Electric bicycle intelligent control system and control method thereof

Abstract

The invention discloses an electric bicycle intelligent control system and a control method thereof. The control method comprises the following steps: acquiring current driving environment sensing data, current bicycle state data and current rider behavior monitoring data corresponding to a safe driving intelligent detection instruction; determining a first driving risk assessment result based on a road surface risk assessment strategy, the current driving environment perception data and the current vehicle state data; determining a second driving risk assessment result based on the driving behavior assessment strategy and the current rider behavior monitoring data; and if the first driving risk assessment result and the second driving risk assessment result determine that driving risks exist correspondingly, performing corresponding safe driving control based on a safe driving intervention strategy. Through the method, the driving related data and the driving evaluation related strategy can be timely acquired in the safe driving mode to determine whether the driving risk exists at present, and corresponding control is performed through the safe driving intervention strategy when the driving risk exists, so that the driving safety of a driver is ensured.

Description

Technical Field

[0001] The present invention relates to the field of green and low-carbon technology, and in particular to an intelligent control system for an electric bicycle and a control method thereof. Background Art

[0002] At present, electric bicycles have been widely used due to their flexible mobility and convenient power charging. For example, electric bicycles have keyless smart unlocking, intelligent instrument display, monitoring of battery temperature and voltage and push alerts when abnormalities occur, and automatic emergency braking safety functions. However, the automatic emergency braking safety of electric bicycles can only be activated when obstacles are detected in front (such as cars braking suddenly or pedestrians who stop walking, etc.). When encountering other complex road conditions (such as potholes, slippery roads and construction roads, intersections with many vehicles and pedestrians, etc.), the corresponding intelligent driving mode cannot be activated to deal with the current complex road conditions for safe driving to ensure the safety of the driver. Summary of the invention

[0003] The embodiments of the present invention provide an intelligent control system for an electric bicycle and a control method thereof, aiming to solve the problem that in the prior art methods, the electric bicycle has an automatic emergency braking safety function which can only be activated when an obstacle is detected ahead, and when encountering other complex road conditions, the corresponding intelligent driving mode cannot be activated to cope with the current complex road conditions and drive safely to ensure the driver's safety.

[0004] In a first aspect, an embodiment of the present invention provides an electric bicycle intelligent control system, which includes: a current detection data acquisition unit, for responding to a safe driving intelligent detection instruction, acquiring current driving environment perception data, current vehicle state data, and current rider behavior monitoring data corresponding to the safe driving intelligent detection instruction; A first driving risk assessment unit, configured to determine a first driving risk assessment result based on a preset road surface risk assessment strategy, the current driving environment perception data, and the current vehicle state data; a second driving risk assessment unit, configured to determine a second driving risk assessment result based on a preset driving behavior assessment strategy and the current rider behavior monitoring data; The safe driving intervention strategy execution unit is used to perform corresponding safe driving control on the electric bicycle based on a preset safe driving intervention strategy if it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result.

[0005] In a second aspect, an embodiment of the present invention provides an intelligent control method for an electric bicycle, which includes: In response to the safe driving intelligent detection instruction, obtaining current driving environment perception data, current vehicle status data and current rider behavior monitoring data corresponding to the safe driving intelligent detection instruction; Determining a first driving risk assessment result based on a preset road risk assessment strategy, the current driving environment perception data, and the current vehicle state data; Determining a second driving risk assessment result based on a preset driving behavior assessment strategy and the current rider behavior monitoring data; If it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result, corresponding safe driving control is performed on the electric bicycle based on a preset safe driving intervention strategy.

[0006] The embodiment of the present invention provides an intelligent control system for an electric bicycle and a control method thereof, the method comprising: in response to a safe driving intelligent detection instruction, obtaining current driving environment perception data, current vehicle status data and current rider behavior monitoring data corresponding to the safe driving intelligent detection instruction; determining a first driving risk assessment result based on a preset road risk assessment strategy, current driving environment perception data and current vehicle status data; determining a second driving risk assessment result based on a preset driving behavior assessment strategy and current rider behavior monitoring data; if it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result, then performing corresponding safe driving control on the electric bicycle based on a preset safe driving intervention strategy. Through the above method, the current driving environment perception data, current vehicle status data and current rider behavior monitoring data can be obtained in a timely manner in a safe driving mode, and the first driving risk assessment result and the second driving risk assessment result can be quickly determined in combination with the road risk assessment strategy and the driving behavior assessment strategy to determine whether there is a driving risk at present, and when there is a driving risk, corresponding control is performed in a timely manner through a safe driving intervention strategy to ensure the driving safety of the driver. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0008] Figure 1 A schematic diagram of an application scenario of the electric bicycle intelligent control method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a flow chart of an intelligent control method for an electric bicycle provided by an embodiment of the present invention; Figure 3 A schematic diagram of a sub-process of an electric bicycle intelligent control method provided by an embodiment of the present invention; Figure 4 A schematic diagram of a sub-process of an electric bicycle intelligent control method provided by an embodiment of the present invention; Figure 5 A schematic diagram of a sub-process of an electric bicycle intelligent control method provided by an embodiment of the present invention; Figure 6 A schematic block diagram of an electric bicycle intelligent control system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0010] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0011] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0012] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0013] See also Figure 1 and Figure 2 , Figure 1 The embodiment of the present invention provides Figure 1 A schematic diagram of an application scenario of the electric bicycle intelligent control method provided by an embodiment of the present invention; Figure 2 The flowchart of the intelligent control method of an electric bicycle provided by an embodiment of the present invention is shown in FIG. 1 ; the intelligent control method of an electric bicycle is applied to an electric bicycle 10, and the electric bicycle 10 is connected to a roadside communication device 20 (such as a roadside unit) in a vehicle-road cooperative system that can be arranged on the roadside. Figure 2As shown, the method includes steps S110 to S140.

[0014] S110. In response to a safe driving intelligent detection instruction, obtain current driving environment perception data, current vehicle status data, and current rider behavior monitoring data corresponding to the safe driving intelligent detection instruction.

[0015] In this embodiment, the user can initially set the safe driving mode of the electric bicycle, such as setting the instruction generation cycle of the safe driving intelligent detection instruction to 5s, 10s, 15s, 20s, 30s, etc. When the electric bicycle generates safe driving intelligent detection instructions based on the processor therein according to the preset instruction generation cycle, it can execute a complete step S110~S140, that is, each round of safe driving intelligent detection uses the same steps. In this application, the technical solution is first explained by the process of executing a complete step S110~S140.

