# US 9,424,245 B2 · Universal language classification devices, systems, and methods

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

- Number: US 9,424,245 B2
- Document ID: US9424245B2
- Status: Granted
- Kind: B2
- Application number: 13/893,371
- Filed: 2013-05-14
- Published: 2014-04-17
- Granted: 2016-08-23
- Earliest claimed: 2012-05-16
- Assignees: PersonalWeb Technologies, LLC
- Applicants: PersonalWeb Technologies, LLC
- Inventors: Wasef Kassis; Jake Drew; Joshua Cade Jarvis; Bobby Charles Thomas; William Robert Zink
- Web page: https://patentgrep.com/patent/US9424245B2

## CPC

- G06F 40/211: Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
- G06F 9/46: Multiprogramming arrangements
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A computer-implemented method, implemented, at least in part, by hardware in combination with software, the method includes (A) obtaining text from a document; (B) parsing said text using at least one parallel sentence parsing process to obtain sentence data from said text; (C) parsing said sentence data using at least one parallel noun parsing process to obtain text data from said sentence data; (D) scoring said text data using at least one term scorer process and a known word list to obtain scored terms corresponding to said text data; and (E) determining known word scores corresponding to said text data, using said known word list, wherein said known word scores comprise base scores and category penetration scores; wherein steps (B), (C), (D), and (E) operate in parallel for at least some of the text from the document.

## Claims

### Claim 1

A computer-implemented method, implemented, at least in part, by hardware in combination with software, the method comprising:
(A) obtaining text from a document;
(B) parsing said text using at least one parallel sentence parsing process to obtain sentence data from said text;
(C) parsing said sentence data using at least one parallel noun parsing process to obtain text data from said sentence data;
(D) scoring said text data using at least one term scorer process and a known word list to obtain scored terms corresponding to said text data; and
(E) determining known word scores corresponding to said text data, using said known word list, wherein said known word scores comprise base scores and category penetration scores;
wherein steps (B), (C), (D), and (E) operate in parallel for at least some of the text from the document.