Patent Issued for Systems And Methods For Electronically Mining Intellectual Property (USPTO 10,445,331)

2019 OCT 30 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors Fields, Brian Mark (Normal, IL); Peng, Jufeng (Avon, CT); Freeck, Jason (Gurnee, IL); McWilliams, James Maxwell (Rolling Meadows, IL); O’Flaherty, Mark (Champaign, IL); Johnson, Pat J. (Champaign, IL), filed on January 4, 2018, was published online on October 28, 2019, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 10,445,331 is assigned to State Farm Mutual Automobile Insurance Company (Bloomington, Illinois, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “Intellectual properties are recognized as valuable assets in many fields of business. As such, the ability to quickly harvest, discover, analyze and document intellectual properties has become a major goal for many companies and corporations.

“However, many companies do not always have an enterprise view of the business processes and development works that are being planned or implemented. Consequently, many companies fail to properly discover potentially business-critical intellectual properties and/or new opportunities that may help them to innovate or solve their business problems.

“Current methods of discovery rely mostly on managers and other responsible personnel to manually identify potential intellectual properties. For example, project managers may review and rate invention disclosures to determine their worth. However, such decisions are typically made in an ad-hoc manner and may be prone to the personal biases of the decision maker. Further, such decisions are often made without considering or valuing various existing enterprise business processes and interests.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “In one aspect, a computer-implemented method for electronically mining intellectual property using an associative discovery process includes: (1) determining, by one or more processors analyzing one or more enterprise documents in an enterprise dataset associated with a business entity, a set of documents containing one or more keywords and/or phrases associated with an industry trend of interest; (2) for each document in the set of documents, assigning, by one or more processors, a weight, wherein a greater weight is assigned for documents in which the one or more keywords and/or phrases appear more frequently; (3) selecting, by one or more processors, a subset of the set of documents based at least upon the assigned weights; (4) determining, by one or more processors, a feedback score for each document in the subset of documents, wherein the feedback score for a given document indicates relevance of the given document to the industry trend of interest; (5) determining, by one or more processors, an optimal weighing scheme for the determined one or more keywords and/or phrases using a statistical learning model and the feedback scores for the subset of documents, wherein determining an optimal weighing scheme includes calculating an optimal weight for each of the determined one or more keywords and/or phrases; (6) ranking, by one or more processors, all documents in the set of documents according to the optimal weighing scheme, such that the ranking indicates how strongly each document in the set of documents is related to the industry trend of interest; and/or (7) providing, by one or more processors, results of the associative discovery process to a user.

“In another aspect, a non-transitory computer-readable storage memory includes computer-readable instructions to be executed on one or more processors of a system for electronically mining intellectual property using an associative discovery process. The instructions when executed cause the one or more processors to: (1) determine, by analyzing one or more enterprise documents in an enterprise dataset associated with a business entity, a set of documents containing one or more keywords and/or phrases associated with an industry trend of interest; (2) for each document in the set of documents, assign a weight, wherein a greater weight is assigned for documents in which the one or more keywords and/or phrases appear more frequently; (3) select a subset of the set of documents based at least upon the assigned weights; (4) determine a feedback score for each document in the subset of documents, wherein the feedback score for a given document indicates relevance of the given document to the industry trend of interest; (5) determine an optimal weighing scheme for the determined one or more keywords and/or phrases using a statistical learning model and the feedback scores for the subset of documents, wherein determining an optimal weighing scheme includes calculating an optimal weight for each of the determined one or more keywords and/or phrases; (6) rank all documents in the set of documents according to the optimal weighing scheme, such that the ranking indicates how strongly each document in the set of documents is related to the industry trend of interest; and/or (7) provide results of the associative discovery process to a user.

