# US 11,079,238 B2 · Calculating a most probable path > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,079,238 B2 - Document ID: US11079238B2 - Status: Granted - Kind: B2 - Application number: 16/202,380 - Filed: 2018-11-28 - Published: 2020-05-28 - Granted: 2021-08-03 - Earliest claimed: 2018-11-28 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Yasutaka Nishimura; Shoichiro Watanabe; Sanehiro Furuichi; Kenichi Takasaki - Web page: https://patentgrep.com/patent/US11079238B2 ## CPC - G01C 21/20: Instruments for performing navigational calculations (G01C21/24, G01C21/26 take precedence) - G01C 21/3484: {Personalized, e.g. from learned user behaviour or user-defined profiles} - G01C 21/3691: {Retrieval, searching and output of information related to real-time traffic, weather, or environmental conditions (arrangements for giving variable traffic instructions G08G1/09)} - G06N 3/02: Neural networks - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/00: Machine learning - G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method of calculating a most probable path (MPP) comprising: with a classification module, classifying each of a plurality of origin and destination (O/D) trajectories into one of a plurality of periods of time, the classification comprising: changing a data sampling time period of any of the plurality of trajectories within the determined classification periods; with the classification module, detecting any O/D data descriptive of an aperiodic O/D trajectory using context data descriptive of the aperiodic O/D trajectory; and with the classification module, calculating a route trajectory serving as a candidate of the MPP to determine a priority O/D trajectory that matches the context data. ## Claims ### Claim 1 A method of calculating a most probable path (MPP) comprising: with a classification module, classifying each of a plurality of origin and destination (O/D) trajectories into one of a plurality of periods of time, the classification comprising: changing a data sampling time period of any of the plurality of trajectories within the determined classification periods, wherein a first time period is used for periodic O/D trajectories and a second, longer time period is used for aperiodic O/D trajectories; and with the classification module, detecting any O/D data descriptive of an aperiodic O/D trajectory using context data descriptive of the aperiodic O/D trajectory; with the classification module, calculating a route trajectory serving as a candidate of the MPP to determine a priority O/D trajectory that matches the context data; and navigating a vehicle on the most probable path from origin to destination. ### Claim 2 (depends on 1) The method of claim 1, wherein the classification of each of a plurality of O/D trajectories is associated with any of a number of drivers and passengers. ### Claim 3 (depends on 2) The method of claim 2, wherein the MPP is determined based on an identity of the drivers and passengers. ### Claim 4 (depends on 1) The method of claim 1, wherein the context data comprises registrant information, weather, date, time of day, road events, or combinations thereof. ### Claim 5 (depends on 1) The method of claim 1, wherein each of the origin and destination (O/D) trajectories are associated with a weight for the O/D trajectories classification. ### Claim 6 (depends on 5) The method of claim 5, wherein the weight is used to create a decision tree based on the context data. ### Claim 7 (depends on 1) The method of claim 1, wherein the aperiodic O/D trajectory is period temporally longer than a year. ### Claim 8 A system for determining the most probable path (MPP) comprising: a processor; a classification module to, when executed by the processor: determine a date and frequency of each O/D trajectory; classify each of the O/D trajectories into one of a plurality of periods of time based on its date and frequency; change a data sampling time period of any of the plurality of trajectories within the determined classification periods; and detect any O/D data descriptive of any O/D trajectory temporally longer than the determined classification periods based on context data descriptive of an aperiodic O/D trajectory; and with the classification module, calculating a route trajectory serving as a candidate of the MPP to determine a priority O/D trajectory that matches the context data, using a hidden Markov model, and with the classification module, providing the calculated route trajectory to a navigation system to guide a vehicle from origin to destination. ### Claim 9 (depends on 8) The system of claim 8, wherein the classification of each of a plurality of O/D trajectories is associated with any of a number of drivers and passengers. ### Claim 10 (depends on 9) The system of claim 9, wherein the MPP is determined based on an identity of the drivers and passengers. ### Claim 11 (depends on 8) The system of claim 8, wherein the context data comprises registrant information, weather, date, time of day, road events, or combinations thereof. ### Claim 12 (depends on 8) The system of claim 8, wherein each of the origin and destination (O/D) trajectories are associated with a weight for the O/D trajectories classification. ### Claim 13 (depends on 12) The system of claim 12, wherein the weight is used to create a decision tree based on the context data. ### Claim 14 (depends on 13) The system of claim 13, wherein the decision tree is stored on a data storage device and used to iteratively determining the most probable path (MPP). ### Claim 15 A computer program product for determining the most probable path (MPP), the computer program product comprising a non-transient computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to: classify each of a plurality of origin and destination (O/D) trajectories into one of a plurality of periods of time; change a data sampling time period of any of the plurality of trajectories within the determined classification periods; detect any O/D data descriptive of an aperiodic O/D trajectory using context data descriptive of the aperiodic O/D trajectory, wherein an aperiodic O/D trajectory is an O/D trajectory that does not occur on a periodic basis; calculate a route trajectory serving as a candidate of the MPP to determine a priority O/D trajectory that matches the context data, using a deep neural network (DNN); and provide the calculated route trajectory to a navigation system to navigate a vehicle from origin to destination. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein the classification of each of a plurality of O/D trajectories is associated with any of a number of drivers and passengers. ### Claim 17 (depends on 16) The computer program product of claim 16, wherein the MPP is determined based on an identity of the drivers and passengers. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein the context data comprises registrant information, weather, date, time of day, road events, or combinations thereof. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein each of the origin and destination (O/D) trajectories are associated with a weight for the O/D trajectories classification. ### Claim 20 (depends on 19) The computer program product of claim 19, wherein the weight is used to create a decision tree based on the context data. ### Claim 21 A method of calculating a most probable path (MPP) comprising: with an identification module, identifying a user of a computing device; with a classification module, classifying each of a plurality of origin and destination (O/D) trajectories into one of a plurality of periods of time based on an identity of the user, the classification comprising: changing a data sampling time period of any of the plurality of trajectories within the determined classification periods; detecting any O/D data descriptive of an aperiodic O/D trajectory using context data descriptive of the aperiodic O/D trajectory, wherein an aperiodic O/D trajectory is an O/D trajectory that occurs once during a longest classification period, wherein the context data indicates whether a date is within a day range of a holiday; with the classification module, detecting any O/D data descriptive of a relatively longer trajectory having a temporal longevity longer than any of the determined classification periods using context data descriptive of the relatively longer trajectory; with the classification module, calculating a route trajectory serving as a candidate of the MPP to determine a priority O/D trajectory that matches the context data, using a deep neural network; and navigating a vehicle from origin to destination using the MPP. ### Claim 22 (depends on 21) The method of claim 21, wherein the classification of each of a plurality of O/D trajectories is associated with any of a number of drivers and passengers. ### Claim 23 (depends on 22) The method of claim 22, wherein the MPP is determined based on an identity of the drivers and passengers. ### Claim 24 (depends on 21) The method of claim 21, wherein the context data comprises registrant information, weather, date, time of day, road events, or combinations thereof. ### Claim 25 (depends on 21) The method of claim 21, wherein each of the origin and destination (O/D) trajectories are associated with a weight for the O/D trajectories classification.