Sentry mode sensitivity adjustment method and apparatus

Abstract

A sentry mode sensitivity adjustment method and apparatus. The adjustment method comprises: acquiring noise data, illumination data, environmental image data, and traffic flow data; on the basis of the noise data, the illumination data, the environmental image data and the traffic flow data, obtaining a corresponding target noise weight, a corresponding target illumination weight, a corresponding target collision weight, and a corresponding target traffic flow weight; obtaining a target safety level on the basis of the target noise weight, the target illumination weight, the target collision weight and the target traffic flow weight; and on the basis of the target safety level, adjusting the sensitivity of a sentry mode.

Description

A method and apparatus for adjusting the sensitivity of sentry mode Technical Field

[0001] This application relates to the field of intelligent early warning technology, and in particular to a method and apparatus for adjusting the sensitivity of sentry mode. Background Technology

[0002] Sentry mode in intelligent vehicles is an important security feature that monitors the surrounding environment when the vehicle is parked and issues alarms or records events in case of anomalies. Traditional sentry mode requires users to manually set sensitivity levels, such as low, medium, and high. However, this manual setting method cannot adapt to different environments: varying ambient noise levels, lighting conditions, and pedestrian traffic can all affect the triggering of sentry mode. Manually set sensitivity cannot accommodate these changes, easily leading to false alarms or missed alarms. Summary of the Invention

[0003] To address this issue, this application provides a method and apparatus for adjusting the sensitivity of the sentinel mode, thereby resolving the problem of false alarms or missed alarms that can easily occur due to manually set sensitivity in the prior art.

[0004] Firstly, a method for adjusting the sensitivity of sentry mode is provided, the method comprising:

[0005] Each time, sensing data is acquired; the sensing data includes noise data, illumination data, environmental image data, and traffic flow data;

[0006] The target weights are obtained based on the perceived data; the target weights include noise target weights, illumination target weights, collision target weights, and traffic flow target weights.

[0007] The target security level is obtained based on the perceived data and the target weight;

[0008] Adjust the sensitivity of the sentry mode according to the target security level.

[0009] In some embodiments, obtaining the target weight based on the perceived data includes:

[0010] Initial weights are obtained through fuzzy preprocessing based on the perceived data; the initial weights include initial weights for noise, illumination, collision, and traffic flow.

[0011] The initial weights are normalized to obtain the target weights.

[0012] In some embodiments, the fuzzing preprocessing includes:

[0013] Noise weights are obtained based on the noise data and a preset noise mapping table; illumination weights are obtained based on the illumination data and a preset illumination mapping table; collision coefficients are obtained based on the environmental image data using existing target detection and motion analysis algorithms, and collision weights are obtained based on the collision coefficients and a preset coefficient mapping table; traffic flow weights are obtained based on traffic flow data and a preset traffic flow mapping table.

[0014] The initial weights are obtained by adjusting the noise weights, illumination weights, collision weights, or traffic flow weights according to the preprocessing algorithm.

[0015] In some embodiments, the preprocessing algorithm includes: when the current time point is within a preset nighttime time range, nighttime preprocessing is performed; the nighttime preprocessing includes: if the noise value in the noise data is greater than a preset noise value, and the first light intensity value in the light data is less than a first preset light intensity, then the noise weight is adjusted according to the noise value to obtain an initial noise weight, and the light weight is adjusted according to the first light intensity value to obtain an initial light weight.

[0016] When the current time point is within the preset daytime range, daytime preprocessing is adopted; the daytime preprocessing includes: if the second light intensity value in the light data is greater than the second preset light intensity, then the collision weight is adjusted according to the second light intensity value to obtain the initial collision weight, and the traffic flow weight is adjusted according to the second light intensity value to obtain the initial traffic flow weight.

[0017] When the collision coefficient is greater than a preset collision coefficient, collision hazard preprocessing is performed; the collision hazard preprocessing includes: adjusting the collision weight, the illumination weight, and the noise weight according to the collision coefficient;

[0018] The preprocessing priority of the collision hazard preprocessing is higher than that of the nighttime preprocessing and the daytime preprocessing.

