# US 2021/0240753 A1 · Method and system for technical language processing

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

- Number: US 2021/0240753 A1
- Document ID: US20210240753A1
- Status: Published application
- Kind: A1
- Application number: 16/864,060
- Filed: 2020-04-30
- Published: 2021-08-05
- Earliest claimed: 2020-02-04
- Assignees: Inspird, Inc.
- Applicants: InspiRD, Inc.
- Inventors: Sandeep Mehta
- Web page: https://patentgrep.com/patent/US20210240753A1

## CPC

- G06F 16/3344: {using natural language analysis}
- G06F 40/242: Dictionaries
- G06F 16/338: Presentation of query results
- G06F 16/90344: {by using string matching techniques}
- G06F 40/284: Lexical analysis, e.g. tokenisation or collocates
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Exemplary embodiments disclose a method, a computer program product, and a computer system for searching technical documents. Exemplary embodiments may include the use of lexicons to generate customized hash functions; utilizing customized hash functions to generate hashcodes of technical text in document repositories; building a database of hashcodes from the repository; utilizing the customized hash functions for generating a hashcode of a search query; and correlating the search hashcode with the hashcode database to produce search results. A computer-implemented method to search technical text includes constructing one or more base hash functions for generating hashcodes that represent semantic content of technical text and accessing one or more lexicons describing technical terminology. The method includes utilizing the one or more lexicons to create one or more customized hash functions from the one or more base hash functions to generate hashcodes that more accurately represent a semantic content of the technical terminology in the one or more lexicons compared to the base hash functions.

## Claims

### Claim 1

A computer-implemented method for technical language processing, the method comprising:
constructing one or more base hash functions for generating hashcodes that represent semantic content of technical text;
accessing one or more lexicons describing technical terminology; and
utilizing the one or more lexicons to create one or more customized hash functions from the one or more base hash functions to generate hashcodes that more accurately represent a semantic content of the technical terminology in the one or more lexicons compared to the base hash functions.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
parsing documents in a technical document repository into syntactic elements;
utilizing the one or more of the customized hash functions to generate hashcodes for the syntactic elements and storing the hashcodes for the syntactic elements in a hashcode database;
accessing a search query; and
utilizing the one or more customized hash functions to generate a search hashcode for the search query.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, further comprising:
correlating the search hashcode with the hashcode database and determining one or more search results.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, further comprising:
displaying the one or more search results.

### Claim 5 (depends on 2)

The computer-implemented method of claim 2, further comprising:
concatenating the hashcodes for the syntactic elements to generate an aggregate hashcode.

### Claim 6 (depends on 3)

The computer-implemented method of claim 3, further comprising:
modifying the customized hash functions utilizing user feedback on the one or more search results.

### Claim 7 (depends on 2)

The computer-implemented method of claim 2, further comprising:
using one or more computer translation tools to translate document repositories.

### Claim 8

A computer-implemented method for searching a technical documents repository, the method comprising:
constructing one or more base hash functions for generating hashcodes that represent semantic content of technical text;
parsing documents in the technical document repository into syntactic elements;
utilizing the one or more base hash functions to generate hashcodes for the syntactic elements and storing the hashcodes in a hashcode database;
accessing a search query;
utilizing the one or more base hash functions to generate a search hashcode for the search query; and
correlating the search hashcode with the hashcode database and determining one or more search results.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
accessing one or more lexicons describing technical terminology; and
utilizing the one or more lexicons to create one or more customized hash functions from the one or more base hash functions to generate hashcodes that more accurately represent a semantic content of the technical terminology in the one or more lexicons compared to the base hash functions.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
displaying the one or more search results.

### Claim 11 (depends on 9)

The method of claim 9, further comprising:
concatenating the hashcodes generated by the one or more of the customized hash functions to generate an aggregate hashcode.

### Claim 12 (depends on 9)

The method of claim 9, further comprising:
modifying the one or more customized hash functions utilizing user feedback on the one or more search results.

### Claim 13 (depends on 9)

The method in claim 9, further comprising:
using one or more computer translation tools to translate document repositories.

### Claim 14

A computer-program product for searching a technical documents repository, the computer program product comprising:
one or more non-transitory computer-readable storage media and program instructions stored on the one or more non-transitory computer-readable storage media capable of performing a method, the method comprising:
constructing one or more base hash functions for generating hashcodes that represent semantic content of technical text;
parsing documents in the technical document repository into syntactic elements;
utilizing the one or more base hash functions to generate hashcodes of the syntactic elements and storing the hashcodes in a hashcode database;
accessing a search query;
utilizing the one or more base hash functions to generate a search hashcode for the search query; and
correlating the search hashcode with the hashcode database and determining one or more search results.

### Claim 15 (depends on 14)

The computer-program product of claim 14, the method further comprising:
accessing one or more lexicons describing technical terminology; and
utilizing the one or more lexicons to create one or more customized hash functions from the one or more base hash functions to generate hashcodes that more accurately represent a semantic content of the technical terminology in the one or more lexicons compared to the base hash functions.

### Claim 16 (depends on 15)

The computer-program product of claim 15, the method further comprising:
displaying the one or more search results.

### Claim 17 (depends on 15)

The computer-program product of claim 15, the method further comprising:
concatenating the hashcodes generated by the one or more customized hash functions to generate an aggregate hashcode.

### Claim 18 (depends on 15)

The computer-program product of claim 15, the method further comprising:
collecting user feedback on the one or more search results; and
modifying the customized hash functions based on the user feedback.

### Claim 19 (depends on 15)

The computer-program product of claim 15, the method further comprising:
using one or more computer translation tools to translate document repositories.

### Claim 20 (depends on 15)

The computer-program product of claim 15, further comprising:
one or more computer processors capable of executing the program instructions stored on the one or more computer-readable storage media.
