Method, apparatus, device and medium for predicting road congestion based on vehicle behavior analysis

Abstract

The present application relates to a road congestion prediction method, device, equipment and medium based on vehicle behavior analysis, which is applied to the technical field of traffic information processing. The method includes: obtaining road information of the current road; dividing the current road into multiple monitoring sections based on the road information and a preset road division rule; obtaining section information and vehicle information of the monitoring sections within a current preset prediction period; calculating the probability of traffic accidents based on the section information and vehicle information; obtaining historical section congestion information of the monitoring sections within a historical preset prediction period; and generating a road theoretical congestion level based on the probability of traffic accidents and the historical section congestion information. The present application has the effect of improving the efficiency of road congestion prediction.

Description

Technical Field

[0001] The present application relates to the technical field of traffic information processing, and in particular, to a road congestion prediction method, device, equipment and medium based on vehicle behavior analysis. Background Art

[0002] With the development of the automotive industry, the number of motor vehicles in cities has been increasing continuously. Currently, the traffic flow on roads is gradually increasing, the traffic pressure is becoming heavier and heavier, and road congestion has become inevitable, which has brought great challenges to the smooth operation of urban traffic, exacerbated the management problems of traffic-related departments, and also brought inconvenience to the travel of vehicle owners.

[0003] Currently, the prediction of road conditions generally relies on the subjective experience of traffic control personnel. In the case of emergencies such as traffic accidents, roadside parking, and temporary lane occupation, the results of road congestion analysis are inaccurate, and road congestion analysis can only be realized within a relatively small area, resulting in low efficiency of road congestion prediction. Summary of the Invention

[0004] In order to improve the efficiency of road congestion prediction, the present application provides a road congestion prediction method, device, equipment and medium based on vehicle behavior analysis.

[0005] In a first aspect, the present application provides a road congestion prediction method based on vehicle behavior analysis, adopting the following technical solution:

[0006] A road congestion prediction method based on vehicle behavior analysis includes:

[0007] Obtain road information of the current road;

[0008] Divide the current road into multiple monitoring sections based on the road information and a preset road division rule;

[0009] Obtain section information and vehicle information of the monitoring sections within a current preset prediction period;

[0010] Calculate the probability of traffic accidents based on the section information and vehicle information;

[0011] Obtain historical section congestion information of the monitoring sections within a historical preset prediction period;

[0012] Generate a theoretical road congestion level based on the probability of traffic accidents and the historical section congestion information.

[0013] By adopting the above technical solution, a road is divided into multiple monitoring sections, and each monitoring section is monitored separately, so that the obtained data is more detailed and accurate. The traffic accident occurrence probability is calculated based on the section information and vehicle information of each monitoring section, and then the theoretical road congestion level is calculated based on the historical information and the traffic accident occurrence probability. By combining the current situation with the historical records, the road congestion prediction efficiency is improved.

[0014] Optionally, the dividing the current road into multiple monitoring sections based on the road information and a preset road division rule includes:

[0015] Obtain the number of road checkpoints on the current road and the road length between two adjacent road checkpoints;

[0016] Dividing the current road into multiple monitoring sections based on the number of road checkpoints and the road length between two adjacent road checkpoints includes.

[0017] Optionally, the calculating the traffic accident occurrence probability based on the section information and vehicle information includes:

[0018] Obtain the number of lanes on the monitoring section, the number of vehicles on the lane, the vehicle driving speed, and the vehicle driving trajectory;

[0019] Judge whether the vehicle is driving illegally based on the vehicle driving speed and the vehicle driving trajectory;

[0020] If the vehicle is driving illegally, obtain the illegal driving accident occurrence probability;

[0021] Calculate the traffic accident occurrence probability based on the illegal driving accident occurrence probability, the number of lanes, and the number of vehicles on the lane;

[0022] If the vehicle is not driving illegally, calculate the traffic accident occurrence probability based on the number of lanes and the number of vehicles on the lane.

