# US 2021/0174014 A1 · Visualization of the Entities and Relations in a Document > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0174014 A1 - Document ID: US20210174014A1 - Status: Published application - Kind: A1 - Application number: 16/703,854 - Filed: 2019-12-04 - Published: 2021-06-10 - Earliest claimed: 2019-12-04 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Steven I. Ross - Web page: https://patentgrep.com/patent/US20210174014A1 ## CPC - G06F 16/345: {Summarisation for human users} - G06F 40/205: Parsing - G06F 16/148: {File search processing} - G06F 16/156: {Query results presentation} - G06F 16/93: Document management systems - G06F 40/177: of tables; using ruled lines - G06F 40/30: Semantic analysis - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A computer-implemented method, non-transitory computer readable storage medium, and computing device for visualizing entities and relations within a file. The content of at least one portion of a file is parsed by natural language processing (NLP). A frequency is determined of one or more entities within the at least one portion of the file parsed by NLP. Visualization data is generated of at least one entity of the one or more entities in the file, and is output for display. ## Claims ### Claim 1 A computer-implemented method for visualizing entities and relations within a file, the method comprising: parsing a content of at least one portion of a file by natural language processing (NLP); determining a frequency of one or more entities detected within the at least one portion of the file parsed by NLP, wherein the determination of the frequency is able to include different names of a same entity; generating a visualization data of at least one entity of the one or more entities detected within the file; and outputting the visualization data for display. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the one or more entities detected within the file are represented by groups of one or more words. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein parsing the content further includes performing a relation extraction between the one or more entities detected within the file. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein the visualization data is further configured to display the relation between the one or more entities detected within the file, in response to a selection. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein generating the visualization data includes generating a visual representation of the determined frequency of the one or more entities detected within the file. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein generating the visualization data includes labeling the one or more entities detected within the file with at least one of text or images. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein a representation of the one or more entities detected within the file includes a tag cloud. ### Claim 8 (depends on 6) The computer-implemented method of claim 6, wherein the labeling of the one or more entities detected within the file comprises a visible labeling or a hidden labeling. ### Claim 9 (depends on 8) The computer-implemented method of claim 8, further comprising configuring the hidden labeling to be displayed in response to a detected hovering or a selection by a pointing device. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein: the file comprises a text document, and the visualization data is configured for display within and is spatially registered with the text document. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, wherein the visualization data is configured for display in columns within the text document. ### Claim 12 (depends on 11) The computer-implemented method of claim 11, wherein the columns display at least one of photos, logos, graphics or alphanumeric characters that visually indicate a characteristic of the one or more entities within the text document. ### Claim 13 (depends on 12) The computer-implemented method of claim 12, wherein the columns are generated in response to an inquiry. ### Claim 14 (depends on 12) The computer-implemented method of claim 12, wherein the columns are auto-generated based on a predetermined threshold of the determined frequency of the one or more entities. ### Claim 15 A non-transitory computer readable storage medium tangibly embodying a computer readable program code having computer readable instructions that, when executed, causes a computer device to carry out a method for visualizing entities and relations within a file, the method comprising: parsing a content of at least one portion of a file by natural language processing (NLP); determining a frequency of one or more entities within the at least one portion of the file parsed by NLP, wherein the determination of the frequency is able to include different names of a same entity; generating a visualization data of at least one entity of the one or more entities in the file; and outputting the visualization data for display. ### Claim 16 (depends on 15) The non-transitory computer readable storage medium of claim 15, wherein: the file comprises a text document, and parsing the content further includes performing a relation extraction between the one or more entities, and wherein the visualization data is spatially registered with display of the text document. ### Claim 17 (depends on 16) The non-transitory computer readable storage medium of claim 16, wherein the visualization data includes an indication of the extracted relation between the one or more entities. ### Claim 18 A computing device comprising: a processor; a storage device coupled to the processor; a visualization module coupled to the processor, wherein an execution of the visualization module by the processor configures the computing device to: parse a content of at least one portion of a file by natural language processing (NLP); determine a frequency of one or more entities within the at least one portion of the file parsed by NLP, wherein the determination of the frequency is able to include different names of a same entity; generate a visualization data of at least one entity of the one or more entities in the file; and output the visualization data for display. ### Claim 19 (depends on 18) The computing device according to claim 18, wherein execution of the visualization module further configures the computing device to perform a relation extraction between the one or more entities, and wherein the visualization data is spatially registered with display of contents of the file. ### Claim 20 (depends on 19) The computing device according to claim 19, further comprising an output device configured to display the visualization data, and wherein the visualization data includes an indication of the extracted relation between the one or more entities.