Composite entity for rule driven acquisition of input data to chatbots
The present disclosure relates to chatbot systems, and more particularly, to techniques for obtaining data items for input to a chatbot. In certain embodiments, a chatbot system includes a component that can be invoked by a chatbot in the chatbot system to obtain data items needed by the chatbot. The component can be invoked based on a reference to the component in a dialog flow definition configured for the chatbot. The reference to the component can indicate a composite entity that the component will use to determine how the data items are obtained from a user. The composite entity acts as a container for the data items and may be configured separately from the dialog flow definition of the chatbot. The data items can be obtained based on rules specified in a composite entity definition configured for the composite entity.
1. A computer-implemented method comprising:
accessing a plurality of utterances received as part of a conversation between an end user and a chatbot of a chatbot system, the plurality of utterances comprising a first set of entities;
determining, based on the plurality of utterances and a dialog flow definition associated with the conversation, that at least one utterance of the plurality of utterances references a particular component of the dialog flow definition;
in response to determining that the at least one utterance references the particular component, identifying entities included in a second set of entities that are not included in the first set of entities, the second set of entities associated with a component definition of the particular component; and
generating a plurality of prompts for the conversation, at least one prompt of the plurality of prompt configured to prompt the end user to supply information corresponding to at least one entity of the entities included in the second set of entities that are not included in the first set of entities.
2. The method of claim 1 , further comprising:
causing the chatbot to present the at least one prompt to the end user.
3. The method of claim 2 , wherein the plurality of utterances is a plurality of first utterances, and wherein the computer-implemented method further comprises:
accessing a plurality of second utterances received as part of the conversation and in response to the chatbot presenting the at least one prompt.
4. The method of claim 3 , the computer-implemented method further comprising:
causing the chatbot to present at least one response to the end user, wherein the at least one response is generated based on the dialog flow definition and in response to determining that each entity in the second set of entities is associated with at least one piece of information included in at least one of the plurality of first utterances and the plurality of second utterances.
5. The method of claim 3 , the computer-implemented method further comprising:
causing the chatbot to present at least one response to the end user, wherein the at least one response is generated based on the dialog flow definition and in response to determining that information included in the plurality of second utterances does not correspond to any entities in the second set of entities.
6. The method of claim 1 , wherein the at least one prompt is generated based on the component definition.
7. The method of claim 1 , wherein the dialog flow definition and the component definition are stored as separate components of the chatbot system.
8. A system comprising:
one or more processors; and
a memory coupled to the one or more processors, the memory storing instructions that, when executed by the one or more processors, causes the system to perform operations comprising:
accessing a plurality of utterances received as part of a conversation between an end user and a chatbot of a chatbot system, the plurality of utterances comprising a first set of entities;
determining, based on the plurality of utterances and a dialog flow definition associated with the conversation, that at least one utterance of the plurality of utterances references a particular component of the dialog flow definition;
in response to determining that the at least one utterance references the particular component, identifying entities included in a second set of entities that are not included in the first set of entities, the second set of entities associated with a component definition of the particular component; and
generating a plurality of prompts for the conversation, at least one prompt of the plurality of prompt configured to prompt the end user to supply information corresponding to at least one entity of the entities included in the second set of entities that are not included in the first set of entities.
9. The system of claim 8 , the operations further comprising:
causing the chatbot to present the at least one prompt to the end user.
10. The system of claim 9 , wherein the plurality of utterances is a plurality of first utterances, and wherein the operations further comprise:
accessing a plurality of second utterances received as part of the conversation and in response to the chatbot presenting the at least one prompt.
11. The system of claim 10 , the operations further comprising:
causing the chatbot to present at least one response to the end user, wherein the at least one response is generated based on the dialog flow definition and in response to determining that each entity in the second set of entities is associated with at least one piece of information included in at least one of the plurality of first utterances and the plurality of second utterances.
12. The system of claim 10 , the operations further comprising:
causing the chatbot to present at least one response to the end user, wherein the at least one response is generated based on the dialog flow definition and in response to determining that information included in the plurality of second utterances does not correspond to any entities in the second set of entities.
13. The system of claim 8 , wherein the at least one prompt is generated based on the component definition.
14. The system of claim 8 , wherein the dialog flow definition and the component definition are stored as separate components of the chatbot system.
15. A non-transitory computer-readable memory storing instructions that, when executed by one or more processors, causes a system to perform operations comprising:
accessing a plurality of utterances received as part of a conversation between an end user and a chatbot of a chatbot system, the plurality of utterances comprising a first set of entities;
determining, based on the plurality of utterances and a dialog flow definition associated with the conversation, that at least one utterance of the plurality of utterances references a particular component of the dialog flow definition;
in response to determining that the at least one utterance references the particular component, identifying entities included in a second set of entities that are not included in the first set of entities, the second set of entities associated with a component definition of the particular component; and
generating a plurality of prompts for the conversation, at least one prompt of the plurality of prompt configured to prompt the end user to supply information corresponding to at least one entity of the entities included in the second set of entities that are not included in the first set of entities.
16. The non-transitory computer-readable memory of claim 15 , the operations further comprising:
causing the chatbot to present the at least one prompt to the end user.
17. The non-transitory computer-readable memory of claim 16 , wherein the plurality of utterances is a plurality of first utterances, and wherein the operations further comprise:
accessing a plurality of second utterances received as part of the conversation and in response to the chatbot presenting the at least one prompt.
18. The non-transitory computer-readable memory of claim 17 , the operations further comprising:
causing the chatbot to present at least one response to the end user, wherein the at least one response is generated based on the dialog flow definition and in response to determining that each entity in the second set of entities is associated with at least one piece of information included in at least one of the plurality of first utterances and the plurality of second utterances.
19. The non-transitory computer-readable memory of claim 17 , the operations further comprising:
causing the chatbot to present at least one response to the end user, wherein the at least one response is generated based on the dialog flow definition and in response to determining that information included in the plurality of second utterances does not correspond to any entities in the second set of entities.
20. The non-transitory computer-readable memory of claim 15 , wherein the at least one prompt is generated based on the component definition.