Intelligent optimization method and system for intelligent bicycle tail lamp

Abstract

The invention relates to the technical field of bicycle tail lamps, in particular to an intelligent optimization method and system for an intelligent bicycle tail lamp, and the method comprises the steps: periodically collecting environment information and driving information in a bicycle driving process; determining a key characterization value based on the environment humidity and the vibration amplitude in the target time period to determine whether the target time period is marked or not; if the target time period is marked, the bicycle running state is determined based on the environment information and the running information in the target time period, so that bicycle tail lamp optimization modes are determined, and the bicycle tail lamp optimization modes comprise a tail lamp area optimization mode and a tail lamp brightness optimization mode. Intelligent adjustment and optimization of the bicycle tail lamp can be achieved, and the riding safety of the bicycle is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bicycle tail light, and in particular to an intelligent optimization method and system for an intelligent bicycle tail light. BACKGROUND

[0002] With the promotion of the "double carbon" goal and the deep popularization of the concept of green travel, bicycles are not only the core tool for short-distance commuting, but also an important carrier for fitness, leisure and other diversified scenarios. The global bicycle sales continue to rise, and the global market size has exceeded 60 billion US dollars in 2024. As the core pain point restricting the development of the industry, the safety of cycling has always been highly concerned by the industry chain and consumers. As the key warning component for conveying the intention of driving to the rear vehicles and pedestrians during cycling, the performance of the bicycle tail light directly determines the personal safety of the cyclist and becomes the core breakthrough for intelligent upgrading.

[0003] The traditional bicycle tail light has undergone three generations of development: "mechanical reflection - fixed light - simple electronic control". Although it has made a leap from "passive reflection" to "active light", there are still significant shortcomings in adaptability and warning accuracy in complex cycling scenarios. The early mechanical reflection type tail light relies on external light source reflection to achieve warning, which is completely ineffective in dark night, tunnel and other low light environments, and has been gradually eliminated by the market; the second generation of fixed light type tail light uses a single brightness LED light source, only supports constant light or fixed frequency flashing mode, and cannot adapt to different light environments, for example, insufficient brightness in strong light during the day makes it difficult for the following vehicle to detect, and excessive brightness in weak light at night easily causes the driver of the following vehicle to be dazzled, thereby increasing the safety hazard; the third generation of simple electronic control tail light introduces a light sensor to achieve basic brightness adjustment, but still cannot break through the limitation of "single parameter driving + fixed logic control", and cannot cope with complex and variable cycling scenarios and driving states, lacks a linkage mechanism for scenario screening and accurate response, so that the tail light cannot accurately match the driving state and cannot meet the safety warning demand in complex environments, making it difficult to realize intelligent adjustment and optimization of the bicycle tail light, resulting in low driving safety of the bicycle. SUMMARY

[0004] Therefore, the present application provides an intelligent optimization method and system for an intelligent bicycle tail light to overcome the problem that the prior art cannot realize intelligent adjustment and optimization of the bicycle tail light, resulting in low driving safety of the bicycle.

[0005] To achieve the above-mentioned purpose, in one aspect, the present application provides an intelligent optimization method for an intelligent bicycle tail light, comprising: periodically collecting environmental information and driving information during the driving of the bicycle, wherein the environmental information includes light intensity and environmental humidity, and the driving information includes driving speed, driving inclination angle and vibration amplitude; determine a key characteristic value based on the ambient humidity and the vibration amplitude in the target time period, to determine whether to mark the target time period; if the target time period is marked, determine a bicycle riding state based on the ambient information and the riding information in the target time period, to determine a bicycle tail light optimization mode, including a tail light area optimization mode and a tail light brightness optimization mode; wherein, for the tail light area optimization mode, determine a riding characteristic value based on the riding information in the target time period, to determine a tail light optimization area; for the tail light brightness optimization mode, determine a tail light brightness adjustment amount based on the riding speed in the target time period, or determine the tail light brightness adjustment amount based on the current ambient information.

[0006] Further, the key characteristic value is determined, including: construct an ambient humidity change curve based on the ambient humidity in the target time period, to determine a humidity characteristic value; construct a vibration change curve based on the vibration amplitude in the target time period, to determine a vibration characteristic value; determine the key characteristic value based on the humidity characteristic value and the vibration characteristic value.

[0007] Further, it is determined whether to mark the target time period based on the comparison result of the key characteristic value and the preset characteristic value.

