Microsoft patents search system that uses AI to refine your queries
Microsoft describes a method where a large language model takes a user's search input and breaks it down into specific search functions. It then executes these functions to find better data filters and creates a modified, more precise version of the original query to return improved results.
In the filing’s own words
Embodiments of the disclosed technologies include receiving a first query including at least one first query term and configuring at least one prompt to cause a large language model to translate the at least one first query term into a set of functions that can be executed to obtain at least one second query term and generate and output a plan that is executable to create a modified version of the first query based on the at least one second query term. The plan is obtained by applying the large language model to the at least one prompt as configured. The plan is executed to determine the at least one second query term and create the modified version of the first query. The modified version of the first query is executed to provide, via the user interface, a response to the first query.
What exactly they claim (claim 1)
1. A method comprising: receiving, by a processor, an input via a device; extracting a plurality of intents via execution of an intent query against an intent library of a computer system, wherein the intent query comprises the input as a parameter; providing the input, the plurality of intents, and a prompt to a generative machine learning model executed on the computer system, wherein the prompt is formulated using the input and the plurality of intents, wherein the prompt comprises instructions received via an instruction library; receiving a first output via the generative machine learning model by executing the prompt using the input and the plurality of intents, wherein the first output comprises a first function and a first function parameter, wherein the first function comprises a search function of a particular type selected from a plurality of function types by the generative machine learning model and the first function parameter comprises at least one of a parameter value and a search term determined by the generative machine learning model; formulating, by the processor, a first result or a second result via execution of the first function, wherein the formulating of the first result or the second result comprises retrieving at least one of a facet and a filter from a data resource of a computing system, wherein the data resource is selected via the generative machine learning model by executing the prompt using the input; and causing presentation of at least one of the first result or the second result to generate a search improvement recommendation via the device.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Dynamic query planning and execution
- Patent number
- US12743423B2
- Application number
- 19192207
- Filed
- Apr 28, 2025
- Granted
- Sep 22, 2026
- Inventors
- 6
- Claims
- 20
Classified under
G06F 16/24542 Physics & computingG06F 16/2425 Physics & computingG06F 16/243 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.