[0016] When the electric bicycle detects the currently generated safe driving intelligent detection instruction, it needs to obtain the current driving environment perception data, the current vehicle status data and the current rider behavior monitoring data. Among them, by setting environmental perception sensors (such as millimeter wave radar, laser radar, infrared sensor, positioning module, etc.), vehicle status sensors (such as inertial measurement unit, torque sensor, tire pressure monitoring system, etc.), and rider behavior monitoring devices (such as pressure sensors and rotation angle detection sensors on the handlebars, eye tracking cameras, etc.) on the electric bicycle, the current driving environment perception data can be detected by the environmental perception sensor, the current vehicle status data can be detected by the vehicle status sensor, and the current rider behavior monitoring data can be detected by the rider behavior monitoring device. The current driving environment perception data, current vehicle status data and current rider behavior monitoring data obtained can be comprehensively analyzed in the local processor of the electric bicycle or in the vehicle-road cooperative system connected to it, so as to determine whether there is a driving risk at present.

[0017] S120. Determine a first driving risk assessment result based on a preset road risk assessment strategy, the current driving environment perception data, and the current vehicle state data.

[0018] In this embodiment, after the current driving environment perception data and the current vehicle state data of the electric bicycle are obtained, they can be used as input data of the road risk assessment strategy, so as to analyze and obtain the first driving risk assessment result, and the obtained first driving risk assessment result is only used as the assessment result of the first dimension. Wherein, when the first driving risk assessment result takes a value of 1, it indicates that there is a driving risk, and when the first driving risk assessment result takes a value of 0, it indicates that there is no driving risk.

[0019] In one embodiment, the current driving environment perception data at least includes a current road surface image corresponding to the current driving road, current positioning data and current road vehicle and pedestrian distribution data; the current vehicle state data at least includes a current vehicle speed and a current pedal stepping data sequence; Figure 3 As shown, as a first embodiment of step S120, step S120 includes: S1201: If it is determined based on the road risk assessment strategy that the road recognition result corresponding to the current road image, the positioning position result corresponding to the current positioning data, and the current road vehicle and pedestrian distribution data meet a first preset judgment condition, and it is determined based on the road risk assessment strategy that the current vehicle speed and the current pedal data sequence meet a second preset judgment condition, then the existence of driving risk is taken as the first driving risk assessment result; S1202. If it is determined based on the road surface risk assessment strategy that the road surface recognition result corresponding to the current road surface image, the positioning position result corresponding to the current positioning data, and the current road vehicle and pedestrian distribution data do not meet the first preset judgment condition, and it is determined based on the road surface risk assessment strategy that the current vehicle driving speed and the current pedal data sequence do not meet the second preset judgment condition, then the absence of driving risk is taken as the first driving risk assessment result.

[0020] In this embodiment, at least the current road surface image, current positioning data and current road vehicle and pedestrian distribution data of the current driving road can be obtained through the current driving environment perception data, and at least the current vehicle speed and current pedal stepping data sequence can be obtained through the current vehicle state data, and the above data or information obtained can be used as input parameters or input data of the road risk assessment strategy to perform specific driving risk assessment. Specifically, if it is determined based on the road risk assessment strategy that the road surface recognition result corresponding to the current road surface image, the positioning position result corresponding to the current positioning data and the current road vehicle and pedestrian distribution data meet the first preset judgment condition (the first preset judgment condition can be flexibly set based on the safe driving requirement), and it is determined based on the road risk assessment strategy that the current vehicle speed and the current pedal data sequence meet the second preset judgment condition (similarly, the second preset judgment condition can be flexibly set based on the safe driving requirement), once the current driving environment perception data meets the first preset judgment condition and the current vehicle state data meets the second preset judgment condition, there may be a driving risk as the first driving risk assessment result. If the current driving environment perception data does not meet the first preset judgment condition and the current vehicle status data does not meet the second preset judgment condition, then the absence of driving risk can be used as the first driving risk assessment result. If the current driving environment perception data meets the first preset judgment condition or the current vehicle status data meets the second preset judgment condition, then it can be considered that the electric bicycle has potential driving risks and a voice prompt can be given directly.

[0021] In one embodiment, the first preset judgment condition includes: the road surface recognition result corresponds to a preset road surface type, the current positioning data corresponds to a preset road type, and the current road vehicle and pedestrian distribution data exceeds a preset comprehensive traffic density; wherein; the preset road surface types include potholes, slippery roads and construction roads, and the preset road types include crossroads, three-way intersections, roundabouts and multi-way intersections; The second preset judgment condition includes: the current vehicle driving speed exceeds the preset driving speed threshold; there are mutation sequence values ​​in the current pedal data sequence, or the standard deviation of the current pedal data sequence exceeds the preset standard deviation threshold, or the statistical number of the current pedal data sequence that continuously exceeds the preset pedal force threshold exceeds the preset number threshold.

[0022] In this embodiment, as the first preset judgment condition and the second preset judgment condition specifically set in step S120, the driving risk is evaluated and analyzed mainly from five dimensions: whether the road surface recognition result corresponds to the preset road surface type, whether the current positioning data corresponds to the preset road type, whether the current road vehicle and pedestrian distribution data exceeds the preset comprehensive traffic density, whether the current vehicle driving speed exceeds the preset driving speed threshold, and whether there are specified data features in the current pedal data sequence (such as the existence of mutational sequence values, or the standard deviation of the current pedal data sequence exceeds the preset standard deviation threshold, or the statistical number of the current pedal data sequence that continuously exceeds the preset pedal force threshold exceeds the preset number threshold).

