Patent · US11205424B2 · B2 · US
Conversation apparatus, robot, conversation apparatus control method, and non-transitory computer-readable recording medium
- (11) Publication number
- US11205424B2
- (21) Application number
- 16/414,850
- (22) Filing date
- 2019-05-17
- (30) Priority date
- 2018-05-24
- (43) Publication date
- 2021-12-21
- (45) Date of grant
- 2021-12-21
- (51) IPC
- G10L 15/22; G10L 17/00; G10L 17/02; G10L 25/63
- (52) CPC
- (73) Assignee
- Casio Computer Co Ltd
- (72) Inventors
- Kazuhisa Nakamura
- (54) Title
- Conversation apparatus, robot, conversation apparatus control method, and non-transitory computer-readable recording medium
- (57) Abstract
A conversation apparatus includes an audio speaker and a processor. The audio speaker makes an utterance to users. The processor acquires a feature of each of the users, selects, based on the acquired feature of each of the users, a target user to tune to or to not tune to from among the users, and executes utterance control that controls the audio speaker so as to make an utterance that corresponds to the selected target user.
- Full text
- View on Google Patents
Claims (6)
- A conversation apparatus, comprising: a microphone configured to acquire a conversation between users as speech information; an audio speaker configured to output, as the speech information, an utterance to at least one of the users; and a processor configured to execute: selection processing of, when the conversation between the users is acquired via the microphone as the speech information, (i) referencing a first storage storing information related to a feature of each of the users and (ii) selecting a target user to tune to from among the users based on the information related to the feature of each of the users; and output control processing of outputting, from the audio speaker, as the speech information, the utterance in an expression adjusted for a preference of the target user selected in the selection processing, wherein: the information related to the feature of each of the users includes information related to a personality of each of the users, the information related to the personality of each of the users including information related to at least one of calmness, honesty, kindness, and compassion of each of the users; and the processor is configured to, in the selection processing, (i) reference the first storage storing the information related to at least one of calmness, honesty, kindness, and compassion of each of the users and (ii) select the target user to tune to from among the users based on the information related to at least one of calmness, honesty, kindness, and compassion of each of the users.
- The conversation apparatus according to claim 1, wherein: the processor is configured to, in the output control processing, (i) reference a second storage storing information related to the preference of the target user selected in the selection processing and (ii) output, when content of the utterance matches the preference of the target user, the utterance as the speech information in a positive expression, and output, when the content of the utterance does not match the preference of the target user, the utterance as the speech information in a negative expression.
- The conversation apparatus according to claim 1, wherein: the processor is further configured to execute storage control processing of storing the feature of each of the users in the first storage, based on the speech information of the conversation between the users that is acquired via the microphone.
- A conversation apparatus control method for controlling a conversation apparatus that includes a microphone for acquiring a conversation between users as speech information and an audio speaker for outputting an utterance to at least one of the users as the speech information, the method comprising: when the conversation between the users is acquired via the microphone as the speech information, (i) referencing a first storage storing information related to a feature of each of the users and (ii) selecting a target user to tune to from among the users based on the information related to the feature of each of the users; and outputting, from the audio speaker, as the speech information, the utterance in an expression adjusted for a preference of the selected target user, wherein: the information related to the feature of each of the users includes information related to a personality of each of the users, the information related to the personality of each of the users including information related to at least one of calmness, honesty, kindness, and compassion of each of the users; and said (i) referencing comprises referencing the first storage storing the information related to at least one of calmness, honesty, kindness, and compassion of each of the users and said (ii) selecting comprises selecting the target user to tune to from among the users based on the information related to at least one of calmness, honesty, kindness, and compassion of each of the users.
- A non-transitory computer-readable recording medium that stores a program executable by a processor included in a conversation apparatus that includes a microphone for acquiring a conversation between users as speech information and an audio speaker for outputting an utterance to at least one of the users as the speech information, the program causing the processor to execute: selection processing of, when the conversation between the users is acquired via the microphone as the speech information, (i) referencing a first storage storing information related to a feature of each of the users and (ii) selecting a target user to tune to from among the users based on the information related to the feature of each of the users; and output control processing of outputting, from the audio speaker, as the speech information, the utterance in an expression adjusted for a preference of the target user selected in the selection processing; wherein: the information related to the feature of each of the users includes information related to a personality of each of the users, the information related to the personality of each of the users including information related to at least one of calmness, honesty, kindness, and compassion of each of the users; and in said selection processing, said (i) referencing comprises referencing the first storage storing the information related to at least one of calmness, honesty, kindness, and compassion of each of the users and said (ii) selecting comprises selecting the target user to tune to from among the users based on the information related to at least one of calmness, honesty, kindness, and compassion of each of the users.
