KR20220023208A - Terminal devices running voice recognition-based AI agent programs and how they work - Google Patents

Abstract

A terminal device running a voice recognition-based AI agent program according to an embodiment of the present invention comprises: a voice matching unit filtering voice frequency of voice information inputted by using a frequency band filter and then determining identity thereof with preset voice frequency; a voice-character transformation unit transforming the voice information into a character string; an instruction setup unit setting an instruction related to at least one among an online product order, an emergency rescue request and a web search; an instruction extraction unit extracting an instruction, identical to the instruction set by the instruction setup unit, from the character string resulted from the transformation of the voice-character transformation unit; and an AI agent unit separating the instruction, extracted by the instruction extraction unit, into a search instruction and a running instruction, then accessing a URL related to the running instruction and then searching for information and performing an action in correspondence with the search instruction. The present invention can easily treat the web search, an emergency rescue, a shopping, a purchase order and a payment.

Description

Terminal devices running voice recognition-based AI agent programs and how they work

The present invention relates to a terminal device that executes an AI agent program based on voice recognition.

Recently, with the rapid development of information and communication technology, interest in and demand for Internet of Things (IoT) technology is rapidly increasing. The IoT may be defined in various ways depending on the viewpoint from which it is viewed. However, in essence, IoT is an intelligent information and communication technology or service that enables communication between people and things and between things and things by connecting various things through a communication network based on the Internet.

These IoT technologies are being applied in various technology fields such as smart home, smart health, and smart car. In particular, research on smart home services in which IoT technology is grafted into home network systems is being actively conducted.

Smart home service refers to the overall system that seeks to improve living standards through IoT devices with Internet of Things (IoT) functions in a residential environment in which a communication network is established. Home appliances such as TVs/refrigerators/air conditioners, energy consumption devices such as electricity/water, and security services are connected through a communication network to allow users to remotely access situation information in the house through a smart phone or voice controller (or AI speaker). to enable real-time confirmation and control. In particular, in recent years, smart home services that can remotely control IoT devices in the house through an AI speaker are increasing.

The AI speaker can provide an interactive AI assistant service using voice recognition technology and artificial intelligence technology. Here, the conversational AI assistant service literally means a service in which artificial intelligence performs the role of a speaker's assistant. These AI speakers provide various services such as personal schedule management service, SNS management service, app execution service, internet shopping service, email management service, messenger management service, multimedia playback service, weather/traffic/travel information provision service, IoT device control service, etc. can provide

On the other hand, in the case of the previously released voice recognition AI program and AI speaker, various voices and voice characteristics from the unique physical and cultural characteristics of each person and various patterns of conversations expressed including regional dialects are smoothly recognized and commanded. There is still a certain limit to the acceptance of AI products, and consumers of interactive AI products initially purchase or use them out of curiosity, but are unable to continue using them anymore due to disappointment and stress caused by frequent errors.

There is a clear difference between the human voice and the various guitar sound patterns (music sounds, noises, object sounds, animal sounds, etc.) The released AI speech recognition program is relatively easy to separate, and it has been confirmed that the recognition rate for short words of less than 2 seconds is at a considerable level. As a trend to utilize, in the case of smartphones, Google's Android and Apple's IOS are set as the default OS and are sold. It is forced to use it after calling it first with a word, and it is also quite unnatural to constantly mention the brand name of the developer, that is, in the case of Google's Android voice recognition AI, "Hi, Google" or "Hello, In the case of Apple's Google, it is forced to call the voice recognition AI when it is first said "Hi, Shiri, or Hello Shiri", and it is also set as the default OS at the time of shipment and is regulated so that users cannot delete or replace it arbitrarily. am.

Accordingly, the present invention is a terminal device for executing a voice recognition-based AI agent program in which the user perfectly collects commands and executes commands not only with short words, but also with long sentences linked between words, rather than prior call actions and interactive commands. would like to provide

Unexamined Patent Publication No. 10-2020-0060331

An object of the present invention is to provide a terminal device that executes a voice recognition-based AI agent program that can solve the problems of the prior art.