[0023] Among them, because potholes, slippery roads and construction roads are more complex road types, crossroads, three-way intersections, roundabouts and multi-way intersections (which can be understood as five-way intersections or more) are road types with more complex road conditions. When the current road vehicle and pedestrian distribution data exceeds the preset comprehensive traffic density, it corresponds to a relatively crowded road condition. Therefore, when the current environment of the electric bicycle meets the above conditions, safe driving assistance is required. In determining whether the road surface recognition result corresponds to the preset road surface type, it can be determined by obtaining the recognition result corresponding to the collected current road surface image through the image recognition model in the road surface risk assessment strategy. For example, when the current road surface image corresponds to a flat road surface, the recognition result corresponds to a flat road surface; when the current road surface image corresponds to a pothole road surface, the recognition result corresponds to a pothole road surface; when the current road surface image corresponds to a non-dry road surface, the recognition result corresponds to a slippery road surface; when the current road surface image corresponds to a non-flat road surface and there are roadblock tools, the recognition result corresponds to a construction road surface, etc. When judging whether the current positioning data corresponds to the preset road type, the specific positioning position currently obtained by the positioning module (such as Beidou positioning module, etc.) on the electric bicycle can be combined with the electronic map data to determine whether it is at a road condition position of a crossroad, a three-way intersection, a roundabout or a multi-way intersection. When judging whether the current road vehicle and pedestrian distribution data exceeds the preset comprehensive traffic density, the total number of vehicles and pedestrians in a unit area at the location of the electric bicycle can be determined by the laser radar and infrared sensor on the electric bicycle. For example, if the sensing range of the laser radar and infrared sensor corresponds to an area of ​​N1 square meters and the total number of vehicles and pedestrians currently sensed is N2, then the current comprehensive traffic density corresponding to the current road vehicle and pedestrian distribution data is N2 / N1 per square meter (where N1 and N2 are both positive numbers). The comparison result of the current comprehensive traffic density N2 / N1 per square meter with the preset comprehensive traffic density determines whether the current road vehicle and pedestrian distribution data exceeds the preset comprehensive traffic density.

[0024] The electric bicycle will also continuously record the vehicle speed and current pedal data (such as the pedal pressure, and different pedal pressures correspond to different vehicle speeds). For example, a data queue that can store a fixed number of pedal pressures can be set in the memory corresponding to the controller of the electric bicycle. N3 pedal pressures can be stored through the data queue (where N3 is a positive integer), and the data storage mechanism of the data queue is first-in-first-out, that is, the data queue is initially filled with N3 pedal pressures in ascending order of the pedal pressure collection time. Before each new pedal pressure is stored, the pedal pressure currently ranked first is removed and the remaining pedal pressures are moved forward one arrangement position, and then the newly stored pedal pressure is stored at the end of the data queue. When the current vehicle speed and the current pedal data sequence of the electric bicycle are known (obtained from the above data queue), it is possible to specifically determine whether the vehicle speed exceeds the preset speed threshold, and it is also possible to determine whether there are mutation sequence values ​​in the current pedal data sequence (such as a pedal pressure that exceeds the preset change rate threshold or a change value exceeds the preset change value threshold compared to one or more previous pedal pressures), or the standard deviation of the current pedal data sequence exceeds the preset standard deviation threshold, or the statistical number of the current pedal data sequence that continuously exceeds the preset pedal force threshold exceeds the preset number threshold. It can be seen that based on the above first preset judgment condition and the second preset judgment condition, the first dimension of driving risk assessment can be performed from the current driving environment perception data and the current vehicle state data.

[0025] In one embodiment, the current driving environment perception data at least includes a current road surface image corresponding to the current driving road, current positioning data and current road vehicle and pedestrian distribution data; the current vehicle state data at least includes a current vehicle speed and a current pedal stepping data sequence; Figure 4 As shown, as a second embodiment of step S120, step S120 includes: S1211, obtaining a classification model corresponding to the road risk assessment strategy, and obtaining current input feature data consisting of a road recognition result identification value corresponding to the current road image, a road type identification value corresponding to the current positioning data, a comprehensive traffic density corresponding to the current road vehicle and pedestrian distribution data, the current vehicle travel speed, and the current pedal stepping data sequence; S1212: Input the current input feature data into the classification model to obtain the first driving risk assessment result.

[0026] In this embodiment, the difference from the first embodiment of step S120 is that artificial intelligence technology can also be combined to intelligently obtain the first driving risk assessment result, such as pre-storing the classification model corresponding to the road surface risk assessment strategy in the processor of the electric bicycle (or in the vehicle-road cooperative system), and inputting the current input feature data composed of the road surface recognition result identification value corresponding to the current road surface image, the road type identification value corresponding to the current positioning data, the comprehensive traffic density corresponding to the current road vehicle and pedestrian distribution data, the current vehicle driving speed and the current pedal stepping data sequence into the classification model (such as a random forest model, a decision tree model, etc.) to quickly obtain the first driving risk assessment result.

[0027] S130: Determine a second driving risk assessment result based on a preset driving behavior assessment strategy and the current rider behavior monitoring data.

[0028] In this embodiment, after the current rider behavior monitoring data of the electric bicycle is obtained, it can be used as input data of the driving behavior evaluation strategy to analyze and obtain the second driving risk evaluation result, and the obtained second driving risk evaluation result is only used as the evaluation result of the second dimension. Wherein, when the second driving risk evaluation result is 1, it indicates that there is a driving risk, and when the second driving risk evaluation result is 0, it indicates that there is no driving risk.

[0029] In one embodiment, the current rider behavior monitoring data includes a current handlebar rotation angle data sequence and a rider sight direction recognition result sequence; Figure 5 As shown, step S130 includes: S131, if it is determined based on the driving behavior assessment strategy that the current handlebar rotation angle data sequence and the rider's line of sight direction recognition result sequence meet a third preset judgment condition, then the existence of driving risk is taken as the second driving risk assessment result; S132: If it is determined based on the driving behavior evaluation strategy that the current handlebar rotation angle data sequence and the rider's line of sight direction recognition result sequence do not satisfy a third preset judgment condition, then taking that no driving risk exists as the second driving risk evaluation result.

[0030] Among them, the third preset judgment condition includes the presence of a mutation sequence value in the current handlebar rotation angle data sequence; the number of changes in the recognition result of the rider's line of sight direction recognition result sequence exceeds a preset change number threshold.

[0031] In this embodiment, referring to the collection method and judgment method for the current pedal data sequence in the above embodiment, the current handlebar rotation angle data sequence can also be collected based on the rotation angle detection sensor on the handlebar (its storage method can also refer to the storage method of the current pedal data sequence in the data queue, that is, N4 handlebar rotation angles are stored in another data queue in a first-in-first-out manner, N4 is a positive integer), and the eye tracking camera set near the main control screen of the electric bicycle can collect the rider's line of sight direction image in time sequence and correspondingly identify the rider's line of sight direction recognition result sequence (its storage method can also refer to the storage method of the current pedal data sequence in the data queue, that is, N5 rider line of sight direction recognition results are stored in another data queue in a first-in-first-out manner, N5 is a positive integer). As the third preset judgment condition specifically set in step S130, the driving risk is also mainly evaluated and analyzed from two dimensions: whether there is a sudden change sequence value in the current handlebar rotation angle data sequence, and whether the number of changes in the recognition result in the rider's line of sight direction recognition result sequence exceeds the preset change number threshold.

