Adaptive interference rejection method, microcontroller and system

Abstract

The application discloses an adaptive anti-interference method, a microcontroller and a system, and relates to the technical field of smart home. The method comprises the following steps: acquiring current time information in real time; comparing the current time information with a preset commonly used time period table to assign a time period attribute to the current time information; acquiring a reference distance, a response time and a duration of a current triggering event collected by a sensing module in real time; calculating feature scores of the reference distance, the response time and the duration according to preset segmentation characteristics; performing weighted calculation on the feature scores according to the time period attribute to generate a comprehensive confidence; and controlling a working state of a load module according to the comprehensive confidence and the time period attribute. The application can effectively improve the anti-interference capability, environmental adaptability and user experience.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, and in particular to an adaptive anti-interference method, microcontroller, and system. Background Technology

[0002] As the smart home market continues to expand, bathrooms, as spaces with high usage frequency and high demand for intelligence, are becoming a key area for upgrading sensing layer technology. However, traditional sensing solutions are increasingly revealing problems in the high-temperature, high-humidity, and steamy environment of bathrooms, while the maturity of millimeter-wave radar technology provides a new solution to this dilemma.

[0003] Existing millimeter-wave radar human presence detection technology mainly relies on software adjustments to the trigger thresholds of various distance gates or on extracting and filtering characteristic values ​​of specific simulated interference sources. However, for millimeter-wave radar human presence detection technology applied to bathroom heaters, it is susceptible to environmental interference such as vibrations from ceiling-mounted sewage pipes and the operation of bathroom exhaust fans in specific bathroom environments. In practical applications, it mainly faces the following technical problems: (1) Lack of closed-loop user feedback and insufficient time-based adaptability: For the actual usage scenarios of the product itself, no user active operation data (such as turning on heating / ventilation through the panel or APP) is collected, and it is impossible to use real usage behavior to infer the detection time period; the uniform detection rules are used all day long, which makes it easy to be mistakenly triggered by environmental interference during non-use periods such as late at night, resulting in ineffective energy consumption and user sleep disturbance.

[0004] (2) Fixed parameters and lack of self-learning ability: The judgment rules and parameters are fixed after leaving the factory. They cannot adapt to different installation environments (installation height, interference source location) based on long-term operation data, nor can they use user behavior patterns to optimize the detection rules in reverse. Environmental compatibility and user experience are limited.

[0005] (3) Insufficient use of features: Relying solely on the single physical quantity of "distance" for judgment makes it difficult to effectively distinguish between low-posture human bodies and fixed interference objects (such as toilets and bathroom cabinets); at the same time, "response time" is not used as a criterion for judgment, making it impossible to distinguish between mechanical vibration interference and real human body entry events, resulting in a high misjudgment rate in low-height scenes and instantaneous vibration scenes. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide an adaptive anti-interference method, microcontroller and system that can effectively improve anti-interference capability.

[0007] To solve the above technical problem, the present invention provides an adaptive anti-interference method, comprising: acquiring current time information in real time; comparing the current time information with a preset common time period table to assign a time period attribute to the current time information; acquiring a reference distance, a response time and a duration of a current trigger event collected by a sensing module in real time; respectively calculating feature scores of the reference distance, the response time and the duration according to preset segmented characteristics; performing weighted calculation on the feature scores according to the time period attribute to generate a comprehensive confidence level; and controlling an operating state of a load module according to the comprehensive confidence level and the time period attribute.

[0008] As an improvement of the above solution, the step of comparing the current time information with a preset common time period table to assign a time period attribute to the current time information comprises: comparing the current time information with a common time period table, wherein common time periods are recorded in the common time period table; setting the time period attribute of the current time information as "common time period" if the current time information falls within the common time period; and setting the time period attribute of the current time information as "uncommon time period" if the current time information does not fall within the common time period.

[0009] As an improvement of the above solution, the step of calculating the feature score of the reference distance according to preset segmented characteristics comprises: when 0.3m < L < 2m, SL=1-(|L-1.15| / 0.85); when L ≤ 0.3m or L ≥ 2m, SL=0; wherein L is the reference distance, and SL is the feature score of the reference distance.