[0019] In some embodiments, the step of normalizing the initial weights to obtain the target weights includes:

[0020] The target weight is obtained through a weight normalization formula, which is: Among them, W i_n Let W be the weight of target i, i∈{N,L,O,C}, where N represents noise, L represents illumination, O represents collision, and C represents traffic flow; i The initial weights are i; W N W represents the initial noise weights. L W represents the initial illumination weights. O W represents the initial collision weights. C This is the initial traffic flow weight.

[0021] In some embodiments, obtaining the target security level based on the perceived data and the target weight includes:

[0022] The target security level is obtained based on the security level formula, which is: Where S represents the target security level; W N_n For the target weight of noise; D N The noise membership degree is obtained based on noise data; W L_n D represents the target weight for illumination. L W represents the membership degree of illumination obtained based on illumination data. O_n D represents the collision target weights. O The collision membership degree is obtained based on environmental image data; W C_n Traffic flow target weight; D C This refers to the membership degree of traffic flow obtained based on traffic flow data.

[0023] In some embodiments, adjusting the sensitivity of the sentry mode according to the target security level includes:

[0024] The target sensitivity is obtained by using a preset sensitivity mapping table based on the target security level.

[0025] Adjust the sensitivity of the sentry mode to match the target sensitivity.

[0026] In some embodiments, the method further includes:

[0027] The target sensitivity is displayed in real time on the vehicle's display screen and sent to a preset contact.

[0028] In some embodiments, the method further includes:

[0029] Upon receiving an adjustment instruction from the preset contact, the sensitivity of the sentry mode is changed according to the adjustment instruction.

[0030] Secondly, a device for adjusting the sensitivity of a sentry mode is provided, the device comprising:

[0031] The acquisition module is used to acquire sensing data, which includes noise data, illumination data, environmental image data, and traffic flow data.

[0032] The weighting module is used to obtain target weights based on the perceived data; the target weights include noise target weights, illumination target weights, collision target weights, and traffic flow target weights.

[0033] The security level module is used to obtain the target security level based on the perceived data and the target weight;

[0034] The adjustment module is used to adjust the sensitivity of the sentry mode according to the target security level.

[0035] The application employs the above technical solution and has at least the following beneficial effects:

[0036] This invention provides a method and apparatus for adjusting the sensitivity of a sentry mode. The method involves acquiring noise data, illumination data, environmental image data, and traffic flow data. Based on these data, corresponding target weights for noise, illumination, collision, and traffic flow are obtained. A target safety level is then determined based on these weights. The sensitivity of the sentry mode is adjusted according to the target safety level. This application analyzes environmental factors and dynamically adjusts the influence weights of each factor on the sensitivity, thereby more accurately controlling the triggering of the sentry mode, effectively reducing false alarms or missed alarms, and providing a better user experience.

[0037] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 is a flowchart illustrating an exemplary embodiment of this application of a method for adjusting the sensitivity of a sentinel mode;

[0040] Figure 2 is a schematic block diagram of a sentinel mode sensitivity adjustment device shown in an exemplary embodiment of this application. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0042] Sentry mode in smart cars is an important security feature that monitors the surrounding environment when the vehicle is parked and issues alarms or records events in case of anomalies. Traditional sentry mode requires users to manually set sensitivity levels, such as low, medium, and high. However, this manual setting method has several drawbacks: 1. Inability to adapt to different environments: Varying ambient noise levels, lighting conditions, and pedestrian traffic can all affect sentry mode triggering. Manually set sensitivity cannot adapt to these changes, potentially leading to false alarms or missed alarms. 2. Potential energy waste: High sensitivity triggers sentry mode frequently, consuming more power; low sensitivity may fail to effectively monitor the environment. 3. Poor user experience: Users need to manually set sensitivity based on experience, which is cumbersome and makes it difficult to find the most suitable setting.

[0043] This application provides a method and apparatus for adjusting the sensitivity of sentry mode. By analyzing environmental factors in real time, the influence weight of each factor on the sensitivity is dynamically adjusted, thereby more accurately controlling the triggering of sentry mode, optimizing energy consumption and improving user experience.

[0044] The methods and apparatus of this application are described below through specific embodiments.

