Remote control method and device based on low-power Hall sensor

Abstract

The present invention relates to the technical field of remote control, and particularly to a remote control method and device based on a low-power Hall sensor. The method includes the following steps: obtaining remote control device type data; deploying Hall sensors based on the remote control device type data to generate Hall sensor deployment data; calibrating the working magnetic field direction of the Hall sensors for the Hall sensor deployment data to generate Hall sensor deployment correction data; performing real-time signal acquisition on the Hall sensor deployment correction data to obtain a standard remote control device magnetic field detection signal; performing lightweight signal decoding on the standard remote control device magnetic field detection signal to generate remote control device lightweight decoding data; and performing remote control mode recognition on the remote control device lightweight decoding data to generate remote control operation intention data. The present invention improves the accuracy and efficiency of remote control by optimizing Hall sensor deployment, signal decoding, response delay, and multi-device collaborative control.

Description

Technical Field

[0001] The present invention relates to the technical field of remote control, and particularly to a remote control method and device based on a low-power Hall sensor. Background Art

[0002] Early remote control methods mainly relied on infrared or radio frequency (RF) technologies, which were limited by energy consumption, communication distance, and anti-interference ability. However, with the maturity of low-power sensor technology, Hall sensors have gradually replaced traditional sensors and become the core components in long-distance, low-power, and efficient remote control systems. During this process, the development of low-power Hall sensors has evolved from single magnetic field detection to an integrated multi-functional sensing system. For example, the application of integrated circuit (IC) technology has made Hall sensors smaller, lower in power consumption, and have higher accuracy and response speed. In addition, remote control systems based on Hall sensors have gradually achieved intelligence, digitization, and remote control. Through wireless communication modules and embedded microcontrollers, convenient control of household appliances, industrial equipment, etc. can be realized. However, currently, there are problems such as excessive redundant information and slow processing speed in the signal decoding of traditional Hall sensors. Especially when the sensor signal contains complex operation modes, and at the same time, due to the delay in remote transmission of signal packets and instruction response time during the transmission process, the control of traditional systems has problems of untimely response, resulting in relatively low accuracy and efficiency of remote control. Summary of the Invention

[0003] Based on this, it is necessary to provide a remote control method and device based on a low-power Hall sensor to solve at least one of the above technical problems.

[0004] To achieve the above object, a remote control method based on a low-power Hall sensor, the method includes the following steps:

[0005] Step S1: Obtain remote control device type data; deploy Hall sensors based on the remote control device type data to generate Hall sensor deployment data; calibrate the working magnetic field direction of the Hall sensors for the Hall sensor deployment data to generate Hall sensor deployment correction data; perform real-time signal acquisition on the Hall sensor deployment correction data to obtain a standard remote control device magnetic field detection signal;

[0006] Step S2: Perform lightweight signal decoding on the standard remote control device magnetic field detection signal to generate remote control device lightweight decoding data; perform remote control mode recognition on the remote control device lightweight decoding data to generate remote control operation intention data; optimize the signal decoding of the remote control device lightweight decoding data based on the remote control operation intention data to generate optimized decoded control signal data;

[0007] Step S3: Remotely transmit the optimized decoded control signal data to generate decoded control signal packet transmission data; perform instruction reception response analysis on the decoded control signal packet transmission data to generate receiving device instruction execution data and receiving device instruction execution response time; optimize the response delay of the receiving device instruction execution data based on the receiving device instruction execution response time to generate response optimization instructions;

[0008] Step S4: Evaluate the remote control completion rate of the receiving device instruction execution data based on the response optimization instructions to generate the remote control completion rate; compare the remote control completion rate with the preset remote control standard completion rate. When the remote control completion rate is less than the preset remote control standard completion rate, adaptively adjust the multi-device collaborative control task allocation data until the remote control completion rate is greater than or equal to the preset remote control standard completion rate to execute the remote control operation.

[0009] The present invention ensures that the Hall sensor can adapt to the working environments of different remote control devices by obtaining remote control device type data and precisely deploying the Hall sensor according to the device characteristics. After calibrating the working magnetic field direction of the sensor, it can accurately collect standard remote control device magnetic field detection signals, thereby improving the accuracy and reliability of the signals. The lightweight signal decoding reduces the data burden during transmission and improves the decoding efficiency; through remote control mode recognition, it can accurately capture the control intentions of remote control devices, further enhancing the system's response ability to remote control operations. The signal decoding optimization based on the control intentions reduces redundant information and improves the decoding accuracy and speed of the signals. The optimized decoded control signal packet can be transmitted more effectively remotely, reducing signal loss and interference. By analyzing and optimizing the instruction execution response time of the receiving device, the response delay is significantly reduced, improving the real-time performance and stability of the system, and ensuring timely feedback of remote control operations. By evaluating the remote control completion rate, the execution effect of remote control tasks can be monitored in real time to ensure the smooth completion of control tasks. The adaptive adjustment of multi-device collaborative control tasks can dynamically optimize task allocation according to actual situations, improving the flexibility and scalability of the system, and ensuring that remote control tasks can still meet the preset standards in complex environments. Therefore, the present invention improves the accuracy and efficiency of remote control by optimizing Hall sensor deployment, signal decoding, response delay, and multi-device collaborative control.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Obtain remote control device type data;

[0012] Step S12: Select the Hall sensor type based on the remote control device type data to obtain the Hall sensor type data of the remote control device; deploy the Hall sensor according to the Hall sensor type data of the remote control device to generate Hall sensor deployment data;

[0013] Step S13: Sense the device magnetic field of the remote control device according to the Hall sensor deployment data to generate remote control device magnetic field sensing data; calibrate the working magnetic field direction of the Hall sensor according to the remote control device magnetic field sensing data to generate Hall sensor deployment correction data;

[0014] Step S14: Perform real-time signal acquisition on the Hall sensor deployment correction data to obtain the original magnetic field detection signal of the remote control device; perform signal preprocessing on the original magnetic field detection signal of the remote control device to generate a standard remote control device magnetic field detection signal, where the signal preprocessing includes signal denoising, signal enhancement, and signal normalization.

[0015] In the present invention, by selecting a suitable Hall sensor type according to the type of the remote control device, it is possible to ensure that the selected sensor is suitable for the specific application scenario, thereby improving the detection accuracy and stability. By calibrating the working magnetic field direction of the Hall sensor, the magnetic field sensing ability of the sensor for the remote control device can be maximized, the error in magnetic field sensing can be reduced, and the accuracy of the data can be improved. By preprocessing the original magnetic field detection signal, including denoising, enhancement, and normalization, noise interference can be effectively removed, and the characteristics of the signal can be strengthened, making the signal for subsequent analysis and application clearer and capable of providing more reliable magnetic field data. The real-time signal acquisition function can provide real-time feedback on the magnetic field state of the remote control device, provide timely feedback information, be suitable for applications in dynamic environments, and improve the performance of the remote control device in complex environments. By obtaining and analyzing the remote control device type data, the system can flexibly adapt to different types of remote control devices and achieve unified and efficient management and operation in diverse products.

[0016] Preferably, calibrating the working magnetic field direction of the Hall sensor according to the remote control device magnetic field sensing data includes:

[0017] Confirm the sensor installation coordinates for the Hall sensor deployment data to obtain sensor installation coordinate data; analyze the installation angle for the Hall sensor deployment data based on the sensor installation coordinate data to generate sensor installation angle data;

[0018] Extract the induction data of a single Hall sensor from the remote control device magnetic field sensing data to obtain Hall sensor induction data, where the extraction of Hall sensor induction data includes magnetic field strength extraction, magnetic field direction extraction, and magnetic field change extraction; aggregate and compare the lateral magnetic field azimuth based on the Hall sensor induction data to generate lateral magnetic field azimuth aggregation data;

[0019] Adjust the installation orientation of the Hall sensor deployment data according to the lateral magnetic field orientation aggregation data to generate Hall sensor deployment correction data.

[0020] In the present invention, by confirming the installation coordinates of the Hall sensor deployment data (the "sensor installation coordinate data" mentioned in the steps), the installation position of the sensor can be ensured to be accurate, thereby improving the magnetic field perception accuracy and reliability of the sensor. By analyzing the installation angle of the sensor (the "sensor installation angle data" in step S12), it can be ensured that the installation direction of the sensor meets the design requirements, thus ensuring that the response angle of the sensor to the magnetic field is correct and reducing the measurement error caused by improper installation. By extracting the induction data of a single Hall sensor, including the extraction of magnetic field intensity, magnetic field direction, and magnetic field change (step S13), more detailed and accurate magnetic field information can be obtained, and this fine data provides a reliable basis for subsequent analysis and calibration. Based on the Hall sensor induction data for lateral magnetic field orientation aggregation comparison (the "lateral magnetic field orientation aggregation data" in step S13), it is possible to effectively compare the data of different sensors, analyze the change of magnetic field distribution, ensure the consistency of the induction data between each sensor, and reduce interference and errors. Through the aggregation comparison of the lateral magnetic field orientation, further adjust the installation orientation of the Hall sensor deployment (the "Hall sensor deployment correction data" in step S14) to ensure that the magnetic field perception direction of the sensor is consistent with the actual magnetic field direction and improve the overall measurement accuracy. The realization of the entire calibration process can eliminate the errors caused by installation errors, magnetic field interference, or inaccurate sensor positioning, improve the stability and robustness of the magnetic field perception system of the remote control device, and enable it to maintain a high accuracy in complex and dynamic environments.

[0021] Preferably, step S2 includes the following steps:

[0022] Step S21: Extract multi-dimensional magnetic field features from the magnetic field detection signal of the standard remote control device to obtain multi-dimensional magnetic field feature data of the remote control device, where the multi-dimensional magnetic field feature data of the remote control device includes magnetic field intensity feature data, magnetic field change rate feature data, and magnetic field timestamp data;

[0023] Step S22: Perform spatial information association on the magnetic field intensity feature data, magnetic field change rate feature data, and magnetic field timestamp data based on the sensor installation coordinate data to generate spatial association data of the remote control device magnetic field; perform lightweight signal decoding on the magnetic field detection signal of the standard remote control device according to the spatial association data of the remote control device magnetic field to generate lightweight decoding data of the remote control device;

[0024] Step S23: Identify the remote control mode for the lightweight decoded data of the remote control device to generate remote control operation intention data; optimize the signal decoding of the lightweight decoded data of the remote control device based on the remote control operation intention data to generate optimized decoded control signal data.

