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 10,417,341 B2
• Filed: 02/09/2018
• Issued: 09/17/2019
• 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:
  US15/892,679
• Publication Number:
  US 20180232361A1
• Time in Patent Office: 585 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 for using machine learning and rules-based algorithms to automatically convert a set of patent claims into a patent specification, the system comprising:

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

obtain a claim set, the claim set including a numbered list of sentences that precisely define an invention, the claim set including an independent claim and one 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;

determine, based on the claim set, a first data structure representing the claim set, the first data structure including language units from the claim set, the language units in the first data structure being organized according to one or more classifications of individual language elements, the language units being in patentese, wherein patentese includes text structure and legal jargon commonly used in patent claims, and a given language element includes one or more of a word, a phrase, a clause, or a sentence;

determine, based on the first data structure, a second data structure, the second data structure having same dimensions as the first data structure such that a given data structure element at a given position within the first data structure corresponds to a given data structure element at a same position within the second data structure, the second data structure including language elements associated with the claim set, the language elements of the second data structure being in prose rather than patentese, wherein prose includes an ordinary form of written language,

wherein a given language unit in patentese is transformed into a corresponding language unit in prose based on a natural language generation operation, and wherein the natural language generation operation includes one or more of paraphrase induction, simplification, compression, clause fusion, or expansion;

determine, based on language units from the first data structure and the second data structure, a third data structure including ordered content, 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; and

determine one or more sections of the patent specification by assembling language units from the first data structure, the second data structure, and the third data structure.

2. 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.

3. The system of claim 1, 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 3, wherein the ordered content includes one or more software component names, and wherein a given software component is associated with one or more main features.

5. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to:

determine a title of the patent specification;

determine a field of disclosure of the patent specification;

wherein the title and the field of disclosure are determined based on a preamble base stored in the second data structure.

6. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to determine a background of the patent specification, wherein the background is determined based on information provided in an invention disclosure from one or more inventors.

7. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to determine a summary of the patent specification.

8. The system of claim 7, wherein:

the summary includes a first summary portion, a second summary portion, and a third summary portion;

the first summary portion is associated with an independent system claim;

the first summary portion is determined based on the first data structure and the second data structure;

the second summary portion is associated with an independent method claim;

the second summary portion is determined based on the first data structure and the second data structure; and

the third summary portion includes boilerplate language associated with summary.

9. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to determine a brief description of the drawings of the patent specification, wherein the brief description of the drawings is determined based on a preamble base stored in the second data structure.

10. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to determine a detailed description of the patent specification, wherein the detailed description includes a first description portion and a second description portion, wherein the first description portion is determined based on the third data structure, and wherein the second description portion is determined based on the first data structure, the second data structure, and the third data structure.

11. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to determine system claims for the patent specification, wherein the system claims are determined based on the first data structure and the second data structure.

12. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to determine method claims for the patent specification, wherein the method claims are determined based on the first data structure.

13. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to determine an abstract for the patent specification, wherein the abstract is determined based on the first data structure and the second data structure.

14. The system of claim 1, wherein the one or more hardware processors are further configured by machine-readable instructions to determine figure text for the patent specification, wherein the figure text includes first figure text and second figure text, the first figure text being associated with a first figure, the second figure text being associated with a second figure.

15. A method for using machine learning and rules-based algorithms to automatically convert a set of patent claims into a patent specification, the method comprising:

obtaining a claim set, the claim set including a numbered list of sentences that precisely define an invention, the claim set including an independent claim and one 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;

determining, based on the claim set, a first data structure representing the claim set, the first data structure including language units from the claim set, the language units in the first data structure being organized according to one or more classifications of individual language elements, the language units being in patentese, wherein patentese includes text structure and legal jargon commonly used in patent claims, and a given language element includes one or more of a word, a phrase, a clause, or a sentence;

determining, based on the first data structure, a second data structure, the second data structure having same dimensions as the first data structure such that a given data structure element at a given position within the first data structure corresponds to a given data structure element at a same position within the second data structure, the second data structure including language elements associated with the claim set, the language elements of the second data structure being in prose rather than patentese, wherein prose includes an ordinary form of written language,

wherein a given language unit in patentese is transformed into a corresponding language unit in prose based on a natural language generation operation, and wherein the natural language generation operation includes one or more of paraphrase induction, simplification, compression, clause fusion, or expansion;

determining, based on language units from the first data structure and the second data structure, a third data structure including ordered content, 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; and

determining one or more sections of the patent specification by assembling language units from the first data structure, the second data structure, and the third data structure.

16. The method of claim 15, 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.

17. The method of claim 15, 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.

18. The method of claim 17, wherein the ordered content includes one or more software component names, and wherein a given software component is associated with one or more main features.

19. The method of claim 15, further comprising:

determining a title of the patent specification; and

determining a field of disclosure of the patent specification;

wherein the title and the field of disclosure are determined based on a preamble base stored in the second data structure.

20. The method of claim 15, further comprising determining a background of the patent specification, wherein the background is determined based on information provided in an invention disclosure from one or more inventors.

21. The method of claim 15, further comprising determining a summary of the patent specification.

22. The method of claim 21, wherein:

the summary includes a first summary portion, a second summary portion, and a third summary portion;

the first summary portion is associated with an independent system claim;

the first summary portion is determined based on the first data structure and the second data structure;

the second summary portion is associated with an independent method claim;

the second summary portion is determined based on the first data structure and the second data structure; and

the third summary portion includes boilerplate language associated with summary.

23. The method of claim 15, further comprising determining a brief description of the drawings of the patent specification, wherein the brief description of the drawings is determined based on a preamble base stored in the second data structure.

24. The method of claim 15, further comprising determining a detailed description of the patent specification, wherein the detailed description includes a first description portion and a second description portion, wherein the first description portion is determined based on the third data structure, and wherein the second description portion is determined based on the first data structure, the second data structure, and the third data structure.

25. The method of claim 15, further comprising determining system claims for the patent specification, wherein the system claims are determined based on the first data structure and the second data structure.

26. The method of claim 15, further comprising determining method claims for the patent specification, wherein the method claims are determined based on the first data structure.

27. The method of claim 15, further comprising determining an abstract for the patent specification, wherein the abstract is determined based on the first data structure and the second data structure.

28. The method of claim 15, further comprising determining figure text for the patent specification, wherein the figure text includes first figure text and second figure text, the first figure text being associated with a first figure, the second figure text being associated with a second figure.