Generated content source

Patent metadata

Field	Value
Publication number	US-2025124024-A1
Application number	US-202318488544-A
Country	US
Kind code	A1
Filing date	Oct 17, 2023
Priority date	Oct 17, 2023
Publication date	Apr 17, 2025
Grant date	—

Abstract

A large language model (LLM) may receive a query via a user interface of a client device. The LLM may generate one or more data queries from the query to query one or more data sets. The LLM may then transmit the one or more data queries to the one or more data sets. The LLM may then receive information associated with the query and a source for the information from the one or more data sets. The source may be indicative of a location within the one or more data sets from where the information was obtained. Following, the LLM may generate a response to the query that includes the information associated with the query and the source for the information and transmit the response to the user interface of the client device for display.

First claim

1 . A method for data processing, comprising:
receiving, via a user interface, a natural language query; parsing, via a large language model, the natural language query into one or more actionable queries, each one of the one or more actionable queries comprising an indication of a respective data set of a plurality of data sets; generating, via the large language model and utilizing the one or more actionable queries, one or more data queries from the natural language query, wherein the one or more data queries are configured to query one or more data sets of the plurality of data sets based at least in part on generation of the one or more data queries comprising transforming the one or more actionable queries to be capable of interacting with the one or more data sets; transmitting the one or more data queries to the one or more data sets of the plurality of data sets; receiving, from the one or more data sets of the plurality of data sets, information associated with the natural language query and a source for the information, the source being indicative of a location within the one or more data sets from which the information is obtained; generating, via the large language model, a response to the natural language query, the response comprising an inference generated by the large language model that is based at least in part on the information associated with the natural language query obtained from the one or more data sets and the source for the information that the inference is based on; and transmitting, to the user interface for display, the response to the natural language query that comprises the inference of the information and the source for the information that the inference is based on.

2 . The method of claim 1 , wherein generating the response comprises:
generating the response that includes the inference related to data obtained from the one or more data sets via the one or more data queries, wherein the source for the information is indicative of the location of the data that is used for the inference by the large language model.

3 . (canceled)

4 . The method of claim 1 , wherein transmitting the response to the user interface for the display further comprises:
transmitting, to the user interface for the display, the response to the natural language query that comprises the source for the information, wherein the source for the information is displayed via the user interface as a footnote, a hyperlink, an in-line citation, or any combination thereof.

5 . The method of claim 1 , further comprising:
generating, via the large language model, a summary of the information associated with the natural language query that is received from the one or more data queries, wherein the response comprises the summary of the information and the source for the information that is summarized.

6 . The method of claim 1 , wherein the information associated with the natural language query that is received from the one or more data queries comprises sensitive data and the method further comprises:
performing, an encryption procedure on the sensitive data included within the information associated with the natural language query that is received from the one or more data queries to generate a set of encrypted information, wherein the response comprises the information associated with the natural language query and the source for the information, and wherein the information includes the set of encrypted information.

7 . The method of claim 6 , further comprising:
transmitting, to the user interface, an authentication request prior to a transmission of the response to the user interface based at least in part on the information included in the response including the set of encrypted information.

8 . The method of claim 1 , wherein the one or more data sets may comprise one or more internal data sets, one or more external data sets, or any combination thereof.

9 . The method of claim 8 , wherein the one or more internal data sets may be directly connected to the large language model and may include a customer relationship management platform, a multi-tenant database system, email archives for one or more tenants in the multi-tenant database system, public records of one or more tenants in the multi-tenant database system, or any combination thereof.

10 . The method of claim 8 , wherein the one or more external data sets may be indirectly connected to the large language model and may include one or more public databases, online information references, data sets from public data providers, or any combination thereof.

11 . An apparatus for data processing, comprising:
one or more memories storing processor-executable code; and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the apparatus to:
receive, via a user interface, a natural language query;
parse, via a large language model, the natural language query into one or more actionable queries, each one of the one or more actionable queries comprising an indication of a respective data set of a plurality of data sets;
generate, via the large language model and utilizing the one or more actionable queries, one or more data queries from the natural language query, wherein the one or more data queries are configured to query one or more data sets of the plurality of data sets based at least in part on generation of the one or more data queries comprises transforming the one or more actionable queries to be capable of interacting with the one or more data sets;
transmit the one or more data queries to the one or more data sets of the plurality of data sets;
receive, from the one or more data sets of the plurality of data sets, information associated with the natural language query and a source for the information, the source being indicative of a location within the one or more data sets from which the information is obtained;
generate, via the large language model, a response to the natural language query, the response comprising an inference generated by the large language model that is based at least in part on the information associated with the natural language query obtained from the one or more data sets and the source for the information that the inference is based on; and
transmit, to the user interface for display, the response to the natural language query that comprises the inference of the information and the source for the information that the inference is based on.

12 . The apparatus of claim 11 , wherein, to generate the response, the one or more processors are individually or collectively operable to execute the code to cause the apparatus to:
generate the response that includes the inference related to data obtained from the one or more data sets via the one or more data queries, wherein the source for the information is indicative of the location of the data that is used for the inference by the large language model.

13 . (canceled)

14 . The apparatus of claim 11 , wherein, to transmit the response to the user interface for the display, the one or more processors are individually or collectively further operable to execute the code to cause the apparatus to:
transmit, to the user interface for the display, the response to the natural language query that comprises the source for the information, wherein the source for the information is displayed via the user interface as a footnote, a hyperlink, an in-line citation, or any combination thereof.

15 . The apparatus of claim 11 , wherein the one or more processors are individually or collectively

Assignees

• Salesforce Inc

Inventors

• Kirk Dustin Allen

Classifications

• G06F16/248

  Presentation of query results · CPC title

• G06F21/602

  Providing cryptographic facilities or services · CPC title

• G06F16/243 Primary

  Natural language query formulation · CPC title