[0025] The present invention extracts multi-dimensional feature data (step S21), including magnetic field strength, magnetic field change rate, and magnetic field timestamp data. These multi-dimensional features can comprehensively reflect the spatio-temporal change characteristics of the magnetic field signal, providing a rich information resource for subsequent analysis. By extracting these features, the state and changes of the remote control device in space can be captured more accurately. This feature extraction can effectively extract valuable features from the original magnetic field signal, helping to better understand the dynamic changes of the remote control device and enhancing the system's ability to identify and respond to remote control signals. By correlating the multi-dimensional features based on the sensor installation coordinate data, spatial correlation data of the magnetic field of the remote control device is generated. This step ensures the spatial consistency of the magnetic field data, enabling the position and movement of the remote control device to be accurately reflected by the signal. This process optimizes the understanding of spatial information and improves the ability to identify the movement of the device in three-dimensional space, providing stronger support for subsequent signal decoding and remote control mode identification. Lightweight signal decoding (step S22) can extract the core information from the magnetic field detection signal of the standard remote control device to generate a simplified data set. This process reduces the complexity of data processing by removing redundant information, enabling the system to process signals more efficiently and improve the response speed. Through signal decoding optimization (step S23), after identifying the remote control operation intention, the signal decoding is further optimized to generate more accurate control signal data. This not only improves the control accuracy but also enables the remote control device to respond more quickly and accurately to the user's operation intention. By analyzing the lightweight decoded data, the control mode of the remote control can be identified and the operation intention data can be extracted. This process provides the remote control device with the ability to "understand" the user's operation and can identify the actions the user hopes to achieve, such as changing the device position, turning on / off functions, etc. By optimizing the signal decoding process (optimized decoded control signal data), the method can significantly improve the response accuracy of the remote control device to commands, reduce errors, and improve the stability and reliability of device control.

[0026] Preferably, the lightweight signal decoding of the magnetic field detection signal of the standard remote control device according to the spatial correlation data of the magnetic field of the remote control device includes:

[0027] Perform a fast Fourier transform on the magnetic field detection signal of the standard remote control device according to the spatial correlation data of the magnetic field of the remote control device to generate the magnetic field frequency domain data of the remote control device; perform signal morphology analysis on the magnetic field frequency domain data of the remote control device to generate a decoded feature data set;

[0028] Construct a dictionary for the magnetic field detection signals of a standard remote control device by decoding a feature dataset, generating a signal representation dictionary; sparsify the decoded feature dataset based on the signal representation dictionary to generate sparsified remote control device signal data, where the formula for signal sparsification is as follows:

[0029]

[0030] In the formula, represents the decoded feature dataset, represents the matrix composed of basis vectors in the dictionary, represents the sparse coefficient vector, represents the reconstruction error;

[0031] Perform a minimization objective calculation on the sparsified remote control device signal data based on the L1 norm to obtain a sparse coefficient matrix, where the formula for the minimization objective calculation is as follows:

[0032]

[0033] In the formula, represents the sparse coefficient matrix, represents the regularization parameter;

[0034] Use the sparse coefficient matrix to optimize the signal decoding of the lightweight decoded data of the remote control device, generating optimized decoded control signal data.

[0035] By converting the magnetic field signal of the remote control device from the time domain to the frequency domain, the present invention can effectively extract the frequency characteristics of the signal, which enables the subsequent analysis and decoding processes to focus on more meaningful frequency information and reduces the noise interference in the time-domain signal. Through the morphological analysis of the magnetic field frequency-domain data, a decoding feature dataset is generated. These features can help better understand the structure of the signal, thereby improving the decoding accuracy and efficiency. By establishing a signal representation dictionary through the decoding feature dataset, the magnetic field signal of the remote control device can be effectively expressed as a linear combination of basis vectors in the dictionary. This representation method can more efficiently capture the essential features of the signal and reduce redundant data. By representing the signal data with the sparse coefficient vector α, the unimportant parts in the signal can be removed, and only the key information is retained. The sparsification process reduces the complexity of the signal representation, making the subsequent calculations more efficient and fast. By introducing the regularization parameter λ, further optimization of signal sparsification is achieved. The minimization of the L1 norm ensures that the obtained sparse coefficient matrix can best represent the essence of the signal, while avoiding overfitting and improving the generalization ability of the model. By optimizing the decoding of the signal of the remote control device based on the sparse coefficient matrix, optimized decoded control signal data is generated. This optimization process ensures a higher degree of signal restoration, reduces decoding errors, and thus provides a more accurate remote control operation control signal. The optimized decoded control signal enables the remote control device to respond more precisely to the user's operation commands, improving the response speed and accuracy of the device. By adopting a lightweight decoding scheme and combining sparse representation and L1 norm minimization, the computational efficiency of the entire system is significantly improved. This process not only accelerates the signal processing process but also maintains a high accuracy of signal restoration, thus ensuring the stability and efficiency of the system in complex environments.

[0036] Preferably, step S23 includes the following steps:

[0037] Step S231: Extract the dynamic change features of the lightweight decoded data of the remote control device to obtain the lightweight decoded dynamic change feature data of the remote control device; divide the lightweight decoded dynamic change feature data of the remote control device into datasets to generate a model training set and a model test set;

[0038] Step S232: Train the model on the model training set according to the recurrent neural network algorithm to generate a pre-model for remote control mode recognition; optimize and iterate the pre-model for remote control mode recognition based on the model test set to generate a remote control mode recognition model; import the lightweight decoded data of the remote control device into the remote control mode recognition model for label mapping to generate operation label mapping data;

[0039] Step S233: Classify the operation label mapping data by operation category to obtain remote control intention data; based on the remote control intention data, modulate the lightweight decoding data of the remote control device to generate optimized decoded control signal data.

[0040] By extracting the dynamic change features of the lightweight decoding data of the remote control device, the present invention can capture the regularity and volatility of the signal over time. This process helps to extract meaningful time series features from the remote control signal, providing a high-quality data basis for subsequent remote control mode recognition. The extracted feature data is divided into a model training set and a model test set, which ensures that the model can effectively learn the rules during the training process and can evaluate the generalization ability of the model during the test process, avoiding overfitting and improving the reliability of the model. RNN is suitable for processing time series data. By training on the model training set, it can effectively identify the time series patterns in the remote control device signal. Since the remote control device signal often has temporality and time dependence, RNN can capture the long-term dependence relationship in the signal, improving the accuracy of pattern recognition. Through optimization iteration based on the test set, the accuracy and robustness of the model are further improved. This process ensures that the model can not only perform well on the training set but also effectively identify new signals during actual use, reducing the risk of overfitting. The trained and optimized remote control mode recognition model can efficiently decode the remote control device signal and identify the potential remote control modes in the signal. Through model recognition, operation label mapping data is generated, enabling the system to identify the specific operation intentions of the user, such as control commands like switch, adjust position, etc. By classifying the operation label mapping data, different operation types received by the remote control device can be accurately identified. This step ensures that the remote control device can distinguish the specific control objectives of the user, such as adjusting the volume, changing the position, or executing other commands. Modulate the signal according to the remote control intention data to optimize the generation process of the control signal. In this process, the system adjusts the signal according to the identified control intention, thereby generating a more accurate control signal to ensure that the remote control device can execute the user's command in a timely and accurate manner. Finally, optimized decoded control signal data is generated. Through this signal, the remote control device can execute the user's instructions with higher precision and faster response speed. Signal modulation optimization enables the control signal to still work stably and effectively in a complex environment.

[0041] Preferably, step S3 includes the following steps:

[0042] Step S31: Package the optimized decoded control signal data into data packets to generate decoded control signal packets; based on the low-power communication protocol, remotely transmit the decoded control signal packets to generate decoded control signal packet transmission data;

[0043] Step S32: Execute the receiving device instructions on the data transmitted in the decoded control signal packet to obtain the receiving device instruction execution data; analyze the instruction response time of the receiving device instruction execution data to generate the receiving device instruction execution response time.

[0044] Step S33: Optimize the response delay of the receiving device instruction execution data based on the receiving device instruction execution response time to generate a response optimization instruction.

[0045] In the present invention, the optimized decoded control signal data is encapsulated to generate a decoded control signal packet. The packet encapsulation not only provides a standardized structure for signal transmission but also ensures the integrity and consistency of the signal during transmission. This process helps to effectively transmit the control signal from the sending end to the receiving end. By using a low-power communication protocol for remote transmission, the decoded control signal packet can ensure transmission stability while reducing power consumption, which is particularly important for remote control devices in battery-powered or long-running scenarios, enabling the extension of the device's service life and the reduction of energy consumption. By receiving and executing the transmitted data packet, the receiving device can promptly respond to the remote control signal and execute the user's instructions. This process is the core of remote control operation, ensuring that the user's control intention can be accurately understood and executed by the device. Analyzing the response time of the receiving device's instruction execution data can evaluate the time required for the device to receive and execute the remote control signal. This analysis helps to identify potential delay bottlenecks and provides data basis for subsequent response delay optimization. By analyzing the receiving device's instruction execution response time and optimizing the device's response delay, this process adjusts the device's execution strategy based on real-time response data, reducing the delay from instruction reception to execution and enabling the device to respond more quickly to the user's control commands. By optimizing the response delay, the device can provide feedback in a shorter time after receiving the instruction, enhancing the user experience. The improvement in response speed not only reduces the operation waiting time but also makes the remote control device more agile, especially in scenarios requiring quick response, such as game control and smart home device operation, providing a smoother operation experience. Through low-power signal transmission and delay optimization, the device can find the best balance between energy efficiency and response time, ensuring high-precision and stable control performance while saving energy. This makes the remote control device more suitable for long-running and quickly responsive application scenarios, such as automation devices, smart homes, and remote monitoring.

