SYSTEMS AND METHODS FOR USING MACHINE LEARNING AND RULES-BASED ALGORITHMS TO CREATE A PATENT SPECIFICATION BASED ON HUMAN-PROVIDED PATENT CLAIMS SUCH THAT THE PATENT SPECIFICATION IS CREATED WITHOUT HUMAN INTERVENTION

Patent №

US 11,651,160

Granted

2023-05-16

Filed 2020

Owner

SPECIFIO, INC.

Lab

—

AI components

ml · nlp · kr · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16739655

Systems and methods for using machine learning and rules-based algorithms to create a patent specification based on human-provided patent claims such that the patent specification is created without human intervention are disclosed. Exemplary implementations may: obtain a claim set; obtain a first data structure representing the claim set; obtain a second data structure; obtain a third data structure; and determine one or more sections of the patent specification based on the first data structure, the second data structure, and the third data structure.

Machine learning Natural language Knowledge representation Planning AI hardwareG06F 40/30G06F 40/137G06F 40/284G06F 40/56G06Q 10/10G06Q 50/184G06N 20/00

Google Patents

AI classification

Natural language1.00

Planning1.00

Knowledge representation0.98

Machine learning0.97

AI hardware0.91

Speech0.03

Vision0.01

Evolutionary computation0.00

Ownership

SPECIFIO, INC.

assignment · 514780974

Assignors

SCHICK, IAN C., KNIGHT, KEVIN

On an employer assignment, the assignors are typically the inventors.

From the same owner

SYSTEMS AND METHODS FOR EXTRACTING PATENT DOCUMENT TEMPLATES FROM A PATENT CORPUSUS 11,593,564 · 2023 SYSTEMS AND METHODS FOR FACILITATING EDITING OF A CONFIDENTIAL DOCUMENT BY A NON-PRIVILEGED PERSON BY STRIPPING AWAY CONTENT AND MEANING FROM THE DOCUMENT WITHOUT HUMAN INTERVENTION SUCH THAT ONLY STRUCTURAL AND/OR GRAMMATICAL INFORMATION OF THE DOCUMENT ARE CONVEYED TO THE NON-PRIVILEGED PERSONUS 11,188,664 · 2021 SYSTEMS AND METHODS FOR PROVIDING ADAPTIVE SURFACE TEXTURE IN AUTO-DRAFTED PATENT DOCUMENTSUS 11,023,662 · 2021 SYSTEMS AND METHODS FOR AUTOMATICALLY CREATING A PATENT APPLICATION BASED ON A CLAIM SET SUCH THAT THE PATENT APPLICATION FOLLOWS A DOCUMENT PLAN INFERRED FROM AN EXAMPLE DOCUMENTUS 10,747,953 · 2020 MACHINE LEARNING MODEL FOR COMPUTER-GENERATED PATENT APPLICATIONS TO PROVIDE SUPPORT FOR INDIVIDUAL CLAIM FEATURES IN A SPECIFICATIONUS 10,713,443 · 2020 SYSTEMS AND METHODS FOR FACILITATING EDITING OF A CONFIDENTIAL DOCUMENT BY A NON-PRIVILEGED PERSON BY STRIPPING AWAY CONTENT AND MEANING FROM THE DOCUMENT WITHOUT HUMAN INTERVENTION SUCH THAT ONLY STRUCTURAL AND/OR GRAMMATICAL INFORMATION OF THE DOCUMENT ARE CONVEYUS 10,621,371 · 2020 SYSTEMS AND METHODS FOR USING MACHINE LEARNING AND RULES-BASED ALGORITHMS TO CREATE A PATENT SPECIFICATION BASED ON HUMAN-PROVIDED PATENT CLAIMS SUCH THAT THE PATENT SPECIFICATION IS CREATED WITHOUT HUMAN INTERVENTIONUS 10,572,600 · 2020 SYSTEMS AND METHODS FOR USING MACHINE LEARNING AND RULES-BASED ALGORITHMS TO CREATE A PATENT SPECIFICATION BASED ON HUMAN-PROVIDED PATENT CLAIMS SUCH THAT THE PATENT SPECIFICATION IS CREATED WITHOUT HUMAN INTERVENTIONUS 10,417,341 · 2019

Cites (30)

