Large language model data object generation

Patent metadata

Field	Value
Publication number	US-2025086407-A1
Application number	US-202418412078-A
Country	US
Kind code	A1
Filing date	Jan 12, 2024
Priority date	Sep 11, 2023
Publication date	Mar 13, 2025
Grant date	—

Abstract

Methods, apparatuses, systems, and computer-program products are disclosed. For example, a system may receive, via a cloud-based platform, first user input including a request for generation of the output data object. The system may generate a prompt based on the first user input and a prompt appendix that defines a response format for a plurality of responses to the prompt that are to be generated by a large language model (LLM). The system may transmit the prompt to the LLM and may receive, from the LLM, the plurality of responses formatted in the response format. The system may generate the output data object that comprises the plurality of responses.

First claim

What is claimed is:

1 . A method for generating an output data object, comprising:
receiving, via a cloud-based platform, first user input comprising a request for generation of the output data object that is to comprise a plurality of responses to a prompt; generating, at a processing layer of the cloud-based platform, the prompt based at least in part on the first user input and a prompt appendix that defines a response format for the plurality of responses to the prompt that are to be generated by a large language model (LLM), the prompt appendix further defining a plurality of response types to which the LLM is to map individual responses of the plurality of responses and including an instruction to generate the plurality of responses in the output data object in accordance with the plurality of response types; transmitting the prompt from the processing layer to the LLM; receiving, from the LLM at the processing layer, the plurality of responses formatted in the response format; and generating the output data object that comprises the plurality of responses based at least in part on a mapping between one or more elements of the response format and one or more elements of a data format corresponding to the output data object.

2 . The method of claim 1 , wherein the response format comprises a response name field, a response type field, a help text field, an optionality field, or any combination thereof.

3 . The method of claim 1 , wherein the first user input further comprises an indication of an output data object type, an indication of a quantity of requested responses, an indication of one or more metrics associated with the plurality of responses, an indication of an industry to be associated with the plurality of responses, an indication of a geographic region to be associated with the plurality of responses, or any combination thereof.

4 . The method of claim 1 , further comprising:
receiving second user input modifying the prompt.

5 . The method of claim 1 , further comprising:
receiving third user input that comprises one or more indications of one or more selected response types of the plurality of response types corresponding to individual responses of the plurality of responses, wherein the one or more selected response types are to be associated with the corresponding individual responses in the output data object.

6 . The method of claim 5 , wherein the plurality of response types comprises a single selection response type, a multiple selection response type, a picklist response type, a net promoter score response type, a customer satisfaction response type, a text entry response type, or any combination thereof.

7 . The method of claim 1 , wherein generating the output data object comprises converting the plurality of responses to the data format corresponding to the output data object based at least in part on the mapping between the one or more elements of the response format and the one or more elements of the data format.

8 . The method of claim 1 , wherein the prompt appendix comprises a request to map each of the plurality of responses to one or more response types of the plurality of response types.

9 . The method of claim 1 , further comprising:
training the LLM with training data comprising feedback information associated with previously-generated output data objects, a plurality of translations of previously-generated output data objects, customer data, customer relationship management software data, or any combination thereof.

10 . The method of claim 1 , wherein:
the prompt further indicates a target language to which the plurality of responses is to be translated by the LLM; and the plurality of responses comprise information expressed in the target language.

11 . The method of claim 1 , wherein the plurality of responses comprises survey questions, the output data object comprises a survey data object, or both.

12 . An apparatus for generating an output data object, 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 cloud-based platform, first user input comprising a request for generation of the output data object that is to comprise a plurality of responses to a prompt;
generate, at a processing layer of the cloud-based platform, the prompt based at least in part on the first user input and a prompt appendix that defines a response format for the plurality of responses to the prompt that are to be generated by a large language model (LLM), the prompt appendix further defining a plurality of response types to which the LLM is to map individual responses of the plurality of responses and including an instruction to generate the plurality of responses in the output data object in accordance with the plurality of response types:
transmit the prompt from the processing layer to the LLM;
receive, from the LLM at the processing layer, the plurality of responses formatted in the response format; and
generate the output data object that comprises the plurality of responses based at least in part on a mapping between one or more elements of the response format and one or more elements of a data format corresponding to the output data object.

13 . The apparatus of claim 12 , wherein the response format comprises a response name field, a response type field, a help text field, an optionality field, or any combination thereof.

14 . The apparatus of claim 12 , wherein the first user input further comprises an indication of an output data object type, an indication of a quantity of requested responses, an indication of one or more metrics associated with the plurality of responses, an indication of an industry to be associated with the plurality of responses, an indication of a geographic region to be associated with the plurality of responses, or any combination thereof.

15 . The apparatus of claim 12 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the apparatus to:
receive second user input modifying the prompt.

16 . The apparatus of claim 12 , wherein the one or more processors are individually or collectively further operable to execute the code to cause the apparatus to:
receive third user input that comprises one or more indications of one or more selected response types of the plurality of response types corresponding to individual responses of the plurality of responses, wherein the one or more selected response types are to be associated with the corresponding individual responses in the output data object.

17 . The apparatus of claim 16 , wherein the plurality of response types comprises a single selection response type, a multiple selection response type, a picklist response type, a net promoter score response type, a customer satisfaction response type, a text entry response type, or any combination thereof.

18 . The apparatus of claim 12 , wherein generating the output data object comprises converting the plurality of responses to the data format corresponding to the output data object based at least in part on the mapping between the one or more elements of the response format and the one or more elements of the data format.

19 . The apparatus of claim 12 , wherein the prompt appendix comprises a request to map each of the plurality of responses to one or more response types of the plurality of respo

Assignees

• Salesforce Inc

Inventors

• Vedula Sundar Ram
• Dua Rajdeep
• Singh Akash
• Subramaniyan Manoj Kumar
• Oberoi Ankit
• Singh Ajay
• Trivedi Arpit

Classifications

• G06F40/58 Primary

  Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation · CPC title

• G06Q30/0203 Primary

  Market surveys; Market polls · CPC title