[0023] Optionally, the generating the theoretical road congestion level based on the traffic accident occurrence probability and the historical section congestion information includes:

[0024] Obtain the congestion information of the same-period section within the historical preset prediction period with the same period time as the current preset prediction period;

[0025] Generate the theoretical road congestion level based on the traffic accident occurrence probability and the congestion information of the same-period section.

[0026] Optionally, the generating the theoretical road congestion level based on the traffic accident occurrence probability and the congestion information of the same-period section includes:

[0027] Obtain the accident level proportion of the probability of the traffic accident occurring and the historical level proportion of the congestion information of the same-period road segments;

[0028] Calculate the accident level based on the probability of the traffic accident occurring and the accident level proportion;

[0029] Calculate the historical level based on the congestion information of the same-period road segments and the historical level proportion;

[0030] Generate the theoretical road congestion level based on the accident level and the historical level.

[0031] Optionally, after generating the theoretical road congestion level based on the probability of the traffic accident occurring and the historical road segment congestion information, it further includes:

[0032] Obtain the solution generation strategy;

[0033] Generate a congestion prevention plan based on the solution generation strategy and the theoretical road congestion level;

[0034] Send the congestion prevention plan to the mobile terminal of the management personnel.

[0035] Optionally, the generating a congestion prevention plan based on the solution generation strategy and the theoretical road congestion level includes:

[0036] Obtain the information of the management personnel responsible for monitoring the road segment and the information of adjacent road segments, where the information of the management personnel includes the number of available management personnel;

[0037] Determine the required number of management personnel based on the theoretical road congestion level;

[0038] Judge whether the number of available management personnel meets the required number of management personnel;

[0039] If the number of available management personnel meets the required number of management personnel, generate a congestion prevention plan based on the information of the management personnel and the information of adjacent road segments;

[0040] If the number of available management personnel does not meet the required number of management personnel, generate management personnel deployment information;

[0041] Generate a congestion prevention plan based on the management personnel deployment information, the information of the management personnel, and the information of adjacent road segments.

[0042] In a second aspect, the present application provides a road congestion prediction device based on vehicle behavior analysis, adopting the following technical solutions:

[0043] A road congestion prediction device based on vehicle behavior analysis, comprising:

[0044] A road information acquisition module, configured to acquire road information of the current road;

[0045] A monitored section division module, configured to divide the current road into multiple monitored sections based on the road information and a preset road division rule;

[0046] A cycle information acquisition module, configured to acquire section information and vehicle information of the monitored section within the current preset prediction cycle;

[0047] An accident probability calculation module, configured to calculate the probability of a traffic accident occurring based on the section information and vehicle information;

[0048] A historical information acquisition module, configured to acquire historical section congestion information of the monitored section within a historical preset prediction cycle;

[0049] A congestion level generation module, configured to generate a theoretical road congestion level based on the probability of a traffic accident occurring and the historical section congestion information.

[0050] By adopting the above technical solution, a road is divided into multiple monitored sections, and each monitored section is monitored separately, so that the obtained data is more detailed and accurate. The probability of a traffic accident occurring is calculated based on the section information and vehicle information of each monitored section, and then the theoretical road congestion level is calculated based on the historical information and the probability of a traffic accident occurring, combining the current situation and historical records, thereby improving the efficiency of road congestion prediction.

[0051] In a third aspect, the present application provides an electronic device, adopting the following technical solution:

[0052] An electronic device includes a processor, and the processor is coupled to a memory;

[0053] The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the computer program of the road congestion prediction method based on vehicle behavior analysis according to any one of the first aspect.

[0054] In a fourth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution:

[0055] A computer-readable storage medium stores a computer program that can be loaded and executed by a processor to execute the road congestion prediction method based on vehicle behavior analysis according to any one of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a schematic flowchart of a road congestion prediction method based on vehicle behavior analysis provided by an embodiment of the present application.

[0057] Figure 2It is a structural block diagram of a road congestion prediction device provided by an embodiment of the present application based on vehicle behavior analysis.

[0058] Figure 3 It is a structural block diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0059] The following further describes the present application in detail with reference to the accompanying drawings.