A terminal device for executing an AI agent program based on voice recognition according to an embodiment of the present invention for solving the above problem filters the voice frequency of the input voice information using a frequency band filter, and then includes a preset voice frequency and a voice matching unit that determines the identity of ; a voice-text converter converting the voice information into a character string; a command setting unit for setting commands related to at least one of an online product order, an emergency rescue request, and a web search; a command extraction unit for extracting the same command as the command set in the command setting unit within the character string converted by the voice-text conversion unit; and after separating the command extracted by the command extraction unit into a search command and an execution command, accessing a URL associated with the execution command, and searching and executing information corresponding to the search command.

In order to solve the above problems, the method of operating a terminal device for executing an AI agent program based on voice recognition according to an embodiment of the present invention is to filter the voice frequency of the input voice information using a frequency band filter in the voice matching unit. thereafter, determining the sameness with a preset voice frequency; converting the voice information into a character string in a voice-text converter; setting a command related to at least one of an online product order, an emergency rescue request, and a web search in the command setting unit; extracting the same command as the command set in the command setting unit from the string converted by the command extraction unit; and after separating the command extracted from the command extraction unit into a search command and an execution command in the AI agent unit, accessing the URL associated with the execution command, and searching for and executing information corresponding to the search command do.

Using a terminal device executing a voice recognition-based AI agent program according to an embodiment of the present invention, the user sets his or her own command and then easily processes web search, emergency rescue, shopping/purchase order/payment There are advantages to being able to

1 and 2 are diagrams illustrating an execution screen of a terminal device executing an AI agent program based on voice recognition according to an embodiment of the present invention.
3 is a block diagram illustrating a detailed configuration of a terminal device executing an AI agent program based on voice recognition according to an embodiment of the present invention.
4 is a flowchart illustrating a method of operating a terminal device for executing an AI agent program based on voice recognition according to an embodiment of the present invention.

It should be noted that the technical terms used in the present invention are only used to describe specific embodiments, and are not intended to limit the present invention. In addition, the technical terms used in the present invention should be interpreted as meanings generally understood by those of ordinary skill in the art to which the present invention belongs, unless otherwise specifically defined in the present invention, and excessively comprehensive It should not be construed in the meaning of a human being or in an excessively reduced meaning. In addition, when the technical term used in the present invention is an incorrect technical term that does not accurately express the spirit of the present invention, it should be understood by being replaced with a technical term that can be correctly understood by those skilled in the art. In addition, the general terms used in the present invention should be interpreted according to the definition in the dictionary or according to the context before and after, and should not be interpreted in an excessively reduced meaning.

Also, the singular expression used in the present invention includes the plural expression unless the context clearly dictates otherwise. In the present invention, terms such as “consisting of” or “comprising” should not be construed as necessarily including all of the various components or various steps described in the invention, and some components or some steps may not be included. It should be construed that it may further include additional components or steps.

Also, terms including ordinal numbers such as first, second, etc. used in the present invention may be used to describe the elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in the description of the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, it should be noted that the accompanying drawings are only for easy understanding of the spirit of the present invention, and should not be construed as limiting the spirit of the present invention by the accompanying drawings.

Hereinafter, a terminal device executing the AI agent program based on voice recognition according to an embodiment of the present invention will be described in more detail with reference to the accompanying drawings.

1 and 2 are diagrams illustrating an execution screen of a terminal device executing a voice recognition-based AI agent program according to an embodiment of the present invention, and FIG. 3 is a voice recognition-based AI according to an embodiment of the present invention. It is a block diagram showing the detailed configuration of a terminal device that executes an agent program.

