Dialogue method, dialogue system, dialogue apparatus and program

{
  "publication_number": "US2019206406A1",
  "country": "US",
  "kind": "A1",
  "title": "Dialogue method, dialogue system, dialogue apparatus and program",
  "abstract": "The present invention improves a sense of participation in a topic and enables a dialogue to continue for a long time. A dialogue system 12 includes at least an input part 1 that receives a user's utterance and a presentation part 5 that presents an utterance. In an utterance receiving step, the input part 1 receives an utterance performed by the user. In a first presentation step, the presentation part 5 presents an utterance determined based on scenarios stored in advance. In a second presentation step, the presentation part 5 presents the utterance determined based on the user's utterance contents. A dialogue control part 8 performs control to execute a dialogue at least including a first dialogue flow which is a dialogue including the utterance receiving step and the first presentation step at least one time respectively based on a predetermined scenario, and a second dialogue flow which is a dialogue including the utterance receiving step and the second presentation step at least one time respectively.",
  "claims": [
    "1. A dialogue method executed by a dialogue system that performs a dialogue with a user, the method comprising: an utterance receiving step in which an input part receives an utterance performed by the user; a first presentation step in which a presentation part presents an utterance determined based on a scenario stored in advance; a second presentation step in which the presentation part presents an utterance determined based on the user's utterance contents; and a dialogue control step in which a dialogue control part performs control to execute a dialogue at least including: a first dialogue flow which is a dialogue including the utterance receiving step and the first presentation step at least one time respectively based on a predetermined scenario; and a second dialogue flow which is a dialogue including the utterance receiving step and the second presentation step at least one time respectively. 2. The dialogue method according to claim 1, wherein the dialogue control step performs control to execute a dialogue according to the second dialogue flow between a first dialogue according to the first dialogue flow and a second dialogue according to the first dialogue flow. 3. The dialogue method according to claim 1 or 2, wherein judgement criteria for judging a failure of the first dialogue flow are predetermined, and the second dialogue flow is executed when the first dialogue flow is judged to be a failure. 4. The dialogue method according to claim 3, wherein the judgement criteria for judging a failure of the first dialogue flow comprise judging that the first dialogue flow fails when the user's utterance received in the utterance receiving step in the first dialogue flow does not match the utterance determined for the utterance based on a scenario stored in advance. 5. The dialogue method according to claim 3, wherein the judgement criteria for judging a failure of the first dialogue flow comprise judging that the first dialogue flow fails when the user's reaction to the utterance in the first presentation step is unfavorable. 6. (canceled) 7. The dialogue method according to claim 1 or 2, wherein the first dialogue flow based on the scenario is executed when at least one of the user's utterance received in the utterance receiving step in the second dialogue flow and the utterance outputted in the second presentation step in the second dialogue flow corresponds to the predetermined scenario. 8. The dialogue method according to claim 1, wherein judgement criteria for judging a failure of the second dialogue flow are predetermined and the first dialogue flow is executed when the second dialogue flow is judged to be a failure. 9. The dialogue method according to claim 8, wherein the judgement criteria for judging a failure of the second dialogue flow comprise judging that the second dialogue flow fails when the user's utterance received in the utterance receiving step in the second dialogue flow does not match the utterance generated at least based on contents of the utterance or when such a mismatch occurs a predetermined number of times or more consecutively. 10 - 11. (canceled) 12. The dialogue method according to claim 1 or 2, wherein the utterance in the first presentation step of the first dialogue flow executed immediately after the second dialogue flow is an utterance with a word representing a change of topics at the head of the utterance. 