[0032] When judging whether there is a mutation sequence value in the current handlebar rotation angle data sequence, it is mainly to judge whether there is a rotation angle data whose change rate exceeds another preset change rate threshold or whose change value exceeds another preset change value threshold compared with one or more previous rotation angle data. When judging whether the number of changes in the recognition result sequence of the rider's line of sight direction exceeds the preset change number threshold, each recognition result is compared with the previous recognition result. When the two recognition results are the same, it is deemed that there is no change and the number of changes in the recognition results is not counted. When the two recognition results are different, it is deemed that there is a change and the number of changes in the recognition results is counted. It can be seen that based on the above-mentioned third preset judgment condition, the second dimension of driving risk assessment can be performed from the current rider behavior monitoring data.

[0033] S140: If it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result, corresponding safe driving control is performed on the electric bicycle based on a preset safe driving intervention strategy.

[0034] In this embodiment, if it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result (wherein the preset risk assessment result is set to exist driving risk), it means that there is a high probability of driving risk at present, and at this time, the electric bicycle can be timely controlled for safe driving based on the preset safe driving intervention strategy, so as to ensure the driving safety of the driver. Among them, the safe driving intervention strategy can be specifically set to a preset duration of handlebar vibration (such as 5s, 10s, etc.), play a pre-stored safe driving prompt voice, automatically limit the speed to a preset driving speed threshold (such as 15km / h, 20km / h, etc.), etc.

[0035] In one embodiment, after step S140, the method further includes: If an intelligent energy recovery control instruction is detected, obtaining current driving user information and energy recovery control preset cycle corresponding to the intelligent energy recovery control instruction, and obtaining driving user habit data in the current driving user information; If it is determined that the time interval between the current system time and the previous energy recovery control time is equal to the preset energy recovery control period, acquiring the current driving condition information based on image acquisition and recognition of the road surface image of the current driving road; Based on the preset output power intelligent control strategy, the current driving condition information and the driving user habit data, an output power data set corresponding to the current target time period is determined, and the power output of the electric bicycle is controlled based on the output power data set during the current target time period.

[0036] In this embodiment, the energy recovery control mode can also be turned on on the electric bicycle at the same time. For example, another instruction generation cycle of the intelligent energy recovery control instruction is set to 5s, 10s, 15s, 20s, 30s, etc. When the electric bicycle generates an intelligent energy recovery control instruction based on the processor therein according to the other instruction generation cycle, the above steps can be executed once completely, that is, each round of intelligent energy recovery control is the same steps. In this application, the technical solution is first explained by the process of executing a complete set of steps.

[0037] When the electric bicycle detects the currently generated intelligent energy recovery control instruction, it is necessary to first obtain the current driving user information (which can be the user's preset entry setting, such as at least including the driving user ID and driving user habit data) and the energy recovery control preset period (such as set to 5min, 10min, 15min, 30min, 60min, etc. based on the actual duration set according to user needs), and obtain the driving user habit data in the current driving user information (such as maintaining low-speed and constant speed driving, medium-speed and constant speed driving, high-speed speed changing driving, etc.). After obtaining the above information, it is also possible to further determine whether the time interval between the current system time and the previous energy recovery control time is equal to the preset energy recovery control cycle. When it is determined that the time interval between the current system time and the previous energy recovery control time is equal to the preset energy recovery control cycle, the current driving condition information is obtained based on the image acquisition and recognition of the road surface image of the current driving road, wherein the current driving condition information can be obtained by referring to the acquisition process of the road surface recognition result corresponding to the current road surface image in the above embodiment, so as to determine whether the current driving is on a flat road surface (which can be divided into a horizontal road surface, an uphill road surface, a downhill road surface, etc.), a pothole road surface, a slippery road surface or a construction road surface. After obtaining the current driving condition information and the driving user habit data, they can be used as input data of the output power intelligent control strategy to obtain the output power data set corresponding to the current target time period, and control the power output of the electric bicycle based on the output power data set in the current target time period. For example, if the current driving condition information corresponds to a pothole road and the driving user habit data is to maintain a low and constant speed driving, then in order to pass the pothole road more quickly, the initial output power data under the user's driving habit of maintaining a low and constant speed can be appropriately increased by a certain percentage (such as an increase of 10% to 30%) to obtain an output power data set corresponding to the current target time period. Among them, the time interval corresponding to the current target time period is [current system time, current system time + energy recovery control preset cycle).

[0038] It can be seen that the embodiment of the method can timely obtain the current driving environment perception data, the current vehicle status data and the current rider behavior monitoring data in the safe driving mode, and combine the road risk assessment strategy and the driving behavior assessment strategy to quickly determine the first driving risk assessment result and the second driving risk assessment result to judge whether there is a driving risk at present, and when there is a driving risk, timely perform corresponding control through the safe driving intervention strategy to ensure the driver's driving safety.

[0039] The embodiment of the present invention further provides an electric bicycle intelligent control system, which is used to execute any embodiment of the above-mentioned electric bicycle intelligent control method. Figure 6 , Figure 6 The following is a schematic block diagram of an electric bicycle intelligent control system provided by an embodiment of the present invention. Figure 6 As shown, the electric bicycle intelligent control system 100 includes a current detection data acquisition unit 110 , a first driving risk assessment unit 120 , a second driving risk assessment unit 130 and a safe driving intervention strategy execution unit 140 .

[0040] The current detection data acquisition unit 110 is used to respond to the safe driving intelligent detection instruction and obtain the current driving environment perception data, current vehicle status data and current rider behavior monitoring data corresponding to the safe driving intelligent detection instruction.

[0041] In this embodiment, the user can initially set the safe driving mode of the electric bicycle, such as setting the instruction generation cycle of the safe driving intelligent detection instruction to 5s, 10s, 15s, 20s, 30s, etc. When the electric bicycle generates safe driving intelligent detection instructions based on its internal processor according to the preset instruction generation cycle, the entire process can be executed once.