[0008] Further, the bicycle riding state is determined, including: construct an illumination intensity change curve based on the illumination intensity in the target time period, to determine an illumination characteristic value; construct a riding speed change curve based on the riding speed in the target time period, to determine a first speed characteristic value; construct a riding inclination angle change curve based on the riding inclination angle in the target time period, to determine a first inclination angle characteristic value; determine the bicycle riding state based on the humidity characteristic value, the illumination characteristic value, the first speed characteristic value, and the first inclination angle characteristic value.

[0009] Further, the bicycle riding state is determined based on the comparison result of the humidity characteristic value and the first preset humidity threshold, the comparison result of the illumination characteristic value and the first preset illumination threshold, the comparison result of the first speed characteristic value and the preset speed threshold, and the comparison result of the first inclination angle characteristic value and the preset inclination angle threshold.

[0010] Further, the riding characteristic value is determined, including: determine a second speed characteristic value based on the comparison result of the maximum riding speed and the current riding speed in the target time period, and the key characteristic value; determining a second inclination angle characteristic value based on a comparison result of a maximum running inclination angle in the target time period and a current running inclination angle and the key characteristic value; determining a running characteristic value based on the second speed characteristic value and the second inclination angle characteristic value.

[0011] Further, determining a tail light optimization region, comprising: determining a first optimization adjustment coefficient based on a comparison result of the running characteristic value and a preset running threshold value; determining the tail light optimization region based on the first optimization adjustment coefficient and the bicycle running state.

[0012] Further, determining a tail light brightness adjustment amount based on a running speed in a target time period, comprising: determining a tail light brightness adjustment amount based on the second speed characteristic value and a preset tail light brightness.

[0013] Further, determining a tail light brightness adjustment amount based on current environmental information, comprising: determining a second optimization adjustment coefficient based on a comparison result of a current illumination intensity and a second preset illumination threshold value and a comparison result of a current environmental humidity and a second preset humidity threshold value; determining the tail light brightness adjustment amount based on the second optimization adjustment coefficient and the preset tail light brightness.

[0014] In another aspect, the present application also provides an intelligent optimization system, comprising: a data acquisition module, which is used to periodically acquire environmental information and running information in a bicycle running process, wherein the environmental information comprises illumination intensity and environmental humidity, and the running information comprises running speed, running inclination angle and vibration amplitude; a data analysis module, which is connected with the data acquisition module, and is used to determine a key characteristic value based on environmental humidity and vibration amplitude in a target time period, so as to determine whether to mark the target time period; an optimization analysis module, which is connected with the data acquisition module and the data analysis module respectively, and is used to determine a bicycle running state based on the environmental information and the running information in the target time period, so as to determine a bicycle tail light optimization mode, including a tail light region optimization mode and a tail light brightness optimization mode; For the tail light region optimization mode, a running characteristic value is determined based on the running information in the target time period, so as to determine a tail light optimization region. For the tail light brightness optimization mode, a tail light brightness adjustment amount is determined based on a running speed in a target time period, or a tail light brightness adjustment amount is determined based on current environmental information.

[0015] Compared with the prior art, the present application has the beneficial effects that, by periodically collecting environmental information and driving information during the driving of the bicycle, the present application can comprehensively perceive the changes in the riding environment, accurately monitor the driving process of the bicycle, and provide data support for subsequent tail light optimization adjustment. By determining the key characteristic value based on the environmental humidity and the vibration amplitude in the target time period to determine whether to mark the target time period, the time period with high safety risk can be quickly and accurately identified, avoiding invalid data processing of non-risk scenarios, providing a reference direction for subsequent tail light optimization by marking the target time period, realizing intelligent optimization of the bicycle tail light, reducing the data processing amount, and improving the optimization efficiency. By determining the bicycle driving state based on the environmental information and driving information in the target time period, the scene demand can be accurately subdivided, and the bicycle tail light optimization mode can be determined based on the bicycle driving state, so as to respond to the scene risk in a targeted manner, avoid a single fixed control logic, improve the visibility and warning effect of the bicycle in a complex environment, and improve the safety of the bicycle driving.

[0016] Further, the present application determines the humidity characteristic value based on the environmental humidity change in the target time period, can accurately capture the change trend of the environmental humidity, quantifies the influence degree of the environmental humidity on the bicycle driving safety, determines the vibration characteristic value based on the vibration amplitude change in the target time period, can accurately capture the change trend of the riding road surface state, quantifies the influence degree of the jolt vibration caused by the road surface condition on the bicycle driving safety, and determines the key characteristic value by comprehensively considering the humidity characteristic value and the vibration characteristic value, can quickly and accurately quantitatively analyze the safety risk degree existing in the target time period, realizes the fine division of the bicycle driving risk, and improves the optimization efficiency of the bicycle tail light.