- A conversation apparatus, comprising: a microphone configured to acquire a conversation between users as speech information; an audio speaker configured to output, as the speech information, an utterance to at least one of the users; and a processor configured to execute: selection processing of, when the conversation between the users is acquired via the microphone as the speech information, (i) referencing a first storage storing information related to a feature of each of the users and (ii) selecting a target user to tune to from among the users based on the information related to the feature of each of the users; and output control processing of outputting, from the audio speaker, as the speech information, the utterance in an expression adjusted for a preference of the target user selected in the selection processing, wherein: the information related to the feature of each of the users includes information related to a personality of each of the users; and the processor is configured to, in the selection processing, (i) reference the first storage storing the information related to the personality of each of the users and (ii) select, from among the users, as the target user, a user that has a most positive personality among the personalities of the users.
Description
This application relates generally to a conversation apparatus, a robot, a conversation apparatus control method, and a non-transitory computer-readable recording medium.
Advances have been made in the development of technologies capable of facilitating communication between users. For example, Unexamined Japanese Patent Application Kokai Publication No. 2016-006607 describes a conversation-type communication system that monitors the state of a conversation taking place between users and, when the conversation becomes stagnated, provides a topic of conversation that is of interest to the users.
A conversation apparatus includes:
an audio speaker configured to make an utterance to users; and
a processor configured to
A more complete understanding of this application can be obtained when the following detailed description is considered in conjunction with the following drawings, in which:
FIG. 1 is a drawing illustrating the functional configuration of a conversation apparatus according to Embodiment 1 of the present disclosure;
FIG. 2 is a drawing illustrating an example of data stored in a feature storage unit of the conversation apparatus according to Embodiment 1;
FIG. 3 is a drawing illustrating an example of a conversation taking place near the conversation apparatus according to Embodiment 1;
FIG. 4 is a drawing illustrating another example of a conversation taking place near the conversation apparatus according to Embodiment 1;
FIG. 5 is a flowchart of feature acquisition processing of the conversation apparatus according to Embodiment 1;
Citations (16)
- US6144938A
- JP2016006607A
- US20160042749A1
- US20170337921A1
- US20190019511A1
- US20190027142A1
- US20180089175A1
- US20190223798A1
- US20200005786A1
- US20200013402A1
- US20200143806A1
- US20190164544A1
- US20200312317A1
- US20190266999A1
- US20190348023A1
- US20200202856A1
Record as JSON
{
"publication_number": "US11205424B2",
"country": "US",
"kind": "B2",
"title": "Conversation apparatus, robot, conversation apparatus control method, and non-transitory computer-readable recording medium",
"abstract": "A conversation apparatus includes an audio speaker and a processor. The audio speaker makes an utterance to users. The processor acquires a feature of each of the users, selects, based on the acquired feature of each of the users, a target user to tune to or to not tune to from among the users, and executes utterance control that controls the audio speaker so as to make an utterance that corresponds to the selected target user.",
"claims": [
"1. A conversation apparatus, comprising: a microphone configured to acquire a conversation between users as speech information; an audio speaker configured to output, as the speech information, an utterance to at least one of the users; and a processor configured to execute: selection processing of, when the conversation between the users is acquired via the microphone as the speech information, (i) referencing a first storage storing information related to a feature of each of the users and (ii) selecting a target user to tune to from among the users based on the information related to the feature of each of the users; and output control processing of outputting, from the audio speaker, as the speech information, the utterance in an expression adjusted for a preference of the target user selected in the selection processing, wherein: the information related to the feature of each of the users includes information related to a personality of each of the users, the information related to the personality of each of the users including information related to at least one of calmness, honesty, kindness, and compassion of each of the users; and the processor is configured to, in the selection processing, (i) reference the first storage storing the information related to at least one of calmness, honesty, kindness, and compassion of each of the users and (ii) select the target user to tune to from among the users based on the information related to at least one of calmness, honesty, kindness, and compassion of each of the users.",
"2. The conversation apparatus according to claim 1, wherein: the processor is configured to, in the output control processing, (i) reference a second storage storing information related to the preference of the target user selected in the selection processing and (ii) output, when content of the utterance matches the preference of the target user, the utterance as the speech information in a positive expression, and output, when the content of the utterance does not match the preference of the target user, the utterance as the speech information in a negative expression.",
"3. The conversation apparatus according to claim 1, wherein: the processor is further configured to execute storage control processing of storing the feature of each of the users in the first storage, based on the speech information of the conversation between the users that is acquired via the microphone.",