13. The dialogue method according to claim 1 or 2, wherein the utterance in the first presentation step of the first dialogue flow executed immediately before the second dialogue flow is an utterance urging the user to perform an utterance other than the utterance about the topic in the first dialogue flow. 14. The dialogue method according to claim 1, wherein selection criteria for selecting one scenario from among a plurality of scenarios stored in advance as a scenario of the first dialogue flow executed immediately after the second dialogue flow comprise criteria based on utterance contents of the second dialogue flow. 15. The dialogue method according to claim 14, wherein the plurality of scenarios stored in advance are stored with a word representing a topic of each scenario associated with each scenario, and the selection criteria are criteria at least based on a level of similarity between a word representing a topic of a scenario and utterance contents of the second dialogue flow. 16. The dialogue method according to claim 14, wherein the selection criteria are criteria at least based on a level of similarity between contents of a leading portion of a scenario and utterance contents of the second dialogue flow. 17. The dialogue method according to any one of claims 14 to 16, wherein the plurality of scenarios stored in advance are stored with information indicating likelihood of selection of each scenario associated with each scenario, and the selection criteria are criteria according to which a selection is performed based on the likelihood when the selection of one scenario from among the plurality of scenarios based on utterance contents of the second dialogue flow is judged to be inappropriate. 18. The dialogue method according to claim 1 or 2, wherein the utterance in the second presentation step in the second dialogue flow executed immediately after the first dialogue flow is generated based on utterance contents of the first dialogue flow. 19. A dialogue system that performs a dialogue with a user, comprising: an input part that receives an utterance performed by the user; an utterance determination part that determines a first utterance based on a scenario stored in advance and a second utterance based on the user's utterance contents; a presentation part that presents the first utterance determined by the utterance determination part and the second utterance determined by the utterance determination part; and a dialogue control part that performs control to execute a dialogue at least including: a first dialogue flow which is a dialogue including receiving the utterance performed by the user and determining an utterance presented by the presentation part at least one time respectively based on a predetermined scenario; and a second dialogue flow which is a dialogue including receiving the utterance performed by the user and determining the utterance presented by the presentation part at least based on the utterance at least one time respectively. 20. A dialogue apparatus that determines an utterance presented by a dialogue system comprising an input part that receives an utterance performed by a user, an utterance determination part that determines an utterance presented by a presentation part, and the presentation part that presents the utterance determined by the utterance determination part, the dialogue apparatus comprising a dialogue control part that performs control to execute a dialogue at least including: a first dialogue flow which is a dialogue including receiving the utterance performed by the user and determining the utterance presented by the presentation part at least one time respectively based on a predetermined scenario; and a second dialogue flow which is a dialogue including receiving the utterance performed by the user and determining the utterance presented by the presentation part at least based on the utterance at least one time respectively. 21. The dialogue apparatus according to claim 20, wherein the dialogue control part causes a dialogue according to the second dialogue flow to be executed between a first dialogue according to the first dialogue flow and a second dialogue according to the first dialogue flow. 22 - 23. (canceled) 24. The dialogue method according to claim 4, wherein the judgement criteria for judging a failure of the first dialogue flow comprise judging that the first dialogue flow fails when the user's reaction to the utterance in the first presentation step is unfavorable. 25. The dialogue method according to any one of claim 3 to 5, or 24, wherein the judgement criteria for judging a failure of the first dialogue flow comprise judging that the first dialogue flow fails when the user's utterance received in the utterance receiving step in the first dialogue flow includes a predetermined phrase. 26. The dialogue method according to claim 2, wherein judgement criteria for judging a failure of the second dialogue flow are predetermined and the first dialogue flow is executed when the second dialogue flow is judged to be a failure. 27. The dialogue method according to claim 26, wherein the judgement criteria for judging a failure of the second dialogue flow comprise judging that the second dialogue flow fails when the user's utterance received in the utterance receiving step in the second dialogue flow does not match the utterance generated at least based on contents of the utterance or when such a mismatch occurs a predetermined number of times or more consecutively. 