[0017] Further, the present application determines the light intensity characteristic value based on the light intensity change in the target time period, can accurately capture the change trend of the light intensity, quantifies the influence degree of the light intensity on the bicycle driving safety, determines the first speed characteristic value based on the driving speed change in the target time period, can accurately capture the change trend of the driving speed, quantifies the influence degree of the driving speed on the bicycle driving safety, determines the first inclination angle characteristic value based on the driving inclination angle change in the target time period, can accurately capture the change trend of the driving inclination angle, quantifies the bicycle inclination type and the curve intensity, and realizes the turning and curve prediction. By determining the bicycle driving state based on the humidity characteristic value, the light intensity characteristic value, the speed characteristic value and the inclination angle characteristic value, multi-dimensional characteristic value fusion analysis can be realized, the bicycle driving state can be comprehensively evaluated, the tail light optimization demand can be more accurately identified, and the safety of the bicycle driving can be improved.

[0018] Further, the application can comprehensively consider the influence of environmental humidity and vibration amplitude on the driving speed by determining the second speed representation value based on the comparison result of the maximum driving speed in the target time period and the current driving speed in combination with the key guarantee value, and accurately quantifying the influence degree of the speed risk. The second inclination angle representation value can be determined by comparing the maximum driving inclination angle in the target time period with the current driving inclination angle in combination with the key representation value, so as to comprehensively consider the influence of environmental humidity and vibration amplitude on the driving inclination angle and accurately quantify the influence degree of the driving inclination angle. The driving representation value can be determined by comprehensively considering the second speed representation value and the second inclination angle representation value, so as to multi-dimensionally quantify the influence of the bicycle driving process on the tail light optimization, and further improve the accuracy of the tail light optimization. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 A flowchart of the intelligent optimization method for the intelligent bicycle tail light according to the embodiment of the application is shown in FIG. 2. Figure 2 A flowchart of determining the key representation value according to the embodiment of the application is shown in FIG. 3. Figure 3 A flowchart of determining the driving representation value according to the embodiment of the application is shown in FIG. 4. Figure 4 A structure block diagram of the intelligent optimization system according to the embodiment of the application is shown in FIG. 5. DETAILED DESCRIPTION

[0020] In order to make the objects and advantages of the application clearer, the application will be further described below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and not to limit the protection scope of the application.

[0021] The preferred embodiments of the application will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the application, and are not intended to limit the protection scope of the application.

[0022] It should be noted that in the description of the application, the terms "upper", "lower", "left", "right", "inner", "outer" and the like indicate the direction or positional relationship terms based on the direction or positional relationship shown in the drawings, which are only for the convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the application.

[0023] Moreover, it needs to be explained that, in the description of the present application, unless explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium, or it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0024] Please refer to Figure 1 As shown in the figure, it is a flowchart of the intelligent optimization method for the intelligent bicycle tail light according to the embodiment of the present application; the embodiment of the present application provides an intelligent optimization method for the intelligent bicycle tail light, which comprises the following steps: Step S1, periodically collecting the environment information and the driving information during the driving of the bicycle, wherein the environment information comprises the illumination intensity and the environmental humidity, and the driving information comprises the driving speed, the driving inclination angle and the vibration amplitude; In the implementation, the specific structure of the collected environment information and driving information is not limited, which is the prior art, any collection device or method capable of collecting environment information and driving information in the prior art falls within the protection scope of the present application, and will not be described here. The collection period is not limited specifically, and can be determined based on the sampling frequency of the collection device or sensor.

[0025] Step S2, determining a key characteristic value based on the environmental humidity and the vibration amplitude in a target time period, to determine whether to mark the target time period; In the implementation, the target time period can be set based on the actual situation, and preferably, the target time period is set to 3s-5s.

[0026] Please refer to Figure 2 As shown in the figure, it is a flowchart of the intelligent optimization method for the intelligent bicycle tail light according to the embodiment of the present application; the embodiment of the present application provides an intelligent optimization method for the intelligent bicycle tail light, which comprises the following steps: Step S21, constructing an environmental humidity change curve based on the environmental humidity in the target time period, to determine a humidity characteristic value; In implementation, the data is fitted to construct the environmental humidity change curve with the collection time as independent variable and the environmental humidity of each collection as dependent variable, the humidity mutation time point is determined based on the environmental humidity change curve, the slope of each position of the environmental humidity change curve can be calculated, and the time point with the maximum absolute value of the slope is determined as the humidity mutation time point (not necessarily the collection time point, but any point on the curve), then the humidity representation value is determined according to the environmental humidity of the humidity mutation time point and the adjacent collection time points before and after the humidity mutation time point, for example, the environmental humidity of the humidity mutation time point is S1, the environmental humidity of the collection time point before the humidity mutation time point is S0, and the environmental humidity of the collection time point after the humidity mutation time point is S2, then the humidity representation value SB=(S2-S1) / (S1-S0).

