# US 11,113,336 B2 · Information processing apparatus to output answer information in response to inquiry information > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,113,336 B2 - Document ID: US11113336B2 - Status: Granted - Kind: B2 - Application number: 16/513,955 - Filed: 2019-07-17 - Published: 2020-01-23 - Granted: 2021-09-07 - Earliest claimed: 2018-07-20 - Assignees: Ricoh Company, Ltd. - Applicants: Takanori Mohri - Inventors: Takanori Mohri - Web page: https://patentgrep.com/patent/US11113336B2 ## CPC - G06F 16/90332: {Natural language query formulation or dialogue systems} - G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30) - G06F 16/3329: Natural language query formulation - G06F 16/3344: {using natural language analysis} - G06F 16/90344: {by using string matching techniques} - G06F 40/205: Parsing - G06F 40/268: Morphological analysis - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract An information processing apparatus outputs answer information corresponding to inquiry information that is input. The information processing apparatus includes a memory and circuitry. The memory is configured to store a plurality of databases each having at least a first field and a second field. The circuitry is configured to: perform morphological analysis on the inquiry information, to divide the inquiry information into morphemes; perform a first matching process based on the morphemes and the first field of each of the plurality of databases, to determine whether to adopt the database as an extraction source from which the answer information is to be extracted; and perform a second matching process based on the morphemes and the first field of the database, which is determined to be adopted as the extraction source, to output, as the answer information, data in the second field corresponding to data in the first field. ## Claims ### Claim 1 An information processing apparatus that outputs particular answer information corresponding to particular inquiry information that is input, the information processing apparatus comprising: memory circuitry storing a plurality of databases, each having at least a first field in which a word related to inquiry information is stored and a second field in which answer information is stored; and circuitry configured to: perform morphological analysis on the particular inquiry information that is input, to divide the particular inquiry information into morphemes; perform a first matching process by comparing the morphemes to the first field of each particular database of the plurality of databases stored in the memory circuitry, to determine whether to adopt the particular database as an extraction source from which the particular answer information is to be extracted; and when a certain database of the plurality of databases is determined to be adopted as the extraction source based on the first matching process, perform a second matching process based on the morphemes and the first field of the certain database that is determined to be adopted as the extraction source, to output, as the particular answer information, data in the second field of the certain database corresponding to data in the first field of the certain database. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein the circuitry is further configured to: authenticate a user who provides the particular inquiry information; and perform the first matching process based on information on the user. ### Claim 3 The information processing apparatus according to claim wherein the circuitry is further configured to: present; together with the particular answer information, options as to whether the particular answer information is a desired answer; and when a particular option indicating that the particular answer information is not the desired answer is selected from the presented options, execute the first matching process again to adopt a different one of the plurality of databases. ### Claim 4 (depends on 3) The information processing apparatus according to claim 3, wherein the circuitry is further configured to switch to answering by an operator when the particular option indicating that the particular answer information is not the desired answer is selected from the presented options. ### Claim 5 (depends on 1) The information processing apparatus according to claim 1, wherein the particular inquiry information is input in a dialogue format. ### Claim 6 (depends on 3) The information processing apparatus according to claim 3, wherein the circuitry is further configured to: learn contents of inquiry information and answer information based on a result of selecting the particular option; and execute the first matching process based on the learned contents. ### Claim 7 A method executed by an information processing apparatus that includes memory circuitry storing a plurality of databases each having at least a first field in which a word related to inquiry information is stored and a second field in which answer information is stored, the method comprising: performing morphological analysis on particular inquiry information that is input, to divide the particular inquiry information into morphemes; performing a first matching process by comparing the morphemes to the first field of each particular database of the plurality of databases stored in the memory circuitry, to determine whether to adopt the particular database as an extraction source from which particular answer information is to be extracted; and when a certain database of the plurality of databases is determined to be adopted as the extraction source based on the first matching process, performing a second matching process based on the morphemes and the first field of the certain database that is determined to be adopted as the extraction source, to output, as the particular answer information, data in the second field of the certain database corresponding to data in the first field of the certain database. ### Claim 8 A non-transitory computer-readable medium storing a program for causing an information processing apparatus that outputs particular answer information corresponding to particular inquiry information that is input to perform a method comprising: storing a plurality of databases, each having at least a first field in which a word related to inquiry information is stored and a second field in which answer information is stored; performing morphological analysis on the particular inquiry information that is input, to divide the particular inquiry information into morphemes; performing a first matching process by comparing the morphemes to the first field of each particular database of the plurality of databases, to determine whether to adopt the particular database as an extraction source from which the particular answer information is to be extracted; and when a certain database of the plurality of databases is determined to be adopted as the extraction source based on the first matching process, performing a second matching process based on the morphemes and the first field of the certain database that is determined to be adopted as the extraction source, to output, as the particular answer information, data in the second field of the certain database corresponding to data in the first field of the certain database.