1 to 3 , the terminal device 100 executing the AI agent program based on voice recognition includes an input unit 101 , a communication unit 110 , a storage unit 120 , a display unit 130 , and a voice output unit. It is composed of a unit 140 and a control unit 150 .

Not all of the components of the terminal device 100 for executing the voice recognition-based AI agent program shown in FIG. 1 are essential components, and voice recognition-based AI has more components than those shown in FIG. The terminal device 100 for executing the agent program may be implemented, and the terminal device 100 for executing the AI agent program based on voice recognition may be implemented with fewer components.

The terminal device 100 for executing the voice recognition-based AI agent program is a smart phone, a portable terminal, a mobile terminal, a foldable terminal, a personal information terminal ( Personal Digital Assistant: PDA, PMP (Portable Multimedia Player) Terminal, Telematics Terminal, Navigation Terminal, Personal Computer, Notebook Computer, Slate PC, Tablet PC , ultrabook, wearable device (including, for example, watch-type terminal (Smartwatch), glass-type terminal (Smart Glass), HMD (Head Mounted Display), etc.), Wibro (Wibro) terminal, IPTV ( It can be applied to various terminals such as Internet Protocol Television) terminals, smart TVs, digital broadcasting terminals, AVN (Audio Video Navigation) terminals, A/V (Audio/Video) systems, flexible terminals, digital signage devices, etc. .

The input unit 101 may include a microphone for inputting an audio signal. The microphone processes external sound signals into electrical voice data. The processed voice data may be variously utilized according to a function being processed by the control unit (or an application program being executed). Meanwhile, various noise removal algorithms for removing noise generated in the process of receiving an external sound signal may be implemented in the microphone.

The communication unit 110 communicates with any internal component or at least one external terminal through a wired/wireless communication network. In this case, the external arbitrary terminal may include a server (not shown), another terminal (not shown), and the like. Here, as wireless Internet technologies, wireless LAN (WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband: Wibro), Wimax (World Interoperability for Microwave Access: Wimax), HSDPA (High Speed Downlink Packet Access) ), High Speed Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), etc. In this case, the communication unit 110 transmits and receives data according to at least one wireless Internet technology within a range including Internet technologies not listed above. In addition, short-range communication technologies include Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and Near Field Communication (NFC). , Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi (Wi-Fi), Wi-Fi Direct (Wi-Fi Direct), etc. may be included. In addition, the wired communication technology may include Power Line Communication (PLC), USB communication, Ethernet, serial communication, optical/coaxial cable, and the like.

Also, the communication unit 110 may mutually transmit information with an arbitrary terminal through a Universal Serial Bus (USB).

In addition, the communication unit 110 is a technology standard or communication method for mobile communication (eg, GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV -Enhanced Voice-Data Optimized or Enhanced Voice-Data Only (DO), Wideband CDMA (WCDMA), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), Long Term Evolution (LTE), LTE-A (Long Term Evolution-Advanced, etc.) transmits and receives radio signals to and from the base station, the server, and the other terminal on a mobile communication network constructed according to the same.

In addition, the communication unit 110 receives an artificial intelligence-based voice search and voice order program app, data related to the app, and the like, provided from a server connected to wired/wireless communication under the control of the control unit 150 .

The storage unit 120 stores various user interfaces (UIs), graphic user interfaces (GUIs), and the like.

In addition, the storage unit 120 stores data and programs necessary for the terminal device 100 to run the voice recognition-based AI agent program.

That is, the storage unit 120 stores a plurality of applications (application programs or applications) driven in the terminal device 100 that executes the voice recognition-based AI agent program, a voice recognition-based AI agent program. It is possible to store data and commands for the operation of the terminal device 100 to be executed. At least some of these applications may be downloaded from an external server through wireless communication. In addition, at least some of these application programs exist on the terminal device 100 executing the voice recognition-based AI agent program from the time of shipment for the basic function of the terminal device 100 executing the voice recognition-based AI agent program. can On the other hand, the application program is stored in the storage unit 120, installed in the terminal device 100 that executes the voice recognition-based AI agent program, and executes the voice recognition-based AI agent program by the control unit 150 may be driven to perform an operation (or function) of the terminal device 100 .

