# US 2021/0081600 A1 · Coaching system and coaching method

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

- Number: US 2021/0081600 A1
- Document ID: US20210081600A1
- Status: Published application
- Kind: A1
- Application number: 16/849,025
- Filed: 2020-04-15
- Published: 2021-03-18
- Earliest claimed: 2019-09-12
- Assignees: Hitachi, Ltd.
- Applicants: Hitachi, Ltd.
- Inventors: Hideki HAYASHI; Akira IOKU
- Web page: https://patentgrep.com/patent/US20210081600A1

## CPC

- G06F 40/169: Annotation, e.g. comment data or footnotes
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 16/93: Document management systems
- G06F 40/30: Semantic analysis
- G06Q 10/10: Office automation; Time management
- G06Q 50/10: Services
- G09B 7/04: characterised by modifying the teaching programme in response to a wrong answer, e.g. repeating the question or supplying a further explanation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)

## Abstract

In coaching with the purpose of creating a document in mind, data containing question group related to components of the document, a question of details, and a question of another topic is included, an increase/decrease of information amount of the answers of the writer is estimated from a writer's past answers and a current answer, and a next question is selected based on the estimation result.

## Claims

### Claim 1

A coaching system for supporting creation of a document, comprising:
a question presenting unit that selects a question for a user;
an answer receiving unit that receives an answer to a question selected by the question presenting unit;
a data management unit that stores an answer received by the answer receiving unit; and
an information amount estimating unit that calculates a similarity between a past answer of the user stored in the data management unit and a current answer,
wherein the question presenting unit selects a topic change question when the similarity received from the information amount estimating unit is greater than a predetermined value, and selects a detail question when the similarity is small.

### Claim 2

A coaching system for supporting creation of a document, comprising:
a processing unit; and
a memory device,
wherein the memory device includes
answer history data for managing a document type ID that specifies a type of a document to be created, a document configuration ID that specifies a component of a document for each document type, a question ID that specifies a question content, and an answer content of a user in correspondence with each other,
wherein the processing unit is configured to
select a question for a document creation user,
receive an answer to the selected question from the document creation user as a current answer, and store the answer as the answer history data,
read a past answer of the user for the selected question with respect to a corresponding document type ID, a corresponding document configuration ID, and a corresponding question ID, which are stored in the answer history data,
calculate a similarity between the past answer and the current answer,
select a topic change question when the similarity is larger than a predetermined value, and
select a detail question when the similarity is small.

### Claim 3 (depends on 2)

The coaching system according to claim 2,
wherein the memory device stores question data for managing the document type ID, the document configuration ID, the question ID, and question content in correspondence with each other,
wherein the question data is managed so that a plurality of the document configuration IDs correspond to one of the document type IDs, and
wherein a plurality of the question IDs and the question content are managed so as to correspond to one of the document configuration IDs.

### Claim 4 (depends on 2)

The coaching system according to claim 2,
wherein the answer history data that is stored in the memory device is managed so that a question time and an answer time that present a question to the document creation user correspond with the question ID, and
wherein the processing unit calculates the similarity according to a difference between the question time and the answer time.

### Claim 5 (depends on 3)

The coaching system according to claim 3, wherein the processing unit selects a question content from the detail question according to the similarity.

### Claim 6 (depends on 3)

The coaching system according to claim 3,
wherein the memory device stores related document data storing a document vector corresponding to the document type ID, and
wherein the processing unit calculates the similarity based on the current answer and a document vector of the related document data.

### Claim 7

A coaching method for supporting creation of a document, in which a processing unit and a memory device are provided, and
wherein the memory device includes
answer history data for managing a document type ID that specifies a type of a document to be created, a document configuration ID that specifies a component of a document for each document type, a question ID that specifies a question content, and an answer content of a user in correspondence with each other,
wherein the processing unit is configured to
select a question for a document creation user,
receive an answer to the selected question from the document creation user as a current answer, and store the answer as the answer history data,
read a past answer of the user for the selected question with respect to a corresponding document type ID, a corresponding document configuration ID, and a corresponding question ID, which are stored in the answer history data,
calculate a similarity between the past answer and the current answer,
select a topic change question when the similarity is larger than a predetermined value, and
select a detail question when the similarity is small.