[0027] In step S22, a vibration change curve is constructed based on the vibration amplitudes in the target time period to determine a vibration representation value. In implementation, the data is fitted to construct the vibration amplitude change curve with the collection time as independent variable and the vibration amplitude of each collection as dependent variable, the vibration mutation time point is determined based on the vibration amplitude change curve, the slope of each position of the vibration amplitude change curve can be calculated, and the time point with the maximum absolute value of the slope is determined as the vibration mutation time point (not necessarily the collection time point, but any point on the curve), then the vibration representation value is determined according to the vibration amplitude of the vibration mutation time point and the adjacent collection time points before and after the vibration mutation time point, for example, the vibration amplitude of the vibration mutation time point is Z1, the vibration amplitude of the collection time point before the vibration mutation time point is Z0, and the vibration amplitude of the collection time point after the vibration mutation time point is Z2, then the vibration representation value ZB=(Z2-Z1) / (Z1-Z0).

[0028] In step S23, the key representation value is determined based on the humidity representation value and the vibration representation value.

[0029] In implementation, the mean value of the humidity representation value and the vibration representation value is determined as the key representation value.

[0030] Specifically, in the step S2, it is determined whether to mark the target time period based on the comparison result of the key representation value and the preset representation value.

[0031] In implementation, if the key representation value is greater than the preset representation value, it is determined to mark the target time period, and if the key representation value is less than or equal to the preset representation value, it is determined not to mark the target time period, and the actual implementer can set the preset representation value based on the actual situation or the minimum value of the key representation value corresponding to the markable time period in the historical data that passes the qualification test.

[0032] Specifically, the application determines the humidity representation value according to the change of the environmental humidity in the target time period, can accurately capture the change trend of the environmental humidity, quantifies the influence degree of the environmental humidity on the bicycle driving safety, determines the vibration representation value according to the change of the vibration amplitude in the target time period, can accurately capture the change trend of the riding road surface state, quantifies the influence degree of the jolt vibration caused by the road surface state on the bicycle driving safety, determines the key representation value by comprehensively considering the humidity representation value and the vibration representation value, can quickly and accurately quantitatively analyze the safety risk degree existing in the target time period, realizes the fine division of the bicycle driving risk, and improves the optimization efficiency of the bicycle tail light.

[0033] In step S3, if the target time period is marked, the bicycle driving state is determined based on the environmental information and the driving information in the target time period, so as to determine the bicycle tail light optimization mode, including the tail light area optimization mode and the tail light brightness optimization mode. Specifically, in the step S3, the bicycle driving state is determined, including: In step S31, the illumination intensity change curve is constructed based on the illumination intensity in the target time period, so as to determine the illumination representation value. In the implementation, the illumination intensity change curve can be constructed by taking the collection time as the independent variable and the illumination intensity of each collection as the dependent variable. The illumination mutation time point can be determined based on the illumination intensity change curve. The slope of each position of the illumination intensity change curve can be calculated, and the time point with the maximum absolute value of the slope is determined as the illumination mutation time point (which is not necessarily a collection time point, but can be any point on the curve). Then, the illumination representation value is determined according to the illumination intensity of the illumination mutation time point and the adjacent collection time points before and after the illumination mutation time point. For example, the illumination intensity of the illumination mutation time point is G1, the illumination intensity of the collection time point before the illumination mutation time point is G0, and the illumination intensity of the collection time point after the illumination mutation time point is G2. Then, the illumination representation value GB=(G2-G1) / (G1-G0).

[0034] In step S32, the driving speed change curve is constructed based on the driving speed in the target time period, so as to determine the first speed representation value. In implementation, the driving speed change curve can be constructed with the collection time as independent variable and the driving speed of each collection as dependent variable, the speed mutation time point can be determined based on the driving speed change curve, the slope of each position of the driving speed change curve can be calculated, and the time point with the maximum absolute value of the slope is determined as the speed mutation time point (not necessarily the collection time point, but any point on the curve), then the first speed characteristic value is determined according to the driving speed of the speed mutation time point and the driving speed of the adjacent collection time points before and after the speed mutation time point, for example, the driving speed of the speed mutation time point is V1, the driving speed of the collection time point before the speed mutation time point is V0, the driving speed of the collection time point after the speed mutation time point is V2, then the first speed characteristic value VB=(V2-V1) / (V1-V0).