[0060] An embodiment of the present application provides a road congestion prediction method based on vehicle behavior analysis. The road congestion prediction method based on vehicle behavior analysis can be executed by an electronic device, which can be a server or a terminal device. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0061] Figure 1 It is a schematic flowchart of a road congestion prediction method based on vehicle behavior analysis provided by an embodiment of the present application.

[0062] As Figure 1 shown, the main process of the method is described as follows (Steps S101 to S104):

[0063] Step S101, obtain road information of the current road.

[0064] In this embodiment, the current road is a main or branch road, such as a road with traffic facilities such as cameras, traffic lights, checkpoints, and electronic eyes, like Jianshe Road or Xinhua Road. The road information includes but is not limited to road length, road start position, road end position, road direction, road checkpoint position, and the connection position of the road with other roads, and no further examples are given here.

[0065] Step S102, divide the current road into multiple monitoring sections based on the road information and a preset road division rule.

[0066] Regarding Step S102, obtain the number of road checkpoints on the current road and the road length between two adjacent road checkpoints; dividing the current road into multiple monitoring sections based on the number of road checkpoints and the road length between two adjacent road checkpoints includes.

[0067] In this embodiment, for the convenience of monitoring, a main road or a branch road is divided into multiple monitoring sections, each monitoring section is monitored, and then summarized to obtain information about the entire road, reducing the possibility that direct monitoring of this road may lead to incomplete monitoring and affect the efficiency and accuracy of the road congestion prediction result.

[0068] When dividing the monitored road sections, it is divided according to the number of road checkpoints and the road length between road checkpoints. According to the number of road checkpoints, the current road is sequentially divided into multiple checkpoint sections starting from the starting position of the road by two adjacent road checkpoints. The length of each checkpoint section is obtained one by one, and it is judged whether the length of the checkpoint section is not less than the preset checkpoint section length. If the length of the checkpoint section is not less than the preset checkpoint section length, the checkpoint section is used as the monitored road section. If the length of the checkpoint section is less than the preset checkpoint section length, the current checkpoint section and the next adjacent checkpoint section are used as the monitored road section.

[0069] It should be noted that the preset checkpoint section length needs to be set according to the actual road length and the checkpoint section length between two adjacent checkpoints, and no specific limitation is made here.

[0070] Step S103, obtain the road section information and vehicle information of the monitored road section within the current preset prediction period.

[0071] In this embodiment, the road section information includes the number of lanes, lane directions, and the number of vehicles on each lane of the monitored road section, etc. The vehicle information includes vehicle driving speed, vehicle driving trajectory, license plate number, and driver information, etc., and no further examples are given here.

[0072] Since the calculation and data collection require a certain amount of time and data basis, it is necessary to obtain the road section information and vehicle information within a period of time. The road section information and vehicle information obtained within the current preset prediction period are used to calculate the road congestion situation in the next preset prediction period. The specific preset prediction period needs to be set according to actual needs. If not set, it defaults to 15 minutes and needs to be set as an integer multiple of 15 minutes, and the maximum time cannot be greater than 1 hour. The preset prediction period lengths in different time periods of a day can be different. For example, the preset prediction period length can be set to a shorter time during the morning and evening rush hours, and the preset prediction period length can be set to a longer time at noon and other time periods, and no specific limitation is made here.

[0073] Step S104, calculate the probability of traffic accidents based on the road section information and vehicle information.

[0074] For step S104, obtain the number of lanes, the number of vehicles on the lane, vehicle driving speed, and vehicle driving trajectory of the monitored road section; judge whether the vehicle is driving illegally based on the vehicle driving speed and vehicle driving trajectory; if the vehicle is driving illegally, obtain the probability of illegal driving accidents; calculate the probability of traffic accidents based on the probability of illegal driving accidents, the number of lanes, and the number of vehicles on the lane; if the vehicle is not driving illegally, calculate the probability of traffic accidents based on the number of lanes and the number of vehicles on the lane.

[0075] In this embodiment, when calculating the probability of a traffic accident based on road section information and vehicle information, first, it is determined whether the vehicle is driving illegally based on the vehicle's driving speed and driving trajectory. The illegal driving is judged according to the preset illegal driving norms, which include speeding, frequent lane changes, cutting in, overtaking, etc. When at least one of them occurs, the vehicle is determined to be driving illegally. Each item in the preset illegal driving norms is set with a corresponding probability of an accident due to illegal driving. The final probability of an accident due to illegal driving is the sum of the probabilities of accidents due to illegal driving corresponding to all illegal items.

