Granted Patent B2

US 12,670,151 · App. 18/817,986 · Granted Jun 30, 2026

Inventors: Atul Chandrakant Kshirsagar (San Ramon, CA); Prithvi Krishnan Padmanabhan (San Ramon, CA); Rajasekar Elango (San Francisco, CA); Bharat Suri (San Francisco, CA); Shipra Gupta (San Francisco, CA)

Assignee: Salesforce, Inc.

G06F16/243G06F16/2428G06F16/252G06F40/205

Abstract

Claims (58)

1 . A computing services environment comprising:

a database system storing a plurality of database records in a storage system for a plurality of client organizations accessing computing services via the computing services environment, the computing services including a conversational chat interface;

an application server including a processor and providing access to the conversational chat interface to a plurality of client machines associated with one or more of the plurality of client organizations; and

an orchestration service including a memory module and being configured to execute an orchestration process based on a natural language request message received from a client machine via the conversational chat interface, wherein executing the orchestration process includes:

executing an information enrichment and disambiguation process to determine candidate information including a plurality of candidate values corresponding to a text portion of the natural language request message, the candidate information including a first database record corresponding to a first database record type and a second database record corresponding to a second database record type,

determining novel clarification text via a generative language model, the novel clarification text requesting clarification of the candidate information, the novel clarification text identifying the first and second database records and database record types,

transmitting the novel clarification text to the client machine via the conversational chat interface,

receiving an indication of the first database record and first database record type from the client machine via the conversational chat interface,

determining updated information based on the candidate information and the first database record,

determining novel response text responsive to the natural language request message based on the updated information,

updating the first database record based on the novel response text, and

transmitting the novel response text to the client machine via the conversational chat interface,

wherein the plurality of candidate values includes a plurality of text values selected from an information source outside of the database system, and wherein determining the updated information includes selecting a text value of the plurality of text values.

2 . The computing services environment recited in claim 1 , wherein the plurality of candidate values includes a plurality of text values selected from an information source outside of the database system, and wherein determining the updated information includes selecting a text value of the plurality of text values.

3 . The computing services environment recited in claim 2 , wherein the information source resides outside of the computing services environment and is accessible via a network interface.

4 . The computing services environment recited in claim 1 , wherein the clarification input includes an indication of a selection of a user interface affordance at the client machine.

5 . The computing services environment recited in claim 4 , wherein the user interface affordance is a virtual button presented on a display screen.

6 . The computing services environment recited in claim 1 , wherein executing an information enrichment and disambiguation process comprises transmitting an information enrichment and disambiguation input prompt to a generative language model and receiving from the generative language model an information enrichment and disambiguation prompt completion.

7 . The computing services environment recited in claim 6 , wherein the information enrichment and disambiguation prompt completion includes a query for retrieving the candidate information, and wherein the candidate information is determined by executing the query.

8 . The computing services environment recited in claim 7 , wherein the query is a database query, and wherein executing the query includes accessing the database system.

9 . The computing services environment recited in claim 1 , wherein the novel response text is determined based on an interaction with a generative language model.

10 . The computing services environment recited in claim 1 , wherein determining the novel response text comprises:

determining a topic identification input prompt that includes the natural language request message and one or more natural language instructions executable by the generative language model to identify a topic based on the natural language request message;

transmitting the topic identification input prompt to the generative language model for completion;

receiving a topic identification prompt completion from the generative language model; and

identifying one or more topics of a plurality of topics by parsing the topic identification prompt completion, wherein each of the plurality of topics corresponds with a respective topic-based subset of a plurality of actions executable at the computing services environment.

11 . The computing services environment recited in claim 10 , further comprising a trust layer, wherein the trust layer is configured to mask sensitive data included the topic identification input prompt before the topic identification input prompt is transmitted to a generative language model for completion.

12 . The computing services environment recited in claim 11 , wherein masking sensitive data includes replacing a text portion with a unique identifier, and wherein the trust layer is further configured to demask the topic identification prompt completion received from the generative language model by replacing the unique identifier with the text portion.

13 . The computing services environment recited in claim 1 , wherein the generative language model is hosted outside the computing services environment.

14 . The computing services environment recited in claim 1 , wherein the generative language model is hosted inside the computing services environment.

15 . A method implement at a computing services environment, the method comprising:

storing a plurality of database records in a database system for a plurality of client organizations accessing computing services via the computing services environment, the computing services including a conversational chat interface;

providing access to the conversational chat interface via an application server to a plurality of client machines associated with one or more of the plurality of client organizations; and

execute an orchestration process via an orchestration service based on a natural language request message received from a client machine via the conversational chat interface, wherein executing the orchestration process includes:

executing an information enrichment and disambiguation process to determine candidate information including a plurality of candidate values corresponding to a text portion of the natural language request message, the candidate information including a first database record corresponding to a first database record type and a second database record corresponding to a second database record type,

determining novel clarification text via a generative language model, the novel clarification text requesting clarification of the candidate information, the novel clarification text identifying the first and second database records and database record types,

transmitting the novel clarification text to the client machine via the conversational chat interface,

receiving an indication of the first database record and first database record type from the client machine via the conversational chat interface,

determining updated information based on the candidate information and the first database record,

determining novel response text responsive to the natural language request message based on the updated information,

updating the first database record based on the novel response text, and

transmitting the novel response text to the client machine via the conversational chat interface.

16 . The method recited in claim 15 , wherein the plurality of candidate values includes a plurality of text values selected from an information source outside of the database system, and wherein determining the updated information includes selecting a text value of the plurality of text values.

17 . The method recited in claim 16 , wherein the information source resides outside of the computing services environment and is accessible via a network interface.

18 . One or more non-transitory computer readable media having instructions stored thereon for performing a method implement at a computing services environment, the method comprising:

storing a plurality of database records in a database system for a plurality of client organizations accessing computing services via the computing services environment, the computing services including a conversational chat interface;

providing access to the conversational chat interface via an application server to a plurality of client machines associated with one or more of the plurality of client organizations; and

execute an orchestration process via an orchestration service based on a natural language request message received from a client machine via the conversational chat interface, wherein executing the orchestration process includes:

executing an information enrichment and disambiguation process to determine candidate information including a plurality of candidate values corresponding to a text portion of the natural language request message, the candidate information including a first database record corresponding to a first database record type and a second database record corresponding to a second database record type,

determining novel clarification text via a generative language model, the novel clarification text requesting clarification of the candidate information, the novel clarification text identifying the first and second database records and database record types,

transmitting the novel clarification text to the client machine via the conversational chat interface,

receiving an indication of the first database record and first database record type from the client machine via the conversational chat interface,

determining updated information based on the candidate information and the first database record,

determining novel response text responsive to the natural language request message based on the updated information,

updating the first database record based on the novel response text, and

transmitting the novel response text to the client machine via the conversational chat interface.

19 . The one or more non-transitory computer readable media recited in claim 18 , wherein the plurality of candidate values includes a plurality of text values selected from an information source outside of the database system, and wherein determining the updated information includes selecting a text value of the plurality of text values.

20 . The one or more non-transitory computer readable media recited in claim 19 , wherein the information source resides outside of the computing services environment and is accessible via a network interface.

Assignments (1)

Continuity (10)

References Cited (322)