# US 2019/0378406 A1 · Method of predicting a traffic behaviour in a road system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0378406 A1 - Document ID: US20190378406A1 - Status: Published application - Kind: A1 - Application number: 16/476,837 - Filed: 2018-01-23 - Published: 2019-12-12 - Earliest claimed: 2017-02-01 - Assignees: Kapsch TrafficCom AG - Applicants: Kapsch TrafficCom AG - Inventors: Carlos Gil Aguirrebeitia; Rubén García Casado - Web page: https://patentgrep.com/patent/US20190378406A1 ## CPC - G08G 1/0129: {for creating historical data or processing based on historical data} - G06N 20/00: Machine learning - G08G 1/0116: {from roadside infrastructure, e.g. beacons} - G08G 1/0125: {Traffic data processing} - G08G 1/0133: {for classifying traffic situation} - G08G 1/065: by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count - 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}) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract The present subject matter relates to a method of predicting a traffic behaviour in a road system, comprising the following steps carried out by at least one processor connected to a database, which contains a set of traffic profiles: clustering the traffic profiles; calculating a significance value; if the significance value of a tag is higher than a threshold value, assigning this tag as a characteristic vector to this cluster; receiving a request having one or more request tags; determining a cluster by means of matching the request tag/s to the characteristic vectors of the clusters; and outputting a predicted traffic behaviour based on the determined cluster. ## Claims ### Claim 1 A method of predicting a traffic behaviour in a road system, comprising the following steps carried out by at least one processor connected to a database, which contains a set of traffic profiles, each traffic profile representing a traffic measure of vehicles in the road system recorded over time, one or more pre-defined tags associated with a time of recording of the respective traffic profile being attributed to said traffic profile: clustering the traffic profiles with their tags into at least one cluster as to similarity of traffic profiles; for at least one tag in each cluster, calculating a significance value by means of a statistical analysis, wherein the significance value of each tag or tag combination, respectively, is calculated by means of a Chi-squared statistic; if the significance value of a tag is higher than a threshold value, assigning this tag as a characteristic vector to this cluster; in a prediction engine, receiving a request having one or more request tags to determine a matching cluster; determining a cluster by means of matching the request tag/s to the characteristic vectors of the clusters; and outputting a predicted traffic behaviour based on the determined cluster. ### Claim 2 (depends on 1) The method according to claim 1, wherein there are at least two variables, and each tag is assigned to a variable, the method comprising the further steps of for at least one variable in each cluster, calculating a significance value; and for at least one tag assigned to the variable with the highest significance value of each cluster, calculating the significance value. ### Claim 3 (depends on 2) The method according to claim 2, wherein the method comprises the further steps of grouping all traffic profiles that do not contain a tag whose significance value lies above said threshold value to a sub-cluster; for at least one variable in the sub-cluster, calculating a significance value; and for a tag assigned to the variable with the highest significance value of the sub-cluster, calculating the significance value. ### Claim 4 (depends on 3) The method according to claim 3, wherein the steps of grouping, calculating the significance value for a variable and calculating the significance value for a tag are repeated until no more traffic profiles are available for grouping. ### Claim 5 (depends on 1) The method according to claim 1, wherein, for at least one tag whose significance value lies below said threshold, a significance value of a combination of said tag with a further tag is calculated and, if said significance value of said tag combination lies above the threshold, assigning said tag combination as a further characteristic vector to the cluster of said tag. ### Claim 6 (depends on 1) The method according to claim 1, wherein for each cluster significance values for all tags of this cluster are calculated. ### Claim 7 (depends on 1) The method according to claim 1, wherein, when two clusters would be assigned the same characteristic vector, the threshold value is lowered and it is again checked if the significance value of each tag or tag combination, respectively, is higher than the threshold value to assign this tag or tag combination, respectively, as a characteristic vector to this cluster. ### Claim 8 (canceled) ### Claim 9 (depends on 1) The method according to claim 1, wherein the significance values of the tags or tag combinations are used when checking whether a request tag matches a characteristic vector. ### Claim 10 (depends on 1) The method according to claim 1, wherein each traffic profile represents the traffic measure of vehicles in the road system over a time-span of 24 hours. ### Claim 11 (depends on 1) The method according to claim 1, wherein at least one tag indicates a day of the week, a month of the year, a week of the month, a school vacation indication, or a special holiday indication of said time of recording. ### Claim 12 (depends on 1) The method according to claim 1, wherein at least one tag indicates a road condition or a weather condition at said time of recording. ### Claim 13 (depends on 2) The method according to claim 2, wherein, for at least one tag whose significance value lies below said threshold, a significance value of a combination of said tag with a further tag is calculated and, if said significance value of said tag combination lies above the threshold, assigning said tag combination as a further characteristic vector to the cluster of said tag. ### Claim 14 (depends on 2) The method according to claim 2, wherein for each cluster significance values for all tags of this cluster are calculated. ### Claim 15 (depends on 2) The method according to claim 2, wherein, when two clusters would be assigned the same characteristic vector, the threshold value is lowered and it is again checked if the significance value of each tag or tag combination, respectively, is higher than the threshold value to assign this tag or tag combination, respectively, as a characteristic vector to this cluster. ### Claim 16 (depends on 2) The method according to claim 2, wherein the significance values of the tags or tag combinations are used when checking whether a request tag matches a characteristic vector. ### Claim 17 (depends on 2) The method according to claim 2, wherein each traffic profile represents the traffic measure of vehicles in the road system over a time-span of 24 hours. ### Claim 18 (depends on 2) The method according to claim 2, wherein at least one tag indicates a day of the week, a month of the year, a week of the month, a school vacation indication, or a special holiday indication of said time of recording. ### Claim 19 (depends on 2) The method according to claim 2, wherein at least one tag indicates a road condition or a weather condition at said time of recording. ### Claim 20 (depends on 3) The method according to claim 3, wherein, for at least one tag whose significance value lies below said threshold, a significance value of a combination of said tag with a further tag is calculated and, if said significance value of said tag combination lies above the threshold, assigning said tag combination as a further characteristic vector to the cluster of said tag. ### Claim 21 (depends on 3) The method according to claim 3, wherein, when two clusters would be assigned the same characteristic vector, the threshold value is lowered and it is again checked if the significance value of each tag or tag combination, respectively, is higher than the threshold value to assign this tag or tag combination, respectively, as a characteristic vector to this cluster.