[0042] When the electric bicycle detects the currently generated safe driving intelligent detection instruction, it needs to obtain the current driving environment perception data, the current vehicle status data and the current rider behavior monitoring data. Among them, by setting environmental perception sensors (such as millimeter wave radar, laser radar, infrared sensor, positioning module, etc.), vehicle status sensors (such as inertial measurement unit, torque sensor, tire pressure monitoring system, etc.), and rider behavior monitoring devices (such as pressure sensors and rotation angle detection sensors on the handlebars, eye tracking cameras, etc.) on the electric bicycle, the current driving environment perception data can be detected by the environmental perception sensor, the current vehicle status data can be detected by the vehicle status sensor, and the current rider behavior monitoring data can be detected by the rider behavior monitoring device. The current driving environment perception data, current vehicle status data and current rider behavior monitoring data obtained can be comprehensively analyzed in the local processor of the electric bicycle or in the vehicle-road cooperative system connected to it, so as to determine whether there is a driving risk at present.

[0043] The first driving risk assessment unit 120 is used to determine a first driving risk assessment result based on a preset road surface risk assessment strategy, the current driving environment perception data and the current vehicle state data.

[0044] In this embodiment, after the current driving environment perception data and the current vehicle state data of the electric bicycle are obtained, they can be used as input data of the road risk assessment strategy, so as to analyze and obtain the first driving risk assessment result, and the obtained first driving risk assessment result is only used as the assessment result of the first dimension. Wherein, when the first driving risk assessment result takes a value of 1, it indicates that there is a driving risk, and when the first driving risk assessment result takes a value of 0, it indicates that there is no driving risk.

[0045] In one embodiment, the current driving environment perception data at least includes a current road surface image corresponding to the current driving road, current positioning data, and current road vehicle and pedestrian distribution data; the current vehicle state data at least includes a current vehicle driving speed and a current pedal stepping data sequence; as a first embodiment of the first driving risk assessment unit 120, the first driving risk assessment unit 120 is specifically used to: If it is determined based on the road risk assessment strategy that the road recognition result corresponding to the current road image, the positioning position result corresponding to the current positioning data, and the current road vehicle and pedestrian distribution data meet the first preset judgment condition, and it is determined based on the road risk assessment strategy that the current vehicle speed and the current pedal data sequence meet the second preset judgment condition, then the existence of driving risk is taken as the first driving risk assessment result; If it is determined based on the road surface risk assessment strategy that the road surface recognition result corresponding to the current road surface image, the positioning position result corresponding to the current positioning data, and the current road vehicle and pedestrian distribution data do not meet the first preset judgment condition, and it is determined based on the road surface risk assessment strategy that the current vehicle driving speed and the current pedal data sequence do not meet the second preset judgment condition, then the absence of driving risk is taken as the first driving risk assessment result.

[0046] In this embodiment, at least the current road surface image, current positioning data and current road vehicle and pedestrian distribution data of the current driving road can be obtained through the current driving environment perception data, and at least the current vehicle speed and current pedal stepping data sequence can be obtained through the current vehicle state data, and the above data or information obtained can be used as input parameters or input data of the road risk assessment strategy to perform specific driving risk assessment. Specifically, if it is determined based on the road risk assessment strategy that the road surface recognition result corresponding to the current road surface image, the positioning position result corresponding to the current positioning data and the current road vehicle and pedestrian distribution data meet the first preset judgment condition (the first preset judgment condition can be flexibly set based on the safe driving requirement), and it is determined based on the road risk assessment strategy that the current vehicle speed and the current pedal data sequence meet the second preset judgment condition (similarly, the second preset judgment condition can be flexibly set based on the safe driving requirement), once the current driving environment perception data meets the first preset judgment condition and the current vehicle state data meets the second preset judgment condition, there may be a driving risk as the first driving risk assessment result. If the current driving environment perception data does not meet the first preset judgment condition and the current vehicle status data does not meet the second preset judgment condition, then the absence of driving risk can be used as the first driving risk assessment result. If the current driving environment perception data meets the first preset judgment condition or the current vehicle status data meets the second preset judgment condition, then it can be considered that the electric bicycle has potential driving risks and a voice prompt can be given directly.

[0047] In one embodiment, the first preset judgment condition includes: the road surface recognition result corresponds to a preset road surface type, the current positioning data corresponds to a preset road type, and the current road vehicle and pedestrian distribution data exceeds a preset comprehensive traffic density; wherein; the preset road surface types include potholes, slippery roads and construction roads, and the preset road types include crossroads, three-way intersections, roundabouts and multi-way intersections; The second preset judgment condition includes: the current vehicle driving speed exceeds the preset driving speed threshold; there are mutation sequence values ​​in the current pedal data sequence, or the standard deviation of the current pedal data sequence exceeds the preset standard deviation threshold, or the statistical number of the current pedal data sequence that continuously exceeds the preset pedal force threshold exceeds the preset number threshold.

[0048] In this embodiment, as the first preset judgment condition and the second preset judgment condition specifically set in the first driving risk assessment unit 120, the driving risk is evaluated and analyzed mainly from five dimensions: whether the road surface recognition result corresponds to the preset road surface type, whether the current positioning data corresponds to the preset road type, whether the current road vehicle and pedestrian distribution data exceeds the preset comprehensive traffic density, whether the current vehicle driving speed exceeds the preset driving speed threshold, and whether there is a specified data feature in the current pedal data sequence (such as the existence of a mutation sequence value, or the standard deviation of the current pedal data sequence exceeds the preset standard deviation threshold, or the statistical number of the current pedal data sequence that continuously exceeds the preset pedal force threshold exceeds the preset number threshold).

[0049] Among them, because potholes, slippery roads and construction roads are more complex road types, crossroads, three-way intersections, roundabouts and multi-way intersections (which can be understood as five-way intersections or more) are road types with more complex road conditions. When the current road vehicle and pedestrian distribution data exceeds the preset comprehensive traffic density, it corresponds to a relatively crowded road condition. Therefore, when the current environment of the electric bicycle meets the above conditions, safe driving assistance is required. In determining whether the road surface recognition result corresponds to the preset road surface type, it can be determined by obtaining the recognition result corresponding to the collected current road surface image through the image recognition model in the road surface risk assessment strategy. For example, when the current road surface image corresponds to a flat road surface, the recognition result corresponds to a flat road surface; when the current road surface image corresponds to a pothole road surface, the recognition result corresponds to a pothole road surface; when the current road surface image corresponds to a non-dry road surface, the recognition result corresponds to a slippery road surface; when the current road surface image corresponds to a non-flat road surface and there are roadblock tools, the recognition result corresponds to a construction road surface, etc. When judging whether the current positioning data corresponds to the preset road type, the specific positioning position currently obtained by the positioning module (such as Beidou positioning module, etc.) on the electric bicycle can be combined with the electronic map data to determine whether it is at a road condition position of a crossroad, a three-way intersection, a roundabout or a multi-way intersection. When judging whether the current road vehicle and pedestrian distribution data exceeds the preset comprehensive traffic density, the total number of vehicles and pedestrians in a unit area at the location of the electric bicycle can be determined by the laser radar and infrared sensor on the electric bicycle. For example, if the sensing range of the laser radar and infrared sensor corresponds to an area of ​​N1 square meters and the total number of vehicles and pedestrians currently sensed is N2, then the current comprehensive traffic density corresponding to the current road vehicle and pedestrian distribution data is N2 / N1 per square meter (where N1 and N2 are both positive numbers). The comparison result of the current comprehensive traffic density N2 / N1 per square meter with the preset comprehensive traffic density determines whether the current road vehicle and pedestrian distribution data exceeds the preset comprehensive traffic density.

