring to FIG. 3 , the receiver terminal 320 may receive a voice call (or voice call) from the caller terminal 310 . The user of the caller terminal 310 may attempt a voice call with the receiver terminal 320 based on identification information (e.g. phone number). For example, the sender terminal 310 and the receiver terminal 320 may perform data exchange by performing data communication with each other, and the embodiment is not limited thereto. Also, the receiver terminal 320 may perform data communication with the AI server 330 . That is, the receiver terminal 320 performs data exchange by communicating with the AI server 330 as a general device rather than a separate server, and can acquire desired information through this. The AI server 330 may be a server that processes the request of the sender terminal 310 and provides it to the receiver terminal 320 . As an example, the AI server 330 may be a server that has a learning model and is continuously updated by learning through a response to a request from a plurality of caller terminals 310 . As an example, the input of the AI server 330 may be a request from the sender terminal 310 , and the output may be a response to the request of the sender terminal 310 . The AI server 330 may continuously perform an update based on the above-described input and output, and may provide a flexible response to the caller terminal 310 based on the update.

As a specific example, when the receiver terminal 320 receives a voice call from the caller terminal 310, the receiver terminal 320 provides an automatic answer to the caller terminal 310, and based on the automatic answer, the caller terminal 320 ) can be processed. For example, when a voice call is automatically received by the receiver terminal 320 , the caller terminal 310 may transmit a query request to the receiver terminal 320 based on the voice call. That is, the user of the caller terminal 310 may transmit "query 1A" to the receiver terminal 320 by voice based on the automatic answer. The receiver terminal 320 may transmit the query request message converted into text to the AI server 330 by processing "Query 1A" from the sender terminal 310 by STT (Speech to Text). Also, as an example, the receiver terminal 320 may generate a request from the sender terminal 310 as a voice file and transmit the generated voice file to the AI server 330 , but is not limited to the above-described embodiment. That is, the receiver terminal 320 may generate "Query 1B" related to "Query 1A" received from the sender terminal 310 in the form of a text or voice file, and transmit it to the AI server 330 . "Query 1B" may be in the form of a text or audio file and is not limited to the above-described embodiment. Thereafter, the receiver terminal 320 may receive "response 1A" which is a response to "query 1B" from the AI server 330 . In this case, "response 1A" may be in the form of a text or voice file. That is, the AI server 330 may respond to “Query 1B” to the receiver terminal 320 as a message in the form of a text message or a message in the form of a voice file. In this case, as an example, the AI server 330 may obtain “answer 1A” that is an output with “query 1B” as an input based on the above-described learning model, and through this, can provide a flexible response.

Thereafter, the receiver terminal 320 may provide the "response 1B" to the sender terminal 310 based on the "response 1A". In this case, when the "response 1A" received from the AI server 330 is text, the "response 1B" may be provided to the caller terminal 310 after conversion to a voice file through text to speech (TTS) processing. On the other hand, when the "response 1A" received from the AI server 330 is a voice file, the receiver terminal 320 may provide the "response 1B" converted to voice to the caller terminal 310 based on the voice call. .

In addition, when the user of the sender terminal 310 has an additional query, as described above, the user of the sender terminal 310 performs an additional query request to the receiver terminal 320 , and the receiver terminal 320 provides a flexible response based on the AI server 330 . Information may be generated and provided to the caller terminal 310 .

*

Here, a method for specifying query information of the caller terminal may be required. As an example, when the response of the receiver terminal is delayed based on the inquiry to the sender terminal, service quality degradation may occur. In this case, when the scope of the query information of the sender terminal is wide, the information processing time of the AI server that receives the related information from the receiver terminal may be delayed, and based on this, delay may occur in service provision.

