# US 12,216,732 B2 · Estimation apparatus, estimation method and program to estimate function parameters and data values > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,216,732 B2 - Document ID: US12216732B2 - Status: Granted - Kind: B2 - Application number: 17/295,291 - Filed: 2019-11-07 - Published: 2024-01-11 - Granted: 2025-02-04 - Earliest claimed: 2018-11-21 - Assignees: Nippon Telegraph and Telephone Corporation - Applicants: Nippon Telegraph and Telephone Corporation - Inventors: Tomoharu Iwata; Hitoshi Shimizu - Web page: https://patentgrep.com/patent/US12216732B2 ## CPC - G06F 17/11: for solving equations {, e.g. nonlinear equations, general mathematical optimization problems (optimization specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06F 16/00: Information retrieval; Database structures therefor; File system structures therefor - G06F 16/20: of structured data, e.g. relational data - G06N 7/00: Computing arrangements based on specific mathematical models - G06N 20/00: Machine learning - G06N 99/00: Subject matter not provided for in other groups of this subclass - G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract An estimation apparatus includes: input means for inputting aggregated data in which a plurality of data are aggregated, and feature data representing a feature of the aggregated data; determination means for determining a parameter of a model of the plurality of data before the aggregation of the aggregated data, using a predetermined function and the feature data; and estimation means for estimating a parameter of the function and the plurality of data by optimizing a predetermined objective function, using the aggregated data. ## Claims ### Claim 1 An estimation apparatus comprising a processor configured to execute operations comprising: receiving aggregated data in which a plurality of data are aggregated, and feature data representing a feature of the aggregated data; determining a parameter of a model of the plurality of data before the aggregation of the aggregated data, using a predetermined function and the feature data; and estimating a parameter of the function and the plurality of data by optimizing a predetermined objective function, using the aggregated data, wherein the objective function is a likelihood indicating a degree of agreement between estimated values of the plurality of data and the parameter of the model, and the aggregated data. ### Claim 2 (depends on 1) The estimation apparatus according to claim 1, wherein: the estimating further comprises estimating the parameter of the function and the plurality of data in such a manner that the likelihood becomes high. ### Claim 3 (depends on 2) The estimation apparatus according to claim 2, wherein the model is one of a first order Markov model or a high order Markov model. ### Claim 4 (depends on 3) The estimation apparatus according to claim 3, wherein the estimator estimates the parameter of the function and the plurality of data in such a manner that the likelihood becomes high while a restriction between the aggregated data and the plurality of data being met. ### Claim 5 (depends on 2) The estimation apparatus according to claim 2, wherein the estimating further comprises estimating the parameter of the function and the plurality of data in such a manner that the likelihood becomes high while a restriction between the aggregated data and the plurality of data being met. ### Claim 6 (depends on 1) The estimation apparatus according to claim 1, wherein: the aggregated data is population data of respective areas k at respective times t; each of the plurality of data is data indicating a number of persons moved from an area k to an area k′ at a time t; and the feature data includes at least one of a vector representing a feature of the area k, a vector representing a feature of the time t and a vector representing a feature of the area k and the time t. ### Claim 7 (depends on 1) The estimation apparatus according to claim 1, wherein: the function includes a neural network; and the determining further comprises the parameter of the model by inputting the feature data to the function. ### Claim 8 A computer-implemented method for estimating, comprising; receiving, aggregated data in which a plurality of data are aggregated and feature data representing a feature of the aggregated data; determining a parameter of a model of the plurality of data before the aggregation of the aggregated data, using a predetermined function and the feature data; and estimating a parameter of the function and the plurality of data by optimizing a predetermined objective function, using the aggregated data, wherein the objective function is a likelihood indicating a degree of agreement between estimated values of the plurality of data and the parameter of the model, and the aggregated data. ### Claim 9 (depends on 8) The estimation method according to claim 8, wherein: the estimating further comprises estimating the parameter of the function and the plurality of data in such a manner that the likelihood becomes high. ### Claim 10 (depends on 9) The estimation method according to claim 9, wherein the model is one of a first order Markov model or a high order Markov model. ### Claim 11 (depends on 10) The estimation method according to claim 10, wherein the estimating further comprises estimates the parameter of the function and the plurality of data in such a manner that the likelihood becomes high while a restriction between the aggregated data and the plurality of data being met. ### Claim 12 (depends on 9) The estimation method according to claim 9, wherein the estimating further comprises estimating the parameter of the function and the plurality of data in such a manner that the likelihood becomes high while a restriction between the aggregated data and the plurality of data being met. ### Claim 13 (depends on 8) The estimation method according to claim 8, wherein: the aggregated data is population data of respective areas k at respective times t; each of the plurality of data is data indicating a number of persons moved from an area k to an area k′ at a time t; and the feature data includes at least one of a vector representing a feature of the area k, a vector representing a feature of the time t and a vector representing a feature of the area k and the time t. ### Claim 14 (depends on 8) The estimation method according to claim 8, wherein: the function includes a neural network; and the determining further comprises determining the parameter of the model by inputting the feature data to the function. ### Claim 15 A non-transitory computer readable recording medium storing computer-executable program instructions for estimating that when executed by a processor cause a computer system to: receive aggregated data in which a plurality of data are aggregated and feature data representing a feature of the aggregated data; determine a parameter of a model of the plurality of data before the aggregation of the aggregated data, using a predetermined function and the feature data; and estimate a parameter of the function and the plurality of data by optimizing a predetermined objective function, using the aggregated data, wherein the objective function is a likelihood indicating a degree of agreement between estimated values of the plurality of data and the parameter of the model, and the aggregated data. ### Claim 16 (depends on 15) The non-transitory computer readable recording medium according to claim 15, wherein: the estimating further comprises estimating the parameter of the function and the plurality of data in such a manner that the likelihood becomes high. ### Claim 17 (depends on 16) The non-transitory computer readable recording medium according to claim 16, wherein the model is one of a first order Markov model or a high order Markov model. ### Claim 18 (depends on 16) The non-transitory computer readable recording medium according to claim 16, wherein the estimating further comprises estimating the parameter of the function and the plurality of data in such a manner that the likelihood becomes high while a restriction between the aggregated data and the plurality of data being met. ### Claim 19 (depends on 15) The non-transitory computer readable recording medium according to claim 15, wherein: the aggregated data is population data of respective areas k at respective times t; each of the plurality of data is data indicating a number of persons moved from an area k to an area k′ at a time t; and the feature data includes at least one of a vector representing a feature of the area k, a vector representing a feature of the time t and a vector representing a feature of the area k and the time t. ### Claim 20 (depends on 15) The non-transitory computer readable recording medium according to claim 15, wherein: the function includes a neural network; and the determining further comprises determining the parameter of the model by inputting the feature data to the function.