[0045] Please refer to Figure 1, which is a flowchart illustrating an exemplary embodiment of this application of a method for adjusting the sensitivity of a sentinel mode. Referring to Figure 1, the method includes:

[0046] Step S11: Acquire sensing data; the sensing data includes noise data, illumination data, environmental image data, and traffic flow data;

[0047] Step S12: Obtain target weights based on perception data; target weights include noise target weights, illumination target weights, collision target weights, and traffic flow target weights;

[0048] Step S13: Obtain the target security level based on the perceived data and target weight;

[0049] Step S14: Adjust the sensitivity of the sentry mode according to the target security level.

[0050] It should be noted that the technical solution provided in this embodiment can be added to the existing sentry system in the form of a mini-program, or it can be provided to the outside world as a standalone application to complete the sentry mode sensitivity adjustment function; applicable scenarios include but are not limited to: smart parking and sentry mode.

[0051] It is understood that the method provided in this embodiment acquires noise data, illumination data, environmental image data, and traffic flow data. Based on the noise data, illumination data, environmental image data, and traffic flow data, it obtains corresponding noise target weights, illumination target weights, collision target weights, and traffic flow target weights. Based on the noise target weights, illumination target weights, collision target weights, and traffic flow target weights, it obtains the target safety level. Based on the target safety level, it adjusts the sensitivity of the sentry mode. This application analyzes environmental factors and dynamically adjusts the influence weights of each factor on the sensitivity, thereby more accurately controlling the triggering of the sentry mode, effectively reducing false alarms or missed alarms, and providing a better user experience.

[0052] In some embodiments, "acquiring sensing data" in step S11 includes: acquiring sensing data in real time, or acquiring sensing data once every preset time interval.

[0053] It should be noted that the system uses a microphone to collect ambient noise signals, a light sensor to collect ambient light intensity, a camera to collect image information of the vehicle's surroundings, and a navigation system or other network connection to obtain traffic flow data and nearby road congestion data for the vehicle's location.

[0054] Specifically, the noise signal is subjected to spectral analysis to extract noise intensity features (N), such as average sound pressure level; the light intensity is converted into a digital signal (L), such as lux; the target hazard level is evaluated using target detection and motion analysis algorithms to obtain the collision coefficient (O), with a higher value indicating a higher hazard level; traffic flow data is analyzed to extract traffic flow level (C), for example, represented by three levels: low, medium, and high, and assigned values ​​of 1, 2, and 3 respectively.

[0055] In some embodiments, step S12, "obtaining target weights based on perception data", specifically involves: obtaining initial weights based on perception data through fuzzy preprocessing; the initial weights include initial weights for noise, initial weights for illumination, initial weights for collisions, and initial weights for traffic flow; and normalizing the initial weights to obtain the target weights.

[0056] Specifically, the fuzzy preprocessing includes: obtaining noise weights based on noise data and a preset noise mapping table; obtaining illumination weights based on illumination data and a preset illumination mapping table; obtaining collision coefficients based on environmental image data using existing target detection and motion analysis algorithms, and obtaining collision weights based on the collision coefficients and a preset coefficient mapping table; obtaining traffic flow weights based on traffic flow data and a preset traffic flow mapping table; and adjusting the noise weights, illumination weights, collision weights, or traffic flow weights according to the preprocessing algorithm to obtain the initial weights.

[0057] It should be noted that the preset noise mapping table, preset illumination mapping table, preset coefficient mapping table, and preset traffic flow mapping table are all set based on historical data from the sentinel mode. The historical data from the sentinel mode includes data on normal triggering, false triggering, and missed triggering of each sensitivity level, as well as the corresponding surrounding environmental data (light, sound, collision coefficient, and traffic flow). The preset noise mapping table contains a one-to-one correspondence between noise values ​​and noise weights. Similarly, the preset illumination mapping table contains a one-to-one correspondence between illumination intensity values ​​and illumination weights, the preset coefficient mapping table contains a one-to-one correspondence between collision coefficients and collision weights, and the preset traffic flow mapping table contains a correspondence between traffic flow and traffic flow weights.