28. The dialogue method according to any one of claim 8, 9, 26, or 27, wherein the judgement criteria for judging a failure of the second dialogue flow comprise judging that the second dialogue flow fails when the user's reaction to the utterance in the second presentation step is unfavorable. 29. The dialogue method according to any one of claim 8, 9, 26, or 27, wherein the judgement criteria for judging a failure of the second dialogue flow comprise judging that the second dialogue flow fails when the user's utterance received in the utterance receiving step in the second dialogue flow includes a predetermined phrase. 30. A non-transitory computer readable recording medium including computer executable instructions that make a dialogue system perform a dialogue method, wherein the dialogue system performs a dialogue with a user, the dialogue method comprising: an utterance receiving step in which an input part receives an utterance performed by the user; a first presentation step in which a presentation part presents an utterance determined based on a scenario stored in advance; a second presentation step in which the presentation part presents an utterance determined based on the user's utterance contents; and a dialogue control step in which a dialogue control part performs control to execute a dialogue at least including: a first dialogue flow which is a dialogue including the utterance receiving step and the first presentation step at least one time respectively based on a predetermined scenario; and a second dialogue flow which is a dialogue including the utterance receiving step and the second presentation step at least one time respectively. 31. A non-transitory computer readable recording medium including computer executable instructions that make a dialogue apparatus perform a dialogue method that determines an utterance presented by a dialogue system comprising an input part that receives an utterance performed by a user, an utterance determination part that determines an utterance presented by a presentation part, and the presentation part that presents the utterance determined by the utterance determination part, the method comprising: a dialogue control step in which a dialogue control part performs control to execute a dialogue at least including: a first dialogue flow which is a dialogue including receiving the utterance performed by the user and determining the utterance presented by the presentation part at least one time respectively based on a predetermined scenario; and a second dialogue flow which is a dialogue including receiving the utterance performed by the user and determining the utterance presented by the presentation part at least based on the utterance at least one time respectively."
  ],
  "description_excerpt": "The present invention relates to a technique for a computer to perform a dialogue with a human using a natural language, which is applicable to a robot or the like communicating with humans.\n\nIn recent years, research and development on robots communicating with humans has been progressing and put to practical use at various scenes. For example, at the site of communication therapy, there is a usage pattern in which a robot serves as a companion to talk with a person feeling loneliness. More specifically, a robot plays a role of a listener to a resident at elder care facilities, and can thereby heal the loneliness of the resident, and also can show the resident having dialogue with the robot to make chances to start dialogue between the resident and people around the resident such as his/her family and nurses. In addition, at the site of communication training, there is a usage pattern in which a robot becomes a training partner. More specifically, the robot becomes a training partner for foreign language learners at foreign language schools, thus helping the foreign language learners to efficiently proceed with foreign language learning. Furthermore, in an application as an information presentation system, robots perform a dialogue with each other and have their dialogue heard by people as a basis, sometimes talk to people, cause the people to join in dialogue without making the people bored, and can thereby present information in a form easily acceptable to the people.",
  "cpc": [
    "G10L 15/22",
    "A63H 2200/00",
    "A63H 3/003",
    "A63H 3/28",
    "B25J 11/0005",
    "B25J 13/08",
    "G10L 13/00",
    "G10L 13/043",
    "G10L 15/26",
    "G10L 15/265",
    "G10L 2015/223",
    "G10L 2015/225"
  ],
  "ipc": [
    "B25J 11/00",
    "G10L 13/04",
    "G10L 15/22",
    "G10L 15/26"
  ],
  "assignees": [
    "Nippon Telegraph and Telephone Corp",
    "Osaka University NUC"
  ],
  "inventors": [
    "Hiroaki Sugiyama",
    "Toyomi MEGURO",
    "Junji Yamato",
    "Yuichiro YOSHIKAWA",
    "Hiroshi Ishiguro"
  ],
  "filing_date": "2017-05-19",
  "publication_date": "2019-07-04",
  "priority_date": "2016-05-20",
  "application_number": "US-201716301641-A",
  "family_id": "60326301",
  "cited_by_count": 16,
  "citations": [
    "US20140149121A1",
    "US20060177802A1",
    "US20070255566A1",
    "US20120035935A1",
    "US20120173244A1",
    "US20140136212A1"
  ]
}