# US 11,305,780 B2 · Road condition status prediction method, device, and server, and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,305,780 B2 - Document ID: US11305780B2 - Status: Granted - Kind: B2 - Application number: 16/508,771 - Filed: 2019-07-11 - Published: 2019-10-31 - Granted: 2022-04-19 - Earliest claimed: 2017-04-14 - Assignees: Tencent Technology (Shenzhen) Company Limited - Applicants: Tencent Technology (Shenzhen) Company Limited - Inventors: Chen Yuan; Hong Chao Zhao; Bo Li; Zhi Jun Wang - Web page: https://patentgrep.com/patent/US11305780B2 ## CPC - B60W 50/0097: {Predicting future conditions} - G01C 21/3492: {employing speed data or traffic data, e.g. real-time or historical (traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968)} - B60W 40/06: Road conditions - G06N 5/046: Forward inferencing; Production systems - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G08G 1/0133: {for classifying traffic situation} - B60W 2556/10: Historical data - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 3/08: Learning methods - G06N 3/126: Evolutionary algorithms, e.g. genetic algorithms or genetic programming - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT - 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 - 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 A road condition status prediction method is performed by a server and includes obtaining historical road segment information, the historical road segment information including road condition statuses and classification events that are used to classify the road condition statuses, and the classification events being determined based on content of the classification events, and obtaining an occurrence probability of each of the classification events, based on the obtained historical road segment information. The road condition status prediction method further includes obtaining a conditional probability of each of the classification events in each of the road condition statuses, based on the obtained historical road segment information, and predicting a road condition status of a road segment, based on the obtained occurrence probability of each of the classification events and the obtained conditional probability of each of the classification events in each of the road condition statuses. ## Claims ### Claim 1 A road condition status prediction method, the road condition status prediction method being executable by a processor associated with a server, and the road condition status prediction method comprising: obtaining historical road segment information, the historical road segment information comprising road condition statuses and classification events that are used to classify the road condition statuses, and the classification events being determined based on content of the classification events; obtaining an occurrence probability of each of the classification events, based on the obtained historical road segment information; obtaining a conditional probability of each of the classification events in each of the road condition statuses, based on the obtained historical road segment information; and predicting a road condition status of a road segment, based on the obtained occurrence probability of each of the classification events and the obtained conditional probability of each of the classification events in each of the road condition statuses. ### Claim 2 (depends on 1) The road condition status prediction method of claim 1, wherein the predicting the road condition status of the road segment comprises: obtaining target classification events comprised in the road segment; obtaining, from the obtained occurrence probability of each of the classification events and the obtained conditional probability of each of the classification events in each of the road condition statuses, an occurrence probability of each of the obtained target classification events and a conditional probability of each of the obtained target classification events in each of the road condition statuses; inputting the obtained occurrence probability of each of the target classification events and the obtained conditional probability of each of the target classification events in each of the road condition statuses, to a conditional probability expression of each of the road condition statuses when all of the classification events jointly occur, to obtain a conditional probability of each of the road condition statuses when all of the target classification events jointly occur, the conditional probability expression being determined based on a Bayesian classification formula; obtaining one of the road condition statues having a maximum conditional probability among the obtained conditional probability of each of the road condition statuses when all of the target classification events jointly occur; and predicting the obtained one of the road condition statues having the maximum conditional probability, as the road condition status of the road segment. ### Claim 3 (depends on 2) The road condition status prediction method of claim 2, wherein the Bayesian classification formula is represented as P(C/X)*P(X)=P(C)*P(X/C), and wherein C indicates one of the road condition statuses, P(C) indicates the occurrence probability of the one of the road condition statuses, X indicates the classification events, P(X) indicates the occurrence probability of each of the classification events, and P(C/X) indicates the conditional probability of the one of the road condition statuses when all of the classification events jointly occur. ### Claim 4 (depends on 1) The road condition status prediction method of claim 1, wherein the obtaining the occurrence probability of each of the classification events comprises: obtaining a quantity of occurrence times of each of the classification events, based on the obtained historical road segment information; and obtaining the occurrence probability of each of the classification events, based on the obtained quantity of occurrence times of each of classification events and a quantity of information pieces of the obtained historical road segment information. ### Claim 5 (depends