Back to results
US 11,893,537 B2Granted
Linguistic analysis of seed documents and peer groups
AssigneeAon Risk Services, Inc. of Maryland
InventorDavid Craig Andrews
Life of this patent
Estimating the term…
Abstract
Systems may evaluate a claim or patent with respect to a related set of claims or patent documents. The systems may perform linguistic analyses of claims included in the patent and the related set of patent documents. Based on the linguistic analyses, the systems may identify claim limitations, and/or claim elements. The systems may generate a claim profile for each claim being evaluated. The claim profile may include ratings or scores for various metrics related to the claims being evaluated. The systems may also generate a peer group profile that provides an overall measure of metrics for claims included in a peer group of patent documents.
Claims20
A method comprising:
- obtaining a first patent document;
- analyzing content of the first patent document to identify a first claim of the first patent document, the first claim including a first plurality of words;
- performing a first linguistic analysis of the first plurality of words of the first claim;
- generating, based at least partly on the first linguistic analysis, a first tag for at least one word of the first plurality of words of the first claim, the first tag being one of a first plurality of first tags and the first tag being applied to a first syntactic category corresponding to the at least one word;
- generating a first profile for the first claim that includes a first set of metrics for the first claim, the first set of metrics being determined by at least one machine learning model and based at least partly on the first plurality of first tags applied to at least a portion of the first plurality of words of the first claim;
- receiving additional patent documents from a searching authority, the additional patent documents being ranked by the searching authority and related to the first patent document;
- analyzing additional content of the additional patent documents to identify a second claim of the additional patent documents, the second claim including a second plurality of words;
- performing a second linguistic analysis on the second plurality of words of the second claim;
- generating, based at least partly on the second linguistic analysis, a second tag for at least one word of the second plurality of words of the second claim of the additional patent documents, the second tag being of a second plurality of second tags and the second tag being applied to at least a portion of the second plurality of words from the second claim;
- generating a second profile that includes a second set of metrics, the second set of metrics being determined by the at least one machine learning model and based at least partly on the second plurality of second tags applied to at least a portion of the second plurality of words of the second claim;
- determining that the first plurality of first tags and the second plurality of second tags are similar,
- generating, based at least in part on the determination, a peer group claim set profile;
- receiving a request to perform a third linguistic analysis of the peer group claim set profile;
- receiving a request for third linguistic analysis results to be displayed in a specific ranking associated with a selected relevancy of multiple selectable data points, wherein the request indicates the third linguistic analysis results are to be ranked based at least in part on selected data points, the selected data points based at least in part on the selected relevancy of multiple selectable data points;
- re-ranking the additional patent documents based on the selected data points;
- and
- generating data of a user interface that includes at least one claim profile of the peer group claim set profile, wherein the data indicates the re-ranking.
14 more elements
A system comprising:
- one or more processors;
- and
- non-transitory computer-readable media storing computer-executable instructions, that when executed by the one or more processors cause the one or more processors to perform operations comprising:
- obtaining a patent document;
- analyzing the patent document to identify a first independent claim of the patent document, the first independent claim including a first plurality of words;
- determining a first syntactic category for individual words of the first plurality of words of the first independent claim;
- determining, based at least partly on first syntactic categories of the individual words of the first plurality of words, a first number of groups of words that include the first plurality of words of the first independent claim;
- generating a first claim profile for the first independent claim that includes a first set of metrics, the first set of metrics determined by at least one machine learning model and corresponding to at least one of the first number of groups of words of the first independent claim or the first syntactic categories;
- analyzing content of the patent document to identify at least one additional independent claim, the at least one additional independent claim including a plurality of additional words;
- determining an additional syntactic category for additional individual words of the plurality of additional words;
- determining, based at least partly on additional syntactic categories of the additional individual words, a number of additional groups of words that include the plurality of additional words;
- generating an additional claim profile for the at least one additional independent claim that includes an additional set of metrics, the additional set of metrics determined by at least one machine learning model and corresponding to at least one of the number of additional groups of words of the at least one additional independent claim or the additional syntactic categories;
- determining that the first set of metrics and the additional set of metrics are similar;
- generating, based at least in part on the determination, a peer group claim set profile;
- receiving a request to perform a linguistic analysis of the peer group claim set profile;
- receiving a request for linguistic analysis results to be displayed in a specific ranking associated with a selected relevancy of multiple selectable data points, wherein the request indicates the linguistic analysis results are to be ranked based at least in part on selected data points, the selected data points based at least in part on the selected relevancy of multiple selectable data points;
- re-ranking the at least one additional independent claim based on the selected data points;
- and
- generating data of a user interface that includes at least one claim profile of the peer group claim set profile wherein the data indicates the re-ranking.
16 more elements
A method comprising:
- obtaining a first patent document;
- analyzing the first patent document to identify a first claim of the first patent document, the first claim including a first plurality of words;
- determining a first syntactic category for individual words of the first plurality of words of the first claim;
- determining, based at least partly on syntactic categories of the individual words of the first plurality of words, a first number of groups of words that include the first plurality of words of the first claim;
- generating a first claim profile for the first claim that includes values for a first set of metrics, the first set of metrics determined by at least one machine learning model and corresponding to at least one of the first number of groups of words of the first claim or the syntactic categories;
- determining a first rating for the first claim based at least partly on a value of a first metric of the first set of metrics with respect to a framework of thresholds for the first metric;
- receiving at least one additional patent document from a searching authority, the at least one additional patent document being ranked by the searching authority and related to the first patent document;
- analyzing content of the at least one additional patent document to identify at least one additional claim, the at least one additional claim including a plurality of additional words;
- determining an additional syntactic category for additional individual words of the plurality of additional words;
- determining, based at least partly on additional syntactic categories of the additional individual words, a number of additional groups of words that include the plurality of additional words;
- generating an additional claim profile for the at least one additional claim that includes additional values for an additional set of metrics, the additional set of metrics determined by at least one machine learning model and corresponding to at least one of the number of additional groups of words of the at least one additional claim or the additional syntactic categories;
- determining an additional rating for the at least one additional claim based at least partly on an additional value of an additional metric of the additional set of metrics with respect to an additional framework of thresholds for the additional metric;
- determining that the first set of metrics and the additional set of metrics are similar;
- generating, based at least in part on the determination, a peer group claim set profile;
- receiving a request to perform a linguistic analysis of the peer group claim set profile;
- receiving a request for linguistic analysis results to be displayed in a specific ranking associated with a selected relevancy of multiple selectable data points, wherein the request indicates the linguistic analysis results are to be ranked based at least in part on selected data points, the selected data points based at least in part on the selected relevancy of multiple selectable data points;
- re-ranking the at least one additional patent document based on selected data points;
- and
- generating data of a user interface that includes at least one claim profile of the peer group claim set profile, the first rating, or the additional rating, wherein the data indicates the re-ranking.
16 more elements
Dependencies are inferred from the claim text.