Context retrieval for chatbots

Patent metadata

Field	Value
Publication number	US-2021165967-A1
Application number	US-201916701263-A
Country	US
Kind code	A1
Filing date	Dec 3, 2019
Priority date	Dec 3, 2019
Publication date	Jun 3, 2021
Grant date	—

Abstract

A method for supplementing context in dialog flows for chatbot systems includes responsive to receiving identification information associated with a user and a topic for a chatbot conversation, initializing a chatbot conversation between a chatbot and the user. The method identifies a set of entities and a set of one or more relationships, wherein each relationship from the set one or more relationships is between two entities from the set of entities. The method determines an initial set of relevancy scores for each entity in the set of entities and the set of one or more relationships, wherein the initial set of relevancy scores are based at least on a domain for the topic of the chatbot conversation. The method generates a first response to the user based on the initial set of relevancy scores, wherein the first response includes at least one entity and at least one relationship.

First claim

What is claimed is:

1 . A method comprising:
responsive to receiving identification information associated with an end user and a topic for a chatbot conversation, initializing, by one or more processors, a chatbot conversation between a chatbot and the end user; identifying, by one or more processors, a set of entities and a set of one or more relationships provided by the end user in the identification information and the topic, wherein each relationship from the set one or more relationships is between two entities from the set of entities; determining, by one or more processors, an initial set of relevancy scores for each entity in the set of entities and the set of one or more relationships, wherein the initial set of relevancy scores are based at least on a domain for the topic of the chatbot conversation; and generating, by one or more processors, a first response to the end user based on the initial set of relevancy scores, wherein the first response includes at least one entity from the set of entities and at least one relationship from of the set of one or more relationships.

2 . The method of claim 1 , further comprising:
responsive to receiving a second response from the end user, updating, by one or more processors, the initial set of relevancy scores for the set of entities and the set of one or more relationships, wherein the second response includes a confirmation to a question presented in the first response; and generating, by one or more processors, a third response to the end user based on the updated initial set of relevancy scores, wherein the third response includes the least one entity from the set of entities and the at least one relationship from of the set of one or more relationships from the first response.

3 . The method of claim 1 , further comprising
responsive to receiving a second response from the end user, updating, by one or more processors, the initial set of relevancy scores for the set of entities and the set of one or more relationship, wherein the second response includes a rejection to a question presented in the first response; and generating, by one or more processors, a third response to the end user based on the updated initial set of relevancy scores, wherein the third response excludes the least one entity from the set of entities and the at least one relationship from of the set of one or more relationships from the first response.

4 . The method of claim 1 , further comprising:
generating, by one or more processors, a prerequisite knowledge store based on structured and unstructured data from publicly accessible sources, wherein the prerequisite knowledge store includes a plurality of entities and a plurality of relationships; assigning, by one or more processors, a plurality of relevancy scores for the plurality of entities and the plurality of relationships; and updating, by one or more processors, the prerequisite knowledge store based on the domain for the chatbot.

5 . The method of claim 4 , wherein the plurality of entities includes the set of entities and the plurality of relationships includes the set of one or more relationships.

6 . The method of claim 4 , wherein updating the prerequisite knowledge store based on the domain for the chatbot is based on a plurality of topics for associated with a plurality of previous chatbot conversations.

7 . The method of claim 2 , wherein the third response includes a resolution to an issue presented in the topic.

8 . A computer program product comprising:
one or more computer readable storage media and program instructions stored on at least one of the one or more storage media, the program instructions comprising: program instructions to, responsive to receiving identification information associated with an end user and a topic for a chatbot conversation, initialize a chatbot conversation between a chatbot and the end user; program instructions to identify a set of entities and a set of one or more relationships provided by the end user in the identification information and the topic, wherein each relationship from the set one or more relationships is between two entities from the set of entities; program instructions to determine an initial set of relevancy scores for each entity in the set of entities and the set of one or more relationships, wherein the initial set of relevancy scores are based at least on a domain for the topic of the chatbot conversation; and program instructions to generate a first response to the end user based on the initial set of relevancy scores, wherein the first response includes at least one entity from the set of entities and at least one relationship from of the set of one or more relationships.

9 . The computer program product of claim 8 , further comprising program instructions, stored on the one or more computer readable storage media, which when executed by a processor, cause the processor to:
responsive to receiving a second response from the end user, update the initial set of relevancy scores for the set of entities and the set of one or more relationships, wherein the second response includes a confirmation to a question presented in the first response; and generate a third response to the end user based on the updated initial set of relevancy scores, wherein the third response includes the least one entity from the set of entities and the at least one relationship from of the set of one or more relationships from the first response.

10 . The computer program product of claim 8 , further comprising program instructions, stored on the one or more computer readable storage media, which when executed by a processor, cause the processor to:
responsive to receiving a second response from the end user, update the initial set of relevancy scores for the set of entities and the set of one or more relationship, wherein the second response includes a rejection to a question presented in the first response; and generate a third response to the end user based on the updated initial set of relevancy scores, wherein the third response excludes the least one entity from the set of entities and the at least one relationship from of the set of one or more relationships from the first response.

11 . The computer program product of claim 8 , further comprising program instructions, stored on the one or more computer readable storage media, which when executed by a processor, cause the processor to:
generate a prerequisite knowledge store based on structured and unstructured data from publicly accessible sources, wherein the prerequisite knowledge store includes a plurality of entities and a plurality of relationships; assign a plurality of relevancy scores for the plurality of entities and the plurality of relationships; and updating, by one or more processors, the prerequisite knowledge store based on the domain for the chatbot.

12 . The computer program product of claim 11 , wherein the plurality of entities includes the set of entities and the plurality of relationships includes the set of one or more relationships.

13 . The computer program product of claim 11 , wherein updating the prerequisite knowledge store based on the domain for the chatbot is based on a plurality of topics for associated with a plurality of previous chatbot conversations.

14 . The computer program product of claim 9 , wherein the third response includes a resolution to an issue presented in the topic.

15 . A computer system comprising:
one or more computer processors; one or more computer readable storage media; and program instructions stored on the computer read

Assignees

• IBM

Inventors

• Shek Elinna
• Ding Chengmin
• Filoti Octavian Florin
• Vernier Stanley John
• Decker Renee F

Classifications

• G06F40/295

  Named entity recognition · CPC title

• G06F40/35 Primary

  Discourse or dialogue representation · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title