[0076] For example, the probability of an accident due to speeding is 5%, the probability of an accident due to frequent lane changes is 4%, the probability of an accident due to cutting in is 6%, and the probability of an accident due to overtaking is 2%. When the three illegal driving behaviors of speeding, frequent lane changes, and cutting in occur, the final probability of an accident due to illegal driving is 15%. The specific preset driving norms and the probabilities of accidents due to illegal driving need to be set according to actual needs and are not specifically limited here.

[0077] When there is no probability of an accident due to illegal driving, the probability of a traffic accident for the number of lanes and the number of vehicles on the lanes is determined according to the preset combinations and combination probability scores. Multiple combinations of the number of lanes and the number of vehicles on the lanes are set in the preset combinations, and each combination corresponds to a combination probability score. When setting the combination probability score, a reference value can be set according to the number of lanes, and then an additional value is set according to the number of vehicles on the lanes. The combination probability score is the sum of the two. When the additional value is 0, the combination probability score is directly set to 0 points. Each additional value interval corresponds to an additional value. When determining the additional value, it is necessary to determine the additional value interval according to the number of vehicles. As the number of additional value intervals increases, the corresponding additional value also gradually increases. The specific reference value, additional value, and the division of the additional value intervals need to be set according to actual needs and are not specifically limited here.

[0078] When there is a probability of an accident due to illegal driving, the sum of the probability of an accident due to illegal driving and the combination probability score is calculated, and the sum of the probability of an accident due to illegal driving and the combination probability score is used as the probability of a traffic accident.

[0079] Step S105: Obtain the historical road section congestion information of the monitored road section within the historical preset prediction period.

[0080] In this embodiment, the historical road section congestion information includes but is not limited to the historical road section congestion level, congestion duration, the number of vehicles during congestion, the number of monitored road sections affected, whether a traffic accident occurred during congestion, and the cause of the traffic accident, and no further examples are given here.

[0081] Step S106: Generate a theoretical road congestion level based on the probability of traffic accidents and historical road section congestion information.

[0082] Regarding step S106, obtain the congestion information of the same-period road sections within the historical preset prediction period with the same cycle time as the current preset prediction period; generate a theoretical road congestion level based on the probability of traffic accidents and the congestion information of the same-period road sections.

[0083] Furthermore, obtain the proportion of accident levels of the probability of traffic accidents and the historical level proportion of the congestion information of the same-period road sections; calculate the accident level based on the probability of traffic accidents and the proportion of accident levels; calculate the historical level based on the congestion information of the same-period road sections and the historical level proportion; generate a theoretical road congestion level based on the accident level and the historical level.

[0084] In this embodiment, each preset prediction period corresponds to multiple historical preset prediction periods with the same cycle time. For example, if the current preset prediction period is from 9:00 to 9:30 in the morning, the historical preset prediction periods include, but are not limited to, from 9:00 to 9:30 in the morning yesterday, and from 9:00 to 9:30 in the morning the day before yesterday. The historical preset prediction periods can range from one day, two days to one week or half a month. The congestion information of the same-period road sections includes the historical theoretical road congestion level and the accident occurrence situation. If the congestion information of the same-period road sections only includes the historical theoretical road congestion level, calculate the average value of all historical theoretical road congestion levels, and use the average value of the historical theoretical road congestion levels as the historical congestion level. If the congestion information of the same-period road sections includes the historical theoretical road congestion level and the accident occurrence situation, calculate the average value of all historical theoretical road congestion levels, and obtain the accident level corresponding to the accident occurrence situation, calculate the average value of the accident levels, and use the average value of the historical theoretical road congestion levels and the average value of the accident levels as the historical congestion level.

