EP-4738263-A1 - ARTIFICIAL INTELLIGENCE DEVICE AND OPERATING METHOD THEREOF

EP4738263A1EP 4738263 A1EP4738263 A1EP 4738263A1EP-4738263-A1

Abstract

An artificial intelligence device according to an embodiment of the present disclosure includes a communication unit that communicates with a display device and a processor configured to receive a request for generating an image for a standby screen from the display device, and operating state information of an electronic device linked with the display device through the communication unit, generate a first prompt for natural language generation based on an analysis result of the image generation request and the operating state information of the electronic device, transmit the first prompt to a first generative artificial intelligence server, receive a plurality of sentences in response to the first prompt from the first generative artificial intelligence server, generate a second prompt for image generation based on the plurality of sentences, transmit the second prompt to a second generative artificial intelligence server, and receive a plurality of images corresponding to operating states of the electronic device from the second generative artificial intelligence server.

Inventors

KIM, YONG TAE
PARK, Jae Cul
LEE, SEONG HAK

Assignees

LG Electronics Inc.

Dates

Publication Date: 20260506
Application Date: 20230914

Claims (15)

An artificial intelligence device comprising: a communication unit configured to communicate with a display device; and a processor configured to: receive, through the communication unit, a request for generating an image for a standby screen from the display device, and operating state information of an electronic device linked with the display device, generate a first prompt for natural language generation based on an analysis result of the image generation request and the operating state information of the electronic device, transmit the first prompt to a first generative artificial intelligence server, receive a plurality of sentences in response to the first prompt from the first generative artificial intelligence server, generate a second prompt for image generation based on the plurality of sentences, transmit the second prompt to a second generative artificial intelligence server, and receive a plurality of images corresponding to operating states of the electronic device from the second generative artificial intelligence server.
The artificial intelligence device of claim 1, wherein the processor is further configured to transmit the plurality of images to the display device through the communication unit.
The artificial intelligence device of claim 1, wherein the processor is configured to obtain, as the first prompt, a sentence generated by combining the analysis result, a name of the electronic device, and the operating state information of the electronic device.
The artificial intelligence device of claim 3, wherein each of the plurality of sentences is a sentence commanding generation of an image reflecting the analysis result and a characteristic of each operating state of the electronic device.
The artificial intelligence device of claim 4, wherein the second prompt includes the plurality of sentences and the operating states of the electronic device corresponding to each sentence.
The artificial intelligence device of claim 4, wherein the second prompt includes any one of the plurality of sentences and the operating state of the electronic device corresponding to the any one sentence.
The artificial intelligence device of claim 1, wherein the plurality of images includes: a basic image reflecting the analysis result and a basic operating state of the electronic device, a first image obtained by merging a characteristic of a first operating state of the electronic device with the basic image, and a second image obtained by merging a characteristic of a second operating state of the electronic device with the first image.
The artificial intelligence device of claim 1, wherein: the image generation request is a voice command uttered by a user, and the processor is configured to convert the voice command into text data and obtain the analysis result based on the converted text data.
An operation method of an artificial intelligence device, the method comprising: receiving a request for generating an image for a standby screen from a display device, and operating state information of an electronic device linked with the display device, generating a first prompt for natural language generation based on an analysis result of the image generation request and the operating state information of the electronic device; transmitting the first prompt to a first generative artificial intelligence server; receiving a plurality of sentences in response to the first prompt from the first generative artificial intelligence server; generating a second prompt for image generation based on the plurality of sentences; transmitting the second prompt to a second generative artificial intelligence server; and receiving a plurality of images corresponding to operating states of the electronic device from the second generative artificial intelligence server.
The operation method of claim 9, further comprising transmitting the plurality of images to the display device.
The operation method of claim 9, wherein generating the first prompt includes obtaining, as the first prompt, a sentence generated by combining the analysis result, a name of the electronic device, and the operating state information of the electronic device.
The operation method of claim 11, wherein each of the plurality of sentences is a sentence commanding generation of an image reflecting the analysis result and a characteristic of each operating state of the electronic device.
The operation method of claim 12, wherein the second prompt includes the plurality of sentences and the operating states of the electronic device corresponding to each sentence.
The operation method of claim 12, wherein the second prompt includes any one of the plurality of sentences and the operating state of the electronic device corresponding to the any one sentence.
The operation method of claim 9, wherein the plurality of images includes: a basic image reflecting the analysis result and a basic operating state of the electronic device, a first image obtained by merging a characteristic of a first operating state of the electronic device with the basic image, and a second image obtained by merging a characteristic of a second operating state of the electronic device with the first image.

