Chatbot system and machine learning modules for query analysis and interface generation

Patent metadata

Field	Value
Publication number	US-12373893-B2
Application number	US-202217855184-A
Country	US
Kind code	B2
Filing date	Jun 30, 2022
Priority date	Jun 30, 2021
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

Aspects of the disclosure relate to using machine learning methods for chatbot selection. A computing platform may train a plurality of machine learning models, each corresponding to a chatbot. The computing platform may train an additional machine learning model to route queries to the plurality of machine learning models based on contents of the queries. The computing platform may receive a query, and may analyze the query using the additional machine learning model. The computing platform may route, based on the query analysis, the query to the plurality of machine learning models. The computing platform may generate, using the plurality of machine learning models, a response to the query. The computing platform may send the response to the query and one or more commands directing a client device to display the response to the query, which may cause the client device to display the response to the query.

First claim

What is claimed is:

1. A chatbot system configured to analyze query data, the chatbot system comprising:
a plurality of machine learning models and a plurality of chatbots, each of the plurality of machine learning models corresponding to a respective chatbot of the plurality of chatbots; and
a computing platform comprising a processor, a non-transitory computer-readable memory communicatively coupled to the processor, and machine-readable instructions stored in the memory that, when executed by the processor, cause the processor of the computing platform to, across at least one or more intelligent platforms, technical platforms, or combinations thereof:
parse a query comprising a content to identify at least a category and at least a first sub-category and a second sub-category, each associated with the category corresponding to the query;
route the query to at least two selected models of the plurality of machine learning models based on the content of the query and the at least the first sub-category and the second sub-category that are identified such that the query is routed to at least two selected chatbots of the plurality of chatbots, wherein the query is routed to a first selected chatbot of the at least two selected chatbots based on the first sub-category as identified and the query is routed to the a second selected chatbot different from the first selected chatbot based on the second sub-category as identified;
generate a response to the query, using the at least two selected models and corresponding at least two selected chatbots, as part of a conversation between a user of a client device and the computing platform;
display the response to the query;
generate a prompt to the user on a graphical user interface of the client device requesting a rating of the response to the query;
generate analytics based on the rating of the response to the query and historical data;
display the analytics on a graphical user interface of an enterprise client device; and
train the at least two selected models of the plurality of machine learning models by generating an association between the analytics and the at least two selected chatbots.

2. The chatbot system of claim 1 , wherein the machine-readable instructions further, when executed by the processor, cause the processor of the computing platform to:
train a computing platform machine learning model corresponding to the computing platform to route queries to one or more of the plurality of machine learning models based on the respective content of the queries; and
route the query to the at least two selected models of the plurality of machine learning models based on the computing platform machine learning model as trained.

3. The chatbot system of claim 1 , wherein the machine-readable instructions further, when executed by the processor, cause the processor of the computing platform to:
train each of the plurality of machine learning models on one or more topics to be associated with the corresponding chatbot of the plurality of chatbots;
generate an association between the content of the query and the one or more topics for at least one chatbot of the plurality of chatbots;
route the query to the at least one chatbot based on the association and the respective trained machine learning model corresponding to the at least one chatbot.

4. The chatbot system of claim 1 , wherein the machine-readable instructions further, when executed by the processor, cause the processor of the computing platform to:
identify, using a first machine learning technique associated with a first machine learning model for the computing platform, a top level category as the category corresponding to the query, the top level category being one of a plurality of categories, the top level category having a highest category ranking as a match to the query; and
identify, using a second machine learning technique associated with a second machine learning model for the computing platform different from the first machine learning model, the second machine learning technique different from the first machine learning technique, a plurality of sub-categories corresponding to the query, and having a highest sub-category ranking the first sub-category and the second sub-category having respectively a first highest sub-category ranking and a second highest sub-category ranking as a match to the query.

5. The chatbot system of claim 4 , wherein the machine-readable instructions further, when executed by the processor, cause the processor of the computing platform to:
identify the top level category and the first sub-category and the second sub-category based on a number of utterances corresponding to the query, labeled data corresponding to the query, unlabeled data corresponding to the query, or combinations thereof, wherein the top level category is associated with a type of insurance, and each of the first sub-category and the second sub-category is associated with one or more requirements for the type of insurance.

6. The chatbot system of claim 1 , wherein the analytics displayed on the graphical user interface of the enterprise client device comprise information regarding whether the user is a flight risk such that the user may discontinue a service based on the rating and the historical data.

7. The chatbot system of claim 1 , wherein the machine-readable instructions further, when executed by the processor, cause the processor of the computing platform to:
receive a configuration update for a selected model of the plurality of machine learning models via an enterprise user device; and
update the selected model based on the configuration update without affecting the other models of the plurality of machine learning models.

8. The chatbot system of claim 7 , wherein the configuration update comprises a JavaScript Object Notation (JSON) object created by a user of an enterprise client device, and the selected model is updated based on storing the JSON object such that additional coding is not required to update the selected model.

9. The chatbot system of claim 1 , wherein the machine-readable instructions further, when executed by the processor, cause the processor of the computing platform to:
generate a plurality of interface screens on a graphical user interface of the client device to display as an information prompt to the user on the graphical user interface requesting information from the user; and
receive information from the user via the plurality of interface screens, each interface screen requesting information from the user to generate the response to the query.

10. The chatbot system of claim 1 , wherein the machine-readable instructions further, when executed by the processor, cause the processor of the computing platform to:
receive the query comprising the content from a graphical user interface of the user of the client device as part of the conversation between the user of the client device and the computing platform; and
display the response to the query to the user on the graphical user interface of the client device of the user.

11. The chatbot system of claim 1 , wherein the query comprises an inquiry regarding a type of insurance, and the response to the query comprises information regarding the type of insurance to address the inquiry.

12. The chatbot system of claim 11 , wherein the type of insurance comprises collision insurance.

13. The chatbot system of claim 12 , wherein the machine-readable instructions further, when executed by the processor, cause the processor of the computing platform to:
generate a customized output comprising a quote for collision insurance based on the respo

Assignees

• Allstate Insurance Co
• Allstate Northern Ireland Ltd

Inventors

• Nguyen Dao
• Gillespie Mark
• Hooper Benjamin
• Kashyap Mridu
• Barzano Keith

Classifications

• G06N20/20

  Ensemble learning · CPC title

• G06F18/285

  Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system · CPC title

• H04L51/02

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G06Q40/08 Primary

  Insurance · CPC title