In addition, the storage unit 120 is a flash memory type (Flash Memory Type), a hard disk type (Hard Disk Type), a multimedia card micro type (Multimedia Card Micro Type), a card type memory (eg, SD or XD) memory, etc.), magnetic memory, magnetic disk, optical disk, RAM (Random Access Memory: RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory: ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), It may include at least one storage medium among Programmable Read-Only Memory (PROM). In addition, the terminal device 100 executing the voice recognition-based AI agent program operates a web storage that performs a storage function of the storage unit 120 on the Internet, or related to the web storage and may work.

In addition, the storage unit 120 stores the received word learning app (program) and data related to the corresponding app (program) under the control of the controller 150 .

The display unit (or display unit) 130 uses a user interface and/or a graphic user interface stored in the storage unit 120 and the control unit 150 under the control of the control unit 150 to display a variety of menu screens, etc. content can be displayed.

Here, the content displayed on the display unit 130 includes various text or image data (including various information data) and a menu screen including data such as icons, list menus, and combo boxes. Also, the display unit 130 may be a touch screen.

In addition, the display unit 130 includes a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display. (Flexible Display), a three-dimensional display (3D Display), an e-ink display (e-ink display), may include at least one of LED (Light Emitting Diode).

In addition, the display unit 130 displays a screen of the execution result of the English word memorization app under the control of the control unit 150 .

The audio output unit 140 outputs audio information included in a signal processed by the control unit 150 . Here, the audio output unit 140 may include a receiver, a speaker, a buzzer, and the like.

In addition, the voice output unit 140 outputs a guide voice generated by the control unit 150 .

In addition, the voice output unit 140 outputs voice information (or sound effects) corresponding to the execution result screen of the word learning app by the control unit 150 .

The controller (or microcontroller unit) 150 executes the overall control function of the terminal device 100 for executing the AI agent program based on the voice recognition.

In addition, the control unit 150 executes the overall control function of the terminal device 100 for executing the AI agent program based on voice recognition using the program and data stored in the storage unit 120 . The controller 150 may include RAM, ROM, CPU, GPU, and a bus, and the RAM, ROM, CPU, GPU, etc. may be connected to each other through a bus. The CPU may access the storage unit 120 to perform booting using the O/S stored in the storage unit 120 , and use various programs, contents, data, etc. stored in the storage unit 120 . Thus, various operations can be performed.

In addition, the control unit 150 is installed in the terminal device 100 for executing the artificial intelligence-based voice search and voice order program (app) provided from the server. In this case, the dedicated app may be an artificial intelligence-based voice search and voice order program.

In addition, when the dedicated app (or application) installed in the terminal device 100 executing the voice recognition-based AI agent program is selected (or touched/executed) according to the user's (voice or user touch/input), the The controller 150 executes the dedicated app and displays the app execution result screen on the display unit 130 .

The control unit 150 includes a voice matching unit 151 , a voice-text conversion unit 152 , a command setting unit 153 , a command extraction unit 154 , and an AI agent unit 155 .

The voice matching unit 151 filters the input voice frequency using a frequency band filter, and then outputs a voice recognition signal that recognizes a user through the sameness with a preset voice frequency.

The voice-text conversion unit 152 may be configured to convert the input voice into numbers and character strings when receiving a voice recognition signal from the voice matching unit 151 .

The command setting unit 153 functions to set a command that the user wants to use in a category such as order, web search, contact, etc. in a macro format.

Meanwhile, the macro-type command set in the command setting unit 153 may be classified into a search macro and an execution macro, and in the case of an execution macro, a URL address may be set together.

When a command recognized as an execution macro is set, the command setting unit 153 may automatically mark and set a URL address associated with the command. Also, the command setting unit 153 may store the command as a template composed of a combination of short and complex sentences.

