MLchartDataset catalogue

Patent · US10916236B2 · B2 · US

Output device, output method, and electronic apparatus

(11) Publication number
US10916236B2
(21) Application number
16/298,158
(22) Filing date
2019-03-11
(30) Priority date
2017-01-30
(43) Publication date
2021-02-09
(45) Date of grant
2021-02-09
(51) IPC
B25J 11/00; G06F 40/279; G06F 40/30; G10L 15/02; G10L 15/22
(52) CPC
  • G10L Speech analysis techniques or speech synthesis; speech recognition; speech or voice processing techniques; speech or audio coding or decoding: 15/02, 15/22
  • B25J Manipulators; chambers provided with manipulation devices: 11/00, 11/0005
  • G06F Electric digital data processing: 40/279, 40/30
(73) Assignee
Fujitsu Ltd
(72) Inventors
Kaoru Kinoshita; Masayoshi Shimizu; Shinji Kanda
(54) Title
Output device, output method, and electronic apparatus
(57) Abstract

An output device includes a memory and a processor coupled to the memory. The processor obtains an utterance command and an action command, analyzes an utterance content of the utterance command inputted after an action performed in response to the action command, modifies the action command based on a result of the analysis, and outputs the modified action command and the utterance command.

Full text
View on Google Patents

Claims (7)

  1. An output device comprising: a memory; and a processor coupled to the memory and configured to: obtain an utterance command and an action command, the utterance command including a first utterance content and a second utterance content, and the action command being located between the first utterance content and the second utterance content; analyze the utterance command by at least one of: extracting a keyword from each of the first utterance content and the second utterance content, and identifying a modification example based on the extracted keywords; extracting the keyword from each of the first utterance content and the second utterance content, identifying a parameter value associated with the action command, and calculating a modification amount based on the extracted keywords and the parameter value; and extracting the keyword from each of the first utterance content and the second utterance content, identifying a degree of association between the action command and an emotion, and calculating a modification amount based on the extracted keywords and the degree of association being greater than a threshold; modify the action command based on at least one of the modification example and the modification amount; and output the modified action command and the utterance command.
  2. The output device according to claim 1, wherein the processor is configured to: store a plurality of modification examples for the action command; and select the modification example, corresponding to the keyword of the first utterance content and the keyword of the second utterance content, out of the plurality of modification examples.
  3. The output device according to claim 1, wherein the processor is configured to calculate the modification amount by including weighting.
  4. The output device according to claim 1, wherein the extracted keywords are stored in advance.
  5. An electronic apparatus comprising: a speaker configured to make an utterance in response to an utterance command, the utterance command including a first utterance content and a second utterance content; a body configured to perform an action in response to an action command, the action command being located between the first utterance content and the second utterance content; and an output device including: a memory; and a processor coupled to the memory and configured to: analyze the utterance command by at least one of: extracting a keyword from each of the first utterance content and the second utterance content, and identifying a modification example based on the extracted keywords; extracting the keyword from each of the first utterance content and the second utterance content, identifying a parameter value associated with the action command, and calculating a modification amount based on the extracted keywords and the parameter value; and extracting the keyword from each of the first utterance content and the second utterance content, identifying a degree of association between the action command and an emotion, and calculating a modification amount based on the extracted keywords and the degree of association being greater than a threshold; modify the action command based on at least one of the modification example and the modification amount; and control the action of the body based on result of the modification.
  6. An output method executed by a processor included in an output device, the method comprising: obtaining an utterance command and an action command, the utterance command including a first utterance content and a second utterance content, and the action command being located between the first utterance content and the second utterance content; analyzing the utterance command by at least one of: extracting a keyword from each of the first utterance content and the second utterance content, and identifying a modification example based on the extracted keywords; extracting the keyword from each of the first utterance content and the second utterance content, identifying a parameter value associated with the action command, and calculating a modification amount based on the extracted keywords and the parameter value; and extracting the keyword from each of the first utterance content and the second utterance content, identifying a degree of association between the action command and an emotion, and calculating a modification amount based on the extracted keywords and the degree of association being greater than a threshold; modifying the action command based on at least one of the modification example and the modification amount; and outputting the modified action command and the utterance command.
  7. A non-transitory computer-readable recording medium storing a program that causes a processor included in an output device to execute a process, the process comprising: obtaining an utterance command and an action command, the utterance command including a first utterance content and a second utterance content, and the action command being located between the first utterance content and the second utterance content; analyzing the utterance command by at least one of: extracting a keyword from each of the first utterance content and the second utterance content, and identifying a modification example based on the extracted keywords; extracting the keyword from each of the first utterance content and the second utterance content, identifying a parameter value associated with the action command, and calculating a modification amount based on the extracted keywords and the parameter value; and extracting the keyword from each of the first utterance content and the second utterance content, identifying a degree of association between the action command and an emotion, and calculating a modification amount based on the extracted keywords and the degree of association being greater than a threshold; modifying the action command based on at least one of the modification example and the modification amount; and outputting the modified action command and the utterance command.

