17296463. METHOD FOR OUTPUTTING TEXT IN ARTIFICIAL INTELLIGENCE VIRTUAL ASSISTANT SERVICE AND ELECTRONIC DEVICE FOR SUPPORTING THE SAME simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)

METHOD FOR OUTPUTTING TEXT IN ARTIFICIAL INTELLIGENCE VIRTUAL ASSISTANT SERVICE AND ELECTRONIC DEVICE FOR SUPPORTING THE SAME

Organization Name

SAMSUNG ELECTRONICS CO., LTD.

Inventor(s)

Kichul Kim of Suwon-si, Gyeonggi-do (KR)

Yoonjae Park of Suwon-si, Gyeonggi-do (KR)

Jooyong Byeon of Suwon-si, Gyeonggi-do (KR)

Youngkyu Kim of Suwon-si, Gyeonggi-do (KR)

Byungkeon Park of Suwon-si, Gyeonggi-do (KR)

Soowon Jang of Suwon-si, Gyeonggi-do (KR)

Changyong Jeong of Suwon-si, Gyeonggi-do (KR)

Sungbin Jin of Suwon-si, Gyeonggi-do (KR)

Jaeyung Yeo of Suwon-si, Gyeonggi-do (KR)

METHOD FOR OUTPUTTING TEXT IN ARTIFICIAL INTELLIGENCE VIRTUAL ASSISTANT SERVICE AND ELECTRONIC DEVICE FOR SUPPORTING THE SAME - A simplified explanation of the abstract

This abstract first appeared for US patent application 17296463 titled 'METHOD FOR OUTPUTTING TEXT IN ARTIFICIAL INTELLIGENCE VIRTUAL ASSISTANT SERVICE AND ELECTRONIC DEVICE FOR SUPPORTING THE SAME

Simplified Explanation

The patent application describes an electronic device that uses an artificial intelligence model to provide text-based responses to user utterances. The device obtains the text corresponding to the user's speech, determines the intent and emotion of the utterance, and generates a response text based on this information. The device also adds markup language to the response text, which includes information about the output unit of the text (e.g., phoneme, syllable, word). The response text is then provided to the user.

• The electronic device uses an artificial intelligence model to generate text-based responses to user utterances.
• The device analyzes the user's speech to obtain the corresponding text and determine the intent and emotion of the utterance.
• Based on the intent and emotion information, the device generates a response text.
• The device adds markup language to the response text, which includes information about the output unit of the text.
• The response text, with the added markup language, is provided to the user.

Potential Applications

• Virtual assistant services: The technology can be used in virtual assistant devices or applications to provide text-based responses to user queries or commands.
• Customer service chatbots: The technology can be applied in chatbot systems to generate text-based responses to customer inquiries or complaints.
• Language learning tools: The technology can be used in language learning applications to provide text-based feedback or responses to learners' speech.

Problems Solved

• Improved user experience: By generating text-based responses, the technology allows for more accurate and precise communication between the user and the electronic device.
• Enhanced understanding of user intent and emotion: The device analyzes both the speech and text to determine the intent and emotion of the user, leading to more contextually appropriate responses.
• Customizable output units: The technology allows for flexibility in choosing the output unit of the response text, enabling customization based on user preferences or specific applications.

Benefits

• Efficient communication: The technology enables quick and accurate generation of text-based responses, facilitating efficient communication between the user and the electronic device.
• Enhanced user interaction: By considering the user's intent and emotion, the device can provide more personalized and engaging responses, improving the overall user experience.
• Customization options: The ability to choose the output unit of the response text provides flexibility and customization options for different user needs or applications.

Original Abstract Submitted

According to an embodiment, an electronic device comprises: a memory, a communication module comprising communication circuitry, and a processor operatively connected with the memory and the communication module. The processor is configured to control the electronic device to: obtain a utterance text corresponding to utterance speech, obtain an intent of the utterance text and emotion information based on the utterance speech and the utterance text, obtain a response text for the utterance text based on the intent of the utterance text and the emotion information, obtain a markup language including information about an output unit of text of the response text based on at least one of the intent of the utterance text, the emotion information, or the response text, and add the markup language to the response text and provide the response text. The text output unit is at least one selected from among a phoneme unit, a consonant and vowel unit, a syllable unit, or a word unit. A text output method in an artificial intelligence virtual assistant service of an electronic device may be performed using an artificial intelligence model.