[0010] As an improvement of the above solution, the step of calculating the feature score of the response time according to preset segmented characteristics comprises: when T1 ≤ 150MS, ST1=0; when 150MS < T1 < 1500MS, ST1=(T1-150) / 1200; when T1 ≥ 1500MS, ST1=1; wherein T1 is the response time, and ST1 is the feature score of the response time.

[0011] As an improvement of the above solution, the step of calculating the feature score of the duration according to preset segmented characteristics comprises: when T2 ≤ 2min, ST2=0.2; when 2min < T2 < 15min, ST2=0.2+0.8(T2-2) / 13; when 15min ≤ T2 ≤ 45min, ST2=1; when 45min < T2 < 90min, ST2=1-(T2-45) / 45; when T2 ≥ 90min, ST2=0; wherein T2 is the duration, and ST2 is the feature score of the duration.

[0012] As an improvement to the above scheme, the step of weighting the feature scores according to the time period attributes to generate a comprehensive confidence score includes: calculating the comprehensive confidence score according to the formula C=WL×SL+WT1×ST1+WT2×ST2; where C is the comprehensive confidence score, WL is the weight of the baseline distance, SL is the feature score of the baseline distance, WT1 is the weight of the response time, ST1 is the feature score of the response time, WT2 is the weight of the duration, and ST2 is the feature score of the duration.

[0013] As an improvement to the above scheme, when the time period attribute is "frequent time period", the weights of the reference distance, response time, and duration decrease sequentially; when the time period attribute is "unfrequent time period", the weights of the reference distance, duration, and response time increase sequentially.

[0014] As an improvement to the above solution, the step of controlling the working state of the load module based on the comprehensive confidence level and time period attribute includes: comparing the comprehensive confidence level with a preset confidence level interval; when the comprehensive confidence level is greater than or equal to the maximum value of the confidence level interval, determining that the current triggered event is a real event and outputting a control command to drive the load module; when the comprehensive confidence level is within the confidence level interval and the time period attribute is "frequently used time period", determining that the current triggered event is a real event and outputting a control command to drive the load module; when the comprehensive confidence level is within the confidence level interval and the time period attribute is "not frequently used time period", determining that the current triggered event is an interference event and ignoring the current triggered event; when the comprehensive confidence level is less than or equal to the minimum value of the confidence level interval, determining that the current triggered event is an interference event and ignoring the current triggered event.

[0015] As an improvement to the above scheme, the confidence interval is (0.4, 0.6).

[0016] As an improvement to the above scheme, the adaptive anti-interference method further includes: acquiring feedback data; and dynamically updating preset parameters based on the feedback data using a self-learning algorithm, wherein the preset parameters include common time periods, feature weights, and confidence intervals.

[0017] Accordingly, the present invention also provides a microcontroller, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described adaptive anti-interference method.

[0018] Accordingly, the present invention also provides an adaptive anti-interference system, comprising: a sensing module for real-time detection of the reference distance, response time, and duration of the currently triggered event; a communication module for acquiring current time information from a cloud time server; the aforementioned microcontroller; and a load module for executing control instructions from the microcontroller.

[0019] Implementing this invention has the following beneficial effects: The adaptive anti-interference method of this invention incorporates the "response time" feature into the detection system. It utilizes the inherent physical difference between mechanical vibration (millisecond level) and the fact that human targets enter the sensing range from far to near, providing a key basis for interference identification.

[0020] Meanwhile, the adaptive anti-interference method of this invention introduces a multi-feature weighted fusion scoring method, which maps the three physical quantities of reference distance, response time and duration to scoring functions respectively, and obtains the comprehensive confidence score by weighted summation, thus solving the problem that a single distance feature cannot distinguish between low-posture human bodies and fixed interference.

[0021] Furthermore, the adaptive anti-interference method of the present invention introduces a dual-time period weight adaptive mechanism, which can dynamically switch the feature weight allocation under "frequently used time period" and "unfrequently used time period" according to the current time information of the current triggered event, so as to realize the automatic switching between the two strategies of "user priority" and "interference priority".

