# US 11,443,538 B2 · System and method for machine assisted documentation in medical writing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,538 B2 - Document ID: US11443538B2 - Status: Granted - Kind: B2 - Application number: 17/036,005 - Filed: 2020-09-29 - Published: 2021-04-22 - Granted: 2022-09-13 - Earliest claimed: 2019-10-16 - Assignees: Tata Consultancy Services Limited - Applicants: Tata Consultancy Services Limited - Inventors: Sanjeev Manchanda; Ashish Indani; Mahesh Kshirsagar - Web page: https://patentgrep.com/patent/US11443538B2 ## CPC - G06V 30/416: Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors - G06F 40/226: Validation - G06F 40/295: Named entity recognition - G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract In medical writing, manual process of creating, updating and maintaining documents is expensive, time consuming. This disclosure provides a method of an automatic medical document writing by receiving, a plurality of input documents as an input; processing, the inputted plurality of documents by extracting into an at least one section to generate a list of sections; classifying, at least one category corresponding to the at least one section to generate a summary set; generating, at least one of a local context and a global context based on the summary set; parsing, at least one sentence based on the generated local context and global context to generate at least one sequence of the plurality of sentences; processing, the at least one sequence of the plurality of sentence to generate a queue of the at least one sequence; validating, the queue of the at least one sequence to obtain a combined summary set. ## Claims ### Claim 1 A processor implemented method of a machine assisted documentation in a medical writing, comprising: receiving, via one or more hardware processors, a plurality of input documents as an input for different type of documents to be created; processing, via the one or more hardware processors, the inputted plurality of documents by extracting into an at least one section to generate a list of sections, wherein the sections are processed based on a natural language processing; classifying, via the one or more hardware processors, at least one category from a plurality of categories corresponding to the at least one section to generate a summary set, wherein the at least one category corresponds to a Summarizable category, wherein the summary set comprises a plurality of sentences; generating, via the one or more hardware processors, at least one of (i) a local context, (ii) a global context, and combination thereof based on the summary set, wherein a knowledge base is utilized for the local context and the global context for processing a plurality of natural language inputs; parsing, via the one or more hardware processors, at least one sentence based on the generated local context, or global context to generate at least one sequence of the plurality of sentences, wherein sequencing of the plurality of documents and the sections is pre-defined; processing, via the one or more hardware processors, the at least one sequence of the plurality of sentences to generate a queue of the at least one sequence; and validating, via the one or more hardware processors, the queue of the at least one sequence to obtain a combined summary set, wherein validation is based on abstractive summarization, extractive summarization, feature extraction and Table, Figures and Listings (TFL) summarization to extract output for respective document and generate the summary, wherein generating the summary includes at least one of (i) a context generator, (ii) a section content parser, and (iii) a logical sequence tagger, wherein the context generator is configured to create the local context of input data; generating a context set for use in summarization and the feature extraction; creating tagging information for maintaining the sequence of plurality of input document sequences for maintaining logical sequence and wherein the generated summary is validated and updated by generating a final output. ### Claim 2 (depends on 1) The processor implemented method of claim 1, wherein the plurality of logical categories corresponds to at least one of (i) a Summarizable sections, (ii) brief summaries, and (iii) text sections excluded. ### Claim 3 (depends on 1) The processor implemented method of claim 1, wherein the Summarizable Sections category comprises at least one section of (i) introduction, (ii) problem statement, (iii) research methodology, and (iv) experimentation with associated results. ### Claim 4 (depends on 1) The processor implemented method of claim 1, wherein the brief summaries category comprises at least one section of (i) abstract, and (ii) conclusion, wherein the text sections excluded category comprises at least one section of (i) historical background, (ii) references, and (iii) appendix. ### Claim 5 (depends on 1) The processor implemented method of claim 1, wherein the local context comprises at least one of (i) overall context of the input documents, (ii) an extracted context of a plurality of referenced documents or combination thereof. ### Claim 6 A system (100) for a machine assisted documentation in a medical writing, comprising: a memory (102) storing instructions; one or more communication interfaces (106); and one or more hardware processors (104) coupled to the memory (102) via the one or more communication interfaces (106), wherein the one or more hardware processors (104) are configured by the instructions to: receive, a plurality of input documents as an input for different type of documents to be created; process, the inputted plurality of documents by extracting into an at least one section to generate a list of sections, wherein the sections are processed based on a natural language processing; classify, at least one category from a plurality of categories corresponding to the at least one section to generate a summary set, wherein the at least one