# US 2022/0019576 A1 · Using stored execution plans for efficient execution of natural language questions

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

- Number: US 2022/0019576 A1
- Document ID: US20220019576A1
- Status: Published application
- Kind: A1
- Application number: 17/358,901
- Filed: 2021-06-25
- Published: 2022-01-20
- Earliest claimed: 2019-03-20
- Assignees: Promethium, Inc.
- Applicants: Promethium, Inc.
- Inventors: Kaycee Lai
- Web page: https://patentgrep.com/patent/US20220019576A1

## CPC

- G06F 16/243: {Natural language query formulation}
- G06F 16/24522: {Translation of natural language queries to structured queries}
- G06F 16/24524: {Access plan code generation and invalidation; Reuse of access plans}
- G06F 16/24558: {Binary matching operations}
- G06F 16/24573: {using data annotations, e.g. user-defined metadata}
- G06F 16/24578: {using ranking}
- G06F 16/256: {in federated or virtual databases}
- G06F 16/28: Databases characterised by their database models, e.g. relational or object models
- G06F 16/288: {Entity relationship models}
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06F 40/295: Named entity recognition
- G06F 40/30: Semantic analysis
- G06F 40/35: Discourse or dialogue representation
- G06F 40/56: Natural language generation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An analysis system connects to a set of data sources and perform natural language questions based on the data sources. The analysis system connects with the data sources and retrieves metadata describing data assets stored in each data source. The analysis system generates an execution plan for the natural language question. The analysis system finds data assets that match the received question based on the metadata. The analysis system ranks the data assets and presents the ranked data assets to users for allowing users to modify the execution plan. The analysis system may use execution plans of previously stored questions for executing new questions. The analysis system supports selective preprocessing of data to increase the data quality.

## Claims

### Claim 1

(canceled)

### Claim 2

A computer-implemented method comprising:
storing a plurality of natural language questions, each natural language question processing data obtained from one or more data sources;
for each of the plurality of natural language questions:
generating an execution plan comprising instructions for accessing data from the one or more data sources for answering the natural language question;
storing the plurality of natural language questions and their execution plans;
receiving a new natural language question;
matching the new natural language question with one or more stored natural language questions;
identifying a subset of stored natural language questions matching the new natural language question;
sending information describing the subset of stored natural language questions;
receiving a selection of a stored natural language question; and
executing an execution plan for the new natural language question, the execution plan determined from the execution plan of the selected stored natural language question.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a number of times each stored natural language question matching the new natural language question was invoked.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a degree of match of each stored natural language question matching the new natural language question with the new natural language question.

### Claim 5 (depends on 2)

The computer-implemented method of claim 2, wherein matching the new natural language question against a stored natural language question comprises ignoring one or more values specified in the new natural language question.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, further comprising:
substituting one or more values of the execution plan based on the stored natural language question with corresponding values from the new natural language question.

### Claim 7 (depends on 2)

The computer-implemented method of claim 2, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on an amount of data stored in a data asset processed by an execution plan of each stored natural language question matching the new natural language question.

### Claim 8 (depends on 2)

The computer-implemented method of claim 2, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a measure of quality of data processed by an execution plan of each stored natural language question matching the new natural language question.

### Claim 9

A non-transitory computer readable storage medium for storing instructions that when executed by a computer processor, cause the computer processor to perform for steps comprising:
storing a plurality of natural language questions, each natural language question processing data obtained from one or more data sources;
for each of the plurality of natural language questions:
generating an execution plan comprising instructions for accessing data from the one or more data sources for answering the natural language question;
storing the plurality of natural language questions and their execution plans;
receiving a new natural language question;
matching the new natural language question with one or more stored natural language questions;
identifying a subset of stored natural language questions matching the new natural language question;
sending information describing the subset of stored natural language questions;
receiving a selection of a stored natural language question; and
executing an execution plan for the new natural language question, the execution plan determined from the execution plan of the selected stored natural language question.

### Claim 10 (depends on 9)

The non-transitory computer readable storage medium of claim 9, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a number of times each stored natural language question matching the new natural language question was invoked.

### Claim 11 (depends on 9)

The non-transitory computer readable storage medium of claim 9, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a degree of match of each stored natural language question matching the new natural language question with the new natural language question.

### Claim 12 (depends on 9)

The non-transitory computer readable storage medium of claim 9, wherein matching the new natural language question against a stored natural language question comprises ignoring one or more values specified in the new natural language question.

### Claim 13 (depends on 12)

The non-transitory computer readable storage medium of claim 12, further comprising:
substituting one or more values of the execution plan based on the stored natural language question with corresponding values from the new natural language question.

### Claim 14 (depends on 9)

The non-transitory computer readable storage medium of claim 9, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on an amount of data stored in a data asset processed by an execution plan of each stored natural language question matching the new natural language question.

### Claim 15 (depends on 9)

The non-transitory computer readable storage medium of claim 9, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a measure of quality of data processed by an execution plan of each stored natural language question matching the new natural language question.

### Claim 16

A computer system comprising:
a computer processor; and
a non-transitory computer readable storage medium for storing instructions that when executed by a computer processor, cause the computer processor to perform for steps comprising:
storing a plurality of natural language questions, each natural language question processing data obtained from one or more data sources;
for each of the plurality of natural language questions:
generating an execution plan comprising instructions for accessing data from the one or more data sources for answering the natural language question;
storing the plurality of natural language questions and their execution plans;
receiving a new natural language question;
matching the new natural language question with one or more stored natural language questions;
identifying a subset of stored natural language questions matching the new natural language question;
sending information describing the subset of stored natural language questions;
receiving a selection of a stored natural language question; and
executing an execution plan for the new natural language question, the execution plan determined from the execution plan of the selected stored natural language question.

### Claim 17 (depends on 16)

The computer system of claim 16, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a number of times each stored natural language question matching the new natural language question was invoked.

### Claim 18 (depends on 16)

The computer system of claim 16, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a degree of match of each stored natural language question matching the new natural language question with the new natural language question.

### Claim 19 (depends on 16)

The computer system of claim 16, wherein matching the new natural language question against a stored natural language question comprises ignoring one or more values specified in the new natural language question.

### Claim 20 (depends on 19)

The computer system of claim 19, further comprising:
substituting one or more values of the execution plan based on the stored natural language question with corresponding values from the new natural language question.

### Claim 21 (depends on 9)

The non-transitory computer readable storage medium of claim 9, wherein identifying the subset of stored natural language questions matching the new natural language question comprises:
ranking the stored natural language questions matching the new natural language question based on a measure of quality of data processed by an execution plan of each stored natural language question matching the new natural language question.