[0022] More preferably, the adaptive anti-interference method of the present invention is based on a time-period self-learning algorithm of user behavior clustering, which can continuously adapt to changes in user lifestyle habits and differences in installation environment, and systematically improve anti-interference ability, environmental adaptability and user experience. Attached Figure Description

[0023] Figure 1 This is a flowchart of the first embodiment of the adaptive anti-interference method of the present invention; Figure 2 This is a flowchart of the second embodiment of the adaptive anti-interference method of the present invention; Figure 3 This is a schematic diagram of an embodiment of the adaptive anti-interference system of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. It is hereby declared that the directional terms such as up, down, left, right, front, back, inside, and outside used in this text are based solely on the accompanying drawings and are not intended to specifically limit the invention.

[0025] See Figure 1 , Figure 1A flowchart of a first embodiment of the adaptive anti-interference method of the present invention is shown, which includes: S101, obtain the current status in real time; In practical applications, the communication module can be used to synchronize with a time server to obtain the current time information.

[0026] S102, compare the current time information with the preset commonly used time period table, and assign time period attributes to the current time information; It should be noted that the frequently used time periods table records frequently used time periods; generally, the frequently used time periods can be set according to the actual situation.

[0027] For example, when the adaptive anti-interference method of the present invention is applied to a bathroom heater, the commonly used time period can be set to "06:00~08:00" or "18:00~23:00", but this is not a limitation.

[0028] Accordingly, the steps of comparing the current time information with a preset list of commonly used time periods to assign time period attributes to the current time information include: (1) Compare the current time information with the commonly used time period table; (2) If the current time information falls within a frequently used time period, then set the time period attribute of the current time information to "frequently used time period"; (3) If the current time information does not fall within the commonly used time period, the time period attribute of the current time information is set to "uncommon time period".

[0029] S103, real-time acquisition of the reference distance, response time and duration of the current triggered event collected by the sensing module; It should be noted that when the sensing module detects a human target in real time, it generates a current trigger event and collects the reference distance, response time, and duration in real time.

[0030] When the adaptive anti-interference method of the present invention is applied to a bathroom heater, the antenna surface of the sensing module can be oriented towards the bottom of the bathroom space and installed on the ceiling along with the main panel.

[0031] Therefore, the adaptive anti-interference method of this invention incorporates the "response time" feature into the detection system, and utilizes the inherent physical difference between mechanical vibration (millisecond level) and the human target entering the sensing range from far to near, to provide a key basis for interference identification.

[0032] S104, calculate the feature scores of the reference distance, response time and duration according to the preset segmentation characteristics; In the adaptive anti-interference method of the present invention, different piecewise linear score calculation functions are preset in combination with different application scenarios, and respectively map the feature scores of reference distance, response time and duration. Wherein, the response time can be correspondingly defined as the delay time when the sensing module collects a valid signal for the first time after being started.

[0033] In practical applications, the feature parameters (reference distance, response time and duration) can be mapped to feature scores in the interval of 0 to 1; wherein, the larger the feature score of the feature parameter is, the closer the feature parameter is to a real user.

[0034] The feature scores of the reference distance, the response time and the duration are respectively described in detail below.

[0035] 1. Feature score of reference distance When the adaptive anti-interference method of the present invention is applied to a bathroom heater, since the average ceiling height is about 2.1m to 2.4m in the top-mounted environment, combined with the average height of a human body, the steps of calculating the feature score of the reference distance according to the preset sectional characteristics comprise: (1) When 0.3m < L < 2m, SL=1-(|L-1.15| / 0.85); (2) When L ≤ 0.3m or L ≥ 2m, SL=0; Wherein, L is the reference distance, and SL is the feature score of the reference distance.

[0036] 2. Feature score of response time Based on the normal moving speed of a human body, the steps of calculating the feature score of the response time according to the preset sectional characteristics comprise: (1) When T1 ≤ 150MS, ST1=0; (2) When 150MS < T1 < 1500MS, ST1=(T1-150) / 1200; (3) When T1 ≥ 1500MS, ST1=1; Wherein, T1 is the response time, and ST1 is the feature score of the response time.

[0037] 3. Feature score of duration Based on the average bathroom usage time of a human body, the steps of calculating the feature score of duration according to the preset sectional characteristics comprise: (1) When T2 ≤ 2min, ST2=0.2; (2) When 2min < T2 < 15min, ST2=0.2+0.8(T-2) / 13; (3) When 15min ≤ T2 ≤ 45min, ST2=1; (4) When 45min < T2 < 90min, ST2=1-(T2-45) / 45; (5) When T2 ≥ 90min, ST2=0; wherein, T2 is the duration, and ST2 is the characteristic score of the duration.