[0035] In step S33, the inclination angle change curve is constructed based on the driving inclination angle in the target time period to determine the first inclination angle characteristic value. In implementation, the driving inclination angle change curve can be constructed with the collection time as independent variable and the driving inclination angle of each collection as dependent variable, the inclination angle mutation time point can be determined based on the driving inclination angle change curve, the slope of each position of the driving inclination angle change curve can be calculated, and the time point with the maximum absolute value of the slope is determined as the inclination angle mutation time point (not necessarily the collection time point, but any point on the curve), then the first inclination angle characteristic value is determined according to the driving inclination angle of the inclination angle mutation time point and the driving inclination angle of the adjacent collection time points before and after the inclination angle mutation time point, for example, the driving inclination angle of the inclination angle mutation time point is W1, the driving inclination angle of the collection time point before the inclination angle mutation time point is W0, the driving inclination angle of the collection time point after the inclination angle mutation time point is W2, then the first inclination angle characteristic value WB=(W2-W1) / (W1-W0).

[0036] In step S34, the bicycle driving state is determined based on the humidity characteristic value, the illumination characteristic value, the first speed characteristic value and the first inclination angle characteristic value.

[0037] In implementation, the actual implementer can set the bicycle driving state reference table based on actual situation, and the bicycle driving state includes humidity exceeding state (rain or fog), dim state (overcast or night and the like), sudden braking state, turning state (lane changing or turning) and normal driving state.

[0038] Specifically, in step S3, the bicycle driving state is determined based on the comparison result of the humidity characteristic value and the first preset humidity threshold, the comparison result of the illumination characteristic value and the first preset illumination threshold, the comparison result of the first speed characteristic value and the preset speed threshold, and the comparison result of the first inclination angle characteristic value and the preset inclination angle threshold.

[0039] In a specific embodiment, if the humidity characteristic value is greater than a first preset humidity threshold, the bicycle driving state is determined as a humidity exceeding state, if the illumination characteristic value is less than a first preset illumination threshold, the bicycle driving state is determined as a dim state, if the first speed characteristic value is less than a preset speed threshold, the bicycle driving state is determined as a sudden braking state, if the first inclination angle characteristic value is greater than a preset inclination angle threshold, the bicycle driving state is determined as a variable turning state, otherwise, the bicycle driving state is determined as a normal driving state.

[0040] It can be understood that the actual implementer can set the first preset humidity threshold based on the mean value of the humidity characteristic value that passes the qualification test in the actual situation or historical data, the actual implementer can set the first preset illumination threshold based on the mean value of the illumination characteristic value that passes the qualification test in the actual situation or historical data, the actual implementer can set the preset speed threshold based on the mean value of the first speed characteristic value that passes the qualification test in the actual situation or historical data, and the actual implementer can set the preset inclination angle threshold based on the mean value of the first inclination angle characteristic value that passes the qualification test in the actual situation or historical data.

[0041] Specifically, the application can accurately capture the change trend of the illumination intensity, quantify the influence degree of the illumination intensity on the bicycle driving safety by determining the illumination characteristic value based on the illumination intensity change in the target time period, accurately capture the change trend of the driving speed, quantify the influence degree of the driving speed on the bicycle driving safety by determining the first speed characteristic value based on the driving speed change in the target time period, accurately capture the change trend of the driving inclination angle, quantify the bicycle inclination type and the curve intensity by determining the first inclination angle characteristic value based on the driving inclination angle change in the target time period, and realize turning and curve prediction. The bicycle driving state is determined by the humidity characteristic value, the illumination characteristic value, the speed characteristic value and the inclination angle characteristic value, which can realize multi-dimensional characteristic value fusion analysis, comprehensively evaluate the bicycle driving state, and thus more accurately identify the tail light optimization demand and improve the bicycle driving safety.

[0042] Among them, for the tail light area optimization mode, the driving characteristic value is determined based on the driving information in the target time period to determine the tail light optimization area. Please refer to Figure 3 As shown in the figure, it is a flowchart of determining the driving characteristic value according to an embodiment of the application; specifically, in step S3, the driving characteristic value is determined, including: Step S351, determining a second speed characteristic value based on the comparison result of the maximum driving speed and the current driving speed in the target time period and the key characteristic value; In implementation, the difference between the maximum driving speed and the current driving speed is determined as a first difference value, the ratio of the first difference value to the current driving speed is determined as a first characteristic value, and the product of the first characteristic value and the key characteristic value is determined as a second speed characteristic value.