Description

The embodiments discussed herein are related to an output device, an output method, and an electronic apparatus.

There have been developed robots that make expressions using both utterance and action in combination. For such robots, to avoid a stereotypical action being selected in response to the same phrase, a technology that uses random numbers for avoiding the exact same action has been disclosed (for example, see International Publication Pamphlet No. WO/2012/103030). There has also been disclosed a technology that allows an animal robot to act based on history of inputted information (for example, see Japanese Laid-open Patent Publication No. 2010-149276).

According to an aspect of the embodiments, an output device includes a memory and a processor coupled to the memory. The processor obtains an utterance command and an action command, analyzes an utterance content of the utterance command inputted after an action performed in response to the action command, modifies the action command based on a result of the analysis, and outputs the modified action command and the utterance command.

The object and advantages of the invention will be realized and attained by means of the elements and combinations particularly pointed out in the claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention.

FIG. 1A is a block diagram for describing an electronic apparatus to which a device control circuit according to Embodiment 1 is applied, and FIG.

Citations (17)

  • US20020050802A1
  • JP2010149276A
  • US20010021907A1
  • US20040024602A1
  • JP2004268235A
  • US20060184273A1
  • JP2007050461A
  • JP2010188429A
  • US20120191460A1
  • WO2012103030A1
  • JP2014504959A
  • US20150206534A1
  • JP2015138147A
  • JP2016126294A
  • US20190294638A1
  • US20200016745A1
  • US20200020333A1
Record as JSON
{
  "publication_number": "US10916236B2",
  "country": "US",
  "kind": "B2",
  "title": "Output device, output method, and electronic apparatus",
  "abstract": "An output device includes a memory and a processor coupled to the memory. The processor obtains an utterance command and an action command, analyzes an utterance content of the utterance command inputted after an action performed in response to the action command, modifies the action command based on a result of the analysis, and outputs the modified action command and the utterance command.",
  "claims": [
    "1. An output device comprising: a memory; and a processor coupled to the memory and configured to: obtain an utterance command and an action command, the utterance command including a first utterance content and a second utterance content, and the action command being located between the first utterance content and the second utterance content; analyze the utterance command by at least one of: extracting a keyword from each of the first utterance content and the second utterance content, and identifying a modification example based on the extracted keywords; extracting the keyword from each of the first utterance content and the second utterance content, identifying a parameter value associated with the action command, and calculating a modification amount based on the extracted keywords and the parameter value; and extracting the keyword from each of the first utterance content and the second utterance content, identifying a degree of association between the action command and an emotion, and calculating a modification amount based on the extracted keywords and the degree of association being greater than a threshold; modify the action command based on at least one of the modification example and the modification amount; and output the modified action command and the utterance command.",
    "2. The output device according to claim 1, wherein the processor is configured to: store a plurality of modification examples for the action command; and select the modification example, corresponding to the keyword of the first utterance content and the keyword of the second utterance content, out of the plurality of modification examples.",
    "3. The output device according to claim 1, wherein the processor is configured to calculate the modification amount by including weighting.",
    "4. The output device according to claim 1, wherein the extracted keywords are stored in advance.",
    "5. An electronic apparatus comprising: a speaker configured to make an utterance in response to an utterance command, the utterance command including a first utterance content and a second utterance content; a body configured to perform an action in response to an action command, the action command being located between the first utterance content and the second utterance content; and an output device including: a memory; and a processor coupled to the memory and configured to: analyze the utterance command by at least one of: extracting a keyword from each of the first utterance content and the second utterance content, and identifying a modification example based on the extracted keywords; extracting the keyword from each of the first utterance content and the second utterance content, identifying a parameter value associated with the action command, and calculating a modification amount based on the extracted keywords and the parameter value; and extracting the keyword from each of the first utterance content and the second utterance content, identifying a degree of association between the action command and an emotion, and calculating a modification amount based on the extracted keywords and the degree of association being greater than a threshold; modify the action command based on at least one of the modification example and the modification amount; and control the action of the body based on result of the modification.",
