# US 11,113,324 B2 · Classifier system and method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,324 B2 - Document ID: US11113324B2 - Status: Granted - Kind: B2 - Application number: 16/045,902 - Filed: 2018-07-26 - Published: 2020-01-30 - Granted: 2021-09-07 - Earliest claimed: 2018-07-26 - Assignees: Janzz Ltd - Applicants: JANZZ Ltd - Inventors: Stefan Winzenried; Adrian Hossu - Web page: https://patentgrep.com/patent/US11113324B2 ## CPC - G06F 16/254: {Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses} - G06F 16/334: Query execution (filtering based on additional data G06F16/335) - G06F 16/285: {Clustering or classification} - G06F 16/353: into predefined classes - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Disclosed herein are systems and methods for classifying unstructured datasets according to a classification system and generating an enhanced, classified and structured data-set enabling efficient supplemental computer-based processing. The exemplary computer-implemented classification algorithms involve, for each entry in the input dataset, semantically interpreting a text-based occupation description, analyzing the description according to an ontology of interrelated “concepts” and identifying semantically relevant concept(s) and any associated descriptors specific to the classification system. The system is also configured to expand the list of relevant concepts to include concepts that bear a relationship thereto, scoring the various concepts and associated descriptors and identifying the concept(s) and descriptors that most accurately correspond to the input data. Further, the system is configured to generate the new structured and classified occupation dataset by selectively combining certain input data and augmenting each entry with supplemental information inferred through the classification process. ## Claims ### Claim 1 A method for classifying an unstructured data set according to a classification system to generate an enhanced, classified and structured data-set that enables efficient supplemental computer-based processing, the method comprising: for each item of unstructured data in the unstructured data set: interpreting a given item of unstructured data in the unstructured data set, wherein the given item includes at least a semantic description; analyzing at least the semantic description included in the given item in accordance with an ontology of occupational concepts to identify a list of one or more concepts related to the given item; expanding the list of concepts to include other concepts that have a salient relationship to the previously identified concepts in the list to generate an expanded list; determining, from the expanded list, one or more concepts that most accurately correspond to the given item; and recording at least one of the one or more determined concepts as an entry in a classified occupation data-set, wherein each entry in the classified data set is structured in accordance with standards prescribed by a given classification system of interest. ### Claim 2 (depends on 1) The method of claim 1 wherein analyzing at least the semantic description comprises parsing the semantic description into individual terms and analyzing several combinations of those terms with an ontology of occupational concepts that have logical relation to a classification system of interest. ### Claim 3 (depends on 1) The method of claim 1 further comprising: identifying concept(s) and any classification system-specific codes that correspond to the given item, and wherein the given item corresponds to a respective occupation. ### Claim 4 (depends on 3) The method of claim 3, wherein determining comprises determining related classification system codes that most accurately correspond to the one or more concepts determined to most accurately correspond to the given item. ### Claim 5 (depends on 1) The method of claim 1, wherein expanding the list comprises identifying the other concepts that have a salient relationship to the previously identified concepts based on a respective hierarchical relationship or similarity to one or more of the previously identified concepts. ### Claim 6 (depends on 1) The method of claim 1, wherein recording comprises structuring the classified data set in accordance with a plurality of classification systems of interest. ### Claim 7 (depends on 1) The method of claim 1 where in recording the one or more determined concepts comprises creating an entry in the classified data-set through the selective combination of information obtained from multiple disparate data sources. ### Claim 8 (depends on 7) The method of claim 7, wherein creating an entry in the classified data-set comprises recording a select subset of information from the given item of unstructured data in the entry along with select information associated with the determined one or more concepts that most accurately correspond to the given item. ### Claim 9 (depends on 1) The method of claim 1, further comprising ranking the one or more concepts in the expanded list. ### Claim 10 (depends on 9) The method of claim 9, wherein ranking comprises: generating scores for attributes of the one or more concepts in the expanded list; elevating one or more of the scores by a prescribed amount as a function of additional factors; and normalizing the scores to provide a respective confidence score for the one or more concepts in the expanded list. ### Claim 11 A system for classifying an unstructured data set according to a classification system to generate an enhanced, classified and structured data-set that enables efficient supplemental computer-based processing, the system comprising: a non-transitory computer-readable storage medium; a processor configured by executing one or more software modules including instructions in the form of code stored in the storage medium, the modules including: a database module, that configures the processor to access respective items of unstructured data in the unstructured data set, an ontology of occupational concepts and standards prescribed by a given classification system of interest; an interpretation module that configures the processor to, for each item of the data set, interpret a given item of unstructured data in the unstructured data set, wherein the given item includes at least a semantic description, a classification module that configures the processor to, for each item of the data set: analyze at least the semantic description in accordance with the ontology of occupational concepts to identify a list of one or more concepts related to the given item, expand the list of concepts to include other concepts that have a salient relationship to the previously identified concepts in the list to generate an expanded list, determine, from the expanded list, one or more concepts that most accurately correspond to the given item representing the occupation; and wherein the database module further configures the processor to record the one or more determined concepts as an entry in a classified occupation data-set, wherein each entry in the classified data set is structured in accordance with standards prescribed by a given classification system of interest. ### Claim 12 (depends on 11) The system of claim 11 wherein the processor is configured to analyze the semantic description using the ontology. ### Claim 13 (depends on 12) The system of claim 12 wherein the processor is configured to identify concept(s) and any classification system-specific codes that correspond to the given item, and wherein the given item corresponds to a respective occupation. ### Claim 14 (depends on 13) The system of claim 13 wherein the processor is configured to determine related classification system codes that most accurately correspond to the one or more concepts determined to most accurately correspond to the given item describing the occupation. ### Claim 15 (depends on 11) The system of claim 11, wherein the processor is configured to expand the list by identifying the other concepts that have a salient relationship to the previously identified concepts based on a respective hierarchical relationship or similarity to one or more of the previously identified concepts. ### Claim 16 (depends on 11) The system of claim 11, wherein the processor is configured to structure the classified data set in accordance with a plurality of classification systems of interest. ### Claim 17 (depends on 11) The system of claim 11, where the processor is configured to record the one or more determined concepts by creating an entry in the classified data-set through the selective combination of information obtained from multiple disparate data sources. ### Claim 18 (depends on 17) The system of claim 17, wherein the processor is configured to create the entry in the classified data-set by recording a select subset of information from the given item of unstructured data in the entry along with select information associated with the determined one or more concepts that most accurately correspond to the given item. ### Claim 19 (depends on 11) The system of claim 11, further comprising a scoring module that configures the processor to score the one or more concepts in the expanded list. ### Claim 20 (depends on 19) The system of claim 19, wherein the scoring module configures the processor to score the one or more concepts by: generating scores for attributes of the one or more concepts in the expanded list; elevating one or more of the scores by a prescribed amount as a function of additional factors; and normalizing the scores to provide a respective confidence score for the one or more concepts in the expanded list.