[0043] Step S352, determining a second slope angle characteristic value based on the comparison result of the maximum driving slope angle and the current driving slope angle within the target time period and the key characteristic value; In implementation, the difference between the maximum driving slope angle and the current driving slope angle is determined as a second difference value, the ratio of the second difference value to the current driving slope angle is determined as a second characteristic value, and the product of the second characteristic value and the key characteristic value is determined as the second slope angle characteristic value.

[0044] Step S353, determining a driving characteristic value based on the second speed characteristic value and the second slope angle characteristic value.

[0045] In implementation, the average of the second speed characteristic value and the second slope angle characteristic value is determined as the driving characteristic value.

[0046] Specifically, in the step S3, the tail light optimization region is determined, including: Step S361, determining a first optimization adjustment coefficient based on the comparison result of the driving characteristic value and a preset driving threshold value; In implementation, the ratio of the driving characteristic value to the preset driving threshold value is determined as the first optimization adjustment coefficient.

[0047] Step S362, determining the tail light optimization region based on the first optimization adjustment coefficient and the bicycle driving state.

[0048] In the implementation, the tail light area is divided into an initial warning area and an optimized warning area, the initial warning area is located at the center of the tail light area, and the optimized warning area is located at the periphery of the initial warning area. Each bicycle driving state has a corresponding initial tail light warning area. The tail light area is evenly divided into a plurality of grids. The actual implementer can set the number of grids corresponding to each bicycle driving state based on the actual situation. For example, the normal driving state corresponds to the entire area of the tail light area, and the tail light brightness can be set to 0 without adjusting the tail light brightness. The initial tail light warning area corresponding to the humidity exceeding state and the dim state is the entire area of the initial warning area (the brightness of the optimized warning area can be set to 0), and the brightness of the initial tail light warning area corresponding to the humidity exceeding state and the dim state can be different. The tail light brightness corresponding to the humidity exceeding state can be set to 1.5, and the tail light brightness corresponding to the dim state can be set to 2. The initial tail light warning area corresponding to the emergency braking state is the entire area of the optimized warning area (the brightness of the initial warning area can be set to 0), and the corresponding tail light brightness can be set to 1.5. The initial warning area is evenly divided into left and right parts in the variable turning state. The left turn or left lane change corresponds to the left part of the initial warning area, and the right turn or right lane change corresponds to the right part of the initial warning area. When the bicycle is turning left or changing lanes to the left, the tail light brightness corresponding to the left part of the initial warning area can be set to 1.5, and the tail light brightness of the remaining areas can be set to 0. When the bicycle is turning right or changing lanes to the right, the tail light brightness corresponding to the right part of the initial warning area can be set to 1.5, and the tail light brightness of the remaining areas can be set to 0. The tail light brightness of each area corresponding to each bicycle driving state can be superimposed. For example, the tail light brightness corresponding to the humidity exceeding state is 1.5, and the tail light brightness corresponding to the dim state is 2. If the bicycle driving state is both the humidity exceeding state and the dim state, the corresponding tail light brightness can be set to 1.5+2=3.5. It should be noted that the above brightness is only to illustrate the difference in tail light brightness corresponding to each bicycle driving state. The actual implementer can set the tail light brightness based on the actual situation.

[0049] It can be understood that for each bicycle driving state, the number of grid increases is determined based on the product of the first optimization adjustment coefficient and the number of grids in the area corresponding to each bicycle driving state, and the brightness of the grids outside the area corresponding to each bicycle driving state is adjusted according to the number of grid increases. For example, for the humidity exceeding state and the dim state, the number of grid increases is determined based on the product of the first optimization adjustment coefficient and the number of grids in the initial warning area, and the brightness of the grids adjacent to the initial warning area in the optimized warning area is adjusted according to the number of grid increases. The remaining grids adjacent to the area corresponding to each bicycle driving state are preferentially adjusted. The same applies to the above.

[0050] Specifically, the application can comprehensively consider the influence of environmental humidity and vibration amplitude on driving speed by determining the second speed representation value based on the comparison result of the maximum driving speed in the target time period and the current driving speed in combination with the key guarantee value, and accurately quantifying the influence degree of speed risk. By determining the second tilt angle representation value based on the comparison result of the maximum driving tilt angle in the target time period and the current driving tilt angle in combination with the key representation value, the influence of environmental humidity and vibration amplitude on driving tilt angle can be comprehensively considered, and the influence degree of driving tilt angle can be accurately quantified. By determining the driving representation value by comprehensively considering the second speed representation value and the second tilt angle representation value, the influence of the bicycle driving process on the tail light optimization can be quantified in multiple dimensions, and the accuracy of the tail light optimization can be further improved.