[0038] S105, performing weighted calculation on the characteristic scores according to the time period attribute to generate a comprehensive confidence; correspondingly, the comprehensive confidence can be calculated according to the following formula: C=WL×SL+WT1×ST1+WT2×ST2 wherein: C is the comprehensive confidence; WL is the weight of the reference distance; SL is the characteristic score of the reference distance; WT1 is the weight of the response time; ST1 is the characteristic score of the response time; WT2 is the weight of the duration; ST2 is the characteristic score of the duration.

[0039] further, the adaptive anti-interference method of the present invention allocates different weights according to the time period attribute of the current time information to realize adaptive adjustment of weights, specifically: (1) When the time period attribute is "common time period", a "user-prioritized weight proportion strategy" can be adopted, so that the weight of the reference distance, the weight of the response time and the weight of the duration decrease sequentially; for example, when the time period attribute is "common time period", the weight of the reference distance can be set to 0.5, the weight of the response time can be set to 0.3, and the weight of the duration can be set to 0.2.

[0040] (2) When the time period attribute is "uncommon time period", an "interference-prioritized weight strategy" can be adopted, so that the weight of the reference distance, the weight of the duration and the weight of the response time increase sequentially.

[0041] for example, when the time period attribute is "uncommon time period", the weight of the reference distance can be set to 0.25, the weight of the response time can be set to 0.4, and the weight of the duration can be set to 0.35.

[0042] therefore, the adaptive anti-interference method of the present invention introduces a dual time period weight adaptive mechanism, which can dynamically switch the characteristic weight allocation under "common time period" and "uncommon time period" according to the current time information of the current trigger event, and realize automatic switching between the "user-prioritized" and "interference-prioritized" strategies.

[0043] S106, controlling the working state of the load module according to the comprehensive confidence and the time period attribute.

[0044] In practical applications, the overall confidence level and time period attributes can be used to determine whether the current triggering event is a "real event" or a "disruptive event," thereby filtering out "disruptive events" and controlling the working state of the load module in a targeted manner.

[0045] When the adaptive anti-interference method of the present invention is applied to a bathroom heater, the load module can be a lighting module, a ventilation module, a heating module, a sterilization module, a louver control unit, etc. Each load module can perform corresponding actions according to the judgment result of the current triggering event.

[0046] Accordingly, the steps for controlling the operating state of the load module based on the comprehensive confidence level and time period attributes include: (1) Compare the overall confidence level with the preset confidence level interval; In this embodiment, the confidence interval is (0.4, 0.6), but it is not a limitation and can be set according to the actual situation.

[0047] (2) When the overall confidence level is greater than or equal to the maximum value of the confidence level interval, the current triggering event is determined to be a real event, and a control command is output to drive the load module; (3) When the overall confidence level is within the confidence level range and the time period attribute is "common time period", the current triggering event is determined to be a real event, and a control command is output to drive the load module; (4) When the overall confidence level is within the confidence level range and the time period attribute is "uncommon time period", the current triggering event is determined to be an interference event and is ignored; In other words, when the current triggering event is a disturbance event, it should be ignored so that the load module does not perform any function and avoids accidental triggering.

[0048] (5) When the overall confidence level is less than or equal to the minimum value of the confidence level interval, the current triggering event is determined to be an interference event and is ignored.

[0049] Therefore, the adaptive anti-interference method of this invention introduces a multi-feature weighted fusion scoring method, which maps the three physical quantities of benchmark distance, response time and duration to scoring functions respectively, obtains the comprehensive confidence score by weighted summation, and compares it with the two thresholds to achieve three-level decision-making.

[0050] In summary, the adaptive anti-interference method of this invention introduces a dual-time-period adaptive strategy, employing a lenient "user-first" rule during "frequently used time periods" and a strict "interference-first" rule during "unfrequently used time periods." Actual testing shows that this method can reduce the false trigger rate by over 90% during late-night hours. Furthermore, by fusing three features—reference distance, response time, and duration—and assigning differentiated weights, this adaptive anti-interference method solves the problem that a single distance feature cannot distinguish between low-profile human bodies and fixed interference.

