Copilot for multi-user, multi-step collaborations

Patent metadata

Field	Value
Publication number	US-12218890-B2
Application number	US-202318490236-A
Country	US
Kind code	B2
Filing date	Oct 19, 2023
Priority date	Jun 22, 2023
Publication date	Feb 4, 2025
Grant date	Feb 4, 2025

Abstract

The present disclosure relates to methods and systems for sharing with a plurality of users a chat session that uses large language models to provide responses for input messages received for the chat session. The methods and systems provide access to the chat session to the users and update the chat session in response to any changes made to the chat session by any of the users. The methods and systems allow the users to resume the chat session at a future time using the chat session history.

First claim

What is claimed is:

1. A method, comprising:
providing, to a plurality of users, access to a chat session that uses a plurality of large language models to provide responses to input messages received for the chat session;
receiving changes to the chat session;
updating the chat session in response to the changes to the chat session, wherein the plurality of large language models use the changes to the chat session in responding to subsequent input messages received for the chat session; and
storing the changes to the chat session in a chat session history, wherein the chat session history maintains a state of the chat session that includes exchanges between the plurality of users and pages created for the chat session and the plurality of large language models use the chat session history in preparing subsequent responses to subsequent input messages.

2. The method of claim 1 , wherein the pages correspond to input messages received in the chat session from any of the plurality of users and responses to the input messages provided by the plurality of large language models, and
wherein the changes include modifications to the pages in the chat history.

3. The method of claim 1 , wherein the responses received from the plurality of large language models include a plan with steps for responding to an input message and the changes to the chat session include modifications to the plan.

4. The method of claim 1 , further comprising:
resuming the chat session at a future time using the chat session history.

5. The method of claim 1 , wherein the changes include an input message provided to the large language model from a user of the plurality of users and the chat session is updated to include the input message and a response from the plurality of large language models to the input message.

6. The method of claim 1 , wherein the changes include an input message provided to the plurality of large language models from two or more users of the plurality of users and the chat session is updated to include the input message and a response from the plurality of large language models to the input message.

7. The method of claim 1 , wherein the changes include:
a first input message provided to the plurality of large language models from a first user of the plurality of users and the chat session is updated to include the first input message and a first response from the plurality of large language models to the first input message; and
a second input message provided to the plurality of large language models from a second user of the plurality of users and the chat session is updated to include the second input message and a second response from the plurality of large language models to the second input message.

8. The method of claim 1 , wherein the changes include a modification to a previous input message or response in the chat session.

9. The method of claim 1 , wherein each user of the plurality of users accesses the chat session from a different device and the chat session is displayed on a user interface of each device.

10. The method of claim 1 , wherein the plurality of users access the chat session at a same time.

11. The method of claim 1 , wherein the plurality of users access the chat session at different times to make changes to the chat session.

12. The method of claim 1 , wherein the plurality of large language models:
retrieve relevant data from a grounded dataset for answering an input message for the chat session; and
output a response with the relevant data with reference links identifying a source of the relevant data and a summary with reasoning on how the relevant data leads to conclusions in the response.

13. A device, comprising:
a memory to store data and instructions; and
a processor operable to communicate with the memory, wherein the processor is operable to:
provide, to a plurality of users, access to a chat session that uses a plurality of large language models to provide responses to input messages received for the chat session;
receive changes to the chat session;
update the chat session in response to the changes to the chat session, wherein the plurality of large language models use the changes to the chat session in responding to subsequent input messages received for the chat session; and
store the changes to the chat session in a chat session history with pages that correspond to input messages received in the chat session from any of the plurality of users and responses to the input messages provided by the plurality of large language models, wherein the plurality of large language models use the chat session history in preparing subsequent responses to subsequent input messages.

14. The device of claim 13 , wherein the processor is further operable to:
resume the chat session at a future time using the chat session history.

15. The device of claim 13 , wherein the plurality of users access the chat session at different times to make changes to a chat session history.

16. The device of claim 13 , wherein the changes include:
a first input message provided to the plurality of large language models from a first user of the plurality of users and the chat session is updated to include the first input message and a first response from the plurality of large language models to the first input message; and
a second input message provided to the large language model from a second user of the plurality of users and the chat session is updated to include the second input message and a second response from the plurality of large language models to the second input message.

17. The device of claim 13 , wherein the plurality of users accesses the chat session from different devices at a same time.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Abraham Robin
• Du Liang
• Mao Manqing
• Ting Paishun
• Chen Julia
• Lin Jianzhe
• Xiang Yijian
• Xu Mingyang
• Wang Wenhan
• Raja Fahimeh

Classifications

• G06Q10/0633

  Workflow analysis · CPC title

• H04L51/216

  Handling conversation history, e.g. grouping of messages in sessions or threads · CPC title

• H04L51/04

  Real-time or near real-time messaging, e.g. instant messaging [IM] · CPC title

• H04L51/02 Primary

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