In consideration of the foregoing, referring to FIG. 4A , when the caller terminal 410 and the receiver terminal 420 perform an automatic answer based on a voice call, the receiver terminal 420 and the caller terminal 410 are related content can be determined. Here, the related content may be determined based on the characteristics or content of the receiver terminal 420 . As a more specific example, when the operator of the receiver terminal 420 sets the receiver terminal 420 based on the food industry, related content may be set based on related information. Referring to FIG. 4B , the related content may be set to any one of order-related, consultation-related, and business hours-related. However, this is only one example, and related content may be set in various ways, and is not limited to the above-described embodiment. Also, as an example, when the operator of the receiver terminal 420 sets the receiver terminal 420 based on health-related business, related content may be set based on related information. Referring to FIG. 4C , the related content may be set to any one of sports related, counseling related, business hours related, and visiting method related. However, this is only one example, and related content may be set in various ways, and is not limited to the above-described embodiment. Also, as an example, when the operator of the receiver terminal 420 sets the receiver terminal 420 based on sales related to product sales, related content may be set based on related information. Referring to FIG. 4D , the related content may be set to any one of shopping item related, consultation related, and business hours related. However, this is only one example, and related content may be set in various ways, and is not limited to the above-described embodiment.

That is, as described above, related contents may be determined based on the characteristics and contents of the recipient terminal 420 , and specific related contents among a plurality of related contents are based on consultation between the sender terminal 410 and the recipient terminal 420 . can be decided. For example, referring to FIG. 4A , the receiver terminal 420 provides a plurality of related content information in an automatic response, and the sender terminal 410 determines specific related content and provides the corresponding information to the receiver terminal 420 . can Thereafter, the receiver terminal 420 may transmit the determined related content information to the AI server 430 . In this case, the AI server 430 may process each of the related contents in an integrated form or exist separately for each related content, and is not limited to the above-described embodiment. However, since the AI server 430 can check the response to the inquiry request from the caller terminal 410 based on the determined information based on the related content, the information processing time may be reduced. Then, the sender terminal 410 provides a query based on the determined related content to the receiver terminal 420, and the receiver terminal 420 responds to the query through the AI server 430 based on the query from the sender terminal 410. A response may be obtained and provided, and a specific method may be the same as that of FIG. 3 .

As another example, after the voice call between the caller terminal and the receiver terminal is received based on an automatic answer, it may be converted into a data call. Referring to FIG. 5A , the receiver terminal 520 inquires the caller terminal 510 for data call transfer, and if the caller terminal 510 accepts, ends the voice call, and a data call (e.g. Voice over Internet Protocol (VOIP)) ) can be converted to Here, the sender terminal may provide information on whether to accept to the receiver terminal 520 based on a voice response or a key input method.

For example, when the receiver terminal 520 maintains a voice call with the caller terminal 510 differently from the existing ARS server, the receiver terminal 520 may not receive a voice call to another caller terminal. In consideration of the above, the receiver terminal 520 needs to convert a voice call into a data call. In addition, when providing a response based on a query from the caller terminal 510, there is a need to store related information in a database and perform voice recognition or other data processing, but providing information based on a voice call In some cases, there may be limitations in data processing. That is, the receiver terminal 520 has a limit in processing the query of the caller terminal 510 based on the voice call, and conversion to the data call may be performed in consideration of the above points.

As a more specific example, referring to FIG. 5B , the receiver terminal 520 may perform data call conversion with the caller terminal 510 based on a preset time. That is, the receiver terminal 520 processes the query of the caller terminal 510 for a certain period of time, such as a short answer, and when a preset time elapses after automatic connection, considers the voice call of another caller terminal 510 and tries to switch the data call. can do. As an example, the receiver terminal 520 may notify the caller terminal 510 of a reference time for a voice call after a preset time after automatic connection and transmit a request for whether to switch a data call. Thereafter, if the caller terminal 510 accepts this, it may switch to a data call and process the query of the caller terminal 510 .

In addition, as an example, the receiver terminal 520 may perform data call conversion based on the query content of the caller terminal. That is, when a predetermined time is required to respond to a query or a predetermined visual information is required to be provided, data call conversion can be performed. For example, data currency conversion may be performed to provide terms and conditions, receive specific user opinions, explicitly confirm specific items, conclude a contract, remittance, exchange, set the disclosure scope of information, etc., but the present invention is limited thereto. not.

