KR20230142265A - System and method for processing phone reservations based on artificial intelligence - Google Patents

Abstract

An artificial intelligence phone reservation system according to an embodiment of the present invention includes an AI reservation call server that infers and generates query intents related to reservations from the call contents of the customer terminal; After extracting the reservation event (reservation query) sent from the AI reservation call server from the reservation manual, the input operation of the input device is controlled so that the reservation is entered into the reservation platform according to the extracted reservation manual, and the reservation processing information is stored in the AI reservation. It includes a reservation operation terminal provided by a call server, and the AI reservation call server generates an answer to the reservation inquiry based on the reservation processing information transmitted from the reservation operation terminal based on the learned data, and then uses voice language. It is characterized in that it is converted to and provided to the customer terminal.

Description

Artificial intelligence phone reservation system and method {System and method for processing phone reservations based on artificial intelligence}

The present invention relates to an artificial intelligence phone reservation system and method.

Recently, phone call technology using AI, where AI takes the phone and answers it or makes a call and has a conversation, is becoming more and more advanced. However, in the case of humans, it is possible to make a reservation based on the information displayed on the screen while placing a PC reservation application on the screen and making a call using the mouse and keyboard, whereas AI phone call technology requires a reservation to be made. This is a reality that is impossible without the API provided by the application.

KR 10-2004-0097814 A KR 10-2012-0073170 A KR 10-2019-0109614 A

The purpose of the present invention is to provide an artificial intelligence phone reservation system and method that can solve conventional problems.

An artificial intelligence phone reservation system according to an embodiment of the present invention to solve the above problem includes an AI reservation call server that infers and generates query intents related to reservations from the call contents of the customer terminal; After extracting the reservation event (reservation query) sent from the AI reservation call server from the reservation manual, the input operation of the input device is controlled so that the reservation is entered into the reservation platform according to the extracted reservation manual, and the reservation processing information is stored in the AI reservation. It includes a reservation operation terminal provided by a call server, and the AI reservation call server generates an answer to the reservation inquiry based on the reservation processing information transmitted from the reservation operation terminal based on the learned data, and then uses voice language. It is characterized in that it is converted to and provided to the customer terminal.

In one embodiment, the AI reservation call server includes a call connection unit that supports call connection (incoming and outgoing) with the customer terminal; a conversion unit that converts the call content related to the reservation of the customer terminal transmitted through the call connection unit into text; It includes an intent inference unit that infers a reservation inquiry based on data learned from the call contents converted into text.

In one embodiment, the AI reservation call server further provides an answer content unit that generates and provides answers to reservation inquiries based on data learned in a learning result database based on reservation processing information transmitted from the reservation operation terminal. Includes.

In one embodiment, the reservation operation terminal receives a reservation event (reservation inquiry) sent from the AI reservation call server, and extracts and provides a reservation command related to the reservation event from the reservation manual provided in the reservation manual DB. /sender; When reception of the reservation event is confirmed, a platform execution unit that executes a preset reservation platform; and a device control unit that controls the input operation of the input device so that reservation information is input into the reservation platform according to the reservation command.

The artificial intelligence phone reservation method according to an embodiment of the present invention to solve the above problem includes the steps of connecting (receiving and making) a call to a customer terminal in an AI reservation call server, and then converting the call content related to the reservation into text; A step of generating and providing a reservation intent that infers a reservation inquiry based on data learned about reservation-related inquiries from the call contents converted into text; After the reservation operation terminal extracts the reservation event (reservation inquiry) sent from the AI reservation call server from the reservation manual, it controls the input operation of the input device so that the reservation information is entered into the reservation platform according to the reservation command of the extracted reservation manual. step; And a step where the AI reservation call server extracts an answer corresponding to the reservation processing result processed by the reservation operation terminal from the learning result database unit, then converts the extracted answer into a voice and provides it to the customer terminal.

In one embodiment, the step of generating and providing the inferred reservation intent includes the process of understanding the flow of the call content and learning the object to be reserved and questions related to the reservation.

By using the artificial intelligence phone reservation system and method according to an embodiment of the present invention, even if there is no API provided by the reservation application, a person can make a reservation by looking at the eye and making a call through mouse and keyboard control and image recognition technology. There is an advantage in that the same effect can be obtained.

1 is a device configuration diagram of an artificial intelligence phone reservation system according to an embodiment of the present invention.
Figure 2 is a detailed configuration diagram of the AI reservation call server and reservation operation terminal shown in Figure 1.
Figure 3 is an example diagram showing the inference process in the intent inference unit shown in Figure 2.
Figure 4 is an example diagram showing a machine learning process in the machine learning learning unit shown in Figure 2.
Figure 5 is a flowchart explaining an artificial intelligence phone reservation method according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. In addition, the components and 'parts' may be implemented to regenerate one or more CPUs within the device or secure multimedia card.