“In another aspect, a computer system for electronically mining intellectual property using an associative discovery process includes one or more dataset repositories and an analysis server. The analysis server includes a memory having instructions for execution on one or more processors. The instructions, when executed by the one or more processors, cause the analysis server to: (1) determine, by analyzing one or more enterprise documents in an enterprise dataset associated with a business entity, a set of documents containing one or more keywords and/or phrases associated with an industry trend of interest; (2) for each document in the set of documents, assign a weight, wherein a greater weight is assigned for documents in which the one or more keywords and/or phrases appear more frequently; (3) select a subset of the set of documents based at least upon the assigned weights; (4) determine a feedback score for each document in the subset of documents, wherein the feedback score for a given document indicates relevance of the given document to the industry trend of interest; (5) determine an optimal weighing scheme for the determined one or more keywords and/or phrases using a statistical learning model and the feedback scores for the subset of documents, wherein determining an optimal weighing scheme includes calculating an optimal weight for each of the determined one or more keywords and/or phrases; (6) rank all documents in the set of documents according to the optimal weighing scheme, such that the ranking indicates how strongly each document in the set of documents is related to the industry trend of interest; and/or (7) provide results of the associative discovery process to a user.

“Advantages will become more apparent to those skilled in the art from the following description of the preferred embodiments which have been shown and described by way of illustration. As will be realized, the present embodiments may be capable of other and different embodiments, and their details are capable of modification in various respects. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive.”

The claims supplied by the inventors are:

“What is claimed:

“1. A computer-implemented method for electronically mining intellectual property using an associative discovery process, the method comprising: determining, by one or more processors analyzing one or more enterprise documents in an enterprise dataset associated with a business entity, a set of documents containing one or more keywords and/or phrases associated with an industry trend of interest; for each document in the set of documents, assigning, by one or more processors, a weight, wherein a greater weight is assigned for documents in which the one or more keywords and/or phrases appear more frequently; selecting, by one or more processors, a subset of the set of documents based at least upon the assigned weights; determining, by one or more processors, a feedback score for each document in the subset of documents, wherein the feedback score for a given document indicates relevance of the given document to the industry trend of interest; determining, by one or more processors, an optimal weighing scheme for the determined one or more keywords and/or phrases using a statistical learning model and the feedback scores for the subset of documents, wherein determining an optimal weighing scheme includes calculating an optimal weight for each of the determined one or more keywords and/or phrases; ranking, by one or more processors, all documents in the set of documents according to the optimal weighing scheme, such that the ranking indicates how strongly each document in the set of documents is related to the industry trend of interest; and providing, by one or more processors, results of the associative discovery process to a user.

“2. The computer-implemented method of claim 1, further comprising: performing, by one or more processors, a normalization on the weighted set of documents, wherein selecting the subset of documents includes selecting the subset of documents from the normalized weighted set of documents.

“3. The computer-implemented method of claim 1, wherein the one or more enterprise documents describe one or more of an enterprise business process, an enterprise application, or an enterprise project that is being generated or explored by the business entity.

“4. The computer-implemented method of claim 1, wherein the industry trend of interest describes one or more of a new business process, or a new technology, that is relevant to a field in which the business entity operates.

“5. The computer-implemented method of claim 1, wherein the feedback score is a score generated based on words and/or phrases associated with business decisions made by the business entity.

“6. The computer-implemented method of claim 1, further comprising, prior to determining the set of documents: receiving one or more industry datasets specifying one or more technology trends that are relevant to a field in which the business entity operates; and identifying, by one or more processors, the industry trend of interest from the one or more industry datasets.

“7. The computer-implemented method of claim 1, further comprising: prior to determining the set of documents, determining, by one or more processors analyzing one or more industry datasets specifying one or more technology trends that are relevant to a field in which the business entity operates, the one or more keywords and/or phrases.

“8. A non-transitory computer-readable storage memory including computer-readable instructions to be executed on one or more processors of a system for electronically mining intellectual property using an associative discovery process, the instructions when executed causing the one or more processors to: determine, by analyzing one or more enterprise documents in an enterprise dataset associated with a business entity, a set of documents containing one or more keywords and/or phrases associated with an industry trend of interest; for each document in the set of documents, assign a weight, wherein a greater weight is assigned for documents in which the one or more keywords and/or phrases appear more frequently; select a subset of the set of documents based at least upon the assigned weights; determine a feedback score for each document in the subset of documents, wherein the feedback score for a given document indicates relevance of the given document to the industry trend of interest; determine an optimal weighing scheme for the determined one or more keywords and/or phrases using a statistical learning model and the feedback scores for the subset of documents, wherein determining an optimal weighing scheme includes calculating an optimal weight for each of the determined one or more keywords and/or phrases; rank all documents in the set of documents according to the optimal weighing scheme, such that the ranking indicates how strongly each document in the set of documents is related to the industry trend of interest; and provide results of the associative discovery process to a user.

