# US 2024/0256582 A1 · Search with Generative Artificial Intelligence

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0256582 A1
- Document ID: US20240256582A1
- Status: Published application
- Kind: A1
- Application number: 18/330,999
- Filed: 2023-06-07
- Published: 2024-08-01
- Earliest claimed: 2023-01-28
- Assignees: Glean Technologies, Inc.
- Applicants: Glean Technologies, Inc.
- Inventors: Arvind Jain; Calvin Qi; Chau Hai Tran; Eddie Zhou; Megha Jhunjhunwala; Mrinal Mohit; Pancham Yadav; Philip Ophus; Shivaal Roy; Vivek Choksi
- Web page: https://patentgrep.com/patent/US20240256582A1

## CPC

- G06F 16/3329: Natural language query formulation
- G06F 16/338: Presentation of query results
- G06F 16/345: {Summarisation for human users}
- G06N 3/045: Combinations of networks
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Methods and apparatuses for utilizing generative artificial intelligence (AI) techniques to automatically generate and display summaries of search results are described. A search and knowledge management system may generate a set of search results for a given search query and provide the set of search results (e.g., a set of verified documents that are the most relevant verified documents for the search query) as part of an input prompt to guide a generative AI model in generating a summary response of the set of search results. The generative AI model may comprise a Generative Pre-trained Transformer (GPT) model. The summary response may comprise a natural language text response and the set of search results may comprise electronic documents and messages and/or portions thereof.

## Claims

### Claim 1

A system, comprising:
a storage device configured to store a prompt; and
one or more processors in communication with the storage device configured to:
identify a search query;
generate a set of search results using the search query;
detect that an answer summary for the set of search results should be generated;
determine a latency for generating the answer summary;
identify a subset of the set of search results based on the latency for generating the answer summary;
generate the answer summary using the subset of the set of search results and the prompt; and
store the answer summary.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to generate the answer summary using a generative artificial intelligence model, the prompt, and the subset of the set of search results.

### Claim 3 (depends on 2)

The system of claim 2, wherein:
the generative artificial intelligence model comprises a generative pre-trained transformer model.

### Claim 4 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to detect that at least a threshold number of users have submitted a semantically similar search query to the search query and detect that the answer summary for the set of search results should be generated in response to detection that at least the threshold number of users have submitted the semantically similar search query to the search query.

### Claim 5 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to determine a location within a document and identify the search query based on the location within the document.

### Claim 6 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to determine a maximum snippet size for the set of search results based on the latency for generating the answer summary and determine the subset of the set of search results based on the maximum snippet size.

### Claim 7 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to cause the answer summary to be displayed.

### Claim 8 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to input the subset of the set of search results and a text directive to generate the answer summary to a generative artificial intelligence model.

### Claim 9 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to input the subset of the set of search results and a text directive to reference one or more search results that were used to generate the answer summary to a generative artificial intelligence model.

### Claim 10 (depends on 1)

The system of claim 1, wherein:
each of the set of search results comprises an electronic document that was verified by a document owner.

### Claim 11 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to determine an estimated latency for generating the answer summary and determine a number of search results comprising the subset of the set of search results based on the estimated latency.

### Claim 12 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to determine an amount of time to generate the answer summary and determine a number of search results comprising the subset of the set of search results based on the amount of time to generate the answer summary.

### Claim 13 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to determine an amount of time to generate the answer summary and determine a total amount of text for the subset of the set of search results based on the amount of time to generate the answer summary.

### Claim 14 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to detect that an amount of time to generate the answer summary is greater than a threshold amount of time and generate the answer summary in the background while the subset of the set of search results is displayed.

### Claim 15 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to detect that an amount of time to generate the answer summary using a generative artificial intelligence model is greater than a threshold amount of time and generate the answer summary while the subset of the set of search results is displayed.

### Claim 16 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to detect a triggering condition and perform a search for the search query using user permissions based on a number of end users that submitted search queries that are semantically similar to the search query.

### Claim 17 (depends on 1)

The system of claim 1, wherein:
the one or more processors are configured to generate the answer summary using a first set of documents and generate a second answer summary in the background using a second set of documents that is larger than the first set of documents.

### Claim 18

A method for operating a search system, comprising:
identifying a search query;
generating a set of search results using the search query;
detecting that an answer summary for the set of search results should be generated in response to detection that at least a threshold number of users have submitted a semantically similar search query to the search query;
determining a maximum latency for generating the answer summary;
determining a subset of the set of search results based on the maximum latency for generating the answer summary;
generating the answer summary using the subset of the set of search results; and
storing the answer summary using a non-volatile storage device.

### Claim 19 (depends on 18)

The method of claim 18, wherein:
the generating the answer summary includes generating the answer summary by inputting the subset of the set of search results to a generative pre-trained transformer model.

### Claim 20

One or more storage devices containing processor readable code for configuring one or more processors to perform a method for operating a search system, wherein the processor readable code configures the one or more processors to:
generate a set of search results for a search query;
detect that an answer summary for the set of search results should be generated;
determine an estimated amount of time to generate the answer summary;
identify a subset of the set of search results based on the estimated amount of time to generate the answer summary;
generate the answer summary using the subset of the set of search results; and
display the answer summary.