[0085] Each probability of traffic accident corresponds to a congestion level, and the congestion levels corresponding to multiple adjacent probabilities of traffic accidents can be the same. Calculate the historical level based on the historical congestion level and the historical level proportion, calculate the accident level based on the congestion level and the proportion of accident levels. After calculating the historical level and the accident level respectively, calculate the sum of the historical level and the accident level, and use the sum of the historical level and the accident level as the theoretical road congestion level of the current monitored road section. Calculate the average value of the theoretical road congestion levels of all monitored road sections, and use the average value of the theoretical road congestion levels of all monitored road sections as the theoretical road congestion level of the current road. When the theoretical road congestion level is calculated, if the theoretical road congestion level is a decimal, the rounding principle is adopted for the selection of the decimal.

[0086] In this embodiment, a solution generation strategy is obtained; a congestion prevention solution is generated based on the solution generation strategy and the theoretical road congestion level; and the congestion prevention solution is sent to the mobile terminal of the management personnel.

[0087] Specifically, the information of management personnel and adjacent road sections of the management and monitoring section is obtained, where the information of management personnel includes the number of available management personnel; the number of management personnel required is determined based on the theoretical road congestion level; it is judged whether the number of available management personnel meets the number of management personnel required; if the number of available management personnel meets the number of management personnel required, a congestion prevention solution is generated based on the information of management personnel and adjacent road sections; if the number of available management personnel does not meet the number of management personnel required, management personnel deployment information is generated; and a congestion prevention solution is generated based on the management personnel deployment information, the information of management personnel and adjacent road sections.

[0088] In this embodiment, different theoretical road congestion levels correspond to different congestion prevention solutions, and different congestion prevention solutions correspond to different numbers of management personnel. After determining the congestion prevention solution, the congestion prevention solution is sent to the mobile terminal of the corresponding management personnel to notify the management personnel to carry out preventive management in advance.

[0089] When generating the congestion prevention solution, first determine whether vehicles can be diverted to adjacent road sections according to the information of adjacent road sections. If vehicles can be diverted to adjacent road sections, calculate the number of diverted vehicles. Then, determine the management personnel who can carry out preventive management according to the information of management personnel. The information of management personnel includes the number of available management personnel and the management experience of available personnel in the area corresponding to the current road. When assigning tasks, distribute the key tasks to the management personnel with high management experience. Different theoretical road congestion levels correspond to different numbers of management personnel required. Compare the number of available management personnel with the number of management personnel required, and judge whether the number of available management personnel meets the number of management personnel required. If the number of available management personnel does not meet the number of management personnel required, calculate the number of personnel to be deployed and generate management personnel deployment information.

[0090] When the number of available management personnel meets the number of management personnel required and vehicles can be diverted to adjacent road sections, a congestion prevention plan is generated based on the number of available management personnel, the number of diverted vehicles, and the information of all monitored road sections of the current road; when the number of available management personnel meets the number of management personnel required and vehicles cannot be diverted to adjacent road sections, a congestion prevention plan is generated based on the number of available management personnel and the information of all monitored road sections of the current road; when the number of available management personnel does not meet the number of management personnel required but vehicles can be diverted to adjacent road sections, a congestion prevention plan is generated based on the management personnel deployment information, the number of available management personnel, the number of diverted vehicles, and the information of all monitored road sections of the current road; when the number of available management personnel does not meet the number of management personnel required and vehicles cannot be diverted to adjacent road sections, a congestion prevention plan is generated based on the management personnel deployment information, the number of available management personnel, and the information of all monitored road sections of the current road. The specific content of the congestion prevention plan needs to be set according to actual requirements and is not specifically limited here.

[0091] Figure 2 The structural block diagram of a road congestion prediction device 200 provided for the application embodiment based on vehicle behavior analysis.

[0092] As Figure 2 shown, the road congestion prediction device 200 based on vehicle behavior analysis mainly includes:

[0093] A road information acquisition module 201, configured to acquire the road information of the current road;

[0094] A monitored road section division module 202, configured to divide the current road into multiple monitored road sections based on the road information and a preset road division rule;

[0095] A period information acquisition module 203, configured to acquire the road section information and vehicle information of the monitored road sections within the current preset prediction period;

[0096] An accident probability calculation module 204, configured to calculate the probability of a traffic accident occurring based on the road section information and vehicle information;

[0097] A historical information acquisition module 205, configured to acquire the historical road section congestion information of the monitored road sections within the historical preset prediction period;

[0098] A congestion level generation module 206, configured to generate a theoretical road congestion level based on the probability of a traffic accident occurring and the historical road section congestion information.