“9. The non-transitory computer-readable storage memory of claim 8, wherein: the instructions further cause the one or more processors to perform a normalization on the weighted set of documents; and selecting the subset of documents includes selecting the subset of documents from the normalized weighted set of documents.

“10. The non-transitory computer-readable storage memory of claim 8, wherein the one or more enterprise documents describe one or more of an enterprise business process, an enterprise application, or an enterprise project that is being generated or explored by the business entity.

“11. The non-transitory computer-readable storage memory of claim 8, wherein the industry trend of interest describes one or more of a new business process, or a new technology, that is relevant to a field in which the business entity operates.

“12. The non-transitory computer-readable storage memory of claim 8, wherein the feedback score is a score generated based on words and/or phrases associated with business decisions made by the business entity.

“13. The non-transitory computer-readable storage memory of claim 8, wherein the instructions further cause the one or more processors to, prior to determining the set of documents: receive one or more industry datasets specifying one or more technology trends that are relevant to a field in which the business entity operates; and identify the industry trend of interest from the one or more industry datasets.

“14. The non-transitory computer-readable storage memory of claim 8, wherein the instructions further cause the one or more processors to: prior to determining the set of documents, determine, by analyzing one or more industry datasets specifying one or more technology trends that are relevant to a field in which the business entity operates, the one or more keywords and/or phrases.

“15. A computer system for electronically mining intellectual property using an associative discovery process, the system comprising: one or more dataset repositories; and an analysis server, including a memory having instructions for execution on one or more processors, wherein the instructions, when executed by the one or more processors, cause the analysis server to determine, by analyzing one or more enterprise documents in an enterprise dataset associated with a business entity, a set of documents containing one or more keywords and/or phrases associated with an industry trend of interest, for each document in the set of documents, assign a weight, wherein a greater weight is assigned for documents in which the one or more keywords and/or phrases appear more frequently, select a subset of the set of documents based at least upon the assigned weights, determine a feedback score for each document in the subset of documents, wherein the feedback score for a given document indicates relevance of the given document to the industry trend of interest, determine an optimal weighing scheme for the determined one or more keywords and/or phrases using a statistical learning model and the feedback scores for the subset of documents, wherein determining an optimal weighing scheme includes calculating an optimal weight for each of the determined one or more keywords and/or phrases, rank all documents in the set of documents according to the optimal weighing scheme, such that the ranking indicates how strongly each document in the set of documents is related to the industry trend of interest, and provide results of the associative discovery process to a user.

“16. The computer system of claim 15, wherein: the instructions further cause the analysis server to perform a normalization on the weighted set of documents; and selecting the subset of documents includes selecting the subset of documents from the normalized weighted set of documents.

“17. The computer system of claim 15, wherein the one or more enterprise documents describe one or more of an enterprise business process, an enterprise application, or an enterprise project that is being generated or explored by the business entity.

“18. The computer system of claim 15, wherein the feedback score is a score generated based on words and/or phrases associated with business decisions made by the business entity.

“19. The computer system of claim 15, wherein the instructions further cause the analysis server to, prior to determining the set of documents: receive one or more industry datasets specifying one or more technology trends that are relevant to a field in which the business entity operates; and identify the industry trend of interest from the one or more industry datasets.

“20. The computer system of claim 15, wherein the instructions further cause the analysis server to: prior to determining the set of documents, determine, by analyzing one or more industry datasets specifying one or more technology trends that are relevant to a field in which the business entity operates, the one or more keywords and/or phrases.”

URL and more information on this patent, see: Fields, Brian Mark; Peng, Jufeng; Freeck, Jason; McWilliams, James Maxwell; O’Flaherty, Mark; Johnson, Pat J. Systems And Methods For Electronically Mining Intellectual Property. U.S. Patent Number 10,445,331, filed January 4, 2018, and published online on October 28, 2019. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=10,445,331.PN.&OS=PN/10,445,331RS=PN/10,445,331

(Our reports deliver fact-based news of research and discoveries from around the world.)