Next, the command extraction unit 154 functions to extract the same command as the command set in the command setting unit from within the numbers and character strings converted by the voice-text conversion unit 152 .

The command extracting unit 154 may call a sentence template of preset transcription data according to the macro function set in the command setting unit 153 . In this case, the sentence template format is not limited to any one. The sentence template format may be implemented not only in a short sentence format but also in a format including a plurality of sentences.

For example, when voice data such as "call template no. 1" or "call template no. 1" is input, a template sentence designated as template No. 1 can be called from the saved template list.

Accordingly, the template may be called by a method of retrieving the contents recorded in the command setting unit 153 . That is, various and updatable template types can be used.

In this case, the template may be classified by serial number or by contextual keyword. Identification information for template classification, ie, a serial number or a keyword for each situation, may be preset by the user.

For example, in the state in which the terms 'yogiyo', 'app', 'restaurant', 'jajangmyeon', and 'search' are set in the order category of the command setting unit 153, the user says "Search for a jjajangmyeon restaurant in Yogiyo" When a voice is input, the command extraction unit 154 extracts terms such as 'yogiyo', 'app', 'restaurant', 'jajangmyeon', and 'search'.

Next, the AI agent unit 155 separates the search command and the execution command among the commands extracted from the command extraction unit 153, accesses the URL associated with the execution command, and searches for information corresponding to the search command. function.

The AI agent unit 155 may have a chatbot function, and may support a voice service by providing result information to the user after execution and search results according to commands.

In addition, when the user's voice information does not match the information set in the command setting unit 153 , the AI agent unit 155 may present the most similar command to the user.

In addition, the AI agent unit 155 may include a function to receive commands (search and execution) frequently used by the public from an external server and to support automatic setting in the command setting unit 153 .

In addition, the AI agent unit 155 may support a chatbot service capable of interactive conversation.

Since various similar terms exist for a chatbot, the chatbot according to an embodiment of the present invention includes an intelligent virtual assistant, a virtual personal assistant, an intelligent personal assistant, and a conversational agent. , virtual companion (virtual companion), virtual assistant (virtual assistant), etc. may be included in the scope of the chatbot of the present invention even if used as terms.

In addition, the chatbot can be composed of a chat app that shares chatting, a server that searches for information and provides services according to the chat content, and a bot API that relays the chat app and server, and uses natural language processing (NLP) through reinforcement learning algorithms in the artificial intelligence field. ) and natural language generation (NLG). A chatbot can understand human speech and text and analyze the data it possesses or learned to respond with speech and text that humans can understand. It can process the written language, and even logical reasoning is possible. In addition, the chatbot may find the information requested by the user from the unstructured data, and may provide an intelligent service that informatizes and utilizes the real situation.

To this end, the chatbot according to an embodiment of the present invention provides a pattern recognition (Pattern Recognition) in which a machine identifies a figure, a text, a voice, etc., an information search, a question answering system, and a system so that the machine recognizes a language commonly used by humans. Natural Language Processing with automatic translation and interpretation functions, Semantic Web that understands the meaning of information data and even logical reasoning, Text Mining that finds new and useful information from unstructured text data ( Text Mining), it is possible to perform the function of context-aware computing (Text Aware Computing) that informatizes the real situation in virtual space and provides a user-centered intelligent service by using it.

In this case, according to an embodiment of the present invention, a character may be given to the chatbot, that is, an identity may be planted to learn to have various personalities. It has been found through various studies that the probability of recognizing a chatbot as a person increases when an identity is implanted in the chatbot. Giving robots personalities by humans can help and increase their preferences as it makes it easier for robot users to understand the robot's behavior and allows for more friendly interactions.