[0099] As an optional implementation manner of this embodiment, the monitored road section division module 202 is specifically configured to acquire the number of road checkpoints of the current road and the road length between two adjacent road checkpoints; dividing the current road into multiple monitored road sections based on the number of road checkpoints and the road length between two adjacent road checkpoints includes.

[0100] As an alternative implementation of this embodiment, the accident probability calculation module 204 is specifically configured to obtain the number of lanes, the number of vehicles on the lanes, the vehicle driving speed, and the vehicle driving trajectory of the monitored section; determine whether the vehicle is driving illegally based on the vehicle driving speed and the vehicle driving trajectory; if the vehicle is driving illegally, obtain the accident probability of illegal driving; calculate the traffic accident probability based on the accident probability of illegal driving, the number of lanes, and the number of vehicles on the lanes; if the vehicle is not driving illegally, calculate the traffic accident probability based on the number of lanes and the number of vehicles on the lanes.

[0101] As an alternative implementation of this embodiment, the congestion level generation module 206 includes:

[0102] An information acquisition module, configured to acquire the congestion information of the same-period section within the historical preset prediction period with the same period time as the current preset prediction period;

[0103] A level generation module, configured to generate a theoretical road congestion level based on the traffic accident probability and the congestion information of the same-period section.

[0104] In this alternative embodiment, the level generation module is specifically configured to obtain the proportion of accident levels of the traffic accident probability and the historical proportion of levels of the congestion information of the same-period section; calculate the accident level based on the traffic accident probability and the proportion of accident levels; calculate the historical level based on the congestion information of the same-period section and the historical proportion of levels; generate a theoretical road congestion level based on the accident level and the historical level.

[0105] As an alternative implementation of this embodiment, the road congestion prediction device 200 based on vehicle behavior analysis further includes:

[0106] A strategy acquisition module, configured to acquire a solution generation strategy;

[0107] A solution generation module, configured to generate a congestion prevention solution based on the solution generation strategy and the theoretical road congestion level;

[0108] A solution sending module, configured to send the congestion prevention solution to the mobile terminal of the management personnel.

[0109] In this alternative embodiment, the solution generation module is specifically configured to obtain the information of the management personnel for monitoring sections and the information of adjacent sections, where the information of the management personnel includes the number of available management personnel; determine the required number of management personnel based on the theoretical congestion level of the road; determine whether the number of available management personnel meets the required number of management personnel; if the number of available management personnel meets the required number of management personnel, generate a congestion prevention solution based on the information of the management personnel and the information of adjacent sections; if the number of available management personnel does not meet the required number of management personnel, generate management personnel deployment information; and generate a congestion prevention solution based on the management personnel deployment information, the information of the management personnel, and the information of adjacent sections.

[0110] In one example, the modules in any of the above devices may be one or more integrated circuits configured to implement the above methods. For example: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0111] Again, when the modules in the device can be implemented in the form of a processing element scheduler, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call programs. Again, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0112] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0113] Figure 3 This is a block diagram of the structure of the electronic device 300 provided in the embodiments of the present application.

[0114] As Figure 3 shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.

[0115] Among them, the processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps of the above-mentioned road congestion prediction method based on vehicle behavior analysis; the memory 302 is used to store various types of data to support the operation of the electronic device 300. These data may include, for example, instructions for any application or method operating on the device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, one or more of a magnetic disk or an optical disc.

[0116] The I / O interface 303 provides an interface between the processor 301 and other interface modules. The above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 304 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them. Therefore, the corresponding communication component 104 may include: a Wi-Fi component, a Bluetooth component, an NFC component.

[0117] The electronic device 300 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the road congestion prediction method based on vehicle behavior analysis given in the above embodiments.