Description

[Technical Field] The present disclosure relates to an artificial intelligence device, and more particularly, to an artificial intelligence device capable of generating images that match user utterances. [Background Art] Digital TV services using wired or wireless communication networks are becoming widespread. Digital TV services can provide various services that could not be provided by conventional analog broadcasting services. For example, in the case of IPTV (Internet Protocol Television) and smart TV services, which are types of digital TV services, they provide interactivity that allows users to actively select the type of viewing program, viewing time, and the like. Based on this interactivity, IPTV and smart TV services can also provide various additional services, such as internet search, home shopping, online games, and the like. Conventional standby screens provided by TVs use a method where users select images from a predetermined UI, resulting in limited standby screen settings. Additionally, the information that TVs can utilize for providing images for standby screens has been limited to predetermined content such as connected products and connection information delivered based on predetermined rules. [Disclosure] [Technical Problem] An object of the present disclosure is to provide information and user interfaces desired by users on a standby screen without changing the software of a display device. Another object of the present disclosure is to provide desired images on a standby screen with simple utterances for image generation. [Technical Solution] An artificial intelligence device according to an embodiment of the present disclosure includes a communication unit that communicates with a display device, and a processor configured to receive a request for generating an image for a standby screen from the display device and operating state information of an electronic device linked with the display device through the communication unit, generate a first prompt for natural language generation based on an analysis result of the image generation request and the operating state information of the electronic device, transmit the first prompt to a first generative artificial intelligence server, receive a plurality of sentences in response to the first prompt from the first generative artificial intelligence server, generate a second prompt for image generation based on the plurality of sentences, transmit the second prompt to a second generative artificial intelligence server, and receive a plurality of images corresponding to operating states of the electronic device from the second generative artificial intelligence server. An operation method of an artificial intelligence device according to an embodiment of the present disclosure includes receiving a request for generating an image for a standby screen from a display device and operating state information of an electronic device linked with the display device; generating a first prompt for natural language generation based on an analysis result of the image generation request and the operating state information of the electronic device; transmitting the first prompt to a first generative artificial intelligence server; receiving a plurality of sentences in response to the first prompt from the first generative artificial intelligence server; generating a second prompt for image generation based on the plurality of sentences; transmitting the second prompt to a second generative artificial intelligence server; and receiving a plurality of images corresponding to operating states of the electronic device from the second generative artificial intelligence server. [Advantageous Effect] According to an embodiment of the present disclosure, information and user interfaces desired by users can be provided on a standby screen without changing the software of the display device. Accordingly, the utilization of the standby screen reflecting the user's intention can be increased. According to an embodiment of the present disclosure, users can have desired images provided on a standby screen with simple utterances for image generation. Accordingly, the interaction between the user and the display device can be strengthened. [Description of Drawings] FIG. 1 is a block diagram illustrating a configuration of a display device according to an embodiment of the present invention.FIG. 2 is a block diagram of a remote control device according to an embodiment of the present invention.FIG. 3 illustrates an actual configuration example of a remote control device according to an embodiment of the present invention.FIG. 4 illustrates an example of utilizing a remote control device according to an embodiment of the present invention.FIG. 5 illustrates an artificial intelligence (AI) server according to an embodiment of the present disclosure.FIG. 6 is a ladder diagram for explaining an operation method of an Al system according to an embodiment of the present disc