Theme detection for object-recognition-based notifications
US-12183330-B2 · Dec 31, 2024 · US
US10529333B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10529333-B2 |
| Application number | US-201815956210-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 18, 2018 |
| Priority date | Oct 3, 2017 |
| Publication date | Jan 7, 2020 |
| Grant date | Jan 7, 2020 |
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 non-transitory computer-readable medium including a command processing program for causing a computer to realize functions to generate a command for carrying out an indication against an operation target in a virtual space on the basis of an input by a user using a natural language is provided. The functions include: a text data obtaining function configured to obtain text data on the basis of the input by the user using the natural language; a syntax analyzing function configured to extract a command from the obtained text data, the user wanting to carry out the command; a command analyzing function configured to generate a primitive type command from the command extracted by the syntax analyzing function; and a specific viewpoint information obtaining function configured to obtain specific viewpoint information at least at a time of an input operation by the user using the natural language.
Opening claim text (preview).
What is claimed is: 1. A non-transitory computer-readable medium including a command processing program for causing a computer to generate a command for carrying out an indication against an operation target in a virtual space on a basis of an input by a user using a natural language, the command processing program, when executed, causing the computer to perform operations comprising: recognizing, by voice recognition, a voice input of the user as a voice of the user; obtaining text data based on the voice input of the user using the natural language; extracting a command from the obtained text data, the user wanting to carry out the command; generating a primitive type command from the extracted command; obtaining specific viewpoint information at least at a time of the voice input of the user using the natural language, the specific viewpoint information indicating a specific viewpoint in the virtual space; evaluating, in a case where the primitive type command includes a plurality of choices, each of the plurality of choices based on a predetermined evaluation standard to output an evaluation result; and determining a choice based on the evaluation result of each of the plurality of choices to determine the command, wherein, in the evaluating, each of the plurality of choices is evaluated in the primitive type command by using the specific viewpoint information. 2. The non-transitory computer-readable medium according to claim 1 , wherein the specific viewpoint information is obtained from a virtual reality device that the user is wearing. 3. The non-transitory computer-readable medium according to claim 1 , the operations further comprising: obtaining time information when the voice of the user is input; and obtaining time information when the specific viewpoint information is obtained, wherein, in the evaluating, each of the plurality of choices is evaluated in the primitive type command so that a time when to produce each element of the text data, obtained based on the voice input of the user, is combined with the specific viewpoint information at a same time. 4. The non-transitory computer-readable medium according to claim 1 , wherein the specific viewpoint information corresponds to a directivity of a predetermined part of a player character in the virtual space. 5. A command processing method of generating a command for carrying out an indication against an operation target in a virtual space on a basis of an input by a user using a natural language, the command processing method comprising: recognizing, by voice recognition, a voice input of the user as a voice of the user; obtaining text data based on the voice input of the user using the natural language; extracting a command from the obtained text data, the user wanting to carry out the command; generating a primitive type command from the extracted command; obtaining specific viewpoint information at least at a time of the voice input of the user using the natural language, the specific viewpoint information indicating a specific viewpoint in the virtual space; evaluating, in a case where the primitive type command includes a plurality of choices, each of the plurality of choices based on a predetermined evaluation standard to output an evaluation result; and determining, by a computer, a choice based on the evaluation result of each of the plurality of choices to determine the command, wherein, in the evaluating, each of the plurality of choices is evaluated in the primitive type command by using the specific viewpoint information. 6. The command processing method according to claim 5 , wherein the specific viewpoint information corresponds to a directivity of a predetermined part of a player character in the virtual space. 7. The command processing method according to claim 5 , wherein the specific viewpoint information is obtained from a virtual reality device that the user is wearing. 8. A command processing apparatus configured to generate a command for carrying out an indication against an operation target in a virtual space on a basis of an input by a user using a natural language, the command processing apparatus comprising: a microphone; and a memory including at least one program that, when executed by the command processing apparatus, causes the command processing apparatus to perform operations including: recognizing, by voice recognition, a voice input of the user as a voice of the user, the voice input of the user being input to the microphone; obtaining text data based on the voice input of the user using the natural language; extracting a command from the obtained text data, the user wanting to carry out the command; generating a primitive type command from the extracted command; obtaining specific viewpoint information at least at a time of the voice input of the user using the natural language, the specific viewpoint information indicating a specific viewpoint in the virtual space; evaluating, in a case where the primitive type command includes a plurality of choices, each of the plurality of choices based on a predetermined evaluation standard to output an evaluation result; and determining a choice based on the evaluation result to determine the command, wherein, in the evaluating, each of the plurality of choices is evaluated in the primitive type command by using the specific viewpoint information. 9. The command processing apparatus according to claim 8 , wherein the specific viewpoint information is obtained from a virtual reality device that the user is wearing. 10. The command processing apparatus according to claim 8 , wherein the specific viewpoint information corresponds to a directivity of a predetermined part of a player character in the virtual space.
Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title
Perspective computation · CPC title
Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title
Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title
Execution procedure of a spoken command · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.