[0058] Specifically, the preprocessing algorithm includes: nighttime preprocessing when the current time point is within a preset nighttime time range; nighttime preprocessing includes: if the noise value in the noise data is greater than a preset noise value, and the first light intensity value in the light data is less than a first preset light intensity, then the noise weight is adjusted according to the noise value to obtain an initial noise weight, and the light weight is adjusted according to the first light intensity value to obtain an initial light weight; daytime preprocessing when the current time point is within a preset daytime time range; daytime preprocessing includes: if the second light intensity value in the light data is greater than a second preset light intensity, then the collision weight is adjusted according to the second light intensity value to obtain an initial collision weight, and the traffic flow weight is adjusted according to the second light intensity value to obtain an initial traffic flow weight; collision hazard preprocessing is used when the collision coefficient is greater than a preset collision coefficient; collision hazard preprocessing includes: adjusting the collision weight, light weight, and noise weight according to the collision coefficient; wherein, the preprocessing priority of collision hazard preprocessing is higher than that of nighttime preprocessing and daytime preprocessing.

[0059] It should be noted that the preset nighttime and preset daytime time ranges are set based on the sunrise and sunset times of each day of the year. The preset daytime time range is from sunrise to sunset, and the preset nighttime time range is from sunset to the next sunrise.

[0060] Specifically, the preset noise value, first preset light intensity, second light intensity, and preset collision coefficient are all set based on historical data from the sentry mode. The historical data from the sentry mode includes data on normal triggering, false triggering, and missed triggering of each sensitivity, as well as corresponding environmental data (light, sound, collision coefficient, and traffic flow). The noise value, first light intensity value, second light intensity value, and collision coefficient are all set with corresponding adjustment values ​​to adjust the corresponding weights. For example, if the current time point is within the preset nighttime time range, the noise value is greater than the preset noise value, and the first light intensity value is greater than the first preset light intensity. Then, the adjustment value can be found through the noise value, and the initial noise weight is obtained by making corresponding adjustments based on the adjustment value. Similarly, the initial light weight is obtained.

[0061] It should be noted that weights that are not adjusted in the preprocessing algorithm are directly used as initial weights. For example, at night, the traffic flow weight does not need to be adjusted and is directly used as the initial traffic flow weight. Higher preprocessing priority weights are preprocessed earlier. For example, at night, when the collision coefficient is greater than the preset collision coefficient, collision hazard preprocessing is used.

[0062] Specifically, if the current time point falls within a preset nighttime range, and the noise level is higher than a preset value while the light intensity is lower than a preset value, then the noise weight adjustment value is positive, and the light intensity adjustment value is also positive, meaning that both the original noise and light intensity weights are increased. If the current time point falls within a preset daytime range, and the light intensity is higher than a preset value, then the collision weight adjustment value is positive, and the traffic flow weight adjustment value is also positive. When the collision coefficient is greater than a preset collision coefficient, if the collision coefficient is greater than a1, then the collision weight adjustment value, the light intensity adjustment value, and the noise weight adjustment value are all positive. If the collision coefficient is less than or equal to a1 but greater than a2, then the collision weight adjustment value is positive. If the collision coefficient is less than or equal to a2, then the noise weight adjustment value and the light intensity adjustment value are both negative. Here, a1>a2, and a1 and a2 are both set according to the collision safety level.

[0063] It is understood that the method provided in this embodiment dynamically adjusts the influence weight of various environmental factors on the sensitivity of the sentry mode, rather than using fixed weights or simple threshold judgments. It takes into account a variety of environmental factors, including noise, illumination, collision coefficient, and regional traffic flow, and achieves more comprehensive environmental perception and more precise sensitivity control.

[0064] In some embodiments, before the initial weight normalization process, the initial weight can be used as input to obtain quasi-weights through a machine learning model; the quasi-weights include noise quasi-weights, illumination quasi-weights, collision quasi-weights, and traffic flow quasi-weights, and the quasi-weights are normalized to obtain the target weights.

[0065] It should be noted that the machine learning model is a linear regression model. Based on historical data and the learned model, the initial weights are input to obtain adjustment parameters, and then quasi-weights are obtained based on these adjustment parameters. The formula is as follows: Among them, W n For n quasi-weights; a n and b n All of these are adjustment parameters corresponding to n; W n_fuzzy Let n be the initial weights for n; n∈{N,L,O,C}, where N represents noise, L represents illumination, O represents collision, and C represents traffic flow.