As another example, referring to FIG. 5C , the receiver terminal 520 (or the AI server 530 ) may request conversion to a data call in consideration of data processing for the inquiry and response of the caller terminal 510 . For example, the AI server 530 may perform a data processing process such as storing related information in a database or converting voice information into text in a process of providing a response based on a query from the caller terminal 510 . Here, there may be a limit in processing information based on a voice call, and the AI server 530 may request conversion to a data call in consideration of the above-mentioned points. For example, voice data received in a voice call connection state may have a larger capacity than voice data received in a data call connection state, or data processing may be complicated. In order to solve this problem, data call conversion may be requested for data processing efficiency at the AI server end or the receiver end.

For example, the AI server 530 may perform a data call transfer request to the receiver terminal 520 in response to a query or through a separate message. In addition, the receiver terminal 520 may also request data call conversion from the caller terminal 510 through a response or a separate message. That is, it may be converted to a data call in consideration of a response or data processing provided, and is not limited to the above-described embodiment. Here, after being converted to a data call, the receiver terminal 520 and the AI server 530 may process a large amount of data. Therefore, after being converted to a data call, the receiver terminal 520 and the AI server 530 may process high-capacity data such as images or videos as well as information through voice and provide them to the caller terminal 510, and the caller terminal is more A specific response can be obtained.

As another example, the data call may be performed based on a third messenger platform. The receiver terminal may process the query of the sender terminal based on data communication with the AI server in the same manner as described above. In addition, since the receiver terminal has a limit in building its own platform for data call, data call can be performed through a third-party messenger platform.

As a more specific example, referring to FIG. 6A , the receiver terminal 620 may request data call transfer from the caller terminal 610 and receive acceptance of the data call from the caller terminal 610 as a response. Thereafter, the receiver terminal 620 may transmit a data call provision request to the third messenger platform 640 based on the information of the caller terminal 610 . Thereafter, the third messenger platform 640 may determine whether to accept the data call provision request based on the request, and transmit the information to the receiver terminal 620 . Here, when the data call provision is accepted by the third messenger platform 640 , the receiver terminal 620 may perform a data call based on the caller terminal 610 and the third messenger platform 640 . That is, the receiver terminal 620 obtains response information through the AI server 630 to the inquiry of the caller terminal 610, and the data call can be performed through a third messenger platform, through which the caller terminal 610 can provide flexible AI assistant services.

As another example, when performing a data call through a third messenger platform, the sender terminal and the receiver terminal need to check identification information on the third messenger platform (e.g. friend relationship). That is, the sender terminal and the receiver terminal. The terminal recognizes mutual identification information based on the third messenger platform, and there is a need for approval for identification information. For example, the third messenger platform may not accept the data call conversion when the calling terminal and the receiving terminal do not recognize mutual identification information.

However, as an example, the third messenger platform may accept the data call based on the record information of the sender terminal and the receiver terminal even if the caller terminal and the receiver terminal do not recognize each other's identification information. The third messenger platform may perform mutual confirmation based on the past call records of the caller terminal and the receiver terminal, and may provide a data call by accepting a data call based on this. As a specific example, the receiver terminal may transmit the phone number of the caller terminal to the third messenger platform. In this case, the third messenger platform may request whether or not to send a data call to the caller terminal based on the received information, and may perform a data call connection based on the acceptance of the caller terminal. That is, the third messenger platform may accept the data call connection based on the fact that the caller terminal and the receiver terminal are users who are approved based on identification information in the third messenger platform, or that the receiver terminal is the receiver of the corresponding number.

Also, as an example, referring to FIG. 6B , the receiver terminal 620 may transmit a data call transfer request to the caller terminal 610 while also delivering a data call-related third messenger platform information provision request. For example, if the receiver terminal 620 recognizes the identification information of the third messenger platform as described above or if there is a past record, acceptance of the data call may be performed based on this. On the other hand, when the above-described information does not exist in the receiver terminal 620 , the receiver terminal 620 may request information for a data call together while transmitting the data call transfer request to the caller terminal 610 . For example, when the caller terminal 610 first attempts a voice call to the receiver terminal 620 , the receiver terminal 620 may not have information related to the caller terminal 610 , and the receiver terminal 620 may provide data Information for a call may be requested from the caller terminal 610 . As an example, the information for the data call may be a request for identification information confirmation and approval based on the third platform 640. (e.g. receiving a response after requesting a friend relationship agreement) That is, the receiver terminal 620 is a third messenger platform ( 640), it is possible to request related information so as to perform a data call with the caller terminal 610, and receive a response thereto to perform preliminary preparation for a data call. Thereafter, the receiver terminal 620 transmits the data call provision request to the third messenger platform 640 and performs a data call connection with the caller terminal 610 based on the acceptance of the third messenger platform 640 . have.

