Intention inference system and intention inference method

US10460034B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10460034-B2
Application numberUS-201515546801-A
CountryUS
Kind codeB2
Filing dateJan 28, 2015
Priority dateJan 28, 2015
Publication dateOct 29, 2019
Grant dateOct 29, 2019

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

An intention inference system includes, a morphological analyzer to perform morphological analysis for a complex sentence with multiple intentions involved, a syntactic analyzer to perform syntactic analysis for the complex sentence morphologically analyzed by the morphological analyzer and to divide it into the first simple sentence and the second simple sentence, an intention inference unit to infer the first intention involved in the first simple sentence and the second intention involved in the second simple sentence, a feature extractor to extract as the first feature a morpheme showing execution order of operations involved in the first simple sentence and to extract as the second feature a morpheme showing execution order of operations involved in the second simple sentence, and an execution order inference unit to infer the execution order of the first operation corresponding to the first intention and the second operation corresponding to the second intention on the basis of the first feature and the second feature extracted by the feature extractor. This enables the system to infer user's intentions accurately.

First claim

Opening claim text (preview).

What is claimed is: 1. An intention inference system comprising: a morphological analyzer to perform morphological analysis for a complex sentence with multiple intentions involved; a syntactic analyzer to perform syntactic analysis for the complex sentence morphologically analyzed by the morphological analyzer and to divide it into a first simple sentence and a second simple sentence; an intention inference unit to infer a first intention involved in the first simple sentence and a second intention involved in the second simple sentence; a feature extractor to extract as a first feature a morpheme included in the first simple sentence indicating a relative timing of a first operation corresponding to the first intention, and to extract as a second feature a morpheme included in the second simple sentence indicating a relative timing of a second operation corresponding to the second intention; and an execution order inference unit to infer a sequential order in which the first operation corresponding to the first intention and the second operation corresponding to the second intention are to be executed, the sequential order being inferred on the basis of the first feature and the second feature extracted by the feature extractor. 2. The intention inference system set forth in claim 1 , wherein the feature extractor extracts the first feature on the basis of a location of the morpheme in the first simple sentence and on the basis of a part-of-speech of the morpheme and extracts the second feature on the basis of a location of the morpheme in the second simple sentence and on the basis of a part-of-speech of the morpheme. 3. The intention inference system set forth in claim 1 , further comprising: a speech sound receiver to accept an input of a speech sound with multiple intentions involved; and a speech recognizer to recognize speech sound data corresponding to the speech sound entering the speech sound receiver and to perform a conversion thereof into text data of a complex sentence with the multiple intentions involved. 4. The intention inference system set forth in claim 1 , further comprising: an operation execution unit to execute the first operation and the second operation on the basis of the sequential order inferred by the execution order inference unit; and a notification unit to notify a user that the operation execution unit has executed the first operation and the second operation. 5. An intention inference system comprising: a morphological analyzer to perform morphological analysis for a complex sentence with multiple intentions involved; a syntactic analyzer to perform syntactic analysis for the complex sentence morphologically analyzed by the morphological analyzer and to divide it into a first simple sentence and a second simple sentence; an intention inference unit to infer a first intention involved in the first simple sentence and a second intention involved in the second simple sentence; a feature extractor to extract as a first feature a morpheme showing operation execution order included in the first simple sentence and to extract as a second feature a morpheme showing operation execution order included in the second simple sentence; an execution order inference unit to infer execution order of the first operation corresponding to the first intention and the second operation corresponding to the second intention on the basis of the first feature and the second feature extracted by the feature extractor; and an execution order information storage to store execution order information that shows scores of multiple features including the first feature and the second feature for each of execution order types of the first operation and the second operation, wherein the execution order inference unit infers the execution order of the first operation and the second operation on the basis of the scores of the multiple features included in the execution order information. 6. The intention inference system set forth in claim 5 , wherein the execution order inference unit obtains scores of the first feature and scores of the second feature using the execution order information to infer the sequential order in which the first operation and the second operation are to be executed on the basis of final scores each obtained as a product of one of the scores of the first feature and one of the scores of the second feature. 7. The intention inference system set forth in claim 5 , wherein the execution order information storage also stores, for each of the execution order types of the first operation and the second operation, scores of multiple top-level intentions' features including a first top-level intention's feature which represents a classification or a function of the first intention and a second top-level intention's feature which represents a classification or a function of the second intention, and the execution order inference unit infers the execution order of the first operation and the second operation on the basis of the scores of the multiple features and the scores of the multiple top-level intentions' features. 8. The intention inference system set forth in claim 7 , wherein the execution order inference unit infers the execution order of the first operation and the second operation on the basis of final scores each obtained as a product of one of the scores of the first feature, one of the scores of the second feature, one of the scores of the first top-level intention's feature, and one of the scores of the second top-level intention's feature. 9. An intention inference method comprising: performing morphological analysis for a complex sentence with multiple intentions involved; performing syntactic analysis for the morphologically analyzed complex sentence and dividing it into multiple simple sentences; inferring intentions involved in each of the multiple simple sentences; extracting as a feature a morpheme included in each of the multiple simple sentences indicating a relative timing of an operation corresponding to the intention inferred from the corresponding simple sentence; and inferring a sequential order in which the operations corresponding to the inferred intentions are to be executed, the sequential order being inferred on the basis of the respective features included in the multiple simple sentences. 10. The intention inference method of claim 9 , further comprising: storing execution order information that shows scores of multiple features including the respective features included in the multiple simple sentences, inferring the sequential order of the operations corresponding to the intentions involved in each of the multiple simple sentence on the basis of the scores of the multiple features included in the execution order information.

Assignees

Inventors

Classifications

  • G06F40/30Primary

    Semantic analysis · CPC title

  • Recognition of textual entities · CPC title

  • G06F40/268Primary

    Morphological analysis · CPC title

  • Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title

  • Speech to text systems (G10L15/08 takes precedence) · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US10460034B2 cover?
An intention inference system includes, a morphological analyzer to perform morphological analysis for a complex sentence with multiple intentions involved, a syntactic analyzer to perform syntactic analysis for the complex sentence morphologically analyzed by the morphological analyzer and to divide it into the first simple sentence and the second simple sentence, an intention inference unit t…
Who is the assignee on this patent?
Mitsubishi Electric Corp
What technology area does this patent fall under?
Primary CPC classification G06F40/30. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Oct 29 2019 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).