- Number
- 20190319898
- Published
- 2019-10-17
- Filed
- 2018-04-12
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Scanlon; Raymond et al.
- CPC
- G06N5/01; G06F16/9535; G06F40/216; G06F40/35; G06N3/006; G06N20/00; H04L51/02; G06F40/295
- Verdict
- Set aside maintaining a conversation, generic chatbot continuity
- Source
- Google Patents · FreePatentsOnline
Abstract
Systems and methods for an interactive communications system capable of generating a response to conversational input are provided. The interactive communications system analyzes the conversational input to determine relevant topics of discussion. The interactive communications system further determines which of the relevant topics of discussion can potentially lead to an unwanted end to a conversation. The interactive communications system redirects the conversation by providing responses to the conversational input that are intended simply to avoid the unwanted end to the conversation.
Background
TECHNICAL FIELD
The present disclosure relates generally to interactive communications systems. More particularly, some embodiments of the present disclosure are directed to providing responses conversational inputs designed to engage a human participant in conversation.DESCRIPTION OF THE RELATED ART
Chatbots refer to computer programs that can conduct a conversation with a human counterpart or participant. Such computer programs are designed to respond to textual and/or auditory (spoken) inputs in a way that attempts to convincingly simulate an actual human-to-human interaction. Other interactive communication systems use interactive agents that may be automatons, puppets, or human actors. These interactive agents engage a human participant in a conversation and can be used as virtual assistants, for entertainment purposes, as well as for promoting products and/or services. Such interactive communications systems are often provided with pre-scripted responses to some conversational input. The pre-scripted responses can be selected using computer programs focused on achieving a particular end-goal, such as engaging a human participant in an interactive story, and guiding the participant through the interactive story until it ends.BRIEF SUMMARY OF THE DISCLOSURE
In accordance with one embodiment, a method comprises receiving conversational input, and determining a likelihood that the conversational input comprises a current conversational topic that will term
Claims
1. A method, comprising: receiving conversational input; determining a likelihood that the conversational input comprises a current conversational topic that will terminate earlier than desired; based on the determined likelihood, seeking out opportunities to segue the current conversational topic to one or more alternative conversational topics, wherein seeking out the opportunities comprises: predicting an end to the current conversational topic based on the conversational input; analyzing the conversational input for cues associated with the alternative conversational topics; and selecting one or more conversational responses associated with the alternative conversational topics to the conversational input.
2. The method of claim 1, wherein the conversational input is received from a human participant of the conversation.
3. The method of claim 1, wherein predicting the end to the conversation comprises parsing the conversational input, and extracting one or more keywords or phrases indicative of at least one of a context of the conversation, an entity providing the conversational input, and one or more topics relevant to the conversation.
4. The method of claim 3, further comprising characterizing at least one of the context of the conversation, the entity providing the conversational input, and the one or more topics relevant to the conversation based upon one or more biometric identifiers of the entity providing the conversational input.
5. The method of claim 3, further comprising characterizing the one or more topics based upon one or more of the context of the conversation and the entity providing the conversational input.
6. The method of claim 3, wherein predicting the end to the conversation further comprises generating a tree structure characterizing a current state of the conversation, wherein each of the one or more topics is represented by a node of the tree structure.
7. The method of claim 6, further comprising updating the tree structure with additional topics as the conversation progresses based upon additional conversational input.
8. The method of claim 6, wherein predicting the end to the conversation further comprises analyzing the tree structure, and determining which of the one or more topics cannot be associated with at least one of knowledge and pre-scripted responses available for presentation to the provider of the conversational input.
9. The method of claim 8, wherein analyzing the conversational input for conversational continuation topics comprises determining which of the one or more topics are associated with at least one of knowledge and pre-scripted responses available for presentation to the provider of the conversational input.
10. The method of claim 9, wherein analyzing the conversational input for conversational continuation topics comprises determining which of the one or more topics associated with the at least one of the knowledge and pre-scripted responses available for presentation to the provider of the conversational input have been previously discussed during progression of the conversation.
11. The method of claim 10, wherein selecting the one or more conversational responses to the conversational input that avoid the predicted end of the conversation comprises the at least one of the knowledge and pre-scripted responses available for presentation to the provider of the conversational input that have not been previously discussed during the progression of the conversation.
12. The method of claim 11, wherein the selection of the one or more conversational responses to the conversational input is based upon non-linear traversal of the tree structure.
13. The method of claim 12, wherein the non-linear traversal of the tree structure comprises selecting the one or more conversational responses to the conversation input that are associated with a sub-topic of one of the one or more topics not previously discussed during the progression of the conversation.
14. The method of claim 12, wherein the non-linear traversal of the tree structure comprises selecting the one or more conversational responses to the conversation input that are associated with a subsequent topic whose subject matter is unrelated to that of a previously discussed topic of the one or more topics.
15. A method, comprising: receiving from a human participant in a simulated conversation, a conversational input; identifying one or more topics for continued discussion during the simulated conversation from the conversational input; determining which of the one or more topics are associated with at least one possible response to the conversational input; and directing the simulated conversation to avoid a first subset of the one or more topics which are not associated with at least one possible response to the conversational input, while maintaining engagement of the human participant in the simulated conversation by generating one or more responses to the conversational input based upon a second subset of the one or more topics which are associated with the at least one possible response to the conversational input.
16. The method of claim 15, wherein the human participant is engaged in the simulated conversation with an interactive agent or a computerized interactive communications system.
17. The method of claim 15, wherein directing the simulated conversation to avoid the first subset of the one or more topics comprises switching to a topic of the second subset of the one or more topics in a non-linear fashion.
18. The method of claim 17, wherein the topic of the second subset of the one more topics comprises a topic previously discussed during the simulated conversation having a related sub-topic that was not previously discussed during the simulated conversation.
19. The method of claim 17, wherein the topic of the second subset of the one or more topics is substantively unrelated to a previous topic of the one or more topics discussed during the simulated conversation.
20. The method of claim 15, further comprising avoiding generating one or more responses to the conversational input based upon a previous topic of the one or more topics discussed during the simulated conversation.