Also, as an example, referring to FIG. 7A , when a data call is converted, related information may be displayed through a messenger as well as a data call. When the data call is switched, information on query details along with information on the receiver terminal may be provided to the calling terminal through the third messenger platform. Also, as an example, not only information on query details but also various related information may be provided through the third messenger platform. As an example, the provided information may be an image or a video, and more specific information may be provided to the caller terminal through the above-mentioned bar.

Also, as an example, referring to FIG. 7B , the sender terminal may also check information on related content through the third messenger platform, and may change the information on this through the third messenger platform. That is, more specific data information may be provided to the caller terminal through the third messenger platform, and through this, a flexible answer may be provided to the caller terminal.

Here, considering a more specific embodiment, when user A (sender terminal) makes a call to Chinese house B (receiver terminal), a voice call is connected (received), and a simple order response is performed based on the AI server can be As an example, the AI server may determine when a call is delayed or data processing capacity is increased, and inquire whether to switch a data call. At this time, if user A accepts, the messenger account of the operator of Chinese house B connects the data call to user A through a messenger, and the related data can be provided through the messenger.

8 is a flowchart illustrating a method of providing an artificial intelligence assistant service through a voice call (voice call) according to an embodiment of the present specification.

Referring to FIG. 8 , the first terminal may receive a voice call from the second terminal and perform automatic connection (S810). Here, the first terminal may be a receiver terminal, and the second terminal may be a caller terminal. . Next, after automatic connection is performed, the first terminal may receive a first query request message from the second terminal (S820). Thereafter, the first terminal sends a second query request message based on the first query request message. It may be transmitted to the AI server. (S830) In this case, the first query request message may be transmitted from the second terminal to the first terminal by voice based on the voice call. Here, the first terminal may transmit the converted text information to the AI server as the second query request message by performing STT (Speech To Text) processing on the first query request message. Also, as an example, the first terminal may transmit voice file information generated based on the first query request message to the AI server as the second query request message, and the embodiment is not limited thereto.

Next, the first terminal may receive a first query response message based on the second query request message from the AI server. (S840) Thereafter, the first terminal receives a second query response message based on the first query response message can be transmitted to the second terminal. (S850) In this case, the first query response message delivered by the AI server to the first terminal is based on the text information generated based on the second query request message and the second query request message. It may include at least one of the generated voice file information. The first terminal may generate a second query response message based on the first query response message received from the AI server, and may provide the generated second query response message to the second terminal by voice based on a voice call.

Also, as an example, the first terminal may transmit a request message for converting a voice call into a data call to the second terminal. In this case, the first terminal may receive an acceptance message in response to the request message from the second terminal, and may convert the voice call into a data call based on the acceptance message. At this time, as described above, the first terminal determines whether a preset time has elapsed after the automatic connection with the second terminal is performed, and when the set time has elapsed after the automatic connection with the second terminal is performed, a request message is sent. It can be transmitted to the second terminal, as described above. As another example, the first terminal or the AI server may determine whether data call conversion is necessary based on the data processing capability. In this case, when the first terminal or the AI server intends to convert the voice call into a data call, the first terminal may transmit a request message to the second terminal.

As another example, the data call may be performed based on a third messenger platform. In this case, as described above, the data call may be performed based on identification information on the third messenger platform of the first terminal and identification information on the third messenger platform of the second terminal. For example, when mutual identification information is recognized and approved, data call connection may be performed, as described above.

