# US 10,771,788 B2 · Information processing device and information processing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,771,788 B2 - Document ID: US10771788B2 - Status: Granted - Kind: B2 - Application number: 16/709,922 - Filed: 2019-12-11 - Published: 2020-04-16 - Granted: 2020-09-08 - Earliest claimed: 2014-10-03 - Assignees: Sony Corporation - Applicants: Sony Corporation - Inventors: Goragot Wongpaisarnsin; Tetsuo Yutani - Web page: https://patentgrep.com/patent/US10771788B2 ## CPC - H04N 19/154: Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion (use of rate-distortion criteria H04N19/147) - G06F 18/22: Matching criteria, e.g. proximity measures - H04N 19/103: Selection of coding mode or of prediction mode - H04N 19/12: Selection from among a plurality of transforms or standards, e.g. selection between discrete cosine transform [DCT] and sub-band transform or selection between H.263 and H.264 - H04N 19/136: Incoming video signal characteristics or properties - H04N 19/149: by estimating the code amount by means of a model, e.g. mathematical model or statistical model - H04N 19/179: the unit being a scene or a shot - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A purpose of the present invention is to easily select an appropriate processing format, an appropriate parameter, or the like by predicting a process result that varies according to content of data before executing the process. According to the present invention, provided is an information processing device including: a feature amount extraction unit configured to extract a feature amount of data serving as a target of a process; a feature amount matching unit configured to match the feature amount with one or more reference feature amounts associated with a prediction result of the process in a database; and a result prediction unit configured to predict a result obtained in a case where the process is executed for the data, on the basis of a result of the matching. ## Claims ### Claim 1 A non-transitory computer-readable storage medium storing executable instructions, which when executed by processing circuitry cause the processing circuitry to execute a method, the method comprising: receiving image data from an image sensor; extracting a feature amount of the image data; matching the feature amount of the image data with one or more reference feature amounts in a database based on a calculated distance between the extracted feature amount and the one or more reference feature amounts; and in response to a matching result, predict a result of a process for the image data, and determine the process to be executed based on the predicted result. ### Claim 2 (depends on 1) The non-transitory computer-readable storage medium of claim 1, wherein the method further comprises: determining a setting of the process to be executed. ### Claim 3 (depends on 2) The non-transitory computer-readable storage medium of claim 2, wherein the setting includes a format of the process or a parameter of the process. ### Claim 4 (depends on 1) The non-transitory computer-readable storage medium of claim 1, wherein the predicted result is quantitative information or qualitative information. ### Claim 5 (depends on 1) The non-transitory computer-readable storage medium of claim 1, wherein the predicted result is information indicating that the process is not suitable for the extracted feature amount. ### Claim 6 (depends on 1) The non-transitory computer-readable storage medium of claim 1, wherein the method further comprises: updating, if the matching result is a failure, the database by registering the extracted feature amount as a new reference feature amount. ### Claim 7 (depends on 1) The non-transitory computer-readable storage medium of claim 1, wherein the method further comprises: executing the determined process regardless of the extracted feature amount if the matching result is a failure. ### Claim 8 (depends on 1) The non-transitory computer-readable storage medium of claim 1, wherein the database is constructed by machine learning. ### Claim 9 An information processing device comprising: processing circuitry configured to receive image data from an image sensor, extract a feature amount of the image data, match the feature amount of the image data with one or more reference feature amounts in a database based on a calculated distance between the extracted feature amount and the one or more reference feature amounts, and in response to a matching result, predict a result of a process for the image data, and determine the process to be executed based on the predicted result. ### Claim 10 (depends on 9) The information processing device according to claim 9, wherein the processing circuitry is further configured to determine a setting of the process to be executed. ### Claim 11 (depends on 10) The information processing device according to claim 10, wherein the setting includes a format of the process or a parameter of the process. ### Claim 12 (depends on 9) The information processing device according to claim 9, wherein the predicted result is quantitative information or qualitative information. ### Claim 13 (depends on 9) The information processing device according to claim 9, wherein the predicted result is information indicating that the process is not suitable for the extracted feature amount. ### Claim 14 (depends on 9) The information processing device according to claim 9, wherein the processing circuitry is further configured to update, if the matching result is a failure, the database by registering the extracted feature amount as a new reference feature amount. ### Claim 15 (depends on 9) The information processing device according to claim 9, wherein the processing circuitry is further configured to execute the determined process regardless of the extracted feature amount if the matching result is a failure. ### Claim 16 (depends on 9) The information processing device according to claim 9, wherein the database is constructed by machine learning. ### Claim 17 A method comprising: receiving image data from an image sensor; extracting a feature amount of the image data; matching the feature amount of the image data with one or more reference feature amounts in a database based on a calculated distance between the extracted feature amount and the one or more reference feature amounts; and in response to a matching result, predict a result of a process for the image data, and determine the process to be executed based on the predicted result.