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

• US 10,572,600 B2
• Filed: 07/12/2019
• Issued: 02/25/2020
• Est. Priority Date: 02/15/2017
• Status: Active Grant

• Current Assignee: Paximal Incorporated
• Original Assignee: Specifio, Inc.
• Inventors: Schick, Ian C., Knight, Kevin
• Primary Examiner(s): Guerra-Erazo, Edgar X
• Application Number:
  US16/510,074
• Publication Number:
  US 20190332674A1
• Time in Patent Office: 228 Days
• CPC Class Codes: G06F 40/137 Hierarchical processing, e.g. outlines
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/184 Intellectual property management

Abstract

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.

Claims

1. A system configured to use machine learning and/or rules-based algorithms to automatically convert portions of patent claims into portions of a patent specification, the system comprising:

one or more hardware processors configured by machine-readable instructions to;

obtain at least a portion of a patent claim, the patent claim being a numbered sentence that precisely defines an invention;

determine, based on the at least the portion of the patent claim, a first data structure representing the at least the portion of the patent claim, the first data structure including language units from the at least the portion of the patent claim, wherein a given language element of the first data structure includes one or more of a word, a phrase, a clause, or a sentence;

determine, based on one or both of the at least the portion of the patent claim or the first data structure, a second data structure, the second data structure including language elements associated with the at least the portion of the patent claim, a given language element of the second data structure being in prose, wherein prose includes an ordinary form of written language, wherein a given language unit in the first data structure is transformed into a corresponding language unit in the second data structure based on a natural language generation operation; and

determine at least a portion of one or more sections of the patent specification by assembling the language units from the first data structure and language units from the second data structure.

2. The system of claim 1, wherein the patent claim is part of a claim set, the claim set including an independent claim and zero or more dependent claims, each dependent claim in the claim set depending on the independent claim by referring to the independent claim or an intervening dependent claim.

3. The system of claim 1, wherein the language units in the first data structure are organized according to one or more classifications of individual language elements, wherein the one or more classifications include one or more of independent claim, dependent claim, preamble, main feature, sub feature, claim line, clause, phrase, or word.

4. The system of claim 1, wherein the first data structure and the second data structure are separate and distinct from each other.

5. The system of claim 1, wherein the natural language generation operation includes one or more of paraphrase induction, simplification, compression, clause fusion, or expansion.

6. The system of claim 1, wherein the patent claim is part of a claim set, wherein the one or more hardware processors are further configured by machine-readable instructions to determine, based on the language units from the first data structure and/or the language units from the second data structure, a third data structure, wherein the ordered content of the third data structure is ordered based on one or more of claim structure of the claim set, antecedent basis in the claim set, or claim dependency in the claim set.

7. The system of claim 6, where the one or more sections of the patent specification are further determined by assembling language units from the third data structure.

8. The system of claim 1, wherein a given data structure includes a specialized format for organizing and storing data, the given data structure including one or more of an array, a list, two or more linked lists, a stack, a queue, a graph, a table, or a tree.

9. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to generate one or more drawing figures described in the patent specification, the one or more drawing figures being generated based on one or both of the first data structure or the second data structure.

10. A method to use machine learning and/or rules-based algorithms to automatically convert portions of patent claims into portions of a patent specification, the method comprising:

obtaining at least a portion of a patent claim, the patent claim being a numbered sentence that precisely defines an invention;

determining, based on the at least the portion of the patent claim, a first data structure representing the at least the portion of the patent claim, wherein a given language element of the first data structure includes one or more of a word, a phrase, a clause, or a sentence;

determining, based on one or both of the at least the portion of the patent claim or the first data structure, a second data structure, the second data structure including language elements associated with the at least the portion of the patent claim, the language elements of the second data structure being in prose, wherein prose includes an ordinary form of written language, wherein a given language unit in the first data structure is transformed into a corresponding language unit in the second data structure based on a natural language generation operation; and

determining at least a portion of one or more sections of the patent specification by assembling the language units from the first data structure and language units from the second data structure.

11. The method of claim 10, wherein the patent claim is part of a claim set, the claim set including an independent claim and zero or more dependent claims, each dependent claim in the claim set depending on the independent claim by referring to the independent claim or an intervening dependent claim.

12. The method of claim 10, wherein the language units in the first data structure are organized according to one or more classifications of individual language elements, wherein the one or more classifications include one or more of independent claim, dependent claim, preamble, main feature, sub feature, claim line, clause, phrase, or word.

13. The method of claim 10, wherein the first data structure and the second data structure are separate and distinct from each other.

14. The method of claim 10, wherein the natural language generation operation includes one or more of paraphrase induction, simplification, compression, clause fusion, or expansion.

15. The method of claim 10, wherein the patent claim is part of a claim set, and wherein the method further comprises determining, based on the language units from the first data structure and/or the language units from the second data structure, a third data structure, wherein the ordered content of the third data structure is ordered based on one or more of claim structure of the claim set, antecedent basis in the claim set, or claim dependency in the claim set.

16. The method of claim 15, where the one or more sections of the patent specification are further determined by assembling language units from the third data structure.

17. The method of claim 10, wherein a given data structure includes a specialized format for organizing and storing data, the given data structure including one or more of an array, a list, two or more linked lists, a stack, a queue, a graph, a table, or a tree.

18. The method of claim 10, further comprising generating one or more drawing figures described in the patent specification, the one or more drawing figures being generated based on one or both of the first data structure or the second data structure.