# US 10,769,516 B2 · Information processing apparatus, program 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 10,769,516 B2 - Document ID: US10769516B2 - Status: Granted - Kind: B2 - Application number: 14/865,274 - Filed: 2015-09-25 - Published: 2016-03-31 - Granted: 2020-09-08 - Earliest claimed: 2014-09-26 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Satoshi Hara; Tetsuro Morimura; Rudy Raymond Harry Putra; Hidemasa Muta - Web page: https://patentgrep.com/patent/US10769516B2 ## CPC - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G08G 1/0129: {for creating historical data or processing based on historical data} - G08G 1/0145: {for active traffic flow control} - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) ## Abstract To identify a scenario that will bear a good simulation result from among a plurality of scenarios used in an agent-based simulation with a reduced amount of computation, there is provided an information processing apparatus comprising a counting part configured to count the number of agents in each of a plurality of states at a middle of a simulation that involves a plurality of agents, and a generation part configured to generate characteristic data used for prediction of a result of the simulation based on the number of agents in each of the plurality of states. ## Claims ### Claim 1 An information processing apparatus, comprising: a processor; and a computer readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising: performing a first simulation that involves a plurality of agents under a first simulation condition; sorting the plurality of agents into a plurality of predefined states, wherein the plurality of predefined states comprises a plurality of different states; counting a number of the plurality of agents that is sorted into each state of the plurality of predefined states at a midpoint of the first simulation, wherein the number of the plurality of agents that is sorted into each state of the plurality of states is represented by a smaller amount of data than states of the plurality of agents; and generating characteristic data, wherein the characteristic data comprises the first simulation condition at the midpoint and a plurality of matrices, wherein each matrix of the plurality of matrices corresponds to one state of the plurality of predefined states, wherein elements of the each matrix comprise the number of the plurality of agents that is sorted into the one state of the plurality of predefined states; and predicting and outputting a result at an end point of the first simulation at the midpoint of the first simulation based on the characteristic data and the number of the plurality of agents that is sorted into the one state at the midpoint of the first simulation. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein the operations further comprise: calculating a value based on the characteristic data; and predicting that the result of the first simulation is good when the value is at least equal to a preset threshold and that the result of the first simulation is bad when the value is less than the preset threshold. ### Claim 3 (depends on 2) The information processing apparatus according to claim 2, wherein the operations further comprise: allowing the predicting to learn from a plurality of pieces of the characteristic data and a plurality of simulation results corresponding to the plurality of pieces of characteristic data. ### Claim 4 (depends on 3) The information processing apparatus according to claim 3, wherein the operations further comprise: interrupting the first simulation in response to a prediction that the result of the first simulation is bad. ### Claim 5 (depends on 4) The information processing apparatus according to claim 4, wherein the interrupting changes a level for interruption of the first simulation based on a predefined number of top-ranked values selected from a plurality of values obtained by completing a plurality of simulations under a plurality of simulation conditions. ### Claim 6 (depends on 4) The information processing apparatus according to claim 4, wherein the first simulation is interrupted with a probability, wherein the probability depends on the value. ### Claim 7 (depends on 4) The information processing apparatus according to claim 4, wherein, in response to an interruption of the first simulation, a second simulation is started under a second simulation condition that is different from the first simulation condition. ### Claim 8 (depends on 7) The information processing apparatus according to claim 7, wherein the calculating calculates the value at an end point of the first simulation. ### Claim 9 (depends on 8) The information processing apparatus according to claim 8, wherein the generating generates the characteristic data at a plurality of points in time during the first simulation, and the calculating calculates the value at the end point of the first simulation from the characteristic data generated at the plurality of points in time. ### Claim 10 (depends on 9) The information processing apparatus according to claim 9, wherein the generating further generates the characteristic data based on the value. ### Claim 11 An information processing method executed by a computer, comprising: a simulation stage of performing a first simulation that involves a plurality