[0046] Preferably, Step S33 includes the following steps:

[0047] Step S331: Identify the response influencing factors of the receiving device instruction execution data based on the receiving device instruction execution response time to generate response influencing factor identification data, where the response influencing factor identification includes network delay identification, device performance identification, and environmental interference identification.

[0048] Step S332: Set the minimization delay optimization target for the response time of the receiving device instruction execution according to the response influence factor identification data to obtain the minimization delay optimization target setting data; optimize the network path for the receiving device instruction execution data based on the minimization delay optimization target setting data to generate network path optimization data;

[0049] Step S333: Optimize the response delay of the receiving device instruction execution data by using the network path optimization data to generate a response optimization instruction.

[0050] Through the comprehensive analysis and optimization of the response time, the overall performance of the system is improved. Especially in applications sensitive to response time, the device can complete instruction execution more quickly. The optimized delay performance enhances the system's instant response ability and provides a better user experience. By optimizing the response delay and enhancing the real-time performance of the system, users can more intuitively feel the fluency of device control. Especially when multiple devices work together, the optimized control instructions can achieve more efficient collaboration. By reducing the network transmission delay and improving the instruction response efficiency, unnecessary energy consumption can be reduced. The optimized network path and device response mechanism not only improve the system performance but also reduce the energy waste of the device during the response delay process. While optimizing the response time, the stability of the system is also improved. Especially in a complex network environment, response delay optimization can effectively avoid response time fluctuations caused by network instability or device performance limitations, ensuring that the device can operate stably in various situations. The optimized response delay significantly reduces the reaction time of the device after receiving the instruction, improving the fluency and real-time feeling of the user experience. When using a remote control device, users can more intuitively feel the efficiency and agility of the system. The effect of response optimization is not limited to speed improvement but also reflected in the improvement of precise control. By reducing the delay and optimizing the network path, users can control the device more precisely and avoid misoperations caused by delay.

[0051] Preferably, step S4 includes the following steps:

[0052] Step S41: Interconnect the receiving device instruction execution data based on the response optimization instruction to generate multi-device collaborative control interconnection data; perform task collaboration and resource allocation on the multi-device collaborative control interconnection data to generate multi-device collaborative control task allocation data;

[0053] Step S42: Feedback the execution status of the multi-device collaborative control task allocation data to generate execution status feedback data; evaluate the remote control completion rate of the execution status feedback data to generate the remote control completion rate;

[0054] Step S43: Compare the remote control completion rate with the preset remote control standard completion rate. When the remote control completion rate is less than the preset remote control standard completion rate, adaptively adjust the multi-device collaborative control task allocation data until the remote control completion rate is greater than or equal to the preset remote control standard completion rate to execute the remote control operation.

[0055] Through device communication and interconnection based on response optimization instructions, the present invention can achieve collaborative operations among multiple devices. By creating multi-device collaborative control interconnection data, devices can share data and coordinate actions with each other, thereby improving the overall efficiency of the system. Task collaboration and resource allocation are performed on the multi-device collaborative control interconnection data to ensure that devices can reasonably allocate the resources required to execute tasks according to their respective characteristics and the requirements of the current task. For example, in a complex automated production line or a smart home system, different devices (such as robots, sensors, controllers, etc.) can cooperate rationally according to task requirements, avoiding resource waste or duplicate task execution. By realizing the effective collaboration of multiple devices, the system can complete complex tasks more efficiently, avoid conflicts or resource redundancy among devices, and thus improve the overall work efficiency and collaboration ability. By providing feedback on the execution status of the multi-device collaborative control task allocation data, the status of each device during task execution can be monitored in real time to understand whether there are task execution deviations or problems. Based on the execution status feedback data, evaluate the remote control completion rate to understand the degree and quality of task completion. This indicator can help determine whether the current collaborative control has achieved the expected goal and whether there are problems such as incomplete execution or delays. For example, if a device fails to complete a task on time when multiple devices collaborate to execute a task, the system can adjust the task allocation in a timely manner through the feedback mechanism to ensure the smooth completion of the task. Real-time execution status feedback and remote control completion rate evaluation can effectively monitor the task execution progress and quality, ensure that the task proceeds as expected, and provide data support for subsequent optimization. Compare the remote control completion rate with the preset remote control standard completion rate to ensure that the execution quality of the task meets the set standards. When the remote control completion rate is lower than the standard, the system will adaptively adjust the multi-device collaborative control task allocation data until the remote control completion rate reaches or exceeds the preset standard. This adaptive adjustment mechanism can dynamically optimize task allocation, ensure the smooth completion of tasks, and improve the flexibility of the system. For example, if a device fails to complete a task on time due to a fault or insufficient resources, the system can automatically adjust the task allocation and reallocate it to other devices to avoid task stagnation or delays.

[0056] In this specification, a remote control device based on a low-power Hall sensor is provided for performing the above-mentioned remote control method based on a low-power Hall sensor. The remote control device based on a low-power Hall sensor includes:

[0057] A sensor deployment module, which is used to obtain remote control device type data; deploy Hall sensors based on the remote control device type data to generate Hall sensor deployment data; calibrate the working magnetic field direction of the Hall sensors for the Hall sensor deployment data to generate Hall sensor deployment correction data; perform real-time signal acquisition on the Hall sensor deployment correction data to obtain a standard remote control device magnetic field detection signal;

[0058] A decoding optimization module, which is used to perform lightweight signal decoding on the standard remote control device magnetic field detection signal to generate remote control device lightweight decoding data; identify the remote control mode for the remote control device lightweight decoding data to generate remote control operation intention data; optimize the signal decoding for the remote control device lightweight decoding data based on the remote control operation intention data to generate optimized decoded control signal data;

[0059] A response optimization module, which is used to remotely transmit the signal packet for the optimized decoded control signal data to generate decoded control signal packet transmission data; analyze the instruction reception response for the decoded control signal packet transmission data to generate receiving device instruction execution data and receiving device instruction execution response time; optimize the response delay for the receiving device instruction execution data through the receiving device instruction execution response time to generate a response optimization instruction;

[0060] A control comparison module, which is used to evaluate the remote control completion rate for the receiving device instruction execution data based on the response optimization instruction to generate a remote control completion rate; compare the remote control completion rate with a preset remote control standard completion rate. When the remote control completion rate is less than the preset remote control standard completion rate, adaptively adjust the multi-device collaborative control task allocation data until the remote control completion rate is greater than or equal to the preset remote control standard completion rate to execute the remote control operation.

[0061] The beneficial effects of the present invention are as follows: By obtaining the data of the remote control device type and deploying Hall sensors based on its characteristics, the accurate deployment of the sensors is ensured, and the accuracy and stability of signal acquisition are improved. Through the calibration of the working magnetic field direction and real-time signal acquisition, a standard magnetic field detection signal for the remote control device is generated, effectively reducing errors and interference in the signal acquisition process, thereby improving the reliability and accuracy of the remote control system. By performing lightweight decoding and remote control mode recognition on the standard magnetic field detection signal of the remote control device, data redundancy is effectively reduced, and the data processing speed and efficiency are improved. The decoding optimization based on the control intention not only improves the decoding accuracy but also makes the transmission of control signals more efficient, reduces unnecessary decoding burdens, and optimizes the response ability of the system. By remotely transmitting the optimized decoded control signal packet and combining the analysis of the instruction execution response time, the response delay of the receiving device is optimized, thereby significantly reducing the delay in the signal transmission process and improving the real-time response ability of the remote control system. This ensures the timeliness and efficiency of device control, especially in real-time control tasks, and reduces the operational inaccuracy caused by delay. By evaluating the completion rate of the remote control and comparing it with the preset standard, the completion status of the control task is monitored in real time. By adaptively adjusting the multi-device collaborative control task allocation, it is ensured that the system can continuously meet the remote control standards in a complex multi-device environment. This not only improves the adaptability and flexibility of the system but also guarantees the efficiency and stability during the collaborative work among devices, thus ensuring the smooth execution of remote control operations. Therefore, the present invention improves the accuracy and efficiency of remote control by optimizing the deployment of Hall sensors, signal decoding, response delay, and multi-device collaborative control. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 FIG. is a schematic flow chart of the steps of a remote control method based on a low-power Hall sensor;

[0063] Figure 2 is Figure 1 a detailed implementation step flow chart of step S2 in

[0064] Figure 3 is Figure 1 a detailed implementation step flow chart of step S3 in

[0065] The realization, functional characteristics, and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0066] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0067] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0068] It should be understood that although terms such as "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0069] To achieve the above object, please refer to Figures 1 to 3 , a remote control method based on a low-power Hall sensor, the method comprising the following steps:

[0070] Step S1: Obtain remote control device type data; deploy Hall sensors based on the remote control device type data to generate Hall sensor deployment data; calibrate the working magnetic field direction of the Hall sensors for the Hall sensor deployment data to generate Hall sensor deployment correction data; perform real-time signal acquisition on the Hall sensor deployment correction data to obtain a standard remote control device magnetic field detection signal;

[0071] Step S2: Perform lightweight signal decoding on the standard remote control device magnetic field detection signal to generate remote control device lightweight decoding data; perform remote control mode recognition on the remote control device lightweight decoding data to generate remote control operation intention data; optimize the signal decoding of the remote control device lightweight decoding data based on the remote control operation intention data to generate optimized decoded control signal data;

[0072] Step S3: Remotely transmit the signal packet of the optimized decoded control signal data to generate decoded control signal packet transmission data; perform instruction reception response analysis on the decoded control signal packet transmission data to generate receiving device instruction execution data and receiving device instruction execution response time; optimize the response delay of the receiving device instruction execution data through the receiving device instruction execution response time to generate a response optimized instruction;

[0073] Step S4: Evaluate the completion rate of remote control for the data of received device instructions based on the response optimization instruction to generate the remote control completion rate; compare the remote control completion rate with the preset standard completion rate of remote control. When the remote control completion rate is less than the preset standard completion rate of remote control, adaptively adjust the multi-device collaborative control task allocation data until the remote control completion rate is greater than or equal to the preset standard completion rate of remote control to execute the remote control operation.