SYSTEMS AND METHODS FOR PROVIDING ADAPTIVE SURFACE TEXTURE IN AUTO-DRAFTED PATENT DOCUMENTSUS 11,023,662 · 2021 GENERATING TEMPLATES FROM USER'S PAST DOCUMENTSUS 10,839,149 · 2020 SYSTEMS AND METHODS FOR AUTOMATICALLY CREATING A PATENT APPLICATION BASED ON A CLAIM SET SUCH THAT THE PATENT APPLICATION FOLLOWS A DOCUMENT PLAN INFERRED FROM AN EXAMPLE DOCUMENTUS 10,747,953 · 2020 MACHINE LEARNING MODEL FOR COMPUTER-GENERATED PATENT APPLICATIONS TO PROVIDE SUPPORT FOR INDIVIDUAL CLAIM FEATURES IN A SPECIFICATIONUS 10,713,443 · 2020 SYSTEMS AND METHODS FOR FACILITATING EDITING OF A CONFIDENTIAL DOCUMENT BY A NON-PRIVILEGED PERSON BY STRIPPING AWAY CONTENT AND MEANING FROM THE DOCUMENT WITHOUT HUMAN INTERVENTION SUCH THAT ONLY STRUCTURAL AND/OR GRAMMATICAL INFORMATION OF THE DOCUMENT ARE CONVEYUS 10,621,371 · 2020 SYSTEMS AND METHODS FOR USING MACHINE LEARNING AND RULES-BASED ALGORITHMS TO CREATE A PATENT SPECIFICATION BASED ON HUMAN-PROVIDED PATENT CLAIMS SUCH THAT THE PATENT SPECIFICATION IS CREATED WITHOUT HUMAN INTERVENTIONUS 10,572,600 · 2020 SECURE MESSAGE SERVICE FOR PREVENTING DISSEMINATION OF SENSITIVE INFORMATION TO THIRD-PARTIESUS 10,469,425 · 2019 SYSTEMS AND METHODS FOR USING MACHINE LEARNING AND RULES-BASED ALGORITHMS TO CREATE A PATENT SPECIFICATION BASED ON HUMAN-PROVIDED PATENT CLAIMS SUCH THAT THE PATENT SPECIFICATION IS CREATED WITHOUT HUMAN INTERVENTIONUS 10,417,341 · 2019 SYSTEMS, METHODS AND USER INTERFACES IN A PATENT MANAGEMENT SYSTEMUS 10,242,066 · 2019 Systems and methods for patent reference comparison in a combined semantical-probabilistic algorithmUS 10,073,890 · 2018 DATA OBFUSCATIONUS 9,946,895 · 2018 System for Search and Customized Information Updating of New Patents and Research, and Evaluation of New Research Projects' and Current Patents' PotentialUS 9,836,805 · 2017 SECURE THIRD-PARTY DOCUMENT EDITINGUS 9,734,137 · 2017 SYSTEMS AND METHODS FOR MANAGING DOCUMENTS ASSOCIATED WITH ONE OR MORE PATENT APPLICATIONSUS 9,607,058 · 2017 IDENTIFYING ENTITY SYNONYMSUS 9,600,566 · 2017 ONTOLOGY-DRIVEN ANNOTATION CONFIDENCE LEVELS FOR NATURAL LANGUAGE PROCESSINGUS 9,547,640 · 2017 SYSTEM, METHODS, AND DATA STRUCTURE FOR MACHINE-LEARNING OF CONTEXTUALIZED SYMBOLIC ASSOCIATIONSUS 9,195,647 · 2015 AUTOMATED SYSTEM & METHOD FOR PATENT DRAFTING & TECHNOLOGY ASSESSMENTUS 8,041,739 · 2011 SYSTEM, METHOD, AND RECORDING MEDIUM FOR DRAFTING AND PREPARING PATENT SPECIFICATIONSUS 6,434,580 · 2002 SYSTEM,METHOD,AND COMPUTER PROGRAM PRODUCT FOR COMPARING TEXT PORTIONS BY REFERENCE TO INDEX INFORMATIONUS 6,014,663 · 2000 SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR GENERATING EQUIVALENT TEXT FILESUS 5,799,325 · 1998 METHOD FOR SYNTACTIC AND SEMANTIC ANALYSIS OF PATENT TEXT AND DRAWINGSUS 5,774,833 · 1998 Patent US 11,341,323US 11,341,323 Patent US 6,049,811US 6,049,811 Patent US 7,890,851US 7,890,851

and 5 more

Related research

Automating Claim Construction in Patent Applications: The CMUmine DatasetOpenAlex InstructPatentGPT: Training patent language models to follow instructions with human feedbackarXiv AutoSpec: An Agentic Framework for Automatically Drafting Patent SpecificationarXiv Machine Learning at the Patent Office: Lessons for Patents and Administrative LawSemantic Scholar An Automatic Generation Method of Patent Specification Abstract Based on "Extraction- Abstraction "ModelOpenAlex

Full text

Google Patents