Artificial intelligence system user interfaces

Patent metadata

Field	Value
Publication number	US-2024338232-A1
Application number	US-202418625032-A
Country	US
Kind code	A1
Filing date	Apr 2, 2024
Priority date	Apr 6, 2023
Publication date	Oct 10, 2024
Grant date	—

Abstract

A data orchestration system can be used to respond to natural language prompts (e.g., user submitted prompts) where the response involves a data processing workflow being executed using one or more data processing services (e.g., microservices of a data processing platform or software). This can provide for execution of data processing workflows (e.g., complex workflows) without a user needing to specify the particular data processing services that are included in the data processing workflows. This can cause new functionality to be available to a user (e.g., to a user who lacks the technical skillset to specify the relevant data processing services without use of the systems and methods disclosed herein), and/or can dramatically reduce the time required to orchestrate the data processing services that are included in the data processing workflows.

First claim

What is claimed is:

1 . A method performed by an orchestration system, the method comprising:
receiving user input of an object type; receiving natural language user prompt from a user; applying a language model to the user prompt to determine a service workflow including at least a first data processing service and a second data processing service; determining a first service orchestrator associated with the first data processing service; instructing the first service orchestrator to request execution of a first data processing task from the first data processing service; receiving a first response from the first data processing service; determining a second service orchestrator associated with the second data processing service; instructing the second service orchestrator to request execution of a second data processing task from the second data processing service, wherein the second service orchestrator is provided with information regarding the first response from the first data processing service; receiving a second response from the second data processing service; and presenting at least a portion of the second response in a user interface.

2 . The method of claim 1 , further comprising:
determining that the first data processing service was selected with below a threshold level of confidence; in response to said determining that the first data processing service was selected with below the threshold level of confidence, presenting a follow-up question to the user requesting additional information; and receiving the additional information from the user, wherein the first data processing service is selected based on both the natural language user prompt and the additional information.

3 . The method of claim 2 , wherein the additional information includes information usable for determining selection of the first data processing service with above the threshold level of confidence.

4 . A computer-implemented method comprising:
by one or more processors executing program instructions: receiving a first user input from a user; providing a first model input to a first language model, wherein the first model input includes at least the first user input; receiving a first model output from the first language model, wherein the first model output comprises at least an indication of a first data processing service, wherein the first data processing service is selected by the first language model based on the first model input; determining a first service orchestrator associated with the first data processing service; providing a second model input to a second language model, wherein the second model input includes at least information associated with the first data processing service; receiving a second model output from the second language model, wherein the second model output comprises at least a formatted query; providing a first processing input to the first data processing service, wherein the first processing input includes at least the formatted query; receiving a first processing output from the first data processing service; and causing presentation of at least a portion of the first processing output in a user interface.

5 . The computer-implemented method of claim 4 , wherein the first user input comprises a natural language prompt.

6 . The computer-implemented method of claim 5 , wherein the first user input comprises a selection and/or identification of a data object type (also referred to as an object type).

7 . The computer-implemented method of claim 4 , wherein the first model input further includes a listing of one or more data processing services.

8 . The computer-implemented method of claim 7 , wherein the first model input further includes information regarding capabilities and/or functionality of each of the one or more data processing services.

9 . The computer-implemented method of claim 7 further comprising:
by the one or more processors executing program instructions:

determining the listing of the one or more data processing services.

10 . The computer-implemented method of claim 9 , wherein the listing of the one or more data processing services is determined based at least in part on at least one of: a data object type associated with the first user input, a data object type derived from the first user input, a data object type selected by the user, the first user input, a context associated with the first user input, semantics and/or embeddings associated with the first user input and/or a context associated with the first user input, or a semantic search of the first user input and/or a context associated with the first user input.

11 . The computer-implemented method of claim 7 , wherein the first model input further includes a context associated with the first user input.

12 . The computer-implemented method of claim 11 , wherein the context associated with the first user input does not include actual data to be processed, but may include a schema or other metadata associated with the actual data to be processed.

13 . The computer-implemented method of claim 4 , wherein the first language model is configured, at least in part by the first model input, to select the first data processing service.

14 . The computer-implemented method of claim 4 , wherein providing the first model input to the first language model, receiving the first model output from the first language model, and determining the first service orchestrator, are performed by one or more orchestrator selectors, selection modules, and/or any combination thereof.

15 . The computer-implemented method of claim 4 , wherein the information associated with the first data processing service includes at least one of: information regarding functionality of the first data processing service, information regarding a query format associated with the first data processing service, or examples of formatted queries and/or data formats associated with the first data processing service.

16 . The computer-implemented method of claim 4 , wherein the second model input further includes the first user input.

17 . The computer-implemented method of claim 4 , wherein the second model input further includes a context associated with the first user input.

18 . The computer-implemented method of claim 4 , wherein the second model input further includes information associated with the user.

19 . The computer-implemented method of claim 18 , wherein the information associated with the user includes permissions information.

20 . The computer-implemented method of claim 4 , wherein the second model input further includes information associated with the first service orchestrator.

Assignees

• Palantir Technologies Inc

Inventors

• Copes Martin
• Trache Mohamed Zaki
• Jeganathan Christopher

Classifications

• G06F40/20

  Natural language analysis (semantic analysis of natural language G06F40/30) · CPC title

• G06N3/10

  Interfaces, programming languages or software development kits, e.g. for simulating neural networks · CPC title

• G06N3/0475

  Generative networks · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• G06F16/252

  between a Database Management System and a front-end application · CPC title