[0074] The present invention ensures that the Hall sensor can adapt to the working environments of different remote control devices by obtaining the remote control device type data and precisely deploying the Hall sensor according to the device characteristics. After calibrating the working magnetic field direction of the sensor, it can accurately collect the standard magnetic field detection signals of the remote control devices, thereby improving the accuracy and reliability of the signals. The lightweight signal decoding reduces the data burden during transmission and improves the decoding efficiency; through remote control mode recognition, it can accurately capture the control intentions of the remote control devices, further enhancing the system's response ability to remote control operations. The signal decoding optimization based on the control intentions reduces redundant information and improves the decoding accuracy and speed of the signals. The optimized decoded control signal packet can be transmitted more effectively remotely, reducing signal loss and interference. By analyzing and optimizing the instruction execution response time of the receiving device, the response delay is significantly reduced, improving the real-time performance and stability of the system and ensuring the timely feedback of remote control operations. By evaluating the remote control completion rate, it can monitor the execution effect of the remote control task in real time and ensure the smooth completion of the control task. The adaptive adjustment of the multi-device collaborative control task can dynamically optimize the task allocation according to the actual situation, improving the flexibility and scalability of the system and ensuring that the remote control task can still meet the preset standards in complex environments. Therefore, the present invention improves the accuracy and efficiency of remote control by optimizing the Hall sensor deployment, signal decoding, response delay, and multi-device collaborative control.

[0075] In the embodiment of the present invention, refer to Figure 1 As shown, it is a schematic flow chart of the steps of a remote control method based on a low-power Hall sensor according to the present invention. In this example, the remote control method based on a low-power Hall sensor includes the following steps:

[0076] Step S1: Obtain the remote control device type data; perform Hall sensor deployment based on the remote control device type data to generate Hall sensor deployment data; calibrate the working magnetic field direction of the sensor for the Hall sensor deployment data to generate Hall sensor deployment correction data; perform real-time signal acquisition on the Hall sensor deployment correction data to obtain the standard magnetic field detection signals of the remote control devices;

[0077] In an embodiment of the present invention, the device type information is obtained through the hardware identification of the remote control device (such as model, manufacturer, built-in sensor type). Hardware identification can obtain the device ID, version number, etc. through the firmware or driver of the device. In the application layer software of the remote control device, the basic information of the device is obtained through the API interface or communication protocol (such as Bluetooth, Wi-Fi). According to the obtained device identification data, the specific type of the remote control device (such as home remote control, industrial control remote control, etc.) is analyzed, and this information helps to determine the subsequent sensor deployment and configuration. According to the acquired remote control device type data, a suitable Hall sensor model is selected. Different types of remote control devices require different types of Hall sensors (such as sensing range, sensitivity, installation method, etc.). When selecting a Hall sensor, the spatial layout of the device, the task requirements (such as measurement accuracy), and the degree of magnetic field interference in the working environment should be considered. According to the type and design of the remote control device, determine the installation location of the Hall sensor (for example, on the housing of the remote control device, near the button, in the control module area, etc.). Use magnetic fixing, screw fixing or gluing to install it to ensure the stability and reliability of the sensor. According to the interface type of the device, select a suitable connection method (such as analog signal interface, digital signal interface or wireless communication). After deployment is complete, record the specific installation location, installation angle, sensor type, working parameters and other information of the Hall sensor, and generate Hall sensor deployment data for use in subsequent steps. Determine the installation coordinates of each Hall sensor for subsequent magnetic field direction calibration. Obtain the spatial coordinates of the sensor by calculation or using the sensor's built-in positioning system (such as optical sensor, laser scanner, etc.). Use the device's built-in positioning data or external positioning system (such as GPS, IMU) to record the precise coordinates of the Hall sensor in space. Use the sensor's installation coordinates and the device's reference coordinate system (such as device housing, axis, etc.) to calculate the installation angle of each Hall sensor. Perform angle calibration by accurately measuring the sensor's installation angle and comparing it with the device's design parameters. Compare the data of multiple Hall sensors horizontally to analyze the magnetic field direction and strength measured by different sensors. Perform azimuth aggregation based on the magnetic field direction data, that is, aggregate the data of multiple sensors into unified magnetic field direction data and compare it with the design parameters. Correct the working direction of the Hall sensor based on the calibrated angle data and magnetic field direction data, generate Hall sensor deployment correction data, and ensure that the measurement data of each sensor is accurate. Start the Hall sensor for real-time data collection and obtain the sensor's sensing data of the magnetic field in the working state. The signal collected by the sensor can be an analog signal (converted to a digital signal through ADC) or a digital signal (output data directly through a digital interface). Perform data preprocessing on the collected raw signal to remove noise, enhance the signal, and perform filtering. Apply filters (such as low-pass filters and high-pass filters) to remove unnecessary noise and maintain valid signals.Enhance the signal according to the characteristics of the magnetic field to improve the signal-to-noise ratio. Adjust the signal to the standard range to ensure that it will not be affected by the range in subsequent processing. After signal preprocessing, the standard magnetic field detection signals of the remote control device are obtained, and these signals will be used as input data for subsequent operations, such as remote control mode recognition and signal decoding.

[0078] Step S2: Perform lightweight signal decoding on the standard magnetic field detection signals of the remote control device to generate lightweight decoded data of the remote control device; perform remote control mode recognition on the lightweight decoded data of the remote control device to generate remote control operation intention data; optimize the signal decoding of the lightweight decoded data of the remote control device based on the remote control operation intention data to generate optimized decoded control signal data;

[0079] In the embodiment of the present invention, the fast Fourier transform (FFT) is used to perform frequency domain conversion on the standard magnetic field detection signals of the remote control device, converting the time domain signal into a frequency domain signal. FFT decomposes the signal into different frequency components, which helps to extract the periodic information in the signal and reduce the computational complexity in the decoding process. The frequency domain data of the magnetic field of the remote control device generated by FFT includes the amplitude and phase information of different frequency components. Perform signal morphology analysis on the frequency domain data after FFT conversion to extract the features helpful for decoding, including frequency distribution, amplitude change trend, phase change, etc. Determine the periodicity, repeating pattern, and signal change rule of the signal through time domain and frequency domain analysis of the signal. Use the dictionary learning method to construct a dictionary for the decoding feature data set. The dictionary consists of a set of basis vectors and is used to represent the main components of the signal. Match the decoding feature data set with the dictionary and perform sparsification processing on the signal through sparse representation technology. The goal of sparsification is to find the core components of the signal and represent them with fewer coefficients. The specific calculation formula is: ; where is the decoding feature data set, is the dictionary matrix, is the sparse coefficient vector, is the reconstruction error. Perform minimization calculation on the sparsified signal data based on the L1 norm to obtain the sparse coefficient matrix: , where Denoted as a regularization parameter, it is used to control the sparsity. The sparse coefficient matrix is utilized to reconstruct and decode the magnetic field detection signals of the standard remote control device, thereby generating lightweight decoded data of the remote control device. These data contain the control signal information of the remote control device, but through sparse representation and optimization, they are convenient for fast transmission and processing. The lightweight decoded data of the remote control device generated from step S2 represent the control signals of the remote control device and can include information such as the mode of the remote control device, key events, and direction control. Dynamic change features of the lightweight decoded data of the remote control device are extracted to obtain the change rules and time series features of the signals. The features include the change rate of the signal, timing pattern, periodicity, etc. The dynamic change feature data are divided into a model training set and a model test set. Deep learning algorithms such as recurrent neural network (RNN) or long short-term memory network (LSTM) are used to train the training set to learn the operation mode of the remote control device. These models can process sequential data and identify dynamic changes over time, making them suitable for remote control mode recognition. During the training process, the network automatically extracts the timing features of the remote control operations based on the input lightweight decoded data and learns the relationships between different modes. Model evaluation is performed on the model test set, and the recognition model is iteratively optimized through backpropagation and optimization algorithms. By continuously adjusting the network parameters, the accuracy of remote control mode recognition is improved. The trained remote control mode recognition model is used to predict the lightweight decoded data of the remote control device, thereby generating remote control operation intention data. These data represent the user's control intentions, such as key operations, adjusting directions, or switching modes. Based on the remote control operation intention data, signal modulation is performed on the lightweight decoded data of the remote control device. According to the operation intention, the parameters of the decoded signal are adjusted, such as changing the signal frequency, amplitude, etc., in order to execute user operations more accurately. The modulated signal is combined with the original decoded data to generate optimized decoded control signal data. The optimized control signal is more precise and can achieve faster response time and higher control accuracy.