[0118] The communication bus 305 may include a path for transmitting information between the above components. The communication bus 305 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 can be divided into an address bus, a data bus, a control bus, etc.

[0119] The electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and may also be a server, etc.

[0120] This application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the road congestion prediction method based on vehicle behavior analysis described above are implemented.

[0121] The computer-readable storage medium may include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0122] The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus.

[0123] The above description is only a preferred embodiment of the present application and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions applied in the present application.

Claims

1. A road congestion prediction method based on vehicle behavior analysis, characterized in that Including: Obtain the road information of the current road; Divide the current road into multiple monitoring sections based on the road information and a preset road division rule; Obtain the section information and vehicle information of the monitoring sections within the current preset prediction period; Calculate the probability of a traffic accident based on the section information and vehicle information; Obtain the historical section congestion information of the monitoring sections within a historical preset prediction period; Generate a theoretical road congestion level based on the probability of a traffic accident and the historical section congestion information; The dividing the current road into multiple monitoring sections based on the road information and a preset road division rule includes: Obtain the number of road checkpoints on the current road and the road length between two adjacent road checkpoints; Divide the current road into multiple monitoring sections based on the number of road checkpoints and the road length between two adjacent road checkpoints; The dividing the current road into multiple monitoring sections based on the number of road checkpoints and the road length between two adjacent road checkpoints includes: Divide the current road into multiple checkpoint sections in sequence starting from the road starting position according to two adjacent road checkpoints; Obtain the length of each checkpoint section in sequence, and determine whether the length of the checkpoint section is not less than a preset checkpoint section length; If the length of the checkpoint section is not less than the preset checkpoint section length, then use the checkpoint section as a monitoring section; If the length of the checkpoint section is less than the preset checkpoint section length, then use the current checkpoint section and the next adjacent checkpoint section as a monitoring section; The generating a theoretical road congestion level based on the probability of a traffic accident and the historical section congestion information includes: Obtain the same-period section congestion information within a historical preset prediction period with the same cycle time as the current preset prediction period; Generate a theoretical road congestion level based on the probability of a traffic accident and the same-period section congestion information; The generating a theoretical road congestion level based on the probability of a traffic accident and the same-period section congestion information includes: Obtain the accident level proportion of the probability of a traffic accident and the historical level proportion of the same-period section congestion information; Calculate the accident level based on the probability of a traffic accident and the accident level proportion; Calculate the historical level based on the same-period section congestion information and the historical level proportion; Generate a theoretical road congestion level based on the accident level and the historical level; The calculating the historical level based on the same-period section congestion information and the historical level proportion includes: If the same-period section congestion information only includes historical theoretical road congestion levels, then calculate the average value of all the historical theoretical road congestion levels, and use the average value of the historical theoretical road congestion levels as the historical congestion level; If the same-period section congestion information includes the historical theoretical road congestion levels and accident occurrence situations, then calculate the average value of all the historical theoretical road congestion levels, and obtain the accident levels corresponding to all the accident occurrence situations, calculate the average value of all the accident levels, and use the average value of the historical theoretical road congestion levels and the average value of the accident levels as the historical congestion level; Calculate the historical level based on the historical congestion level and the historical level proportion.

2. The method according to claim 1, wherein The calculating the probability of traffic accident based on the road segment information and vehicle information includes: Obtain the number of lanes, the number of vehicles on the lanes, the vehicle driving speed, and the vehicle driving trajectory of the monitored road segment; Judge whether the vehicle is driving illegally based on the vehicle driving speed and the vehicle driving trajectory; If the vehicle is driving illegally, obtain the probability of illegal driving accident; Calculate the probability of traffic accident based on the probability of illegal driving accident, the number of lanes, and the number of vehicles on the lanes; If the vehicle is not driving illegally, calculate the probability of traffic accident based on the number of lanes and the number of vehicles on the lanes.

3. The method according to claim 1, wherein After generating the theoretical road congestion level based on the probability of traffic accident and the historical road segment congestion information, it further includes: Obtain the solution generation strategy; Generate a congestion prevention plan based on the solution generation strategy and the theoretical road congestion level; Send the congestion prevention plan to the mobile terminal of the management personnel.

