IP Library › Granted Patent US 12,614,037
Granted Patent B2
US 12,614,037 · App. 18/429,150 · Granted Apr 28, 2026

Large language model interface for complex databases

Inventors: Maria Angels De Luis Balaguer (Redmond, WA); Sara Malvar Maua (Sao Paulo, BR); Swati Sharma (Hayward, CA); Ranveer Chandra (Kirkland, WA)
Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
G06F40/30G06F16/2425G06F16/243G16B50/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,614,037
App. No.
18/429,150
Granted
Apr 28, 2026
Kind
B2
Abstract

This disclosure introduces a novel method and system for using a large language model (LLM) to create a convenient interface for a complex database. The system includes a custom prompt generator that creates custom prompts from natural language queries. The custom prompts are used to control how the LLM interacts with a database look-up tool. The database look-up tool provides queries to the database in a format understandable by the database and receives responses from the database. This system is useful for obtaining information that is not in a natural language, and thus, is poorly suited for being processed as an embedding by the LLM. Information obtained from the database is included in an answer produced by the LLM.

Claims (49)

1 . A method for querying a database comprising:

receiving a natural language query containing a reference to a biological sequence;

generating a custom prompt from the natural language query that includes instructions to access a database look-up tool;

providing the custom prompt to a large language model (LLM);

extracting, by the LLM, the reference to the biological sequence and the instructions to access the database look-up tool;

retrieving the biological sequence from the database by the database look-up tool under control of the LLM, wherein the database look-up tool comprises three tools chained together and retrieving the biological sequence further comprises:

querying, by a first tool, the database with the reference to the biological sequence and retrieving a database-specific gene identifier;

querying, by a second tool, the database with the database-specific gene identifier and retrieving a sequence identifier; and

querying, by a third tool, the database with the sequence identifier and retrieving the biological sequence; and

generating an answer containing the biological sequence.

2 . The method of claim 1 , wherein the natural language query also contains a modifier and the extracting, by the LLM, further comprises modifying the reference to the biological sequence based on the modifier.

3 . The method of claim 1 , wherein the reference to the biological sequence is a common name of a gene.

4 . The method of claim 3 , wherein the first tool generates synonyms to the common name of the gene and submits one query for each synonym to the database.

5 . The method of claim 1 , wherein the custom prompt represents the database look-up tool by a variable.

6 . The method of claim 1 , further comprising:

determining that the reference to the biological sequence resolves to more than one biological sequence in the database, and

generating a response that requests additional description of the biological sequence.

7 . The method of claim 1 , wherein the sequence identifier is a transcript ID, a protein ID, or a GenInfo Identifier (GI) number.

8 . A system for querying a database comprising:

a processor;

a memory;

an interface configured to receive a natural language query containing a reference to a biological sequence and display an answer received from a large language model (LLM), the answer containing the biological sequence;

a custom prompt generator configured to generate a custom prompt from the natural language query containing the reference to the biological sequence and provide the custom prompt to the LLM, wherein the custom prompt includes instructions to access a database look-up tool; and

the database look-up tool configured to submit queries and obtain data from the database, the database look-up tool comprising:

a first tool that is configured to query the database with the reference to the biological sequence and receive a database-specific gene identifier; and

a second tool that is configured to query the database with the database-specific gene identifier and retrieve a sequence identifier.

9 . The system of claim 8 , wherein the interface also comprises an orchestration framework configured to connect the LLM to the custom prompt generator and to the database look-up tool.

10 . The system of claim 8 , wherein the custom prompt generator is further configured to generate the custom prompt based on a modifier contained in the natural language query such that the reference to the biological sequence is modified based on the modifier.

11 . The system of claim 8 , wherein the custom prompt generator is further configured to generate the custom prompt with a variable that represents the database look-up tool.

12 . The system of claim 8 , wherein the database look-up tool comprises a third tool that is configured to query the database with the sequence identifier and retrieve the biological sequence.

13 . The system of claim 8 , wherein the reference to the biological sequence is a common name of a gene.

14 . The system of claim 13 , wherein the first tool generates synonyms to the common name of the gene and submits one query for each synonym to the database.

15 . Computer-readable storage media comprising instructions that, when executed by a computing device, cause the computing device to perform actions comprising:

receiving a natural language query containing a reference to a biological sequence;

generating a custom prompt from the natural language query that includes instructions to access a database look-up tool;

providing the custom prompt to a large language model (LLM);

extracting, by the LLM, the reference to the biological sequence and the instructions to access the database look-up tool;

retrieving the biological sequence from a database by the database look-up tool under control of the LLM, wherein the database look-up tool comprises three tools chained together and retrieving the biological sequence further comprises:

querying, by a first tool, the database with the reference to the biological sequence and retrieving a database-specific gene identifier;

querying, by a second tool, the database with the database-specific gene identifier and retrieving a sequence identifier; and

querying, by a third tool, the database with the sequence identifier and retrieving the biological sequence; and

generating an answer containing the biological sequence.

16 . The computer-readable storage media of claim 15 , wherein the natural language query also contains a modifier and the extracting, by the LLM, further comprises modifying the reference to the biological sequence based on the modifier.

17 . The computer-readable storage media of claim 15 , wherein the custom prompt represents the database look-up tool by a variable.

18 . The computer-readable storage media of claim 15 , wherein the actions further comprise:

determining that the reference to the biological sequence resolves to more than one biological sequence in the database, and

generating a response that requests additional description of the biological sequence.

19 . The computer-readable storage media of claim 15 , wherein the reference to the biological sequence is a common name of a gene.

20 . The computer-readable storage media of claim 19 , wherein the first tool generates synonyms to the common name of the gene and submits one query for each synonym to the database.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 16, 2024
From: DE LUIS BALAGUER, MARIA ANGELS; MAUA, SARA MALVAR; SHARMA, SWATI; CHANDRA, RANVEER
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 066484/0883 →
Continuity (1)
Related Publication 20250245215A1 · Jul 31, 2025
References Cited (19)
US 8719005B1 · Lee · 2014 [cited by examiner]
US 11966704B1 · Magary · 2024 [cited by examiner]
US 12306828B1 · Chakraborty · 2025 [cited by examiner]
US 12353407B1 · Shachaf · 2025 [cited by examiner]
US 20110314006A1 · Sweeney · 2011 [cited by examiner]
US 20240320445A1 · Mallick · 2024 [cited by examiner]
US 20240362212A1 · Sun · 2024 [cited by examiner]
US 20240394285A1 · Cunningham · 2024 [cited by examiner]
US 20240403373A1 · Chao · 2024 [cited by examiner]
US 20250045530A1 · Reddy · 2025 [cited by examiner]
US 20250086213A1 · Dilipkumar · 2025 [cited by examiner]
US 20250103592A1 · Niu · 2025 [cited by examiner]
US 20250124024A1 · Kirk · 2025 [cited by examiner]
US 20250156413A1 · Barkan · 2025 [cited by examiner]
US 20250156574A1 · Eberlein · 2025 [cited by examiner]
US 20250173330A1 · Durg · 2025 [cited by examiner]
US 20250210033A1 · Sharifi · 2025 [cited by examiner]
US 20250217351A1 · Tan · 2025 [cited by examiner]
Jamil, Hasan M. “Knowledge rich natural language queries over structured biological databases.” Proceedings of the 8th ACM international conference on bioinformatics, computational biology, and health informatics. 2017.… [cited by examiner]
Cited By (1)
US 12,737,460