[0051] For the tail light brightness optimization mode, the tail light brightness adjustment amount is determined based on the driving speed in the target time period, or the tail light brightness adjustment amount is determined based on the current environmental information.

[0052] Specifically, in the step S3, the tail light brightness adjustment amount is determined based on the driving speed in the target time period, comprising: The tail light brightness adjustment amount is determined based on the second speed representation value and the preset tail light brightness.

[0053] In implementation, the product of the second speed representation value and the preset tail light brightness is determined as the tail light brightness adjustment amount, and the sum of the tail light brightness before optimization and the tail light brightness adjustment amount is determined as the tail light brightness after optimization.

[0054] It can be understood that the actual implementer can set the preset tail light brightness based on the actual situation, or set the preset tail light brightness based on the current illumination intensity.

[0055] Specifically, in the step S3, the tail light brightness adjustment amount is determined based on the current environmental information, comprising: Step S371, determining a second optimization adjustment coefficient based on the comparison result of the current illumination intensity and the second preset illumination threshold value, and the comparison result of the current environmental humidity and the second preset humidity threshold value; Step S372, determining the tail light brightness adjustment amount based on the second optimization adjustment coefficient and the preset tail light brightness.

[0056] In implementation, the ratio of the current illumination intensity to the second preset illumination intensity is determined as a third feature value, the ratio of the current environmental humidity to the second preset humidity threshold value is determined as a fourth feature value, and the average of the third feature value and the fourth feature value is determined as the second optimization adjustment coefficient. The actual implementer can set the second preset illumination intensity based on the actual situation or based on the illumination intensity at 12 o'clock on a sunny day, and the actual implementer can set the second preset humidity threshold value based on the actual situation or based on the environmental humidity when the horizontal visibility is less than 1 km.

[0057] It can be understood that the product of the second optimization adjustment coefficient and the preset tail lamp brightness is determined as the tail lamp brightness adjustment amount.

[0058] Specifically, the present application can comprehensively perceive the change of the riding environment and accurately monitor the bicycle driving process by periodically collecting environmental information and driving information during the bicycle driving process, thereby providing data support for subsequent tail lamp optimization adjustment. By determining the key characteristic value based on the environmental humidity and the vibration amplitude in the target time period to determine whether to mark the target time period, the time period with high safety risk can be quickly and accurately identified, thereby avoiding invalid data processing of non-risk scenarios, providing a reference direction for subsequent tail lamp optimization by marking the target time period, realizing intelligent optimization of the bicycle tail lamp, reducing the data processing amount, and improving the optimization efficiency. By determining the bicycle driving state based on the environmental information and the driving information in the target time period, the scene demand can be accurately subdivided, and the bicycle tail lamp optimization mode can be determined based on the bicycle driving state, thereby responding to the scene risk in a targeted manner, avoiding a single fixed control logic, improving the visibility and warning effect of the bicycle in a complex environment, and improving the safety of the bicycle driving.

[0059] Referring to Figure 4 The present application also provides an intelligent optimization system, which comprises: A data collection module is configured to periodically collect environmental information and driving information during the bicycle driving process, wherein the environmental information comprises the illumination intensity and the environmental humidity, and the driving information comprises the driving speed, the driving inclination angle, and the vibration amplitude. A data analysis module is connected to the data collection module and is configured to determine a key characteristic value based on the environmental humidity and the vibration amplitude in a target time period to determine whether to mark the target time period. An optimization analysis module is connected to the data collection module and the data analysis module and is configured to determine a bicycle driving state based on the environmental information and the driving information in the target time period to determine a bicycle tail lamp optimization mode, which comprises a tail lamp area optimization mode and a tail lamp brightness optimization mode. For the tail lamp area optimization mode, a driving characteristic value is determined based on the driving information in the target time period to determine a tail lamp optimization area. For the tail lamp brightness optimization mode, a tail lamp brightness adjustment amount is determined based on the driving speed in the target time period, or a tail lamp brightness adjustment amount is determined based on the current environmental information.

[0060] Specifically, the intelligent optimization system provided by the present application embodiment can adopt the above-mentioned intelligent optimization method for intelligent bicycle tail lamp to achieve the same technical effects, which will not be described here again.

[0061] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after these changes or replacements will all fall within the protection scope of the present application.