4. The method according to claim 3, characterized in that, The generating a congestion prevention plan based on the solution generation strategy and the theoretical road congestion level includes: Obtain the information of the management personnel responsible for the monitored road segment and the information of adjacent road segments, where the information of the management personnel includes the number of available management personnel; Determine the required number of management personnel based on the theoretical road congestion level; Judge whether the number of available management personnel meets the required number of management personnel; If the number of available management personnel meets the required number of management personnel, generate a congestion prevention plan based on the information of the management personnel and the information of adjacent road segments; If the number of available management personnel does not meet the required number of management personnel, generate management personnel deployment information; Generate a congestion prevention plan based on the management personnel deployment information, the information of the management personnel, and the information of adjacent road segments.

5. A road congestion prediction device based on vehicle behavior analysis, characterized in that, It includes: A road information acquisition module for acquiring the road information of the current road; A monitored road segment division module for dividing the current road into multiple monitored road segments based on the road information and a preset road division rule; A cycle information acquisition module for acquiring the road segment information and vehicle information of the monitored road segment within the current preset prediction cycle; An accident probability calculation module for calculating the probability of traffic accident based on the road segment information and vehicle information; A historical information acquisition module for acquiring the historical road segment congestion information of the monitored road segment within the historical preset prediction cycle; A congestion level generation module for generating a theoretical road congestion level based on the probability of traffic accident and the historical road segment congestion information; The monitored road segment division module is specifically used for dividing the current road into multiple monitored road segments based on the road information and a preset road division rule, including: Obtain the number of road checkpoints of the current road and the road length between two adjacent road checkpoints; Divide the current road into multiple monitored road segments based on the number of road checkpoints and the road length between two adjacent road checkpoints; The monitoring section division module is specifically configured to divide the current road into multiple monitoring sections based on the number of road checkpoints and the road length between two adjacent road checkpoints, including: Dividing the current road into multiple checkpoint sections in sequence from the starting position of the road according to two adjacent road checkpoints; Sequentially obtaining the length of each checkpoint section and determining whether the length of the checkpoint section is not less than the preset checkpoint section length; If the length of the checkpoint section is not less than the preset checkpoint section length, then use the checkpoint section as a monitoring section; If the length of the checkpoint section is less than the preset checkpoint section length, then use the current checkpoint section and the next adjacent checkpoint section as a monitoring section; The congestion level generation module is specifically configured to generate a theoretical road congestion level based on the probability of traffic accidents and the historical section congestion information, including: Obtaining the congestion information of the same-period section within the historical preset prediction period with the same period time as the current preset prediction period; Generating a theoretical road congestion level based on the probability of traffic accidents and the congestion information of the same-period section; The generating a theoretical road congestion level based on the probability of traffic accidents and the congestion information of the same-period section includes: Obtaining the accident level proportion of the probability of traffic accidents and the historical level proportion of the congestion information of the same-period section; Calculating the accident level based on the probability of traffic accidents and the accident level proportion; Calculating the historical level based on the congestion information of the same-period section and the historical level proportion; Generating a theoretical road congestion level based on the accident level and the historical level; The congestion level generation module is specifically configured to calculate the historical level based on the congestion information of the same-period section and the historical level proportion, including: If the congestion information of the same-period section only includes the historical theoretical road congestion level, then calculate the average value of all the historical theoretical road congestion levels, and use the average value of the historical theoretical road congestion levels as the historical congestion level; If the congestion information of the same-period section includes the historical theoretical road congestion level and the accident occurrence situation, then calculate the average value of all the historical theoretical road congestion levels, and obtain the accident levels corresponding to all the accident occurrence situations, calculate the average value of all the accident levels, and use the average value of the historical theoretical road congestion levels and the average value of the accident levels as the historical congestion level; Calculating the historical level according to the historical congestion level and the historical level proportion.

6. An electronic device, characterized in that, Including a processor, the processor is coupled with a memory; The processor is configured to execute the computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, Including a computer program or instruction, when the computer program or instruction runs on a computer, the computer is caused to execute the method according to any one of claims 1 to 4.

Images