[0066] It is understood that the method provided in this embodiment combines fuzzy logic and machine learning, using fuzzy logic to process expert knowledge and rules, and using machine learning to learn latent patterns in data, thereby improving the robustness and adaptability of the system.

[0067] In some embodiments, step S13, "obtaining the target security level based on the perceived data and target weights," includes: obtaining the target security level according to the security level formula, where the security level formula is: Where S represents the target security level; W N_n For the target weight of noise; D N The noise membership degree is obtained based on noise data; W L_n D represents the target weight for illumination. L W represents the membership degree of illumination obtained based on illumination data. O_n D represents the collision target weights. O The collision membership degree is obtained based on environmental image data; W C_n Traffic flow target weight; D C This refers to the membership degree of traffic flow obtained based on traffic flow data.

[0068] It should be noted that the specific values ​​of each adjustment factor (noise, illumination, collision coefficient, and traffic flow) are converted into fuzzy membership degrees. For noise values, three fuzzy sets can be defined: "low", "medium", and "high". The noise values ​​are mapped to the membership degrees of these three fuzzy sets. Once the specific noise value is obtained, the noise membership degree can be obtained through the mapping relationship. Similarly, the membership degrees of illumination, collision coefficient, and traffic flow are calculated.

[0069] In some embodiments, step S14, "adjusting the sensitivity of the sentry mode according to the target security level", includes: obtaining the target sensitivity according to the target security level through a preset sensitivity mapping table; and adjusting the sensitivity of the sentry mode to the target sensitivity.

[0070] It should be noted that the preset sensitivity mapping table contains a one-to-one correspondence between security levels and sensitivities. The preset sensitivity mapping table is set based on the historical data of the sentry mode. The historical data of the sentry mode includes the normal triggering, false triggering, and missed triggering of each sensitivity and the corresponding security level.

[0071] In some embodiments, the method further includes: displaying the target sensitivity in real time on the vehicle's display screen and sending the target sensitivity to a preset contact.

[0072] In some embodiments, the method further includes: after receiving an adjustment instruction sent by a preset contact, changing the sensitivity of the sentry mode according to the adjustment instruction, wherein the adjustment instruction includes the sensitivity to be set, that is, the sensitivity of the sentry mode can be set remotely and manually.

[0073] Please refer to Figure 2, which is a schematic block diagram of a sentinel mode sensitivity adjustment device according to an exemplary embodiment of this application. Referring to Figure 2, the sentinel mode sensitivity adjustment device 100 includes:

[0074] The acquisition module 101 is used to acquire perception data; the perception data includes noise data, illumination data, environmental image data, and traffic flow data.

[0075] The weighting module 102 is used to obtain target weights based on perception data; the target weights include noise target weights, illumination target weights, collision target weights, and traffic flow target weights.

[0076] Security level module 103 is used to obtain the target security level based on the perceived data and target weight;

[0077] Adjustment module 104 is used to adjust the sensitivity of the sentry mode according to the target security level.

[0078] It should be noted that the technical solution provided in this embodiment can be applied to scenarios including but not limited to: intelligent parking and sentry mode in specific practice.

[0079] It is understood that the device provided in this embodiment acquires noise data, illumination data, environmental image data, and traffic flow data. Based on the noise data, illumination data, environmental image data, and traffic flow data, it obtains corresponding noise target weights, illumination target weights, collision target weights, and traffic flow target weights. Based on the noise target weights, illumination target weights, collision target weights, and traffic flow target weights, it obtains the target safety level and adjusts the sensitivity of the sentry mode according to the target safety level. This application analyzes environmental factors and dynamically adjusts the influence weights of each factor on the sensitivity, thereby more accurately controlling the triggering of the sentry mode, effectively reducing false alarms or missed alarms, and providing a better user experience.

[0080] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

[0081] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0082] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0083] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for adjusting the sensitivity of a sentry mode, characterized in that, The method includes: Acquire sensing data; the sensing data includes noise data, illumination data, environmental image data, and traffic flow data; The target weights are obtained based on the perceived data; the target weights include noise target weights, illumination target weights, collision target weights, and traffic flow target weights. The target security level is obtained based on the perceived data and the target weight; Adjust the sensitivity of the sentry mode according to the target security level.