of agents under a first simulation condition; a counting stage of sorting the plurality of agents into a plurality of predefined states, wherein the plurality of predefined states comprises a plurality of different states, and of counting a number of the plurality of agents that is sorted into each state of the plurality of predefined states at a midpoint of the first simulation, wherein the number of the plurality of agents that is sorted into each state of the plurality of states is represented by a smaller amount of data than states of the plurality of agents; and a generation stage of generating characteristic data, wherein the characteristic data comprises the first simulation condition at the midpoint and a plurality of matrices, wherein each matrix of the plurality of matrices corresponds to one state of the plurality of predefined states, wherein elements of the each matrix comprise the number of the plurality of agents that is sorted into the one state of the plurality of predefined states; and predicting and outputting a result at an end point of the first simulation at the midpoint of the first simulation based on the characteristic data and the number of the plurality of agents that is sorted into the one state at the midpoint of the first simulation. ### Claim 12 A non-transitory machine-readable storage medium encoded with instructions executable by a processor, the machine-readable storage medium comprising: instructions to perform a first simulation that involves a plurality of agents under a first simulation condition; instructions to sort the plurality of agents into a plurality of predefined states, wherein the plurality of predefined states comprises a plurality of different states, and to count a number of the plurality of agents that is sorted into each state of the plurality of predefined states at a midpoint of the first simulation, wherein the number of the plurality of agents that is sorted into each state of the plurality of states is represented by a smaller amount of data than states of the plurality of agents; and instructions to generate characteristic data, wherein the characteristic data comprises the first simulation condition at the midpoint and a plurality of matrices, wherein each matrix of the plurality of matrices corresponds to one state of the plurality of predefined states, wherein elements of the each matrix comprise the number of the plurality of agents that is sorted into the one state of the plurality of predefined states; and instructions to predict and output a result at an end point of the first simulation at the midpoint of the first simulation based on the characteristic data and the number of the plurality of agents that is sorted into the one state at the midpoint of the first simulation. ### Claim 13 (depends on 12) The non-transitory machine-readable storage medium according to claim 12, further comprising: instructions to calculate a value based on the characteristic data, and to predict that the result of the first simulation is good when the value is at least equal to a preset threshold and that the result of the first simulation is bad when the value is less than the preset threshold. ### Claim 14 (depends on 13) The non-transitory machine-readable storage medium according to claim 13, further comprising: instructions to learn from a plurality of pieces of characteristic data and a plurality of simulation results corresponding to the plurality of pieces of characteristic data. ### Claim 15 (depends on 14) The non-transitory machine-readable storage medium according to claim 14, further comprising: instructions to interrupt the first simulation in response to a prediction that the result of the first simulation is bad. ### Claim 16 (depends on 15) The non-transitory machine-readable storage medium according to claim 15, wherein the instructions to interrupt change a level for interruption of the first simulation based on a predefined number of top-ranked value selected from a plurality of values obtained by completing a plurality of simulations under a plurality of simulation conditions. ### Claim 17 (depends on 15) The non-transitory machine-readable storage medium according to claim 15, wherein the instructions to interrupt the first simulation perform an interruption of the first simulation with a probability, wherein the probability depends on the value. ### Claim 18 (depends on 15) The non-transitory machine-readable storage medium according to claim 15, wherein, in response to an interruption of the first simulation, the instructions to interrupt make the instructions to perform the first simulation start a second simulation under a second simulation condition that is different from the first simulation condition. ### Claim 19 (depends on 18) The non-transitory machine-readable storage medium according to claim 18, wherein the instructions to predict calculate the value at an end point of the first simulation. ### Claim 20 (depends on 19) The non-transitory machine-readable storage medium according to claim 19, wherein the instructions to generate the characteristic generate the characteristic data at a plurality of points in time during the first simulation, and the instructions to predict calculate the value at the end point of the first simulation from the characteristic data at the plurality of points in time.