Search

EP-4738144-A1 - ELECTRONIC DEVICE, METHOD, AND COMPUTER-READABLE STORAGE MEDIUM FOR OBTAINING TEXT TO BE INPUT TO NEURAL NETWORK

EP4738144A1EP 4738144 A1EP4738144 A1EP 4738144A1EP-4738144-A1

Abstract

An electronic device according to an embodiment is configured to obtain a first text on the basis of receiving a first user input from a user. The electronic device is configured to generate a second text for obtaining a second user input by using a keyword corresponding to a portion of the first text, and obtain template information indicating a format corresponding to a neural network for obtaining output information related to the first text. The electronic device is configured to obtain a third text obtained on the basis of a second user input after outputting the second text. The electronic device is configured to obtain a fourth text having the format and based on the first text and the third text by using the template information.

Inventors

  • LEE, KWANHO
  • KO, YOUNGTAE

Assignees

  • Samsung Electronics Co., Ltd.

Dates

Publication Date
20260506
Application Date
20240619

Claims (15)

  1. An electronic device (101), comprising: memory (220), storing instructions, comprising one or more storage mediums, at least one processor (210) comprising processing circuitry; and wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: obtain a first text (510), based on receiving a first user input from a user; obtain template information indicating a format corresponding to a neural network (245) for obtaining output information related to the first text and generate a second text (421) for obtaining a second user input, using a keyword (330) corresponding to a portion of the first text; obtain a third text (441) obtained based on the second user input, after outputting the second text; and obtain a fourth text having the format and based on the first text and the third text, using the template information.
  2. The electronic device of claim 1, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: obtain main question information indicating the first text and sub question information indicating the third text, and output the output information indicating an answer to the main question information by inputting the fourth text including the main question information and the sub question information for assisting the main question information to the neural network.
  3. The electronic device of any one of claim 1 and claim 2, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: generate the second text indicating a question for obtaining the sub question information from the user.
  4. The electronic device of any one of claim 1 to claim 3, further comprising: a microphone (260); wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: based on receiving the first user input indicating an utterance of the user through the microphone, obtain the first text corresponding to the utterance.
  5. The electronic device of any one of claim 1 to claim 4, further comprising: a speaker (270); wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: obtain the third text based on the second user input indicating another utterance of the user through the microphone, after outputting an audio signal indicating the second text through the speaker.
  6. The electronic device of any one of claim 1 to claim 5, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: obtain the third text indicating a sentence including a word when the second user input indicates the word.
  7. The electronic device of any one of claim 1 to claim 6, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: generate the second text to obtain the second user input related to a keyword category from the user, using the keyword category mapped to the keyword indicating a specified word, and wherein the second text includes at least one sentence.
  8. The electronic device of any one of claim 1 to claim 7, further comprising: a display (250); wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: obtain the first text, based on receiving the first user input using a screen (705) to obtain a text, display a first text object indicating the second text on the display, obtain the third text, based on receiving the second user input using the screen, and display a second text object indicating the output information outputted by inputting the fourth text to the neural network on the display.
  9. The electronic device of any one of claim 1 to claim 8, wherein the instructions, when executed by the at least one processor individually or collectively, cause the electronic device to: determine the number of the second text based on the number of the keyword.
  10. A method of an electronic device (101), the method comprising: obtaining a first text (510), based on receiving a first user input from a user; obtaining template information indicating a format corresponding to a neural network (245) for obtaining output information related to the first text and generate a second text (421) for obtaining a second user input, using a keyword (330) corresponding to a portion of the first text; obtaining a third text (441) obtained based on the second user input, after outputting the second text; and obtaining a fourth text having the format and based on the first text and the third text, using the template information.
  11. The method of claim 10, obtaining the fourth text comprising: obtaining main question information indicating the first text and sub question information indicating the third text, and outputting the output information indicating an answer to the main question information by inputting the fourth text including the main question information and the sub question information for assisting the main question information to the neural network.
  12. The method of any one of claim 10 and claim 11, comprising: generating the second text indicating a question for obtaining the sub question information from the user.
  13. The method of any one of claim 10 to claim 12, obtaining the first text comprising: based on receiving the first user input indicating an utterance of the user through a microphone (260), obtaining the first text corresponding to the utterance.
  14. The method of any one of claim 10 to claim 13, obtaining the third text comprising: obtaining the third text based on the second user input indicating another utterance of the user through the microphone, after outputting an audio signal indicating the second text through a speaker (270).
  15. A computer readable storage medium storing one or more programs, wherein the one or more programs, when executed by a processor of an electronic device, are configured to cause the electronic device to: obtain a first text (510), based on receiving a first user input from a user; obtain template information indicating a format corresponding to a neural network (245) for obtaining output information related to the first text and generate a second text (421) for obtaining a second user input, using a keyword (330) corresponding to a portion of the first text; obtain a third text (441) obtained based on the second user input, after outputting the second text; and obtain a fourth text having the format and based on the first text and the third text, using the template information.

