EP-4191578-B1 - ELECTRONIC DEVICE, AND PARAMETER ACQUISITION METHOD FOR UNDERSTANDING NATURAL LANGUAGE

EP4191578B1EP 4191578 B1EP4191578 B1EP 4191578B1EP-4191578-B1

Inventors

KIM, KICHUL
BYEON, Jooyong
LEE, JONGWON

Dates

Publication Date: 20260506
Application Date: 20211006

Claims (12)

An electronic device (600) comprising: a display (620) comprising a touchscreen; a microphone (630) configured to receive a voice input from a user; a memory (650); and at least one processor (610) configured to be operatively connected to the display (620), the microphone (630), and the memory (650), wherein the at least one processor is further configured to: obtain an instruction based on text that is input through a touch input on the display or based on a voice input that is input through the microphone, obtain intent corresponding to the instruction using a first application, determine at least one intent execution parameter required to perform an operation corresponding to the obtained intent, extract at least one instruction extraction parameter related to the obtained intent from the obtained instruction; and determine at least one parameter, that is undetermined from the extracted at least one instruction extraction parameter, of the determined at least one intent execution parameter as at least one additionally required parameter that is additionally required to perform the operation corresponding to the obtained intent using the first application, transmit a request for the at least one additionally required parameter to a plurality of second applications registered and approved by the at least one processor, wherein the second applications are different from the first application, and obtain the at least one additionally required parameter from at least one application of the plurality of second applications.
The electronic device (600) as claimed in claim 1, wherein the at least one processor is further configured to transmit a parameter request comprising at least one of information about the obtained intent, a type of the at least one additionally required parameter, or a name of the at least one additionally required parameter to the at least one application stored in the memory.
The electronic device (600) as claimed in claim 2, wherein the at least one processor is further configured to transmit the parameter request to a predetermined application of the at least one application stored in the memory.
The electronic device (600) as claimed in claim 1, wherein, when the at least one additionally required parameter is obtained from the at least one application stored in the memory, the at least one processor is further configured to perform the operation corresponding to the obtained intent using the extracted at least one instruction extraction parameter and the at least one additionally required parameter.
The electronic device (600) as claimed in claim 1, further comprising: a transceiver configured to communicate with an external server, wherein the at least one processor is further configured to: transmit the text input or the voice input to the external server using the transceiver, and receive information relating to the at least one additionally required parameter to perform the operation corresponding to the obtained intent from the external server.
The electronic device (600) as claimed in claim 5, wherein the at least one processor is further configured to: transmit the at least one additionally required parameter obtained from the at least one application stored in the memory to the external server through the transceiver; and receive a resulting value of performing the obtained intent from the external server.
The electronic device (600) as claimed in claim 1, wherein the at least one processor is further configured to verify validity of the at least one additionally required parameter obtained from the at least one application stored in the memory.
The electronic device (600) as claimed in claim 7, wherein, when the at least one application stored in the memory that provides the at least one additionally required parameter is a preregistered application, the at least one processor is further configured to determine that the at least one additionally required parameter is valid.
The electronic device (600) as claimed in claim 1, wherein, when the at least one additionally required parameter is obtained from the at least one application stored in the memory, the at least one processor is further configured to display a graphic object comprising the obtained at least one additionally required parameter and information about the at least one application stored in the memory on the display.
The electronic device (600) as claimed in claim 8, wherein the at least one processor is further configured to use the at least one additionally required parameter obtained from the at least one application stored in the memory to perform the operation corresponding to the obtained intent in response to a user input for the graphic object.
The electronic device (600) as claimed in claim 1, wherein, when the at least one additionally required parameter is not obtained from the at least one application stored in the memory, the at least one processor is further configured to display a query for obtaining the at least one additionally required parameter on the display.
A method for obtaining a parameter for natural language understanding by an electronic device (600), the method comprising: obtaining an instruction based on a touch input or a voice input from a user; obtaining intent corresponding to the instruction; determining at least one intent execution parameter required to perform the operation corresponding to the obtained intent, extract at least one instruction extraction parameter related to the obtained intent from the obtained instruction; determining at least one parameter, that is undetermined from the extracted at least one instruction extraction parameter, of the determined at least one intent execution parameter as at least one additionally required parameter that is additionally required to perform an operation corresponding to the obtained intent; transmitting a request for the at least one additionally required parameter to a plurality of second applications registered and approved by the at least one processor, wherein the second applications are different from the first application; and obtaining the at least one additionally required parameter from at least one application of the plurality of second applications.