category corresponds to a Summarizable category, wherein the summary set comprises a plurality of sentences; generate, at least one of (i) a local context, (ii) a global context, and combination thereof based on the summary set, wherein a knowledge base is utilized for the local context and the global context for processing a plurality of natural language inputs; parse, at least one sentence based on the generated local context, or global context to generate at least one sequence of the plurality of sentences, wherein sequencing of the plurality of documents and the sections is pre-defined; process, the at least one sequence of the plurality of sentences to generate a queue of the at least one sequence; and validate, the queue of the at least one sequence to obtain a combined summary set, wherein validation is based on abstractive summarization, extractive summarization, feature extraction and Table, Figures and Listings (TFL) summarization to extract output for respective document and generate the summary, wherein generating the summary includes at least one of (i) a context generator, (ii) a section content parser, and (iii) a logical sequence tagger, wherein the context generator is configured to create the local context of input data, wherein the context generator is configured to generate a context set for use in summarization and the feature extraction, wherein the logical sequence tagger is configured to create tagging information for maintaining the sequence of plurality of input document sequences for maintaining logical sequence and wherein the generated summary is validated and updated by generating a final output. ### Claim 7 (depends on 6) The system of claim 6, wherein the plurality of logical categories corresponds to at least one of (i) a Summarizable sections, (ii) brief summaries, and (iii) Text sections excluded. ### Claim 8 (depends on 6) The system of claim 6, wherein the Summarizable Sections category comprises at least one section of (i) introduction, (ii) problem statement, (iii) research methodology, and (iv) experimentation with associated results. ### Claim 9 (depends on 6) The system of claim 6, wherein the brief summaries category comprises at least one section of (i) abstract, and (ii) conclusion, wherein the text sections excluded category comprises at least one section of (i) historical background, (ii) references, and (iii) appendix. ### Claim 10 (depends on 6) The system of claim 6, wherein the local context comprises at least one of (i) overall context of the input documents, (ii) an extracted context of a plurality of referenced documents or combination thereof. ### Claim 11 One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors perform actions comprising: receiving, a plurality of input documents as an input for different type of documents to be created; processing, the inputted plurality of documents by extracting into an at least one section to generate a list of sections, wherein the sections are processed based on a natural language processing; classifying, at least one category from a plurality of categories corresponding to the at least one section to generate a summary set, wherein the at least one category corresponds to a Summarizable category, wherein the summary set comprises a plurality of sentences; generating, at least one of (i) a local context, (ii) a global context, and combination thereof based on the summary set, wherein a knowledge base is utilized for the local context and the global context for processing a plurality of natural language inputs; parsing, at least one sentence based on the generated local context, or global context to generate at least one sequence of the plurality of sentences, wherein sequencing of the plurality of documents and the sections is pre-defined; processing, the at least one sequence of the plurality of sentences to generate a queue of the at least one sequence; and validating, the queue of the at least one sequence to obtain a combined summary set, wherein validation is based on abstractive summarization, extractive summarization, feature extraction and Table, Figures and Listings (TFL) summarization to extract output for respective document and generate the summary, wherein generating the summary includes at least one of (i) a context generator, (ii) a section content parser, and (iii) a logical sequence tagger, wherein the context generator is configured to create the local context of input data; generating a context set for use in summarization and the feature extraction; creating tagging information for maintaining the sequence of plurality of input document sequences for maintaining logical sequence and wherein the generated summary is validated and updated by generating a final output. ### Claim 12 (depends on 11) The one or more non-transitory machine-readable information storage mediums of claim 11, wherein the plurality of logical categories corresponds to at least one of (i) a Summarizable sections, (ii) brief summaries, and (iii) text sections excluded. ### Claim 13 (depends on 11) The one or more non-transitory machine-readable information storage mediums of claim 11, wherein the Summarizable Sections category comprises at least one section of (i) introduction, (ii) problem statement, (iii) research methodology, and (iv) experimentation with associated results. ### Claim 14 (depends on 11) The one or more non-transitory machine-readable information storage mediums of claim 11, wherein the brief summaries category comprises at least one section of (i) abstract, and (ii) conclusion, wherein the text sections excluded category comprises at least one section of (i) historical background, (ii) references, and (iii) appendix. ### Claim 15 (depends on 11) The one or more non-transitory machine-readable information storage mediums of claim 11, wherein the local context comprises at least one of (i) overall context of the input documents, (ii) an extracted context of a plurality of referenced documents or combination thereof.