Description

[Technical Field] The present disclosure relates to an electronic device, a method, and a computer readable storage medium for obtaining text to be inputted to a neural network. [Background Art] A large language model (LLM) may mean an interactive language model configured with an artificial neural network including a plurality of parameters. The large language model may be trained using unlabeled learning data based on supervised learning or unsupervised learning. In order to improve quality of a result value to be outputted through the large language model, prompt engineering for adjusting an input value of the large language model may be used. The above-described information may be provided as a related art for a purpose of helping understanding of the present disclosure. No claim or determination is raised as to whether any of the above-described descriptions may be applied as a prior art related to the present disclosure. [Disclosure] [Technical Solution] An electronic device according to an embodiment may include at least one processor including processing circuitry, and memory, storing instructions, including one or more storage media. The instructions, when executed by the at least one processor individually or collectively, may cause the electronic device to obtain a first text, based on receiving a first user input from a user. The instructions, when executed by the at least one processor individually or collectively, may cause the electronic device to obtain template information indicating a format corresponding to a neural network for obtaining output information related to the first text and generate a second text for obtaining a second user input, using a keyword corresponding to a portion of the first text. The instructions, when executed by the at least one processor individually or collectively, may cause the electronic device to obtain a third text obtained based on the second user input, after outputting the second text. The instructions, when executed by the at least one processor individually or collectively, may cause the electronic device to obtain a fourth text having the format and based on the first text and the third text, using the template information. A method of an electronic device according to an embodiment may include obtaining a first text, based on receiving a first user input from a user. The method may include obtaining template information indicating a format corresponding to a neural network for obtaining output information related to the first text and generate a second text for obtaining a second user input, using a keyword corresponding to a portion of the first text. The method may include obtaining a third text obtained based on the second user input, after outputting the second text. The method may include obtaining a fourth text having the format and based on the first text and the third text, using the template information. In a computer readable storage medium storing one or more programs according to an embodiment, the one or more programs, when executed by a processor of an electronic device, may be configured to cause the electronic device to obtain a first text, based on receiving a first user input from a user. The one or more programs, when executed by the processor of the electronic device, may be configured to cause the electronic device to obtain template information indicating a format corresponding to a neural network for obtaining output information related to the first text and generate a second text for obtaining a second user input, using a keyword corresponding to a portion of the first text. The one or more programs, when executed by the processor of the electronic device, may be configured to cause the electronic device to obtain a third text obtained based on the second user input, after outputting the second text. The one or more programs, when executed by the processor of the electronic device, may be configured to cause the electronic device to obtain a fourth text having the format and based on the first text and the third text, using the template information. [Description of the Drawings] FIG. 1 is a block diagram of an electronic device in a network environment according to various embodiments.FIG. 2 illustrates an example of a block diagram of an electronic device according to an embodiment.FIG. 3 illustrates an example of an operation in which an electronic device according to an embodiment obtains a keyword.FIG. 4A illustrates an example of a flowchart indicating an operation of an electronic device according to an embodiment.FIG. 4B illustrates an example of an operation in which an electronic device according to an embodiment obtains sub question information by using an additional question.FIG. 5 illustrates an example of a template obtained by an electronic device according to an embodiment.FIG. 6 illustrates an example of an operation in which an electronic device according to an embodiment generates a prompt.FIG. 7 illustrates