# US 12,518,757 B2 · Explanation support system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,518,757 B2
- Document ID: US12518757B2
- Status: Granted
- Kind: B2
- Application number: 18/575,337
- Filed: 2022-06-03
- Published: 2024-10-03
- Granted: 2026-01-06
- Earliest claimed: 2021-08-02
- Assignees: Interactive Solutions Corp.
- Applicants: Interactive Solutions Corp.
- Inventors: Kiyoshi Sekine
- Web page: https://patentgrep.com/patent/US12518757B2

## CPC

- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G06F 3/01: Input arrangements or combined input and output arrangements for interaction between user and computer (G06F3/16 takes precedence)
- G06F 3/0484: for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F 3/0487: using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F 3/0488: using a touch-screen or digitiser, e.g. input of commands through traced gestures
- G06F 3/16: Sound input; Sound output (speech processing G10L)
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G10L 2015/228: {of application context}
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 70/40: relating to drugs, e.g. their side effects or intended usage
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Provided is a system that performs proper display under recognition of vocalizer in conversation. An explanation support system 1 includes a display unit 3, a material storage unit 5 that stores an explanation material and a plurality of keywords related to the explanation material, a display information storage unit 7 that stores display information displayed on the display unit 3 based on a combination of the keywords, a voice analysis unit 9 that analyzes voice terms that are terms included in voice information related to the explanation material and vocalizers of the voice terms, and a display control unit 11 that identifies which of the plurality of keywords the voice term of a specific vocalizer analyzed by the voice analysis unit 9 is, reads out the display information from the display information storage unit 7 using information related to the identified keyword, and causes the display unit 3 to display the display information.

## Claims

### Claim 1

An explanation support system comprising:
a display unit;
a material storage unit that stores an explanation material and a plurality of keywords related to the explanation material;
a display information storage unit that stores display information displayed on the display unit based on a combination of the keywords;
a voice analysis unit that analyzes a voice term that is a term included in voice information related to the explanation material and analyzes a voiceprint of a vocalizer to determine that the vocalizer of the voice term is a vocalizer derived from a second terminal that is a terminal other than a first terminal based on the voiceprint;
a display control unit that identifies which of the plurality of keywords a voice term of a specific vocalizer analyzed by the voice analysis unit is, reads out the display information from the display information storage unit using information related to both the identified keyword and vocalizer attribute information, and causes the display unit to display the display information, wherein
the display information includes display keywords that are any two or more keywords among the plurality of keywords,
the explanation support system further comprises a selection information input unit that inputs selection information of the display keywords, wherein
the material storage unit stores the keywords in association with a page of the explanation material,
the display control unit displays, based on the selection information of the display keyword input by the selection information input unit, a page of the explanation material stored in association with the selection information from the material storage unit on the display unit,
and
the display control unit controls display content based on a combination of
(i) a relationship between a first entity derived from the first terminal and a second entity derived from the second terminal, and
(ii) keywords contained in the voice term,
wherein the display control unit determines the relationship by analyzing role-based attributes of both entities and selects display information that is optimized for the relationship between vocalizers.

### Claim 2 (depends on 1)

The explanation support system according to claim 1, comprising:
a content display unit for displaying a plurality of contents;
a selected content input unit that inputs a selected content that is a content selected among the plurality of contents;
a content related person information storage unit that stores content related person information related to a plurality of terminals or a plurality of vocalizers associated with the plurality of contents; and
an available person information storage unit that stores available person information about an available terminal or vocalizer in the content related person information stored by the content related person information storage unit, wherein a terminal selection unit that selects the first terminal based on the available person information when the second terminal selects the selected content.

### Claim 3 (depends on 2)

The explanation support system according to claim 2, further comprising
a user storage unit that stores information related to a user of the second terminal, wherein
the terminal selection unit selects the first terminal using the user information stored by the user storage unit, and the available person information.

### Claim 4

A computer-implemented method for supporting a computer implemented explanation, comprising executing on a processor the steps of:
storing an explanation material and a plurality of keywords related to the explanation material;
storing display information displayed on a display based on a combination of the keywords;
analyzing a voice term that is a term included in voice information related to the explanation material and analyzing a voiceprint of a vocalizer to determine that the vocalizer of the voice term is a vocalizer derived from a second terminal that is a terminal other than a first terminal based on the voiceprint;
identifying which of the plurality of keywords a voice term of a specific vocalizer analyzed is, and
reading out the display information using information related to both the identified keyword and vocalizer attribute information, and causing the display to display the display information, wherein
the display information includes display keywords that are any two or more keywords among the plurality of keywords,
the computer-implemented method further comprises the steps of:
inputting selection information of the display keywords,
storing the keywords in association with a page of the explanation material,
displaying, based on the selection information of the display keyword input, a page of the explanation material stored in association with the selection information on the display, and
controlling display content based on a combination of
(i) a relationship between a first entity derived from the first terminal and a second entity derived from the second terminal, and
(ii) keywords contained in the voice term, wherein the controlling step includes determining the relationship by analyzing role-based attributes of both entities and selecting display information that is optimized for the relationship between vocalizers.