[0051] See Figure 2 , Figure 2 A flowchart of a second embodiment of the adaptive anti-interference method of the present invention is shown, which includes: S201, obtain current time information in real time; S202, compare the current time information with the preset commonly used time period table, and assign time period attributes to the current time information; S203, real-time acquisition of the reference distance, response time and duration of the current triggered event collected by the sensing module; S204, calculate the feature scores of the reference distance, response time and duration according to the preset segmentation characteristics; S205, the feature scores are weighted according to the time period attributes to generate a comprehensive confidence score; S206 controls the working status of the load module based on the comprehensive confidence level and time period attributes.

[0052] S207, Obtain feedback data; Feedback data includes user-reported behavioral data (false alarm data, missed alarm data) and interfering events, but is not limited to these and can be obtained according to the actual situation; S208, dynamically updates preset parameters based on feedback data using a self-learning algorithm; and Figure 1 Unlike the first embodiment shown, this embodiment also introduces steps S207 and S208 to update the preset parameters, thereby realizing online self-learning and continuous optimization of the detection strategy.

[0053] In practical applications, preset parameters include common time periods, feature weights (weight of baseline distance, weight of response time, and weight of duration) and confidence intervals.

[0054] For example, when the current triggered event is identified as a disturbance event based on the overall confidence level and time period attributes, the disturbance events can be recorded and periodically summarized to infer the user's actual usage patterns and dynamically update the commonly used time periods, feature weights, and confidence intervals.

[0055] For example, when a false trigger occurs, the user can report the false alarm data, and the false alarm data and the corresponding sensor data can be recorded as negative samples for self-learning.

[0056] For example, when a "missed report" occurs, users can report the missed report data to record the feature vector of the current event, and fine-tune the feature weights through gradient descent to achieve personalized optimization.

[0057] Therefore, the adaptive anti-interference method of this invention is based on a time-period self-learning algorithm of user behavior clustering, which can continuously adapt to changes in user lifestyle habits and differences in installation environment. After long-term operation, the false alarm rate reported by users is reduced to less than 5%, systematically improving anti-interference ability, environmental adaptability and user experience.

[0058] Accordingly, the present invention also discloses a microcontroller, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described adaptive anti-interference method.

[0059] See Figure 3 , Figure 3 The specific structure of the adaptive anti-interference system 100 of the present invention is shown, which includes a sensing module 1, a communication module 2, a microcontroller 3, and a load module 4. The sensing module 1, the communication module 2, and the load module 4 are respectively connected to the microcontroller 3. Specifically: The sensing module 1 is used to detect the reference distance, response time and duration of the current triggered event in real time; wherein, the sensing module 1 can be a sensor with characteristic parameters such as output reference distance, response time and duration, such as a 24GHz millimeter wave radar, infrared sensor, ultrasonic sensor, laser rangefinder sensor, etc.

[0060] Communication module 2 synchronizes with the cloud time server to obtain the current time information from the cloud time server; wherein, communication module 2 is preferably an IoT (Internet of Things) communication module.

[0061] The microcontroller 3 includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described adaptive anti-interference method.

[0062] The load module 4 is used to execute the control instructions of the microcontroller 3. In this embodiment, the load module 4 may be a lighting module, a ventilation module, a heating module, a sterilization module, a leaf-swaying control unit, etc. Each load module can perform corresponding actions according to the judgment result of the current trigger event.

[0063] Furthermore, the communication module 3 is also used to interact with the user's mobile terminal to obtain behavioral data (false alarm data, missed alarm data) from the user.

[0064] Therefore, the adaptive anti-interference system of the present invention systematically improves anti-interference capability, environmental adaptability and user experience by introducing a dual-time period adaptive strategy, a multi-feature weighted fusion mechanism, a time period self-learning algorithm based on user behavior and response time features.