Although various methods exist as a personality type analysis tool, in one embodiment of the present invention, a DISC model that can distinguish types through easily revealed behaviors rather than internal factors such as individual temperament, which is difficult to observe, can be used. This is because the DISC model is suitable for identifying characteristics suitable for artificial intelligence because it is easy to identify users' overall preferences due to simple classification. The two dimensions of the DISC analysis are subject (work/person) and speed (slow/fast). There are four personality types, which can be divided into four types: dominant (D: Dominance), sociable (I: Influences), conscientious (C: Conscientiousness), and stable (S: Steadiness). For example, type D, who is a leader, is task-oriented and places importance on quick decisions and driving force. Type I, the sociable type, is a good influencer, active, and fun personality. Type C is a prudent type, less talkative and analytical and precise. The S-type is a stable, relaxed and rational personality. We can assume that these personality types fit the role of the chatbot. Assume that Type D chatbots can be suitable for task-oriented chatbots where fast and accurate work is important, sociable Type I chatbots can be suitable as companions when bored, and prudent Type C or stable S types can be suitable as chatbots for consultation. can In addition, even if it is defined with the above characteristics, the preference according to the user's taste and type may be reflected and changed and applied.

In addition, an embodiment of the present invention may further include anthropomorphism, which is an interaction design that makes the interactive agent feel like a human. In this case, it is possible to elicit a positive social response by using Computers Are Social Actors (CASA)-related studies to improve the quality of interaction between people and agents.

On the other hand, the AI agent unit 155 may support a function of processing an order and payment after accessing a web and an app based on a search command and an execution command.

The AI agent unit 155 may request and receive web page (search and payment page) information corresponding to the search command from the web server accessed through the search command, and may set and register it in the command setting unit.

In addition, the AI agent unit 155 may access the search payment page based on the execution command (order/payment) and automatically input the execution command to process the product order and payment.

4 is a flowchart illustrating a method of operating a terminal device for executing a voice search and voice order program according to an embodiment of the present invention.

Referring to FIG. 4 , in the operation method ( S700 ) of a terminal device for executing a voice search and voice order program according to an embodiment of the present invention, first, the voice information of voice information inputted by the voice matching unit using a frequency band filter is voiced. After filtering the frequency, if it is determined that the frequency is identical to a preset voice frequency (S710), the voice-text converter converts the voice information into a character string (S720).

Thereafter, a command related to at least one of online product order, emergency rescue request, and web search is set in the command setting unit (S730), and the same command as the command set in the command setting unit within the string converted by the command extraction unit is executed Upon extraction (S740), the AI agent unit separates the command extracted from the command extraction unit into a search command and an execution command, accesses the URL associated with the execution command, and searches for information corresponding to the search command and Execute (S750).

Here, the S730 process may include a process in which the command setting unit 153 sets a command that the user wants to use in a category such as order, web search, contact, etc. in a macro format, and is set by the command setting unit 153 A macro-type command may be classified into a search macro and an execution macro, and in the case of an execution macro, a URL address may be set together.

In addition, the process S730 may include a process in which, when a command recognized as an execution macro by the command setting unit 153 is set, a URL address associated with the command is automatically marked and set. It may further include the process of storing as a template composed of the combined short and complex sentences.

The process S740 may include a process in which the command extracting unit 154 calls a sentence template of the transcription data preset according to the macro function set in the command setting unit 153. In this case, the sentence template format is not limited to any one. does not The sentence template format may be implemented not only in a short sentence format but also in a format including a plurality of sentences.

For example, when voice data such as "call template no. 1" or "call template no. 1" is input, a template sentence designated as template No. 1 can be called from the saved template list.

Accordingly, the template may be called by a method of retrieving the contents recorded in the command setting unit 153 . That is, various and updatable template types can be used.

In this case, the template may be classified by serial number or by contextual keyword. Identification information for template classification, ie, a serial number or a keyword for each situation, may be preset by the user.