As another example, when the first terminal performs a data call based on the third messenger platform, it transmits a data call provision request message to the third messenger platform and receives a data call acceptance message from the third messenger platform Then, a data call can be performed, as described above. Also, as an example, the first terminal may transmit at least one piece of related content information related to the first terminal to the second terminal after automatic connection is performed based on FIGS. 4A to 4D described above. Here, the second terminal may select a specific content based on at least one piece of related content information, and transmit the information to the first terminal. Also, the second terminal may generate the above-described first query request message based on the selected content, as described above.

The embodiments described above may be at least partially implemented as a computer program and recorded in a computer-readable recording medium. A computer-readable recording medium in which a program for implementing the embodiments is recorded includes all types of recording devices in which computer-readable data is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, and optical data storage devices. In addition, the computer-readable recording medium may be distributed in a network-connected computer system, and the computer-readable code may be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the present embodiment may be easily understood by those skilled in the art to which the present embodiment belongs.

Although the present specification described above has been described with reference to the embodiments shown in the drawings, it will be understood that this is merely exemplary, and that various modifications and variations of the embodiments are possible therefrom by those of ordinary skill in the art. However, such modifications should be considered to be within the technical protection scope of the present specification. Accordingly, the true technical protection scope of the present specification should be defined to include other implementations, other embodiments, and equivalents to the claims by the spirit of the appended claims.

The present specification has the advantage of providing a flexible response by generating and providing a response corresponding to the request by analyzing the request of the sender terminal through artificial intelligence, and can be used in industry.

Claims

In the operating method of the first terminal performing a question and answer through a voice call,

receiving a voice call from a second terminal and performing automatic connection;

receiving a first query request message from the second terminal after the automatic connection is performed;

transmitting a second query request message based on the first query request message to an artificial intelligence (AI) server;

receiving a first query response message based on the second query request message from the AI server; and

and transmitting a second query response message based on the first query response message to the second terminal.
The method of claim 1,

The first query request message is transmitted to the first terminal by voice based on the voice call,

The second query request message delivered by the first terminal to the AI server is generated based on text information converted by STT (Speech To Text) processing on the first query request message and the first query request message. A method of operating a first terminal, including at least one of the voice file information.
3. The method of claim 2,

The first query response message delivered by the AI server to the first terminal is at least one of text information generated based on the second query request message and voice file information generated based on the second query request message. including,

The first terminal generates the second query response message based on the first query response message received from the AI server, and uses the generated second query response message as a voice based on the voice call. A method of operating the first terminal, provided to the terminal.
The method of claim 1,

transmitting a request message for converting the voice call into a data call to the second terminal;

receiving an acceptance message in response to the request message from the second terminal; and

Converting the voice call to the data call based on the acceptance message; further comprising, the operating method of the first terminal.
5. The method of claim 4,

Further comprising; determining whether a preset time has elapsed after the automatic connection with the second terminal is performed;

When the set time elapses after the automatic connection with the second terminal is performed, the request message is transmitted to the second terminal, the operating method of the first terminal.
5. The method of claim 4,

Determining whether the data call conversion is necessary based on the data processing capability of the first terminal; further comprising,

When the first terminal determines that the data call conversion is necessary based on the data processing capability, transmitting the request message to the second terminal.
5. The method of claim 4,

The data call is performed based on a third messenger platform,

The method of operating the first terminal, wherein the data call is performed based on identification information in the third messenger platform of the first terminal and identification information in the third messenger platform of the second terminal.
8. The method of claim 7,

transmitting a data call provision request message to the third messenger platform when the first terminal performs the data call based on the third messenger platform; and

Receiving an acceptance message for the data call from the third messenger platform; further comprising,

When the acceptance message is received, the data call is performed based on the third messenger platform.
The method of claim 1,

transmitting at least one piece of related content information related to the first terminal to the second terminal after the automatic connection is performed;

Receiving the related content information selected by the second terminal based on the at least one piece of related content information;

The method of operating the first terminal, wherein the first query request message is generated based on the related content information selected by the second terminal.
A computer program stored in a computer-readable medium to be combined with hardware to execute the method according to any one of claims 1 to 9.