on 1) The road condition status prediction method of claim 1, wherein the obtaining the conditional probability of each of the classification events in each of the road condition statuses comprises: obtaining a quantity of occurrence times of each of the classification events in each of the road condition statuses, based on the obtained historical road segment information; and obtaining the conditional probability of each of the classification events in each of the road condition statuses, based on the obtained quantity of occurrence times of each of the classification events in each of the road condition statuses and a quantity of information pieces of the obtained historical road segment information in each of the road condition statuses. ### Claim 6 (depends on 1) The road condition status prediction method of claim 1, wherein the classification events comprise a travelling speed of a vehicle on a current road segment, a free-flow speed, a road segment level, a city involved, a road condition status before a preset time, a travelling speed before the preset time, a road condition status of a designated road segment, a travelling speed of the vehicle on the designated road segment, and whether a respective one of the classification events is any one or any combination of a holiday, located near a special sector and a deceleration zone, and wherein the designated road segment is before the current road segment and spaced apart from the current road segment by a preset quantity of road segments. ### Claim 7 (depends on 1) The road condition status prediction method of claim 1, wherein the road condition statuses comprise extremely congested, congested, ambling and smooth. ### Claim 8 A road condition status prediction device, the road condition status prediction device being disposed in a server, and the road condition status prediction device comprising: at least one memory configured to store computer program code; and at least one processor configured to access the at least one memory and operate according to the computer program code, the computer program code comprising: information obtaining code configured to cause the at least one processor to obtain historical road segment information, the historical road segment information comprising road condition statuses and classification events that are used to classify the road condition statuses, and the classification events being determined based on content of the classification events; calculation code configured to cause the at least one processor to: obtain an occurrence probability of each of the classification events, based on the obtained historical road segment information; and obtain a conditional probability of each of the classification events in each of the road condition statuses, based on the obtained historical road segment information; and prediction code configured to cause the at least one processor to predict a road condition status of a road segment, based on the obtained occurrence probability of each of the classification events and the obtained conditional probability of each of the classification events in each of the road condition statuses. ### Claim 9 (depends on 8) The road condition status prediction device of claim 8, wherein the prediction code is further configured to cause the at least one processor to: obtain target classification events comprised in the road segment; obtain, from the obtained occurrence probability of each of the classification events and the obtained conditional probability of each of the classification events in each of the road condition statuses, an occurrence probability of each of the obtained target classification events and a conditional probability of each of the obtained target classification events in each of the road condition statuses; input the obtained occurrence probability of each of the target classification events and the obtained conditional probability of each of the target classification events in each of the road condition statuses, to a conditional probability expression of each of the road condition statuses when all of the classification events jointly occur, to obtain a conditional probability of each of the road condition statuses when all of the target classification events jointly occur, the conditional probability expression being determined based on a Bayesian classification formula; obtain one of the road condition statues having a maximum conditional probability among the obtained conditional probability of each of the road condition statuses when all of the target classification events jointly occur; and predict the obtained one of the road condition statues having the maximum conditional probability, as the road condition status of the road segment. ### Claim 10 (depends on 9) The road condition status prediction device of claim 9, wherein the Bayesian classification formula is represented as P(C/X)*P(X)=P(C)*P(X/C), and wherein C indicates one of the road condition statuses, P(C) indicates the occurrence probability of the one of the road condition statuses, X indicates the classification events, P(X) indicates the occurrence probability of each of the classification events, and P(C/X) indicates the conditional probability of the one of the road condition statuses when all of the classification events jointly occur. ### Claim 11 (depends on 8) The road condition status prediction device of claim 8, wherein the calculation code is further configured to cause the at least one processor to: obtain a quantity of occurrence times of each of the classification events, based on the obtained historical road segment information; and obtain the occurrence probability of each of the classification events, based on the obtained quantity of occurrence times of each of classification events and a quantity of information pieces of the obtained historical road segment information. ### Claim 12 (depends on 8) The road condition status prediction device of claim 8, wherein the calculation code is further configured to cause the at least one processor to: obtain a quantity of occurrence times of each of the classification events in each of the road