[0050] The electric bicycle will also continuously record the vehicle speed and current pedal data (such as the pedal pressure, and different pedal pressures correspond to different vehicle speeds). For example, a data queue that can store a fixed number of pedal pressures can be set in the memory corresponding to the controller of the electric bicycle. N3 pedal pressures can be stored through the data queue (where N3 is a positive integer), and the data storage mechanism of the data queue is first-in-first-out, that is, the data queue is initially filled with N3 pedal pressures in ascending order of the pedal pressure collection time. Before each new pedal pressure is stored, the pedal pressure currently ranked first is removed and the remaining pedal pressures are moved forward one arrangement position, and then the newly stored pedal pressure is stored at the end of the data queue. When the current vehicle speed and the current pedal data sequence of the electric bicycle are known (obtained from the above data queue), it is possible to specifically determine whether the vehicle speed exceeds the preset speed threshold, and it is also possible to determine whether there are mutation sequence values ​​in the current pedal data sequence (such as a pedal pressure that exceeds the preset change rate threshold or a change value exceeds the preset change value threshold compared to one or more previous pedal pressures), or the standard deviation of the current pedal data sequence exceeds the preset standard deviation threshold, or the statistical number of the current pedal data sequence that continuously exceeds the preset pedal force threshold exceeds the preset number threshold. It can be seen that based on the above first preset judgment condition and the second preset judgment condition, the first dimension of driving risk assessment can be performed from the current driving environment perception data and the current vehicle state data.

[0051] In one embodiment, the current driving environment perception data at least includes a current road surface image corresponding to the current driving road, current positioning data, and current road vehicle and pedestrian distribution data; the current vehicle state data at least includes a current vehicle driving speed and a current pedal stepping data sequence; as a second embodiment of the first driving risk assessment unit 120, the first driving risk assessment unit 120 is specifically used to: Obtaining a classification model corresponding to the road risk assessment strategy, and obtaining current input feature data consisting of a road recognition result identification value corresponding to the current road image, a road type identification value corresponding to the current positioning data, a comprehensive traffic density corresponding to the current road vehicle and pedestrian distribution data, the current vehicle speed, and the current pedal stepping data sequence; The current input feature data is input into the classification model to obtain the first driving risk assessment result.

[0052] In this embodiment, the difference from the first embodiment of the first driving risk assessment unit 120 is that artificial intelligence technology can also be combined to intelligently obtain the first driving risk assessment result, such as pre-storing the classification model corresponding to the road surface risk assessment strategy in the processor of the electric bicycle (or in the vehicle-road cooperative system), and inputting the current input feature data composed of the road surface recognition result identification value corresponding to the current road surface image, the road type identification value corresponding to the current positioning data, the comprehensive traffic density corresponding to the current road vehicle and pedestrian distribution data, the current vehicle driving speed and the current pedal stepping data sequence into the classification model (such as a random forest model, a decision tree model, etc.) to quickly obtain the first driving risk assessment result.

[0053] The second driving risk assessment unit 130 is used to determine a second driving risk assessment result based on a preset driving behavior assessment strategy and the current rider behavior monitoring data.

[0054] In this embodiment, after the current rider behavior monitoring data of the electric bicycle is obtained, it can be used as input data of the driving behavior evaluation strategy to analyze and obtain the second driving risk evaluation result, and the obtained second driving risk evaluation result is only used as the evaluation result of the second dimension. Wherein, when the second driving risk evaluation result is 1, it indicates that there is a driving risk, and when the second driving risk evaluation result is 0, it indicates that there is no driving risk.

[0055] In one embodiment, the current rider behavior monitoring data includes a current handlebar rotation angle data sequence and a rider sight direction recognition result sequence; the second driving risk assessment unit 130 is specifically used for: If it is determined based on the driving behavior assessment strategy that the current handlebar rotation angle data sequence and the rider's line of sight direction recognition result sequence meet a third preset judgment condition, then the existence of driving risk is taken as the second driving risk assessment result; If it is determined based on the driving behavior evaluation strategy that the current handlebar rotation angle data sequence and the rider's line of sight direction recognition result sequence do not meet the third preset judgment condition, then the second driving risk evaluation result is that there is no driving risk.

[0056] Among them, the third preset judgment condition includes the presence of a mutation sequence value in the current handlebar rotation angle data sequence; the number of changes in the recognition result of the rider's line of sight direction recognition result sequence exceeds a preset change number threshold.

[0057] In this embodiment, referring to the collection method and judgment method for the current pedal data sequence in the above embodiment, the current handlebar rotation angle data sequence can also be collected based on the rotation angle detection sensor on the handlebar (its storage method can also refer to the storage method of the current pedal data sequence in the data queue, that is, N4 handlebar rotation angles are stored in another data queue in a first-in-first-out manner, N4 is a positive integer), and the eye tracking camera set near the main control screen of the electric bicycle can collect the rider's line of sight direction image in time sequence and correspondingly identify the rider's line of sight direction recognition result sequence (its storage method can also refer to the storage method of the current pedal data sequence in the data queue, that is, N5 rider line of sight direction recognition results are stored in another data queue in a first-in-first-out manner, N5 is a positive integer). As the third preset judgment condition specifically set in the second driving risk assessment unit 130, the driving risk is also mainly evaluated and analyzed from two dimensions: whether there is a sudden change sequence value in the current handlebar rotation angle data sequence, and whether the number of changes in the recognition result in the rider's line of sight direction recognition result sequence exceeds the preset change number threshold.