    "6. An output method executed by a processor included in an output device, the method comprising: obtaining an utterance command and an action command, the utterance command including a first utterance content and a second utterance content, and the action command being located between the first utterance content and the second utterance content; analyzing the utterance command by at least one of: extracting a keyword from each of the first utterance content and the second utterance content, and identifying a modification example based on the extracted keywords; extracting the keyword from each of the first utterance content and the second utterance content, identifying a parameter value associated with the action command, and calculating a modification amount based on the extracted keywords and the parameter value; and extracting the keyword from each of the first utterance content and the second utterance content, identifying a degree of association between the action command and an emotion, and calculating a modification amount based on the extracted keywords and the degree of association being greater than a threshold; modifying the action command based on at least one of the modification example and the modification amount; and outputting the modified action command and the utterance command.",
    "7. A non-transitory computer-readable recording medium storing a program that causes a processor included in an output device to execute a process, the process comprising: obtaining an utterance command and an action command, the utterance command including a first utterance content and a second utterance content, and the action command being located between the first utterance content and the second utterance content; analyzing the utterance command by at least one of: extracting a keyword from each of the first utterance content and the second utterance content, and identifying a modification example based on the extracted keywords; extracting the keyword from each of the first utterance content and the second utterance content, identifying a parameter value associated with the action command, and calculating a modification amount based on the extracted keywords and the parameter value; and extracting the keyword from each of the first utterance content and the second utterance content, identifying a degree of association between the action command and an emotion, and calculating a modification amount based on the extracted keywords and the degree of association being greater than a threshold; modifying the action command based on at least one of the modification example and the modification amount; and outputting the modified action command and the utterance command."
  ],
  "description_excerpt": "The embodiments discussed herein are related to an output device, an output method, and an electronic apparatus.\n\nThere have been developed robots that make expressions using both utterance and action in combination. For such robots, to avoid a stereotypical action being selected in response to the same phrase, a technology that uses random numbers for avoiding the exact same action has been disclosed (for example, see International Publication Pamphlet No. WO/2012/103030). There has also been disclosed a technology that allows an animal robot to act based on history of inputted information (for example, see Japanese Laid-open Patent Publication No. 2010-149276).\n\nAccording to an aspect of the embodiments, an output device includes a memory and a processor coupled to the memory. The processor obtains an utterance command and an action command, analyzes an utterance content of the utterance command inputted after an action performed in response to the action command, modifies the action command based on a result of the analysis, and outputs the modified action command and the utterance command.\n\nThe object and advantages of the invention will be realized and attained by means of the elements and combinations particularly pointed out in the claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention.\n\nFIG. 1A is a block diagram for describing an electronic apparatus to which a device control circuit according to Embodiment 1 is applied, and FIG.",
  "cpc": [
    "G10L 15/02",
    "B25J 11/00",
    "B25J 11/0005",
    "G06F 40/279",
    "G06F 40/30",
    "G10L 15/22"
  ],
  "ipc": [
    "B25J 11/00",
    "G06F 40/279",
    "G06F 40/30",
    "G10L 15/02",
    "G10L 15/22"
  ],
  "assignees": [
    "Fujitsu Ltd"
  ],
  "inventors": [
    "Kaoru Kinoshita",
    "Masayoshi Shimizu",
    "Shinji Kanda"
  ],
  "filing_date": "2019-03-11",
  "publication_date": "2021-02-09",
  "grant_date": "2021-02-09",
  "priority_date": "2017-01-30",
  "application_number": "US-201916298158-A",
  "family_id": "62979278",
  "cited_by_count": 2,
  "citations": [
    "US20020050802A1",
    "JP2010149276A",
    "US20010021907A1",
    "US20040024602A1",
    "JP2004268235A",
    "US20060184273A1",
    "JP2007050461A",
    "JP2010188429A",
    "US20120191460A1",
    "WO2012103030A1",
    "JP2014504959A",
    "US20150206534A1",
    "JP2015138147A",
    "JP2016126294A",
    "US20190294638A1",
    "US20200016745A1",
    "US20200020333A1"
  ]
}

Record 1,765 of 8,000 in Patents full text (MLC-0201). Request the full dataset.