Description

[Technical Field] The disclosure relates to an electronic device. More particularly, the disclosure relates to an electronic device and a method of obtaining a natural language understanding (NLU) parameter by an electronic device for obtaining a user input, such as a voice and text, and outputting a processing result of NLU. [Background Art] With the development of mobile communication technology and processor technology, portable electronic devices (hereinafter, electronic devices) can implement various functions in addition to a conventional call function. Further, a variety of platforms may provide interactive services based on artificial intelligence or natural language understanding (NLU), such as a voice assistant or a chatbot, for electronic devices. A user may perform a desired function by giving a command to an electronic device through utterance or text. For example, a service for performing designated intent rather than a simple conversation, such as a task-oriented chatbot, may be provided through an electronic device. An artificial intelligence (AI) engine that provides such a service needs to understand a user's command, understand the intent of the user, and obtain a necessary parameter. The above information is presented as background information only, and to assist with an understanding of the disclosure. No determination has been made, and no assertion is made, as to whether any of the above might be applicable as prior art with regard to the disclosure. US 2018/196683 A1, 12 July 2018, is about systems and processes for application integration with a digital assistant. A method includes receiving an audio input including a natural-language user input and identifying an intent object of a set of intent objects. The intent object may be derived from the natural-language user input. The method further includes identifying a software application associated with the intent object of the set of intent objects, providing the intent object to the software application to cause the software application to perform a task associated with the intent object, receiving a result response indicating whether the task was successfully performed, and providing an output indicating whether the task was performed. EP 2 624 180 Al, 7 August 2013, is about a system of integrating remote services and a method of operating said system. The system comprises a management system, a database with a table of users and a table of data associated with each user, a message input and recognition system for written messages, voice messages, or text messages, etc., an output system, a dialogue system, and an information exchanging system for exchanging information with remote third party services, where the information exchanging system is connected to the management system and comprises connectors suitable for each type of service such that at least one connector is suitable for performing a commercial transaction that can be requested by the user. It is particularly applicable in the field of purchasing electronic tickets or products and in the field of bank transactions from a mobile terminal. [Disclosure of Invention] [Technical Problem] An AI engine (e.g., a voice assistant or a chatbot) may lack parameters necessary to understand and process a command from a user. In this case, to obtain the necessary parameters, the AI engine needs to send an additional inquiry to the user, and the user is required to respond appropriately. This process of continuously asking the user about information required to process the command of the user may cause the user to feel tired and may have a negative impact on the overall experience of the user. Aspects of the disclosure are to address at least the above-mentioned problems and/or disadvantages, and to provide at least the advantages described below. Accordingly, an aspect of the disclosure is to provide an electronic device and a method of obtaining a parameter for natural language understanding that are capable of performing a function corresponding to a user input without an additional query even when there is a lack of parameters required for intent extracted from the user input. [Solution to Problem] Additional aspects will be set forth in part in the description which follows and, in part, will be apparent from the description, or may be learned by practice of the presented embodiments. In accordance with an aspect of the disclosure, an electronic device is provided. The electronic device includes a display including a touchscreen, a microphone configured to receive a voice input from a user, a memory, and at least one processor configured to be operatively connected to the display, the microphone, and the memory, wherein the at least one processor may be configured to obtain an instruction based on text that is input through a touch input on the display or a voice input that is input through the microphone, obtain intent corresponding to the instruction, identify at least one