[0065] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An adaptive anti-interference method, characterized in that, Comprising: acquiring current time information in real time; comparing said current time information with a preset common time period table to assign a time period attribute to said current time information; acquiring in real time the reference distance, response time and duration of a current trigger event collected by a sensing module; calculating feature scores of said reference distance, response time and duration respectively according to preset sectional characteristics; performing weighted calculation on said feature scores according to said time period attribute to generate a comprehensive confidence level; controlling the working state of a load module according to said comprehensive confidence level and the time period attribute.

2. The adaptive anti-interference method as described in claim 1, characterized in that, the step of comparing current time information with a preset common time period table to assign a time period attribute to said current time information comprises: comparing said current time information with a common time period table, wherein common time periods are recorded in said common time period table; if said current time information falls within said common time period, setting the time period attribute of said current time information as "common time period"; if said current time information does not fall within said common time period, setting the time period attribute of said current time information as "uncommon time period".

3. The adaptive anti-interference method as described in claim 1, characterized in that, the step of calculating the feature score of said reference distance according to preset sectional characteristics comprises: when 0.3m<L<2m, SL=1-(|L-1.15| / 0.85); when L≤0.3m or L≥2m, SL=0; wherein L is the reference distance, and SL is the feature score of the reference distance.

4. The adaptive anti-interference method as described in claim 1, characterized in that, the step of calculating the feature score of said response time according to preset sectional characteristics comprises: when T1≤150MS, ST1=0; when 150MS<T1<1500MS, ST1=(T1-150) / 1200; when T1≥1500MS, ST1=1; wherein T1 is the response time, and ST1 is the feature score of the response time.

5. The adaptive anti-interference method as described in claim 1, characterized in that, the step of calculating the feature score of said duration according to preset sectional characteristics comprises: when T2≤2min, ST2=0.2; when 2min<T2<15min, ST2=0.2+0.8(T2-2) / 13; when 15min≤T2≤45min, ST2=1; when 45min<T2<90min, ST2=1-(T2-45) / 45; when T2≥90min, ST2=0; wherein T2 is the duration, and ST2 is the feature score of the duration.

6. The adaptive anti-interference method as described in claim 1, characterized in that, the step of performing weighted calculation on said feature scores according to said time period attribute to generate a comprehensive confidence level comprises: calculating the comprehensive confidence level according to a formula C=WL×SL+WT1×ST1+WT2×ST2; wherein C is the comprehensive confidence level, WL is the weight of the reference distance, SL is the feature score of the reference distance, WT1 is the weight of the response time, ST1 is the feature score of the response time, WT2 is the weight of the duration, and ST2 is the feature score of the duration.

7. The adaptive anti-interference method according to claim 6, characterized in that, when said time period attribute is "common time period", the weight of said reference distance, the weight of said response time and the weight of said duration decrease sequentially; When the time period attribute is "uncommon time period", the weights of the baseline distance, duration, and response time increase sequentially.

8. The adaptive anti-interference method as described in claim 1, characterized in that, The step of controlling the working state of the load module based on the comprehensive confidence level and time period attributes includes: The overall confidence level is compared with a preset confidence level range; When the overall confidence level is greater than or equal to the maximum value of the confidence level interval, the current triggering event is determined to be a real event, and a control command is output to drive the load module. When the overall confidence level is within the confidence level range and the time period attribute is "common time period", the current triggered event is determined to be a real event, and a control command is output to drive the load module. When the overall confidence level is within the confidence level range and the time period attribute is "uncommon time period", the current triggering event is determined to be an interference event and is ignored. When the overall confidence level is less than or equal to the minimum value of the confidence level interval, the current triggering event is determined to be an interference event and is ignored.

9. The adaptive anti-interference method as described in claim 8, characterized in that, The confidence level range is (0.4, 0.6).

10. The adaptive anti-interference method as described in claim 1, characterized in that, Also includes: Obtain feedback data; Based on the feedback data, preset parameters are dynamically updated using a self-learning algorithm. These preset parameters include common time periods, feature weights, and confidence intervals.

11. A microcontroller, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the adaptive anti-interference method according to any one of claims 1 to 10.

12. An adaptive anti-interference system, characterized in that, include: The sensing module is used to detect the reference distance, response time, and duration of the currently triggered event in real time; The communication module is used to obtain the current time information from the cloud time server; The microcontroller of claim 11; The load module is used to execute the control instructions of the microcontroller.

Images