# US 2023/0056987 A1 · Semantic map generation using hierarchical clause structure > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0056987 A1 - Document ID: US20230056987A1 - Status: Published application - Kind: A1 - Application number: 17/892,030 - Filed: 2022-08-19 - Published: 2023-02-23 - Earliest claimed: 2021-08-19 - Assignees: Digital Asset Capital, Inc. - Applicants: Digital Asset Capital, Inc. - Inventors: Edward Hunter - Web page: https://patentgrep.com/patent/US20230056987A1 ## CPC - G06F 40/30: Semantic analysis - G06F 16/313: {Selection or weighting of terms for indexing} - G06F 16/34: Browsing; Visualisation therefor (browsing or visualisation for clustering or classification G06F16/358) - G06F 16/35: Clustering; Classification - G06F 16/367: {Ontology} - G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)} - G06F 16/9038: Presentation of query results - G06F 16/93: Document management systems - G06F 40/117: Tagging; Marking up (details of markup languages G06F40/143); Designating a block; Setting of attributes (style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154) - G06F 40/137: Hierarchical processing, e.g. outlines - G06F 40/169: Annotation, e.g. comment data or footnotes - G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30) - G06F 40/211: Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars - G06F 40/258: Heading extraction; Automatic titling; Numbering - G06F 40/279: Recognition of textual entities - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06Q 50/18: Legal services - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract Techniques include obtaining, with a computer system, a natural-language-text document comprising unstructured text; determining, with the computer system, a document structure corresponding to the unstructured text of the natural language text document; identifying, with the computer system, a plurality of clauses within the document structure; generating, with the computer system, using a trained machine learning model, a hierarchical structure; determining, with the computer system, based on a trigger word associated with a first category within the hierarchical structure and a first set of machine learning model parameters, a region within the unstructured text comprising descriptors associated with the first category; determining, with the computer system, from the region based on a second set of machine learning model parameters, a descriptor describing an action or condition of the first category; generating, with the computer system, a data model object comprising the descriptor defining an action or condition of the first category; and storing, with the computer system, the data model object in memory. ## Claims ### Claim 1 A tangible, non-transitory, machine-readable medium storing instructions that when executed by one or more processors effectuate operations comprising: obtaining, with a computer system, a natural-language-text document comprising unstructured text; determining, with the computer system, a document structure corresponding to the unstructured text of the natural language text document; identifying, with the computer system, a plurality of clauses within the document structure; generating, with the computer system, using a trained machine learning model, a hierarchical structure; determining, with the computer system, based on a trigger word associated with a first category within the hierarchical structure and a first set of machine learning model parameters, a region within the unstructured text comprising descriptors associated with the first category; determining, with the computer system, from the region based on a second set of machine learning model parameters, a descriptor describing an action or condition of the first category; generating, with the computer system, a data model object comprising the descriptor defining an action or condition of the first category; and storing, with the computer system, the data model object in memory. ### Claim 2 (depends on 1) The medium of claim 1, the operations further comprising: determining, with the computer system, based on the trigger word and a second set of machine learning model parameters, a descriptor describing an action or condition of a second category; wherein generating the data model object comprises: populating a first field with the first category, wherein the first category corresponds to a predicate; populating a second field with the second category, wherein the second category corresponds to an object. ### Claim 3 (depends on 1) The medium of claim 1, further comprising: extracting, with the computer system, a document structure corresponding to the unstructured text of the natural-language-text document; generating, with the computer system, a directed graph representing contents of the text of the natural-language text document; and assigning, with the computer system, a label corresponding to each word of the text to generate a tagged token sequence. ### Claim 4 (depends on 3) The medium of claim 3, wherein the directed graph comprises: a first graph vertex based on a first clause; and is associated with the data model object; a second graph vertex based on a second clause; and a first graph edge comprising an identifier of the data model object and an identifier of the second graph vertex. ### Claim 5 (depends on 3) The medium of claim 3, wherein each vertex of the directed graph represents a clause comprising rights, obligations, and prohibitions and each edge of the directed graph represents a relationship between clauses. ### Claim 6 (depends on 3) The medium of claim 3, the operations further comprising: generating, with the computer system, an annotated document comprising annotations within the document structure wherein text associated with vertices of the directed graph are annotated with descriptors corresponding to the first category; causing, with the computer system, a visualization of the annotated document structure in a selectable user interface (UI) to be displayed on a display device of a user. ### Claim 7 (depends on 1) The medium of claim 1, the operations further comprising: wherein extracting the document structure comprises extracting hierarchical structure within the document structure using cascading finite state machines. ### Claim 8 (depends on 1) The medium of claim 1, wherein the category is a right, obligation, or prohibition associated with a clause. ### Claim 9 (depends on 1) The medium of claim 1, wherein storing the data model object in memory comprises storing a data structure comprising the data model object in a distributed, tamper-evident data store of a peer-to-peer sharing network. ### Claim 10 (depends on 1) The medium of claim 1, wherein extracting the document structure comprises extracting the hierarchical structure within the document structure using cascading finite state machines. ### Claim 11 (depends on 1) The medium of claim 1, the operations further comprising: receiving, with the computer system, a query comprising the first category; and causing, with the computer system, a presentation of a visualization of the data model object in response to receiving the query, the visualization comprising: a first shape comprising the region and the first category; and a second shape comprising a first annotation comprising a semantic text clause corresponding to the first category. ### Claim 12 (depends on 1) The medium of claim 1, wherein determining the first data model object comprises steps for determining the first data model obj ect. ### Claim 13 (depends on 1) The medium of claim 1, wherein determining the hierarchical structure comprises steps for determining the hierarchical structure. ### Claim 14 A method, comprising: obtaining, with a computer system, a natural-language-text document comprising unstructured text; determining, with the computer system, a document structure corresponding to the unstructured text of the natural language text document; identifying, with the computer system, a plurality of clauses within the document structure; generating, with the computer system, using a trained machine learning model, a hierarchical structure; determining, with the computer system, based on a trigger word associated with a first category within the hierarchical structure and a first set of machine learning model parameters, a region within the unstructured text comprising descriptors associated with the first category; determining, with the computer system, from the region based on a second set of machine learning model parameters, a descriptor describing an action or condition of the first category; generating, with the computer system, a data model object comprising the descriptor defining an action or condition of the first category; and storing, with the computer system, the data model object in memory.