Auto-generation of support trees
US-2023229680-A1 · Jul 20, 2023 · US
US12554751B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12554751-B2 |
| Application number | US-202318185506-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 17, 2023 |
| Priority date | Apr 26, 2022 |
| Publication date | Feb 17, 2026 |
| Grant date | Feb 17, 2026 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A knowledge extracting device includes: a question input section which inputs a predetermined question; a question transmitting section which transmits the predetermined question and a new question generated by a question generating section to a respondent terminal; a response acquiring section which acquires a response to a question from the respondent terminal; a question generating section which generates a new question related to the response acquired by the response acquiring section; a relating section which generates, as structured knowledge, a tree structure in which a set of responses acquired by the response acquiring section is associated such that a previously obtained response is a superordinate element of the tree structure and a later obtained response is a subordinate element of the tree structure; and a knowledge output section which outputs the generated structured knowledge as a response to the predetermined question.
Opening claim text (preview).
What is claimed is: 1 . A knowledge extracting device comprising: a question input section configured to input a predetermined question; a question transmitting section configured to transmit the predetermined question and a new question generated by a question generating section to a respondent terminal; a response acquiring section configured to respectively acquire responses to the predetermined question and the new question from the respondent terminal; the question generating section configured to generate the new question based on the response to the predetermined question acquired by the response acquiring section; a relating section configured to generate, as structured knowledge, a tree structure in which a set of responses acquired by the response acquiring section is associated such that a previously obtained response is a superordinate element of the tree structure and a later obtained response is a subordinate element of the tree structure; and a knowledge output section configured to output the generated structured knowledge as a response to the predetermined question, wherein the question generating section generates, as question data to be transmitted to the response acquiring section, structured knowledge in which an element for describing a response in a current question is added as a blank space to the structured knowledge generated by the relating section up to the present time. 2 . The knowledge extracting device according to claim 1 , wherein the relating section generates, as the structured knowledge, the tree structure in which responses are associated such that a response to the predetermined question is a first response element of the tree structure, a response to a new question related to the first response element is a second response element of the tree structure, and a response to a new question related to the second response element is a third response element of the tree structure, wherein the question generating section generates a new question related to the first response element and a new question related to the second response element, and wherein the question transmitting section transmits the predetermined question, the new question related to the first response element, and the new question related to the second response element to the respondent terminal. 3 . The knowledge extracting device according to claim 1 , further comprising: a relationship accumulating section configured to accumulate, in a structured knowledge database, the set of responses acquired by the response acquiring section and the structured knowledge generated by the relating section. 4 . The knowledge extracting device according to claim 1 , further comprising: a respondent database; and a respondent selecting section, wherein in the respondent database, a specialization and a number of years of work experience are registered for each respondent candidate, and wherein the respondent selecting section preferentially selects a respondent with a specialization matching a field of a question and longer years of work experience as a transmission destination to which a question is transmitted by the response acquiring section. 5 . The knowledge extracting device according to claim 1 , further comprising: a respondent database; and a respondent selecting section, wherein in the respondent database, a record of past responses is registered for each respondent candidate, and wherein the respondent selecting section preferentially selects a respondent with a longer record of past responses as a transmission destination to which a question is transmitted by the response acquiring section. 6 . The knowledge extracting device according to claim 1 , further comprising: a question area distinguishing section configured to distinguish a subordinate element for a predetermined element as a question area in a case where a number of subordinate elements for the predetermined element is equal to or less than a predetermined threshold among elements constituting structured knowledge obtained by the relating section, wherein the question generating section generates a question for responding to an element of the question area. 7 . The knowledge extracting device according to claim 1 , further comprising: a response evaluating section configured to add a number of responses for each response obtained from one or more respondents, to structured knowledge, as an element evaluation result. 8 . The knowledge extracting device according to claim 1 , further comprising: a respondent database; and a response evaluating section, wherein in the respondent database, a numerical value indicating suitability of a respondent is registered for each respondent, and wherein the response evaluation section calculates certainty of a response on the basis of a number of responses for each response obtained from one or more respondents and suitability of a respondent, and adds the certainty of the response to the structured knowledge as an element evaluation result. 9 . The knowledge extracting device according to claim 1 , wherein the question generating section generates, as question data to be transmitted to the response acquiring section, structured knowledge including a superordinate element that has already been questioned, a subordinate element that has already been received as a response to the superordinate element, and a blank space for discovering a subordinate element differing from the subordinate element. 10 . The knowledge extracting device according to claim 1 , wherein the question generating section generates, as question data to be transmitted to the response acquiring section, structured knowledge including a superordinate element that has already been responded, a question for deeply probing a subordinate element of the superordinate element, and a blank space for recording a response to the question for the deeply probing. 11 . The knowledge extracting device according to claim 1 , further comprising: an incentivizing section configured to provide an incentive to a respondent of the respondent terminal who has responded to the response acquiring section with respect to a question from the question transmitting section. 12 . A knowledge extraction method to be implemented by a knowledge extracting device, wherein the knowledge extracting device includes a question input section, a question transmitting section, a response acquiring section, a question generating section, a relating section, and a knowledge output section, the method comprising: inputting, by the question input section, a predetermined question; transmitting, by the question transmitting section, the predetermined question and to a respondent terminal; acquiring, by the response acquiring section, a response to the predetermined question from the respondent terminal; generating, by the question generating section, a new question based on the response to the predetermined question acquired by the response acquiring section; transmitting, by the question transmitting section, the new question generated by the question generating section, to the respondent terminal; acquiring, by the response acquiring section, a response to the new question from the respondent terminal; generating, by the relating section, as structured knowledge, a tree structure in which a set of responses acquired by the response acquiring section is associated such that a previously obtained response is a superordinate element of the tree structure and a later obtained response is a subordinate element of the tree structure; and outputting, by the knowledge output section, the gene
Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title
Trees · CPC title
Knowledge engineering; Knowledge acquisition · CPC title
Editing, e.g. inserting or deleting · CPC title
Natural language query formulation · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.