[0080] Step S3: Remotely transmit the signal packet of the optimized decoded control signal data to generate decoded control signal packet transmission data; perform instruction reception response analysis on the decoded control signal packet transmission data to generate receiving device instruction execution data and receiving device instruction execution response time; optimize the response delay of the receiving device instruction execution data through the receiving device instruction execution response time to generate response-optimized instructions;

[0081] In the embodiments of the present invention, the optimized decoding control signal data (including various instructions, parameters, configurations, etc.) is encapsulated into a standard data packet format. This format should have efficient compression and encryption capabilities to reduce latency and security risks during transmission. Design a data packet format that includes header information (such as packet header, target device ID, timestamp, data length, etc.), data body (actual control signal data), and tail information (such as checksum, integrity verification information). Use appropriate compression algorithms (such as LZ4 or Zstd) and encryption algorithms (such as AES) to process the data packets to ensure transmission efficiency and data security. Remotely transmit the signal packets to the receiving device via the Internet, wireless network, or dedicated communication link. Adopt reliable transmission protocols (such as TCP / IP, QUIC) to ensure the accurate arrival of the data packets. Select the most suitable protocol according to the application scenario. If high reliability and low packet loss rate are required, the TCP protocol is a better choice; if lower latency is needed, QUIC is more suitable. Perform bandwidth control according to the actual network conditions to ensure that high-priority data packets can be transmitted first and avoid delays caused by network congestion. After the receiving device receives the signal packet, first perform data parsing to extract the decoding control signal and instruction content. And record information such as the processing status and timestamp of the receiving device. Extract the instruction part in the data packet (such as control commands, execution parameters, etc.), and allocate appropriate processing resources according to the processing capabilities and characteristics of the receiving device. Record the time interval from when the receiving device receives the instruction to when it starts to execute, that is, the "instruction execution response time". Analyzing this period helps to evaluate the system performance and response efficiency. Conduct in-depth analysis of the instruction execution response time of the receiving device to identify latency bottlenecks. The main analysis factors include network latency, receiving device processing capabilities, instruction complexity, etc. Through log records and real-time monitoring data, find the main factors affecting the response time. For example, when the network latency is high, the data transmission path can be optimized or the bandwidth can be increased; when the receiving device has insufficient processing capabilities, the device resource allocation can be optimized. Use machine learning models (such as linear regression, decision tree, etc.) to predict future response delays based on historical response time data and optimize. If multiple instructions have similar execution requirements, batch processing can be adopted to reduce the response time of each instruction. Adjust the priority of instruction execution according to the importance and urgency of the instructions. High-priority instructions can be processed first to reduce latency. According to the network analysis results, adjust the transmission path and select the optimal network transmission protocol to reduce the network transmission time. According to the optimization analysis results, generate response optimization instructions to adjust the signal packet transmission and receiving device processing strategies in the system, or directly adjust the processing capabilities and network settings of the receiving device. According to the real-time response delay analysis, the system automatically or manually intervenes to perform dynamic optimization scheduling of the instructions. The optimized instructions are fed back to the receiving device, and the device adjusts the execution process according to the new optimization strategy to reduce subsequent response delays.

[0082] Step S4: Evaluate the completion rate of remote control for the received device instruction execution data based on the response optimization instruction, and generate the remote control completion rate; compare the remote control completion rate with the preset remote control standard completion rate. When the remote control completion rate is less than the preset remote control standard completion rate, adaptively adjust the multi-device collaborative control task allocation data until the remote control completion rate is greater than or equal to the preset remote control standard completion rate to perform the remote control operation.

[0083] In the embodiments of the present invention, the defined Remote Control Completion Rate (CCR) refers to the ratio of the number of instructions successfully executed and responded by the receiving device within a certain period of time. The specific formula is: CCR = (Number of successfully executed instructions ÷ Total number of instructions) × 100%. The number of successfully executed instructions refers to the number of instructions that the receiving device successfully executes and produces the expected effect, and the total number of instructions refers to the total number of instructions received within the evaluation time window. The system monitors the execution process of the receiving device in real time and records the execution status of each instruction, including successful execution, failed execution, timeout execution, etc. Combining the execution data after optimizing the response instructions, evaluate the execution time, response time, and execution result of each instruction, and calculate the remote control completion rate of each device. Based on the above data, comprehensively evaluate the instruction execution situation of all receiving devices, and finally obtain the remote control completion rate of the system. When designing the system, a target remote control completion rate is set according to actual requirements and system performance requirements. For example, the preset standard can be 95%, which means that the system expects more than 95% of the instructions to be successfully executed. The preset standard can be dynamically adjusted according to the specific application scenario and device performance of the system. Compare the actually calculated remote control completion rate with the preset standard completion rate to evaluate the current remote control ability of the system. If the remote control completion rate is lower than the preset standard, it indicates that the system fails to achieve the expected control ability and needs further optimization. When the remote control completion rate is less than the preset standard, the system needs to dynamically adjust the multi-device collaborative control task to improve the overall completion rate. The adaptive adjustment can be carried out in the following ways: Reallocate the control tasks to the devices with lighter loads to avoid the failure or delay of execution caused by some devices being overloaded. Dynamically allocate tasks by calculating the load capacity of each device (such as response time, task execution success rate, etc.). Adjust the priority of the instructions according to the execution ability of the device and the urgency of the task. Give priority to allocating key tasks to devices with stronger execution abilities to ensure the successful completion of key tasks. Optimize resource scheduling according to the real-time status of the device (such as battery power, processing ability, network bandwidth, etc.) to ensure that each device executes tasks in its best state. Allocate multiple tasks to different devices to reduce the burden on a single device and improve the remote control completion rate of the entire system. By coordinating the work processes of multiple devices, reduce conflicts and duplicate work between devices and improve the overall collaborative control efficiency. The system can set a feedback mechanism to adjust the task allocation strategy in real time according to the adjusted task allocation and remote control completion rate. The system continuously monitors the remote control completion rate to ensure the effect after task allocation and resource scheduling adjustment. If the remote control completion rate is lower than the preset standard, continue to adjust; if it reaches or exceeds the preset standard, the system will enter the normal remote control mode. When the remote control completion rate reaches or exceeds the preset standard, stop the adaptive adjustment, confirm that the system has been optimized to the best state, and start executing the remote control operation.After ensuring that the remote control completion rate is greater than or equal to the preset standard, the system will start to execute the remote control task. At this time, the device performs control operations according to the predetermined task, and the system continues to monitor the execution situation to ensure efficient and stable control.

[0084] Preferably, step S1 includes the following steps:

[0085] Step S11: Obtain remote control device type data;

[0086] Step S12: Select the Hall sensor type based on the remote control device type data to obtain the Hall sensor type data of the remote control device; deploy the Hall sensor according to the Hall sensor type data of the remote control device to generate Hall sensor deployment data;

[0087] Step S13: Sense the device magnetic field of the remote control device according to the Hall sensor deployment data to generate remote control device magnetic field sensing data; calibrate the working magnetic field direction of the Hall sensor according to the remote control device magnetic field sensing data to generate Hall sensor deployment correction data;

[0088] Step S14: Collect real-time signals from the Hall sensor deployment correction data to obtain the original magnetic field detection signal of the remote control device; preprocess the original magnetic field detection signal of the remote control device to generate a standard remote control device magnetic field detection signal, where the signal preprocessing includes signal denoising, signal enhancement, and signal normalization.

[0089] In the embodiments of the present invention, it is connected to a remote control device through the hardware interfaces of the device (such as serial ports, I2C, SPI, etc.) or wireless communication interfaces (such as Bluetooth, Wi-Fi, etc.). These interfaces can obtain the basic information of the device, such as model, hardware specifications, sensor types, etc. Use standard protocols (such as Device Description Protocol, DDP) to communicate with the device to obtain the device type and functional parameters. For some intelligent remote control devices, query the device type information through the built-in storage of the device or from the cloud database. Use specific algorithms or rules to classify the device type. For example, determine the category of the device (such as smart home, robot, remote control car, etc.) through the hardware identification code (ID) or configuration file of the device. If the device has multiple sensors and functions, it can be parsed and classified through a software configuration file. According to the device type data (for example, the working scenario and usage environment of the remote control device), select a suitable Hall sensor type. For example: for devices with high-precision positioning requirements, select a linear Hall sensor, which can provide a continuous magnetic field intensity output. For simple magnetic field detection applications, select a digital Hall sensor, which can provide a switching signal of the magnetic field. The selection of the sensor is based on factors such as the magnetic field induction requirements, accuracy requirements, and working environment of the device. Based on the device type data, analyze the performance of different types of sensors through intelligent algorithms (such as machine learning models) and select the Hall sensor that best matches the device. For example, make an automatic selection based on the sensor configuration file and working conditions (such as temperature, humidity, magnetic field intensity) of the device. According to the design requirements of the remote control device, select a suitable position to install the Hall sensor. Common deployment positions include the outer surface of the remote control or near the control unit to ensure that the magnetic field changes around the device can be sensed. Install it inside the device through PCB design, soldering, or sensor module to ensure the stability and accuracy of the sensor. For devices with high-precision requirements, multiple points will also be arranged to obtain more comprehensive magnetic field information. Start the sensor for real-time sensing. Using the Hall effect principle, detect the magnetic field direction and intensity where the device is located. The Hall sensor will convert the magnetic field signal into a voltage signal and transmit it to a processing unit (such as a microcontroller, FPGA, etc.) for further processing. Collect the sensor data and store it to form preliminary magnetic field sensing data, which includes the magnetic field intensity and direction information at the sensor position. Analyze the magnetic field sensing data collected by the remote control device to determine whether the sensor is in the correct working direction. Vector operations can be used to analyze the deviation between the output voltage of each Hall sensor and the theoretical magnetic field direction. If a deviation is found, the sensor installation position needs to be adjusted or the working direction of the sensor needs to be adjusted. Dynamically calibrate the magnetic field direction of the Hall sensor through algorithms (such as the least squares method or Kalman filter) to generate correction coefficients, which will be used to correct the error of the sensor direction in subsequent data processing.If the device permits, directly adjust the hardware position of the sensor or rotate the sensor to ensure its alignment with the magnetic field direction of the device. Based on the calibration process, generate calibration data for the Hall sensor deployment, including the calibrated angle, direction coefficient, etc.

[0090] Preferably, calibrating the working magnetic field direction of the Hall sensor for the Hall sensor deployment data according to the magnetic field perception data of the remote control device includes:

[0091] Confirm the sensor installation coordinates for the Hall sensor deployment data to obtain the sensor installation coordinate data; analyze the installation angle for the Hall sensor deployment data based on the sensor installation coordinate data to generate the sensor installation angle data;

[0092] Extract the induction data of a single Hall sensor from the magnetic field perception data of the remote control device to obtain the Hall sensor induction data, where the extraction of the Hall sensor induction data includes magnetic field strength extraction, magnetic field direction extraction, and magnetic field change extraction; aggregate and compare the lateral magnetic field azimuth based on the Hall sensor induction data to generate the lateral magnetic field azimuth aggregation data;

[0093] Adjust the installation azimuth of the Hall sensor deployment data according to the lateral magnetic field azimuth aggregation data to generate the Hall sensor deployment calibration data.