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

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as:

Hereinafter, the artificial intelligence phone reservation system and method according to an embodiment of the present invention will be described in more detail based on the attached drawings.

Figure 1 is a device configuration diagram of an artificial intelligence phone reservation system according to an embodiment of the present invention, Figure 2 is a detailed configuration diagram of the AI reservation call server and reservation operation terminal shown in Figure 1, and Figure 3 is in Figure 2 It is an example diagram showing the inference process in the intent inference unit shown, and FIG. 4 is an example diagram showing the machine learning process in the machine learning learning unit shown in FIG. 2.

First, as shown in FIG. 1, the artificial intelligence phone reservation system 100 according to an embodiment of the present invention includes an AI reservation call server 200 and a reservation operation terminal 300.

Each component is connected by a network, where the network is a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband (BBN). network), the Internet, etc. may include one or more arbitrary networks.

Additionally, the network may include any one or more of network topologies including, but not limited to, a bus network, star network, ring network, mesh network, star-bus network, tree or hierarchical network, etc. No.

The AI reservation call server 200 may be configured to infer and generate query intents related to reservations from the call contents of the customer terminal.

In addition, the AI reservation call server 200 returns reservation processing information for the query intent from the reservation operation terminal 300, which will be described later, processes the reservation processing information into response information for the query intent, and then processes the reservation processing information into answer information for the query intent. It may be configured to transmit the answer information to the customer through a mechanical sound.

More specifically, the AI reservation call server 200 includes a call connection unit 210, a conversion unit 220, an intent inference unit 230, an answer content unit 240, a machine learning learning unit 250, and a learning result. Includes database 260.

The call connection unit 210 supports call connection (incoming and outgoing calls) of the customer terminal 10.

The conversion unit 220 may be configured to convert the content of a call related to a reservation of a customer terminal transmitted through the call connection unit 210 into text.

Additionally, the conversion unit 220 may be configured to convert text information, which is an answer related to a reservation provided by the answer content unit 240, which will be described later, into voice information.

Accordingly, the conversion unit 220 may be configured to have the SST algorithm and the TTS algorithm installed.

Next, the intent inference unit 230 may be configured to infer a reservation query based on data learned in the learning result database 260, which describes the query content related to the reservation from the call content converted to text. .

In addition, the intent inference unit 230 can apply pattern-based machine learning natural language processing technology to recognize and process slang, abbreviations, buzzwords, etc. to understand all machine-learning sentences.

In addition, because it is possible to understand languages from all over the world by learning them, it is possible to answer in the language the user wants even if he or she uses at least one language. For example, if the inquirer uses a mixture of Korean, Chinese, and English, an answer is possible, and in this case, the answer is provided in the language selected by the inquirer.

Additionally, the intent inference unit 230 includes an inference engine capable of inferring a question through typo analysis and spacing analysis.

Next, the answer content unit 240 provides an answer to the reservation inquiry based on the reservation processing information transmitted from the reservation operation terminal 300, which will be described later, based on data learned in the learning result database 260, which will be described later. It may be a configuration that is created and provided.

Next, the machine learning learning unit 250 is a component that understands the flow of call content and learns the target for reservation and questions related to reservation, and makes reservations based on machine learning, machine learning VCS (supervised learning), and self-features. Learn about the target audience and questions related to reservations.

The machine learning learning unit 250 implements pattern-based machine learning natural language processing technology and is oriented toward RPA (Robotic Process Automation) and deep learning.

Additionally, the machine learning learning unit 250 may perform learning based on the results inferred from the intent inference unit 230.

Next, the learning result database unit 260 builds a database of the results of learning the inferred reservation questions and builds a database of the results of learning the answers to the reservation questions.

Next, the reservation operation terminal 300 extracts the reservation event (reservation inquiry) sent from the AI reservation call server 200 from the reservation manual, and then inputs the input device so that the reservation is entered into the reservation platform according to the extracted reservation manual. It may be a configuration that controls the operation.

More specifically, the reservation operation terminal 300 includes a reception unit 310, a reservation manual DB 320, a device control unit 330, and a platform execution unit 340.

The receiving/sending unit 310 receives a reservation event (reservation inquiry) sent from the AI reservation call server 200, and extracts a reservation command related to the reservation event from the reservation manual provided in the reservation manual DB 320. This may be provided to the device control unit 330, which will be described later.

The reservation manual DB 320 may be configured to register and manage a reservation manual that records reservation commands related to reservations.

The device control unit 330 may be configured to control the input operation of the input device so that reservation information is input into a reservation platform (application or web) described later according to a reservation command.

The device control unit 330 checks whether an input device, such as a mouse, keyboard, and camera, is connected, and when the connection is activated, controls the input operation of the corresponding input device according to the reservation command.

