# US 12,216,695 B2 · Information processing apparatus, information processing method, and program for analyzing text > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,216,695 B2 - Document ID: US12216695B2 - Status: Granted - Kind: B2 - Application number: 18/155,744 - Filed: 2023-01-18 - Published: 2023-08-10 - Granted: 2025-02-04 - Earliest claimed: 2022-02-04 - Assignees: FUJIFILM Corporation - Applicants: FUJIFILM Corporation - Inventors: Ryota Ozaki; Yuki Tagawa; Norihisa Nakano - Web page: https://patentgrep.com/patent/US12216695B2 ## CPC - G06F 16/35: Clustering; Classification - G06F 16/313: {Selection or weighting of terms for indexing} - G06F 40/279: Recognition of textual entities - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - G16H 30/40: for processing medical images, e.g. editing - G16H 40/67: for remote operation - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract Provided are an information processing apparatus, an information processing method, and a program capable of performing analysis of a text with high accuracy. An information processing apparatus includes one or more processors and one or more memories that store a command executed by the one or more processors. The one or more processors are configured to acquire a text, classify attributes of information described in the text into a fixed unit of the text, analyze the text for each of the same classifications based on a result of the classification, and output a result of the analysis. ## Claims ### Claim 1 An information processing apparatus comprising: one or more processors; and one or more memories that store a command executed by the one or more processors, wherein the one or more processors are configured to: acquire a text; classify attributes of information described in each fixed unit of the text; analyze the text for each of same classifications based on a result of the classification to extract terms from a set of fixed units for each of the same classifications; acquire a relationship between the extracted terms in the set of fixed units for each of the same classifications; and output a structured result of the text according to the extracted terms and the relationship between the extracted terms for the set of fixed units for each of the same classifications. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein the each fixed unit is any one of a sentence unit, a phrase unit, a word unit, or a character unit. ### Claim 3 (depends on 1) The information processing apparatus according to claim 1, wherein the text is a medical text. ### Claim 4 (depends on 1) The information processing apparatus according to claim 1, wherein a classification item of the information includes one or more of a human body part, an organ, a type of a disease, a type of a medical process, and a presence or absence of a disease. ### Claim 5 (depends on 4) The information processing apparatus according to claim 4, wherein the type of the medical process includes at least one of findings, diagnosis, or past comparison. ### Claim 6 (depends on 1) The information processing apparatus according to claim 1, wherein the term extraction includes acquisition of a term expression and determination of a term type. ### Claim 7 (depends on 1) The information processing apparatus according to claim 1, wherein the terms are extracted by using a prediction model subjected to machine learning in advance. ### Claim 8 (depends on 1) The information processing apparatus according to claim 1, wherein at least one of the extracted terms or the relationship between the extracted terms is acquired by using a prediction model subjected to machine learning in advance. ### Claim 9 (depends on 8) The information processing apparatus according to claim 8, wherein different prediction models are used depending on the result of the classification. ### Claim 10 (depends on 7) The information processing apparatus according to claim 7, wherein the text for each of the same classifications and classification information of the same classification are used as an input to the prediction model. ### Claim 11 (depends on 1) The information processing apparatus according to claim 1, further comprising: an input apparatus that receives an input of the text; and a display apparatus that displays the result of the analysis. ### Claim 12 (depends on 1) The information processing apparatus according to claim 1, wherein the one or more processors are configured to: save the result of the classification, and perform processing of displaying the result of the classification in an identifiable manner in a case where the acquired text is displayed. ### Claim 13 (depends on 1) The information processing apparatus according to claim 1, wherein the one or more processors determine a type of medical process and a type of organ for the each fixed unit of the text as the attributes of information described in the each fixed unit of the text. ### Claim 14 (depends on 1) The information processing apparatus according to claim 1, wherein the one or more processors analyze the text based on a type of the organ to extract the terms from a set of fixed units for each same type of organ. ### Claim 15 (depends on 1) The information processing apparatus according to claim 1, wherein the one or more processors acquire the relationship between the extracted terms in the set of fixed units having a same type of organ. ### Claim 16 An information processing method executed by one or more processors, the information processing method comprising: by the one or more processors, acquiring a text; classifying attributes of information described in each fixed unit of the text; analyzing the text for each of same classifications based on a result of the classification to extract terms from a set of fixed units for each of the same classifications; acquiring a relationship between the extracted terms in the set of fixed units for each of the same classifications; and outputting a structured result of the text according to the extracted terms and the relationship between the extracted terms for the set of fixed units for each of the same classifications. ### Claim 17 A non-transitory, computer-readable tangible recording medium which records thereon a program for causing, when read by a computer, the computer to realize: acquire a text; classify attributes of information described in each fixed unit of the text; analyze the text for each of same classifications based on a result of the classification to extract terms from a set of fixed units for each of the same classifications; acquire a relationship between the extracted terms in the set of fixed units for each of the same classifications; and output a structured result of the text according to the extracted terms and the relationship between the extracted terms for the set of fixed units for each of the same classifications.