[0094] In the embodiments of the present invention, the installation position of the sensor is defined by using the three-dimensional coordinate system of the device (e.g., based on the Cartesian coordinate system X, Y, Z). The sensor installation coordinate data is usually obtained through measuring tools (such as laser rangefinders, 3D scanners, etc.) to ensure the accuracy of the position of the Hall sensor in space. If the device has multiple sensors, ensure that the relative positions of the sensors are correctly represented within the coordinate system of the device. Use the internal positioning system or image recognition technology of the device (such as computer vision, AR technology, etc.) for auxiliary positioning to ensure that the installation coordinates of each sensor are consistent with the design requirements. After obtaining the sensor installation coordinate data, it is necessary to analyze the installation angle. The goal of the installation angle analysis is to ensure that the installation angle (the included angle with the coordinate system or magnetic field direction of the device) of each Hall sensor meets the requirements. According to the installation position coordinates of the sensor, use the principles of spatial geometry to calculate the installation angle of the Hall sensor relative to the device coordinate system. Usually, the angle between the sensor and the axis of the device coordinate system can be calculated through the vector dot product formula: ; where is the installation direction vector of the sensor, is the magnetic field direction vector of the device, It is the included angle between the two. If there is a deviation in the installation angle of the sensor, a mechanical device needs to be used for physical adjustment, or the sensor installation angle data needs to be corrected through software. If the installation angle does not meet the requirements, optimize and adjust based on software correction or physical adjustment of the sensor to generate accurate installation angle data. Each Hall sensor generates different induction signals, indicating the intensity, direction, and change of the magnetic field. Extract these data through the following steps: The Hall sensor outputs a voltage signal proportional to the magnetic field intensity. These signals can be collected through an ADC (analog-to-digital converter) and converted into digital data, representing the sensed magnetic field intensity. The Hall sensor can sense the direction of the magnetic field. By combining the change of the induction signal with the installation direction of the sensor, the direction of the magnetic field can be deduced. The specific method is to compare with the installation direction of the sensor and analyze the direction of the magnetic field using vector operations. The magnetic field change refers to the change of the magnetic field intensity sensed by the sensor over time. Through real-time signal acquisition, the data of the magnetic field change can be extracted and its fluctuation can be analyzed. Through data processing techniques (such as filtering, smoothing, etc.), the collected magnetic field induction data is structured to obtain a clear set of induction data, which includes the magnetic field intensity, direction, and change information of each sensor. To obtain comprehensive magnetic field sensing data, it is necessary to make a horizontal comparison of the data of multiple Hall sensors. By comparing the magnetic field directions sensed by the sensors at different positions of the device, the magnetic field distribution around the entire device can be obtained. Aggregate analysis is performed on the magnetic field directions of all sensors, especially analyzing the magnetic field change situation between sensors in the horizontal direction (perpendicular to the main direction of the device). This step includes calculating the magnetic field direction difference between sensors and identifying the horizontal change trend of the magnetic field. By making a horizontal comparison of the magnetic field data sensed by different sensors, horizontal magnetic field azimuth aggregation data is generated, which includes the change patterns of the magnetic field intensity and direction, the magnetic field deviation existing in the device, etc. According to the horizontal magnetic field azimuth aggregation data, analyze whether the installation azimuth of each Hall sensor matches the overall magnetic field direction of the device. If a deviation is found, the position and angle of the Hall sensor can be adjusted. If there are significant differences in the magnetic field directions sensed by multiple sensors, the installation angle of the sensors needs to be adjusted or the positions of the sensors need to be rearranged. This adjustment can be achieved through hardware adjustment (such as rotating the sensor) or through software algorithm compensation. The adjusted sensor azimuth generates new deployment correction data. The correction data includes the final installation angle, azimuth, and adjustment parameters of the sensor. This data can be used for subsequent magnetic field induction calculations and device control optimization.

[0095] As an example of the present invention, refer to Figure 2 shown. In this example, step S2 includes:

[0096] Step S21: Extract multi-dimensional magnetic field features from the magnetic field detection signal of the standard remote control device to obtain multi-dimensional magnetic field feature data of the remote control device, where the multi-dimensional magnetic field feature data of the remote control device includes magnetic field intensity feature data, magnetic field change rate feature data, and magnetic field timestamp data;

[0097] Step S22: Perform spatial information association on the magnetic field intensity feature data, magnetic field change rate feature data, and magnetic field timestamp data based on the sensor installation coordinate data to generate spatially associated magnetic field data of the remote control device; perform lightweight signal decoding on the magnetic field detection signal of the standard remote control device according to the spatially associated magnetic field data of the remote control device to generate lightweight decoded data of the remote control device;

[0098] Step S23: Identify the remote control mode for the lightweight decoded data of the remote control device to generate remote control operation intention data; optimize the signal decoding for the lightweight decoded data of the remote control device based on the remote control operation intention data to generate optimized decoded control signal data.

[0099] In the embodiments of the present invention, the magnetic field signals of the remote control device are collected in real time by using Hall sensors to obtain the original magnetic field detection signals, which usually show a voltage output proportional to the magnetic field strength. The collected original magnetic field signals are subjected to signal denoising and filtering processes to remove high-frequency noise and external interference. Common filtering methods include low-pass filtering, Kalman filtering, etc. The intensity characteristics of the magnetic field are extracted from the denoised signals, usually by calculating the instantaneous amplitude of the signals (for example, using the square root algorithm to calculate the amplitude of the signals) to obtain the magnetic field intensity data. According to the time series data (the magnetic field intensity values corresponding to each timestamp), the change rate of the magnetic field intensity at different time points (i.e., the derivative of the magnetic field intensity) is calculated. The change rate of the magnetic field intensity is obtained through the differential calculation of the signals, usually calculated by the following formula: change rate = (magnetic field intensity at the current moment - magnetic field intensity at the previous moment) ÷ time interval. Each collected magnetic field signal corresponds to a timestamp, which is used to mark the time sequence of the signals. The timestamp data is important information for analyzing the change of the magnetic field over time. The timestamps are converted into a unified format (such as UTC format) for subsequent data analysis and processing. The extracted magnetic field intensity, change rate, and timestamp data are combined into a multi-dimensional feature data set, which will serve as the basis for subsequent analysis. According to the installation coordinates of each Hall sensor (including spatial position and installation angle), the magnetic field characteristics (including intensity, change rate, and timestamp) collected by the sensor are mapped into the spatial coordinate system of the device, so that the data collected by each sensor can be associated with the physical position and orientation of the device. By establishing a three-dimensional space coordinate system (such as using the Cartesian coordinate system), the magnetic field data of each sensor is mapped to its specific position in the device, and then the "magnetic field space correlation data" is obtained. This step can map the two-dimensional data of each sensor to the three-dimensional space by methods such as linear transformation and rotation matrix. The magnetic field data (intensity, change rate, and timestamp) of each sensor is combined with its spatial coordinate data to form a unified magnetic field space data structure. According to the timestamps and spatial coordinates, spatio-temporal correlation analysis is carried out to identify the relationship between the magnetic field data collected by different sensors at the same time point. The data is grouped by clustering algorithms (such as K-means or DBSCAN) to identify the magnetic field change patterns in the same area. The processed magnetic field intensity, change rate, and timestamp data are associated with the spatial coordinate data of the sensor to generate the final "remote control device magnetic field space correlation data", which can be represented by a data table or a structured data format (such as JSON, XML). Based on the magnetic field space correlation data, the core features of the signal are extracted by performing lightweight decoding on the signal to generate the "remote control device lightweight decoding data". This process mainly removes redundant information and retains the key spatial and temporal information for subsequent manipulation mode recognition. Based on the lightweight decoding data (such as magnetic field intensity, change rate, timestamp, spatial coordinates, etc.), key features are selected for pattern recognition.Feature selection can use techniques such as PCA (Principal Component Analysis) to reduce the dimensionality and retain the features that best represent the remote control mode. Using an existing manipulation dataset (e.g., trained through historical manipulation data), train a machine learning model (such as Support Vector Machine (SVM), Random Forest, Neural Network, etc.), which can identify different manipulation modes based on the input magnetic field features. For example, by analyzing the change patterns of the magnetic field features, it can identify whether the user is performing operations such as forward, backward, left turn, right turn, etc. The machine learning model will output the prediction results of the manipulation mode (such as forward, backward, turning, etc.), which is the "remote control manipulation intention data". This data can be used to directly control the behavior of the remote control device. Convert the manipulation intention data into an easy-to-process format, such as passing the recognition results to subsequent systems or devices for execution through formats such as JSON, XML, etc. Based on the manipulation intention data, optimize the signal decoding of the remote control device. By combining real-time feedback data (such as the delay and error of sensor signals), adjust the decoding algorithm to make the decoding process more efficient and accurate. The decoding accuracy can be further improved by dynamically learning and adjusting algorithm parameters. For example, according to different manipulation modes of the device, dynamically adjust the decoding strategy to adapt to different remote control requirements. Based on the optimized signal decoding, generate accurate control signal data and transmit it to the control system of the remote control device. This control signal data can be directly used to execute remote control instructions.

[0100] Preferably, lightweight signal decoding of the standard remote control device magnetic field detection signal according to the remote control device magnetic field spatial correlation data includes:

[0101] Perform a fast Fourier transform on the standard remote control device magnetic field detection signal according to the remote control device magnetic field spatial correlation data to generate remote control device magnetic field frequency domain data; perform signal morphology analysis on the remote control device magnetic field frequency domain data to generate a decoding feature dataset;

[0102] Construct a dictionary for the standard remote control device magnetic field detection signal through the decoding feature dataset to generate a signal representation dictionary; perform signal sparsification on the decoding feature dataset based on the signal representation dictionary to generate sparsified remote control device signal data, where the formula for signal sparsification is as follows:

[0103]

[0104] In the formula, is expressed as the decoding feature dataset, is expressed as the matrix composed of basis vectors in the dictionary, is expressed as the sparse coefficient vector, is expressed as the reconstruction error;

[0105] Based on the L1 norm, the minimization objective is calculated for the sparsified signal data of the remote control device to obtain a sparse coefficient matrix. The formula for the minimization objective calculation is as follows:

[0106]

[0107] In the formula, is represented as the sparse coefficient matrix, is represented as the regularization parameter;

[0108] The sparse coefficient matrix is used to optimize the signal decoding of the lightweight decoded data of the remote control device, generating optimized decoded control signal data.