For example, in the state in which the terms 'yogiyo', 'app', 'restaurant', 'jajangmyeon', and 'search' are set in the order category of the command setting unit 153, the user says "Search for a jjajangmyeon restaurant in Yogiyo" When a voice is input, the command extraction unit 154 extracts terms such as 'yogiyo', 'app', 'restaurant', 'jajangmyeon', and 'search'.

Next, the process S750 may include a process in which the AI agent unit 155 supports the voice service by providing the result information to the user after the execution and search results according to the command.

In addition, when the user's voice information does not match the information set in the command setting unit 153, the method may further include a process of presenting the most similar command to the user.

In addition, the method may further include a process of receiving a command (search and execution) frequently used by the public from an external server and supporting the command setting unit 153 to automatically set the command.

Therefore, when using the terminal device executing the voice recognition-based AI agent program according to an embodiment of the present invention, the user sets his or her own command, and then performs web search, emergency rescue, shopping/purchase order/payment It has the advantage of being easy to handle.

“~ part” used in an embodiment of the present invention may be implemented as a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, devices 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 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 running on the operating system.

of software applications. A processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in 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 in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The 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 the computer-readable recording medium 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 floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. 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.

Those of ordinary skill in the art to which the present invention pertains may modify and modify the above-described contents 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 spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100: a terminal device for executing a voice recognition program
100: communication department
120: storage
130: display unit
140: audio output unit
150: control unit
151: voice matching unit
152: voice-text conversion unit
153: command setting unit
154: command extraction unit
155: AI agent unit

Claims (7)

a voice matching unit that filters the voice frequency of the input voice information using a frequency band filter and determines the sameness with a preset voice frequency;
a voice-text converter converting the voice information into a character string;
a command setting unit for setting commands related to at least one of an online product order, an emergency rescue request, and a web search;
a command extraction unit for extracting the same command as the command set in the command setting unit from the character string converted by the voice-text conversion unit; and
After separating the command extracted from the command extracting unit into a search command and an execution command, after accessing the URL associated with the execution command, the voice recognition base includes an AI agent unit that searches and executes information corresponding to the search command A terminal device that runs the AI agent program of
According to claim 1,
The command setting unit records and sets the search command and the execution command in a macro format,
In the case of the macro of the blind command, a terminal device for executing a voice recognition-based AI agent program, characterized in that the URL address is set together.
The method of claim 1,
The command setting unit
Set a sentence template consisting of a short sentence and a complex sentence in which a plurality of commands are combined,
The sentence template is a terminal device for executing a voice search and voice order program, characterized in that the serial number or keyword for each situation is recorded.
4. The method of claim 3,
The command extraction unit
A terminal device for executing a voice search and voice order program, characterized in that the voice-text conversion unit calls a sentence template containing the most converted character strings.
3. The method of claim 2,
The AI agent unit
After separating the search command and the execution command among the commands extracted by the command extraction unit, after accessing the URL associated with the execution command, the voice search and voice order program for searching and executing information corresponding to the search command and the execution command running terminal device.
5. The method of claim 4,
The AI agent unit
After the execution and search results according to the command, the result information to the user is supported by the voice service, and when the user's voice information does not match the information set in the command setting unit, the most similar command is presented to the user, and an external server A terminal device that executes a voice search and voice order program that receives commands (search and execution) frequently used by the public from the command line setting unit and supports automatic settings.
After filtering the voice frequency of the input voice information using a frequency band filter in the voice matching unit, determining the sameness with a preset voice frequency;
converting the voice information into a character string in a voice-text converter;
setting a command related to at least one of an online product order, an emergency rescue request, and a web search in the command setting unit;
extracting the same command as the command set in the command setting unit from within the string converted by the command extraction unit; and
Separating the command extracted from the command extraction unit into a search command and an execution command in the AI agent unit, accessing a URL associated with the execution command, and searching for and executing information corresponding to the search command A method of operating a terminal device for executing a voice search and voice order program.

Images