The platform executing unit 340 may be configured to execute a preset reservation platform when reception of a reservation event is confirmed from the receiving unit 310.

Figure 3 is a flowchart illustrating an artificial intelligence phone reservation method according to an embodiment of the present invention.

As shown in Figure 3, the artificial intelligence phone reservation method (S700) according to an embodiment of the present invention connects (receives and makes) a call with the customer terminal 10 in the AI reservation call server 200, and then makes a reservation. Convert the related call contents into text (S710).

Afterwards, reservation intents are generated (S720) by inferring the reservation inquiry based on the data learned from the call contents converted into text.

The S720 process is a process of understanding the flow of the call content and learning the questions related to the reservation and reservation, using machine learning, machine learning VCS (supervised learning), and self-characteristics. It includes the process of learning the questions asked.

Next, the reservation operation terminal 300 extracts the reservation event (reservation query) transmitted from the AI reservation call server 200 from the reservation manual, and then inputs the reservation information into the reservation platform according to the reservation command in the extracted reservation manual. Controls the input operation of the input device (S730).

Afterwards, the AI reservation call server 200 extracts the answer corresponding to the reservation processing result processed by the reservation operation terminal 300 from the learning result database unit 260, converts the extracted answer into voice, and provides it to the customer terminal. (S740).

Using the artificial intelligence phone reservation system and method according to an embodiment of the invention is the same as making a reservation by looking at the eyes and making a call through mouse and keyboard control and image recognition technology even if there is no API provided by the reservation application. There is an advantage in that the effect can be obtained easily.

The “unit” used in one embodiment of the present invention may be implemented as a hardware component, a software component, and/or a combination of hardware components and software components. For example, devices and components described in embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general-purpose or special-purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing unit includes an operating system (OS) and one or more processors running on the operating system.

Can run software applications. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used by any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and thus stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to an embodiment of the present invention 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., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of 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 optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. 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.

The above-described content can be modified and modified by anyone skilled in the art without departing from the essential characteristics of the present invention. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be construed as being included in the scope of rights of the present invention.

100: Artificial intelligence phone reservation system
200: AI reservation call server
300: Reservation operation terminal

Claims (6)

An AI reservation call server that generates query intents related to reservations by inferring them from the call contents of the customer terminal;
After extracting the reservation event (reservation query) sent from the AI reservation call server from the reservation manual, the input operation of the input device is controlled so that the reservation is entered into the reservation platform according to the extracted reservation manual, and the reservation processing information is stored in the AI reservation. It includes a reservation operation terminal provided by a call server,
The AI reservation call server is
An artificial intelligence phone reservation system that generates answers to reservation inquiries based on the reservation processing information transmitted from the reservation operation terminal, converts them into voice language, and provides them to the customer terminal. .
According to paragraph 1,
The AI reservation call server is
A call connection unit that supports call connection (incoming and outgoing) with the customer terminal;
a conversion unit that converts the call content related to the reservation of the customer terminal transmitted through the call connection unit into text;
An artificial intelligence phone reservation system that includes an intent inference unit that infers reservation inquiries based on data learned from reservation-related inquiries from call contents converted to text.
According to paragraph 2,
The AI reservation call server is
An artificial intelligence telephone reservation system further comprising an answer content unit that generates and provides answers to reservation inquiries based on data learned in a learning result database based on reservation processing information transmitted from the reservation operation terminal.
According to paragraph 3,
The reservation operation terminal is
A receiving/sending unit that receives a reservation event (reservation inquiry) sent from the AI reservation call server, extracts and provides a reservation command related to the reservation event from the reservation manual provided in the reservation manual DB;
When reception of the reservation event is confirmed, a platform execution unit that executes a preset reservation platform;
An artificial intelligence phone reservation system comprising a device control unit that controls an input operation of an input device so that reservation information is input into the reservation platform according to the reservation command.
After connecting (receiving and sending) a call to a customer terminal at the AI reservation call server, converting the call content related to the reservation into text;
A step of generating and providing a reservation intent that infers a reservation inquiry based on data learned about reservation-related inquiries from the call contents converted into text;
After the reservation operation terminal extracts the reservation event (reservation inquiry) sent from the AI reservation call server from the reservation manual, it controls the input operation of the input device so that the reservation information is entered into the reservation platform according to the reservation command of the extracted reservation manual. step; and
Artificial intelligence phone reservation comprising the step of the AI reservation call server extracting the answer corresponding to the reservation processing result processed by the reservation operation terminal from the learning result database unit, converting the extracted answer into voice and providing it to the customer terminal. method.
According to clause 5,
The step of generating and providing the inferred reservation intent is
An artificial intelligence phone reservation method that includes the process of understanding the flow of the call contents, learning the person you want to make a reservation for, and questions related to the reservation.