[0109] In the embodiments of the present invention, the magnetic field detection signal of the remote control device (i.e., the standard magnetic field detection signal collected by the Hall sensor) is used as the input signal. Specifically, this signal is a time-domain signal, containing the change information of the magnetic field of the remote control device. Through the Fast Fourier Transform (FFT), the time-domain signal is converted into a frequency-domain signal. The FFT algorithm can convert a discrete-time signal into its frequency components, helping to extract the periodic information and frequency characteristics in the signal. Through FFT processing, the magnetic field frequency-domain data of the remote control device is obtained, and these data include the amplitude and phase information of each frequency component. By analyzing the frequency-domain signal, the significant frequency components in the signal are extracted. The main frequency components and the noise part can be identified through spectrum analysis (e.g., by calculating the power spectral density). The frequency-domain signal is filtered to remove high-frequency noise and extract the main features of the signal, such as the center frequency, bandwidth, phase information, etc. of the frequency band. The feature information obtained from the above analysis (such as frequency-domain features, phase features, amplitude features, etc.) is organized into a decoded feature dataset, which is used for subsequent dictionary learning and sparsification processing. The goal of dictionary learning is to extract a set of basis vectors from the decoded feature dataset, and these basis vectors can effectively represent the magnetic field detection signal of the remote control device. A dictionary learning method based on sparse coding (such as the K-SVD algorithm) is used to generate the dictionary. This method will automatically learn a set of basis vector sets that can best represent the signal according to the decoded feature dataset. Through an iterative manner, the basis vectors in the dictionary are continuously updated, so that the representation of each feature dataset can be approximated with the least sparse coefficients. For each feature dataset X, it is represented by the dictionary D and the sparse coefficient α: X≈D⋅α, where D is a matrix composed of the learned dictionary basis vectors, and α is a sparse coefficient vector, representing the sparse representation of the signal under the dictionary basis vectors. Through dictionary learning, a dictionary containing multiple basis vectors is generated, and these basis vectors can efficiently represent the magnetic field signal of the remote control device. The signal can be represented by the combination of these basis vectors and sparse coefficients. Through the sparse coding method, the decoded feature dataset is sparsified using the signal representation dictionary, that is, the original signal is represented as a linear combination of the dictionary basis vectors through the sparse coefficient α. The formula for signal sparsification is: In the formula, is represented as the decoded feature dataset, is represented as a matrix composed of the basis vectors in the dictionary, is represented as the sparse coefficient vector, is represented as the reconstruction error; the optimization goal of the sparsification process is to make the representation of the signal under the dictionary basis vectors as sparse as possible while minimizing the reconstruction error. This goal can be achieved through the L1 norm constraint, specifically where, is the sparse coefficient matrix, is the regularization parameter, controlling the degree of sparsity. Through the L1 norm on the coefficient Perform punishment to make the coefficients as sparse as possible, thereby reducing the redundant part of the signal. Use optimization algorithms (such as ISTA, FISTA, etc.) for iterative calculation to obtain a sparse coefficient matrix . Use the sparse coefficient matrix to optimize the signal decoding of the remote control device. The optimized control signal should be able to more accurately reflect the operation intention of the remote control device and remove redundant information. Based on the sparse coefficient matrix and the dictionary , the optimized signal can be reconstructed: X′ = D ⋅ A; where X′ is the optimized signal, reflecting the actual control state of the remote control device. Generate a decoded control signal for controlling the remote control device through the optimized signal data. This signal will be used to drive the actual operation of the remote control device.

[0110] Preferably, step S23 includes the following steps:

[0111] Step S231: Extract the dynamic change features of the lightweight decoding data of the remote control device to obtain the lightweight decoding dynamic change feature data of the remote control device; divide the lightweight decoding dynamic change feature data of the remote control device into data sets to generate a model training set and a model test set;

[0112] Step S232: Train a model on the model training set according to the recurrent neural network algorithm to generate a pre-model for remote control mode recognition; perform model optimization iteration on the pre-model for remote control mode recognition based on the model test set to generate a remote control mode recognition model; import the lightweight decoding data of the remote control device into the remote control mode recognition model for label mapping to generate operation label mapping data;

[0113] Step S233: Classify the operation categories of the operation label mapping data to obtain the remote control operation intention data; modulate the lightweight decoding data of the remote control device based on the remote control operation intention data to generate optimized decoded control signal data.

[0114] In the embodiments of the present invention, analysis is performed based on the lightweight decoded data of the remote control device. The lightweight decoded data is usually the result of the signal after frequency domain analysis and sparsification processing, and contains the operation information of the remote control device. Analyze the change trend of the signal, such as by calculating dynamic features such as the change rate and acceleration of the signal, and extract the change pattern of the signal in time or space. Extract the spectral features of the signal in different time periods, which are of great significance for identifying the control mode of the remote control device. Extract the time series features of the signal, such as peaks, periodic changes, mutations, etc., which helps to capture the dynamic evolution of the signal. The extracted features include dynamic changes in the time dimension (such as increasing or decreasing trends), spectral features (such as band changes), and periodic features, etc., and these features will be used as the input data for subsequent model training. Divide the extracted dynamic change feature data into two parts: a training set and a test set. The training set is used to train the model, and the test set is used to evaluate the performance of the model. The commonly used division ratio is 70% for the training set and 30% for the test set, or 80% and 20%. The dynamic change feature data of the remote control device is used as the input. Each data point contains information such as the time series features and spectral changes of the signal, and these will be input into the RNN model. Use a recurrent neural network (RNN) or its variants (such as LSTM, GRU, etc.) to process time series data. The RNN can remember past states through a recurrent structure, enabling the model to handle the dynamic characteristics in time series signals. Use LSTM units to avoid the problem of gradient vanishing in traditional RNNs and be able to capture dependencies in long time series. GRU is a simplified version of LSTM and can learn more effectively, especially when computing resources are limited. Commonly used loss functions include cross-entropy loss (for classification tasks) or mean squared error (for regression tasks). Common optimization algorithms include the Adam optimizer, SGD (stochastic gradient descent), etc., which can effectively accelerate the training process. Optimize the network weights and biases through the backpropagation algorithm to improve the prediction accuracy. During the training process, the RNN will continuously update its weights according to the training set, and finally generate a preliminary pre-model for remote control mode recognition. Use the test set data to evaluate the trained pre-model. Check the recognition performance of the model by calculating indicators such as the accuracy rate, recall rate, and F1 value of the model. If the performance of the model on the test set is not good, it is necessary to adjust the model structure (such as increasing or decreasing the number of hidden layer nodes), change the learning rate, improve feature selection, or further clean the data. Optimize the model by adjusting the hyperparameters of the RNN (such as the learning rate, the number of hidden layer units, etc.). Methods such as cross-validation can be used to select the best hyperparameters. If the model is not robust enough to the signals of new remote control devices, an incremental learning strategy can be adopted to retrain or fine-tune using more training data. Through multiple optimization iterations, gradually improve the performance of the model so that it can better identify the operation mode of the remote control device. After the optimized model can achieve satisfactory accuracy on the test set, the final remote control mode recognition model can be generated.Infer the lightweight decoded data of a new remote control device using the trained remote control mode recognition model. By importing the input data (lightweight decoded data) into the model, the model will predict the corresponding operation label. Each operation of the remote control device corresponds to a label, and the model will infer the corresponding operation based on the dynamic characteristics of the input signal. For example, certain change patterns represent the "forward" operation, and certain spectral features represent the "stop" operation, etc. The output data will be the current operation intention label of the remote control device, such as "forward", "stop", "turn", etc. Further classify the operation label mapping data. Classify the operation labels according to different types of labels (such as forward, stop, turn, etc.). Traditional classification methods (such as support vector machines, decision trees, etc.) or fully connected layers in deep learning can be used to perform the classification task, depending on the type and complexity of the operation. Generate remote control operation intention data based on the classification results. Each label corresponds to an operation intention, representing the action or state currently executed by the remote control device. Modulate the lightweight decoded data of the remote control device according to the remote control operation intention data. The purpose of this step is to generate a new control signal so that the remote control device can perform corresponding operations according to the recognized operation intention. Traditional modulation methods, such as amplitude modulation (AM), frequency modulation (FM), or feature-based modulation methods, can be adopted, depending on the control requirements of the remote control device. If the "forward" operation intention is recognized, a corresponding signal will be generated to instruct the device to move forward. Finally, the modulated control signal will be used as the input signal of the remote control device to make the device perform corresponding actions, and these control signals will more accurately reflect the operation intention.

[0115] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0116] Step S31: Package the optimized decoded control signal data into data packets to generate decoded control signal packets; remotely transmit the decoded control signal packets based on the low-power communication protocol to generate decoded control signal packet transmission data;

[0117] Step S32: Execute the receiving device instructions on the decoded control signal packet transmission data to obtain receiving device instruction execution data; analyze the instruction response time of the receiving device instruction execution data to generate the receiving device instruction execution response time;

[0118] Step S33: Optimize the response delay of the receiving device instruction execution data through the receiving device instruction execution response time to generate response-optimized instructions.