[0058] When judging whether there is a mutation sequence value in the current handlebar rotation angle data sequence, it is mainly to judge whether there is a rotation angle data whose change rate exceeds another preset change rate threshold or whose change value exceeds another preset change value threshold compared with one or more previous rotation angle data. When judging whether the number of changes in the recognition result sequence of the rider's line of sight direction exceeds the preset change number threshold, each recognition result is compared with the previous recognition result. When the two recognition results are the same, it is deemed that there is no change and the number of changes in the recognition results is not counted. When the two recognition results are different, it is deemed that there is a change and the number of changes in the recognition results is counted. It can be seen that based on the above-mentioned third preset judgment condition, the second dimension of driving risk assessment can be performed from the current rider behavior monitoring data.

[0059] The safe driving intervention strategy execution unit 140 is used to perform corresponding safe driving control on the electric bicycle based on a preset safe driving intervention strategy if it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result.

[0060] In this embodiment, if it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result (wherein the preset risk assessment result is set to exist driving risk), it means that there is a high probability of driving risk at present, and at this time, the electric bicycle can be timely controlled for safe driving based on the preset safe driving intervention strategy, so as to ensure the driving safety of the driver. Among them, the safe driving intervention strategy can be specifically set to a preset duration of handlebar vibration (such as 5s, 10s, etc.), play a pre-stored safe driving prompt voice, automatically limit the speed to a preset driving speed threshold (such as 15km / h, 20km / h, etc.), etc.

[0061] In one embodiment, the electric bicycle intelligent control system 100 further includes: an energy recovery control instruction detection unit, configured to, if an intelligent energy recovery control instruction is detected, obtain current driving user information and an energy recovery control preset period corresponding to the intelligent energy recovery control instruction, and obtain driving user habit data in the current driving user information; a current driving condition information acquisition unit, configured to acquire the current driving condition information based on image acquisition and recognition of a road surface image of a current driving road if it is determined that the time interval between the current system time and the previous energy recovery control time is equal to the preset energy recovery control period; The output power data set acquisition unit is used to determine the output power data set corresponding to the current target time period based on a preset output power intelligent control strategy, the current driving condition information and the driving user habit data, and control the power output of the electric bicycle based on the output power data set during the current target time period.

[0062] In this embodiment, the energy recovery control mode can also be turned on on the electric bicycle at the same time. For example, another instruction generation cycle of the intelligent energy recovery control instruction is set to 5s, 10s, 15s, 20s, 30s, etc. When the electric bicycle generates an intelligent energy recovery control instruction based on the processor therein according to the other instruction generation cycle, the above steps can be executed once completely, that is, each round of intelligent energy recovery control is the same steps. In this application, the technical solution is first explained by the process of executing a complete set of steps.

[0063] When the electric bicycle detects the currently generated intelligent energy recovery control instruction, it is necessary to first obtain the current driving user information (which can be the user's preset entry setting, such as at least including the driving user ID and driving user habit data) and the energy recovery control preset period (such as set to 5min, 10min, 15min, 30min, 60min, etc. based on the actual duration set according to user needs), and obtain the driving user habit data in the current driving user information (such as maintaining low-speed and constant speed driving, medium-speed and constant speed driving, high-speed speed changing driving, etc.). After obtaining the above information, it is also possible to further determine whether the time interval between the current system time and the previous energy recovery control time is equal to the preset energy recovery control cycle. When it is determined that the time interval between the current system time and the previous energy recovery control time is equal to the preset energy recovery control cycle, the current driving condition information is obtained based on the image acquisition and recognition of the road surface image of the current driving road, wherein the current driving condition information can be obtained by referring to the acquisition process of the road surface recognition result corresponding to the current road surface image in the above embodiment, so as to determine whether the current driving is on a flat road surface (which can be divided into a horizontal road surface, an uphill road surface, a downhill road surface, etc.), a pothole road surface, a slippery road surface or a construction road surface. After obtaining the current driving condition information and the driving user habit data, they can be used as input data of the output power intelligent control strategy to obtain the output power data set corresponding to the current target time period, and control the power output of the electric bicycle based on the output power data set in the current target time period. For example, if the current driving condition information corresponds to a pothole road and the driving user habit data is to maintain a low and constant speed driving, then in order to pass the pothole road more quickly, the initial output power data under the user's driving habit of maintaining a low and constant speed can be appropriately increased by a certain percentage (such as an increase of 10% to 30%) to obtain an output power data set corresponding to the current target time period. Among them, the time interval corresponding to the current target time period is [current system time, current system time + energy recovery control preset cycle).

[0064] It can be seen that the implementation example of the device can timely obtain the current driving environment perception data, the current vehicle status data and the current rider behavior monitoring data in the safe driving mode, and combine the road risk assessment strategy and the driving behavior assessment strategy to quickly determine the first driving risk assessment result and the second driving risk assessment result to judge whether there is a driving risk at present. When there is a driving risk, corresponding control is carried out in time through the safe driving intervention strategy to ensure the driver's driving safety.

[0065] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0066] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0067] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0068] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. An intelligent control system for an electric bicycle, characterized in that: include: a current detection data acquisition unit, for responding to a safe driving intelligent detection instruction, acquiring current driving environment perception data, current vehicle state data, and current rider behavior monitoring data corresponding to the safe driving intelligent detection instruction; A first driving risk assessment unit, configured to determine a first driving risk assessment result based on a preset road surface risk assessment strategy, the current driving environment perception data, and the current vehicle state data; a second driving risk assessment unit, configured to determine a second driving risk assessment result based on a preset driving behavior assessment strategy and the current rider behavior monitoring data; The safe driving intervention strategy execution unit is used to perform corresponding safe driving control on the electric bicycle based on a preset safe driving intervention strategy if it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result.

2. The electric bicycle intelligent control system according to claim 1, characterized in that: The current driving environment perception data at least includes a current road surface image corresponding to the current driving road, current positioning data and current road vehicle and pedestrian distribution data; the current vehicle state data at least includes a current vehicle driving speed and a current pedal stepping data sequence; The first driving risk assessment unit is specifically used for: If it is determined based on the road risk assessment strategy that the road recognition result corresponding to the current road image, the positioning position result corresponding to the current positioning data, and the current road vehicle and pedestrian distribution data meet the first preset judgment condition, and it is determined based on the road risk assessment strategy that the current vehicle speed and the current pedal data sequence meet the second preset judgment condition, then the existence of driving risk is taken as the first driving risk assessment result; If it is determined based on the road surface risk assessment strategy that the road surface recognition result corresponding to the current road surface image, the positioning position result corresponding to the current positioning data, and the current road vehicle and pedestrian distribution data do not meet the first preset judgment condition, and it is determined based on the road surface risk assessment strategy that the current vehicle driving speed and the current pedal data sequence do not meet the second preset judgment condition, then the absence of driving risk is taken as the first driving risk assessment result.