Claims

1. A method for intelligent optimization of a smart bicycle tail light, characterized in that, The method comprises: periodically collecting environmental information and travel information during bicycle travel, wherein the environmental information includes light intensity and environmental humidity, and the travel information includes travel speed, travel inclination angle and vibration amplitude; determining a key characteristic value based on the environmental humidity and the vibration amplitude in a target time period to determine whether to mark the target time period; if the target time period is marked, determining a bicycle travel state based on the environmental information and the travel information in the target time period to determine a bicycle taillight optimization mode, including a taillight area optimization mode and a taillight brightness optimization mode; wherein for the taillight area optimization mode, a travel characteristic value is determined based on the travel information in the target time period to determine a taillight optimization area; for the taillight brightness optimization mode, a taillight brightness adjustment amount is determined based on the travel speed in the target time period, or a taillight brightness adjustment amount is determined based on the current environmental information.

2. The method of intelligent optimization for a smart bicycle tail light according to claim 1, wherein, Determining a key characteristic value comprises: constructing an environmental humidity change curve based on the environmental humidity in the target time period to determine a humidity characteristic value; constructing a vibration change curve based on the vibration amplitude in the target time period to determine a vibration characteristic value; determining the key characteristic value based on the humidity characteristic value and the vibration characteristic value.

3. The method of intelligent optimization for a smart bicycle tail light according to claim 2, wherein, Determining whether to mark the target time period based on the comparison result of the key characteristic value and the preset characteristic value.

4. The method for intelligent optimization of a smart bicycle tail light according to claim 3, wherein, Determining a bicycle travel state comprises: constructing a light intensity change curve based on the light intensity in the target time period to determine a light intensity characteristic value; constructing a travel speed change curve based on the travel speed in the target time period to determine a first speed characteristic value; constructing an inclination angle change curve based on the travel inclination angle in the target time period to determine a first inclination angle characteristic value; determining the bicycle travel state based on the humidity characteristic value, the light intensity characteristic value, the first speed characteristic value and the first inclination angle characteristic value.

5. The method of intelligent optimization for a smart bicycle tail light according to claim 4, wherein, Determining the bicycle travel state based on the comparison result of the humidity characteristic value and the first preset humidity threshold, the comparison result of the light intensity characteristic value and the first preset light intensity threshold, the comparison result of the first speed characteristic value and the preset speed threshold, and the comparison result of the first inclination angle characteristic value and the preset inclination angle threshold.

6. The method of intelligent optimization for a smart bicycle tail light according to claim 5, wherein, Determining a travel characteristic value comprises: determining a second speed characteristic value based on the comparison result of the maximum travel speed and the current travel speed in the target time period and the key characteristic value; determining a second inclination angle characteristic value based on the comparison result of the maximum travel inclination angle and the current travel inclination angle in the target time period and the key characteristic value; determining the travel characteristic value based on the second speed characteristic value and the second inclination angle characteristic value.

7. The method of intelligent optimization for a smart bicycle tail light according to claim 6, wherein, Determining a taillight optimization area comprises: determining a first optimization adjustment coefficient based on the comparison result of the travel characteristic value and the preset travel threshold; determining the taillight optimization area based on the first optimization adjustment coefficient and the bicycle travel state.

8. The method for intelligent optimization of a smart bicycle tail light according to claim 7, wherein, Determining a taillight brightness adjustment amount based on the travel speed in the target time period comprises: determining a taillight brightness adjustment amount based on the second speed characteristic value and the preset taillight brightness.

9. The method for intelligent optimization of a smart bicycle tail light according to claim 8, wherein, Determine the tail light brightness adjustment amount based on the current environmental information, comprising: Determine the second optimization adjustment coefficient based on the comparison result of the current light intensity and the second preset light threshold, and the comparison result of the current environmental humidity and the second preset humidity threshold; Determine the tail light brightness adjustment amount based on the second optimization adjustment coefficient and the preset tail light brightness.

10. An intelligent optimization system employing the intelligent optimization method for an intelligent bicycle tail light according to any one of claims 1-9, characterized in that, Comprise: Data acquisition module, used to periodically collect environmental information and travel information during bicycle travel, wherein the environmental information includes light intensity and environmental humidity, and the travel information includes travel speed, travel inclination angle and vibration amplitude; Data analysis module connected with the data acquisition module, used to determine whether to mark the target time period based on the environmental humidity and the vibration amplitude in the target time period to determine the key characteristic value; Optimization analysis module connected with the data acquisition module and the data analysis module respectively, used to determine the bicycle travel state based on the environmental information and the travel information in the target time period to determine the bicycle tail light optimization mode, including tail light area optimization mode and tail light brightness optimization mode; For the tail light area optimization mode, determine the travel characteristic value based on the travel information in the target time period to determine the tail light optimization area; For the tail light brightness optimization mode, determine the tail light brightness adjustment amount based on the travel speed in the target time period, or determine the tail light brightness adjustment amount based on the current environmental information.

Images