"4. A conversation apparatus control method for controlling a conversation apparatus that includes a microphone for acquiring a conversation between users as speech information and an audio speaker for outputting an utterance to at least one of the users as the speech information, the method comprising: when the conversation between the users is acquired via the microphone as the speech information, (i) referencing a first storage storing information related to a feature of each of the users and (ii) selecting a target user to tune to from among the users based on the information related to the feature of each of the users; and outputting, from the audio speaker, as the speech information, the utterance in an expression adjusted for a preference of the selected target user, wherein: the information related to the feature of each of the users includes information related to a personality of each of the users, the information related to the personality of each of the users including information related to at least one of calmness, honesty, kindness, and compassion of each of the users; and said (i) referencing comprises referencing the first storage storing the information related to at least one of calmness, honesty, kindness, and compassion of each of the users and said (ii) selecting comprises selecting the target user to tune to from among the users based on the information related to at least one of calmness, honesty, kindness, and compassion of each of the users.",
"5. A non-transitory computer-readable recording medium that stores a program executable by a processor included in a conversation apparatus that includes a microphone for acquiring a conversation between users as speech information and an audio speaker for outputting an utterance to at least one of the users as the speech information, the program causing the processor to execute: selection processing of, when the conversation between the users is acquired via the microphone as the speech information, (i) referencing a first storage storing information related to a feature of each of the users and (ii) selecting a target user to tune to from among the users based on the information related to the feature of each of the users; and output control processing of outputting, from the audio speaker, as the speech information, the utterance in an expression adjusted for a preference of the target user selected in the selection processing; wherein: the information related to the feature of each of the users includes information related to a personality of each of the users, the information related to the personality of each of the users including information related to at least one of calmness, honesty, kindness, and compassion of each of the users; and in said selection processing, said (i) referencing comprises referencing the first storage storing the information related to at least one of calmness, honesty, kindness, and compassion of each of the users and said (ii) selecting comprises selecting the target user to tune to from among the users based on the information related to at least one of calmness, honesty, kindness, and compassion of each of the users.",
"6. A conversation apparatus, comprising: a microphone configured to acquire a conversation between users as speech information; an audio speaker configured to output, as the speech information, an utterance to at least one of the users; and a processor configured to execute: selection processing of, when the conversation between the users is acquired via the microphone as the speech information, (i) referencing a first storage storing information related to a feature of each of the users and (ii) selecting a target user to tune to from among the users based on the information related to the feature of each of the users; and output control processing of outputting, from the audio speaker, as the speech information, the utterance in an expression adjusted for a preference of the target user selected in the selection processing, wherein: the information related to the feature of each of the users includes information related to a personality of each of the users; and the processor is configured to, in the selection processing, (i) reference the first storage storing the information related to the personality of each of the users and (ii) select, from among the users, as the target user, a user that has a most positive personality among the personalities of the users."
],
"description_excerpt": "This application relates generally to a conversation apparatus, a robot, a conversation apparatus control method, and a non-transitory computer-readable recording medium.\n\nAdvances have been made in the development of technologies capable of facilitating communication between users. For example, Unexamined Japanese Patent Application Kokai Publication No. 2016-006607 describes a conversation-type communication system that monitors the state of a conversation taking place between users and, when the conversation becomes stagnated, provides a topic of conversation that is of interest to the users.\n\nA conversation apparatus includes:\n\nan audio speaker configured to make an utterance to users; and\n\na processor configured to\n\nA more complete understanding of this application can be obtained when the following detailed description is considered in conjunction with the following drawings, in which:\n\nFIG. 1 is a drawing illustrating the functional configuration of a conversation apparatus according to Embodiment 1 of the present disclosure;\n\nFIG. 2 is a drawing illustrating an example of data stored in a feature storage unit of the conversation apparatus according to Embodiment 1;\n\nFIG. 3 is a drawing illustrating an example of a conversation taking place near the conversation apparatus according to Embodiment 1;\n\nFIG. 4 is a drawing illustrating another example of a conversation taking place near the conversation apparatus according to Embodiment 1;\n\nFIG. 5 is a flowchart of feature acquisition processing of the conversation apparatus according to Embodiment 1;",
"cpc": [
"G10L 15/22",
"B25J 11/0005",
"B25J 9/1602",
"G06F 40/35",
"G10L 17/00",
"G10L 17/02",
"G10L 25/63"
],
"ipc": [
"G10L 15/22",
"G10L 17/00",
"G10L 17/02",
"G10L 25/63"
],
"assignees": [
"Casio Computer Co Ltd"
],
"inventors": [
"Kazuhisa Nakamura"
],
"filing_date": "2019-05-17",
"publication_date": "2021-12-21",
"grant_date": "2021-12-21",
"priority_date": "2018-05-24",
"application_number": "US-201916414850-A",
"family_id": "68614846",
"cited_by_count": 0,
"citations": [
"US6144938A",
"JP2016006607A",
"US20160042749A1",
"US20170337921A1",
"US20190019511A1",
"US20190027142A1",
"US20180089175A1",
"US20190223798A1",
"US20200005786A1",
"US20200013402A1",
"US20200143806A1",
"US20190164544A1",
"US20200312317A1",
"US20190266999A1",
"US20190348023A1",
"US20200202856A1"
]
}
Record 1,341 of 8,000 in Patents full text (MLC-0201). Request the full dataset.