3. The electric bicycle intelligent control system according to claim 2 is characterized in that: The first preset judgment condition includes: the road surface recognition result corresponds to a preset road surface type, the current positioning data corresponds to a preset road type, and the current road vehicle and pedestrian distribution data exceeds a preset comprehensive traffic density; wherein; the preset road surface types include potholes, slippery roads and construction roads, and the preset road types include crossroads, three-way intersections, roundabouts and multi-way intersections; The second preset judgment condition includes: the current vehicle driving speed exceeds the preset driving speed threshold; there are mutation sequence values ​​in the current pedal data sequence, or the standard deviation of the current pedal data sequence exceeds the preset standard deviation threshold, or the statistical number of the current pedal data sequence that continuously exceeds the preset pedal force threshold exceeds the preset number threshold.

4. An intelligent control method for an electric bicycle, characterized in that: include: In response to the safe driving intelligent detection instruction, obtaining current driving environment perception data, current vehicle status data and current rider behavior monitoring data corresponding to the safe driving intelligent detection instruction; Determining a first driving risk assessment result based on a preset road risk assessment strategy, the current driving environment perception data, and the current vehicle state data; Determining a second driving risk assessment result based on a preset driving behavior assessment strategy and the current rider behavior monitoring data; If it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result, corresponding safe driving control is performed on the electric bicycle based on a preset safe driving intervention strategy.

5. The method according to claim 4, characterized in that The current driving environment perception data at least includes a current road surface image corresponding to the current driving road, current positioning data and current road vehicle and pedestrian distribution data; the current vehicle state data at least includes a current vehicle driving speed and a current pedal stepping data sequence; The determining of a first driving risk assessment result based on a preset road risk assessment strategy, the current driving environment perception data, and the current vehicle state data includes: If it is determined based on the road risk assessment strategy that the road recognition result corresponding to the current road image, the positioning position result corresponding to the current positioning data, and the current road vehicle and pedestrian distribution data meet the first preset judgment condition, and it is determined based on the road risk assessment strategy that the current vehicle speed and the current pedal data sequence meet the second preset judgment condition, then the existence of driving risk is taken as the first driving risk assessment result; If it is determined based on the road surface risk assessment strategy that the road surface recognition result corresponding to the current road surface image, the positioning position result corresponding to the current positioning data, and the current road vehicle and pedestrian distribution data do not meet the first preset judgment condition, and it is determined based on the road surface risk assessment strategy that the current vehicle driving speed and the current pedal data sequence do not meet the second preset judgment condition, then the absence of driving risk is taken as the first driving risk assessment result.

6. The method according to claim 5, characterized in that The first preset judgment condition includes: the road surface recognition result corresponds to a preset road surface type, the current positioning data corresponds to a preset road type, and the current road vehicle and pedestrian distribution data exceeds a preset comprehensive traffic density; wherein; the preset road surface types include potholes, slippery roads and construction roads, and the preset road types include crossroads, three-way intersections, roundabouts and multi-way intersections; The second preset judgment condition includes: the current vehicle driving speed exceeds the preset driving speed threshold; there are mutation sequence values ​​in the current pedal data sequence, or the standard deviation of the current pedal data sequence exceeds the preset standard deviation threshold, or the statistical number of the current pedal data sequence that continuously exceeds the preset pedal force threshold exceeds the preset number threshold.

7. The method according to claim 4, characterized in that The current driving environment perception data at least includes a current road surface image corresponding to the current driving road, current positioning data and current road vehicle and pedestrian distribution data; the current vehicle state data at least includes a current vehicle driving speed and a current pedal stepping data sequence; The determining of a first driving risk assessment result based on a preset road risk assessment strategy, the current driving environment perception data, and the current vehicle state data includes: Obtaining a classification model corresponding to the road risk assessment strategy, and obtaining current input feature data consisting of a road recognition result identification value corresponding to the current road image, a road type identification value corresponding to the current positioning data, a comprehensive traffic density corresponding to the current road vehicle and pedestrian distribution data, the current vehicle speed, and the current pedal stepping data sequence; The current input feature data is input into the classification model to obtain the first driving risk assessment result.

8. The method according to claim 4, characterized in that The current rider behavior monitoring data includes a current handlebar rotation angle data sequence and a rider sight direction recognition result sequence; The determining of the second driving risk assessment result based on the preset driving behavior assessment strategy and the current rider behavior monitoring data includes: If it is determined based on the driving behavior assessment strategy that the current handlebar rotation angle data sequence and the rider's line of sight direction recognition result sequence meet a third preset judgment condition, then the existence of driving risk is taken as the second driving risk assessment result; If it is determined based on the driving behavior evaluation strategy that the current handlebar rotation angle data sequence and the rider's line of sight direction recognition result sequence do not meet the third preset judgment condition, then the second driving risk evaluation result is that there is no driving risk.

9. The method according to claim 8, characterized in that The third preset judgment condition includes the presence of a mutation sequence value in the current handlebar rotation angle data sequence; the number of changes in the recognition result of the rider's line of sight direction recognition result sequence exceeds a preset change number threshold.

10. The method according to claim 4, characterized in that After performing corresponding safe driving control on the electric bicycle based on a preset safe driving intervention strategy if it is determined that at least one of the first driving risk assessment result and the second driving risk assessment result corresponds to a preset risk assessment result, the method further includes: If an intelligent energy recovery control instruction is detected, obtaining current driving user information and energy recovery control preset cycle corresponding to the intelligent energy recovery control instruction, and obtaining driving user habit data in the current driving user information; If it is determined that the time interval between the current system time and the previous energy recovery control time is equal to the preset energy recovery control period, acquiring the current driving condition information based on image acquisition and recognition of the road surface image of the current driving road; Based on the preset output power intelligent control strategy, the current driving condition information and the driving user habit data, an output power data set corresponding to the current target time period is determined, and the power output of the electric bicycle is controlled based on the output power data set during the current target time period.

Images