condition statuses, based on the obtained historical road segment information; and obtain the conditional probability of each of the classification events in each of the road condition statuses, based on the obtained quantity of occurrence times of each of the classification events in each of the road condition statuses and a quantity of information pieces of the obtained historical road segment information in each of the road condition statuses. ### Claim 13 (depends on 8) The road condition status prediction device of claim 8, wherein the classification events comprise a travelling speed of a vehicle on a current road segment, a free-flow speed, a road segment level, a city involved, a road condition status before a preset time, a travelling speed before the preset time, a road condition status of a designated road segment, a travelling speed of the vehicle on the designated road segment, and whether a respective one of the classification events is any one or any combination of a holiday, located near a special sector and a deceleration zone, and wherein the designated road segment is before the current road segment and spaced apart from the current road segment by a preset quantity of road segments. ### Claim 14 (depends on 8) The road condition status prediction device of claim 8, wherein the road condition statuses comprise extremely congested, congested, ambling and smooth. ### Claim 15 A non-transitory computer-readable storage medium storing instructions that cause at least one processor to: obtain historical road segment information, the historical road segment information comprising road condition statuses and classification events that are used to classify the road condition statuses, and the classification events being determined based on content of the classification events; obtain an occurrence probability of each of the classification events, based on the obtained historical road segment information; obtain a conditional probability of each of the classification events in each of the road condition statuses, based on the obtained historical road segment information; and predict a road condition status of a road segment, based on the obtained occurrence probability of each of the classification events and the obtained conditional probability of each of the classification events in each of the road condition statuses. ### Claim 16 (depends on 15) The non-transitory computer-readable storage medium of claim 15, wherein the instructions further cause the at least one processor to: obtain a quantity of occurrence times of each of the classification events, based on the obtained historical road segment information; and obtain the occurrence probability of each of the classification events, based on the obtained quantity of occurrence times of each of classification events and a quantity of information pieces of the obtained historical road segment information. ### Claim 17 (depends on 15) The non-transitory computer-readable storage medium of claim 15, wherein the instructions further cause the at least one processor to: obtain a quantity of occurrence times of each of the classification events in each of the road condition statuses, based on the obtained historical road segment information; and obtain the conditional probability of each of the classification events in each of the road condition statuses, based on the obtained quantity of occurrence times of each of the classification events in each of the road condition statuses and a quantity of information pieces of the obtained historical road segment information in each of the road condition statuses. ### Claim 18 (depends on 15) The non-transitory computer-readable storage medium of claim 15, wherein the instructions further cause the at least one processor to: obtain target classification events comprised in the road segment; obtain, from the obtained occurrence probability of each of the classification events and the obtained conditional probability of each of the classification events in each of the road condition statuses, an occurrence probability of each of the obtained target classification events and a conditional probability of each of the obtained target classification events in each of the road condition statuses; input the obtained occurrence probability of each of the target classification events and the obtained conditional probability of each of the target classification events in each of the road condition statuses, to a conditional probability expression of each of the road condition statuses when all of the classification events jointly occur, to obtain a conditional probability of each of the road condition statuses when all of the target classification events jointly occur, the conditional probability expression being determined based on a Bayesian classification formula; obtain one of the road condition statues having a maximum conditional probability among the obtained conditional probability of each of the road condition statuses when all of the target classification events jointly occur; and predict the obtained one of the road condition statues having the maximum conditional probability, as the road condition status of the road segment. ### Claim 19 (depends on 15) The non-transitory computer-readable storage medium of claim 15, wherein the classification events comprise a travelling speed of a vehicle on a current road segment, a free-flow speed, a road segment level, a city involved, a road condition status before a preset time, a travelling speed before the preset time, a road condition status of a designated road segment, a travelling speed of the vehicle on the designated road segment, and whether a respective one of the classification events is any one or any combination of a holiday, located near a special sector and a deceleration zone, and wherein the designated road segment is before the current road segment and spaced apart from the current road segment by a preset quantity of road segments. ### Claim 20 (depends on 15) The non-transitory computer-readable storage medium of claim 15, wherein the road condition statuses comprise extremely congested, congested, ambling and smooth.