2. The adjustment method according to claim 1, characterized in that, The step of obtaining the target weight based on the perceived data includes: Initial weights are obtained through fuzzy preprocessing based on the perceived data; the initial weights include initial weights for noise, illumination, collision, and traffic flow. The initial weights are normalized to obtain the target weights.

3. The adjustment method according to claim 2, characterized in that, The fuzzy preprocessing includes: Noise weights are obtained based on the noise data and a preset noise mapping table; illumination weights are obtained based on the illumination data and a preset illumination mapping table; collision coefficients are obtained based on the environmental image data using existing target detection and motion analysis algorithms, and collision weights are obtained based on the collision coefficients and a preset coefficient mapping table; traffic flow weights are obtained based on traffic flow data and a preset traffic flow mapping table. The initial weights are obtained by adjusting the noise weights, illumination weights, collision weights, or traffic flow weights according to the preprocessing algorithm.

4. The adjustment method according to claim 3, characterized in that, The preprocessing algorithm includes: When the current time point is within a preset nighttime time range, nighttime preprocessing is adopted; the nighttime preprocessing includes: if the noise value in the noise data is greater than a preset noise value, and the first light intensity value in the light data is less than a first preset light intensity, then the noise weight is adjusted according to the noise value to obtain an initial noise weight, and the light weight is adjusted according to the first light intensity value to obtain an initial light weight. When the current time point is within the preset daytime range, daytime preprocessing is adopted; the daytime preprocessing includes: if the second light intensity value in the light data is greater than the second preset light intensity, then the collision weight is adjusted according to the second light intensity value to obtain the initial collision weight, and the traffic flow weight is adjusted according to the second light intensity value to obtain the initial traffic flow weight. When the collision coefficient is greater than a preset collision coefficient, collision hazard preprocessing is performed; the collision hazard preprocessing includes: adjusting the collision weight, the illumination weight, and the noise weight according to the collision coefficient; The preprocessing priority of the collision hazard preprocessing is higher than that of the nighttime preprocessing and the daytime preprocessing.

5. The adjustment method according to claim 4, characterized in that, The step of normalizing the initial weights to obtain the target weights includes: The target weight is obtained through a weight normalization formula, which is: ； Among them, W i_n Let W be the weight of target i, i∈{N,L,O,C}, where N represents noise, L represents illumination, O represents collision, and C represents traffic flow; i The initial weights are i; W N W represents the initial noise weights. L W represents the initial illumination weights. O W represents the initial collision weights. C This is the initial traffic flow weight.

6. The adjustment method according to claim 1, characterized in that, The process of obtaining the target security level based on the perceived data and the target weight includes: The target security level is obtained based on the security level formula, which is: ； Where S represents the target security level; W N_n For the target weight of noise; D N The noise membership degree is obtained based on noise data; W L_n D represents the target weight for illumination. L W represents the membership degree of illumination obtained based on illumination data. O_n D represents the collision target weights. O The collision membership degree is obtained based on environmental image data; W C_n Traffic flow target weight; D C This refers to the membership degree of traffic flow obtained based on traffic flow data.

7. The adjustment method according to claim 1, characterized in that, The adjustment of the sentry mode sensitivity based on the target security level includes: The target sensitivity is obtained by using a preset sensitivity mapping table based on the target security level. Adjust the sensitivity of the sentry mode to match the target sensitivity.

8. The adjustment method according to claim 7, characterized in that, The method further includes: The target sensitivity is displayed in real time on the vehicle's display screen and sent to a preset contact.

9. The adjustment method according to claim 8, characterized in that, The method further includes: Upon receiving an adjustment instruction from the preset contact, the sensitivity of the sentry mode is changed according to the adjustment instruction.

10. A device for adjusting the sensitivity of a sentry mode, characterized in that, The device includes: The acquisition module is used to acquire sensing data, which includes noise data, illumination data, environmental image data, and traffic flow data. The weighting module is used to obtain target weights based on the perceived data; the target weights include noise target weights, illumination target weights, collision target weights, and traffic flow target weights. The security level module is used to obtain the target security level based on the perceived data and the target weight; The adjustment module is used to adjust the sensitivity of the sentry mode according to the target security level.

Images