[0119] In the embodiments of the present invention, by adding header information to the signal packet, including the identifier (ID) of the packet, signal type, data length, checksum, etc., it is used to identify the type and integrity of the signal packet. It includes the decoded control signal data itself, such as containing instructions (forward, stop, turn, etc.), control parameters (speed, direction, etc.). The check information and terminator ensure the integrity of the data packet and the correctness during the transmission process. The generated data packet structure should meet the requirements of the low-power communication protocol to ensure energy savings during the transmission process. The data packet after encapsulation will be a signal packet in a standard format and can be used for subsequent remote transmission. This data packet contains operation instructions and control data, with a simple and efficient structure. Select a suitable low-power communication protocol (such as LoRa, Zigbee, BLE (Bluetooth Low Energy), etc.). These protocols can ensure stable data transmission without consuming a large amount of energy. By using a lower data transmission rate to reduce power consumption, but can effectively transmit remote control signals. Some protocols such as LoRa support long-distance, low-bandwidth wireless transmission and are suitable for remote control. The transmission delay of the signal packet is low, ensuring the real-time nature of the control instructions. Send the encapsulated control signal packet to the receiving end through the low-power protocol. During the transmission process, the device ensures that the data packet can be stably sent through parameters such as the set frequency channel and power. An error detection and retransmission mechanism is adopted during the transmission process to ensure that the data is not lost or damaged during remote transmission. The signal packet transmitted through the low-power protocol will be sent to the remote receiving device and decoded at the receiving end. The receiving device will receive the data packet transmitted remotely, first decode the data packet, and obtain the control signal and instruction information therein. The receiving device performs relevant operations according to the instructions in the decoded control signal packet. For example, through the decoded control signal, the device performs actions such as forward, stop, and turn. If other parameters (such as speed, angle, etc.) are included in the control signal, the receiving device will adjust its behavior according to these parameters. The execution data usually includes the result of the operation, the current state of the device, whether an error or fault has occurred, etc. These data will be recorded and used for subsequent response time analysis and optimization. Record the timestamp from the start of sending the control signal packet to the completion of execution by the receiving device and the return of the feedback. Calculate the response time of the device: the delay between the control signal and the device feedback. Considering the transmission delay, processing delay, and execution feedback delay, statistical analysis methods (such as mean, variance) can be used to evaluate the response time. By analyzing the response time under different devices, environmental conditions, and communication network states, generate the response time data of the receiving device. If the response time exceeds a certain predetermined threshold, it indicates that there is a delay problem in the system and further optimization is required. Reduce the delay during the transmission process by adjusting the communication protocol, increasing the signal frequency, optimizing the modulation method, etc. If the device has a long processing response time, the processing speed can be improved by optimizing the hardware and software of the device. For example, adopt a more efficient decoding algorithm, reduce unnecessary calculations, and improve the device processing ability, etc.By optimizing the feedback mechanism, reduce the time from execution to feedback. This can be achieved by compressing feedback data, optimizing feedback signals, etc. Based on the results of latency optimization, generate new control instructions to reduce latency and improve the response speed. Reduce the response latency of the device by adjusting the size of the control signal packet, reducing redundant parts of data transmission, or by modifying the transmission protocol, adjusting the device operation process, etc. The optimized instructions will be sent to the receiving device again to ensure that the response time is effectively optimized. If the optimization measures are effective enough, the receiving device will provide a faster response when executing the control instructions.

[0120] Preferably, step S33 includes the following steps:

[0121] Step S331: Identify the response influencing factors for the receiving device instruction execution data based on the response time of the receiving device instruction execution, and generate response influencing factor identification data, where the response influencing factor identification includes network latency identification, device performance identification, and environmental interference identification;

[0122] Step S332: Set the minimization latency optimization target for the receiving device instruction execution response time according to the response influencing factor identification data to obtain the minimization latency optimization target setting data; optimize the network path for the receiving device instruction execution data based on the minimization latency optimization target setting data to generate network path optimization data;

[0123] Step S333: Use the network path optimization data to optimize the response latency of the receiving device instruction execution data and generate a response optimization instruction.

[0124] In the embodiments of the present invention, by setting specific optimization objectives according to influencing factors, the delay is ensured to be minimized. Based on the network delay identification data, optimization objectives are set to reduce network delay. For example, the objective can be to reduce the impact of high-delay links and select shorter and more stable transmission paths. Based on the device performance identification data, objectives are set to improve the response speed of the receiving device. For example, the objective can be to reduce the CPU load of the device, or optimize the algorithm and task scheduling so that the device can respond to instructions faster. Based on the environmental interference identification data, objectives are set to reduce the impact of the environment on signal transmission. For example, the objective can be to select a clearer wireless frequency band or optimize the device placement to avoid interference sources. According to the above analysis, a comprehensive delay optimization objective is formulated. For example, the optimization objective is divided into three sub-objectives: network delay, device performance, and environmental interference, and each objective has corresponding weights and optimization criteria. The output data set contains the optimization objectives and priorities of each factor. Based on the network delay identification data, the shortest network path with the lowest delay is selected. For example, the optimal path is selected using routing protocols (such as OSPF, BGP, etc.), or the software-defined network (SDN) technology is used to dynamically adjust the transmission path of data packets. The network traffic is evenly distributed to multiple paths through load balancing algorithms (such as the least connection number method, hash algorithm, etc.) to avoid overloading of certain network nodes and reduce the delay. The transmission delay is reduced by reducing the number of forwarding hops of data packets and avoiding network congestion nodes. The optimized network path data is output, which includes the optimal path selected according to the delay optimization objective. This data can include network node information, the optimized path, and the expected delay reduction amount. Based on the optimized network path data, actual delay optimization is carried out. According to the optimized network path data, the transmission route and frequency of signal packets are adjusted to minimize the network delay to the greatest extent. The transmission parameters, such as data packet size, frequency, power, etc., are adjusted to ensure optimal delay and reliability. According to the device performance and environmental interference, the task scheduling and execution logic of the device are optimized to reduce the response time. According to the optimized network path and device adjustment data, response optimization instructions are generated, and these instructions will be executed in the receiving device to achieve low-delay and efficient response.

[0125] Preferably, step S4 includes the following steps:

[0126] Step S41: Based on the response optimization instructions, perform device communication and interconnection on the receiving device instruction execution data to generate multi-device collaborative control interconnection data; perform task collaboration and resource allocation on the multi-device collaborative control interconnection data to generate multi-device collaborative control task allocation data;

[0127] Step S42: Perform execution status feedback on the multi-device collaborative control task allocation data to generate execution status feedback data; perform remote control completion rate evaluation on the execution status feedback data to generate the remote control completion rate;

[0128] Step S43: Compare the remote control completion rate with a preset remote control standard completion rate. When the remote control completion rate is less than the preset remote control standard completion rate, adaptively adjust the multi-device collaborative control task allocation data until the remote control completion rate is greater than or equal to the preset remote control standard completion rate to execute the remote control operation.

[0129] In the embodiments of the present invention, by adopting a low-power and high-performance communication protocol, such as ZigBee, LoRa, or a protocol based on Wi-Fi, Bluetooth Mesh, each device can be interconnected and exchange instructions and data in real time within a certain physical range. A point-to-point communication or a relay-based communication network structure between devices is implemented to ensure that each device can exchange data with other devices. Apply task scheduling algorithms (such as weighted round-robin scheduling algorithm, priority scheduling algorithm, etc.) to make a reasonable allocation according to the current load, task complexity, and priority of each device. According to the resource situation of each device (such as the availability of CPU, memory, sensors), make a reasonable resource allocation for the tasks to ensure the efficient operation of the system. For tasks that require multi-device collaboration to complete, adopt collaborative control algorithms, such as distributed control, leader-follower strategy, etc., to ensure that multiple devices collaborate to execute tasks. Through device communication interconnection and task collaboration, generate multi-device collaborative control task allocation data, including the allocated tasks, required resources, and collaboration methods of each device. Use sensors embedded in the device or an external monitoring system to capture the working state of the device in real time, such as task execution progress, resource consumption, fault information, etc. The device uploads the execution status to the central control system through the communication network to form execution status feedback data, which includes task completion degree, resource usage, abnormal status, etc. Calculate the overall completion rate of the remote control task according to the execution progress and task allocation of the device. For example, set the completion degree of each device and calculate the overall task completion degree according to the weight: Wherein, is the overall task completion degree, is the completion progress of device ; is the total task progress, is device Weight. The remote control completion rate data reflects the completion status of the current task. Compare the calculated remote control completion rate with the preset standard completion rate. If the current completion rate is lower than the preset standard, it indicates insufficient task execution efficiency and optimization is required. According to the comparison result, execute the adaptive adjustment mechanism to optimize task allocation and ensure reasonable load and task allocation for each device. For devices with slower task execution progress, reallocate more suitable tasks or adjust priorities. Optimize the workload of devices through scheduling algorithms (such as Shortest Job First (SJF) or Dynamic Priority Scheduling). If resource bottlenecks of certain devices affect task completion, reallocate resources to ensure timely task completion. For example, adjust the power consumption management mode, communication protocol or cooperation method of the device to reduce communication latency or improve device processing capacity. After each adjustment, recalculate the remote control completion rate and compare it with the standard completion rate until the remote control completion rate is greater than or equal to the preset standard. Once the completion rate reaches the preset standard, stop the adjustment and execute the remote control task.

Claims

1. A remote control method based on a low-power Hall sensor, characterized in that: The following steps are involved: Step S1: Obtain remote control device type data; Perform Hall sensor deployment based on remote control device type data to generate Hall sensor deployment data; Calibrate the working magnetic field direction of the Hall sensor deployment data to generate Hall sensor deployment correction data; Perform real-time signal acquisition on the Hall sensor deployment correction data to obtain the magnetic field detection signal of the standard remote control device; Step S2: performing lightweight signal decoding on the magnetic field detection signal of the standard remote control device to generate lightweight decoded data of the remote control device; performing remote control mode recognition on the lightweight decoded data of the remote control device to generate remote control control intention data; performing signal decoding optimization on the lightweight decoded data of the remote control device based on the remote control operation intention data to generate optimized decoding control signal data; Step S3: remotely transmit the optimized decoding control signal data in the form of signal packets to generate decoding control signal packet transmission data; Performing command reception response analysis on the decoded control signal packet transmission data to generate receiving device command execution data and receiving device command execution response time; Optimizing the response delay of the receiving device instruction execution data by the receiving device instruction execution response time, and generating a response optimization instruction; Step S4: evaluating the remote control completion rate of the receiving device instruction execution data based on the response optimization instruction to generate the remote control completion rate; comparing the remote control completion rate with the preset remote control standard completion rate; when the remote control completion rate is less than the preset remote control standard completion rate, adaptively adjusting the multi-device collaborative control task allocation data until the remote control completion rate is greater than or equal to the preset remote control standard completion rate, so as to execute the remote control operation; Step S4 includes the following steps: Step S41: performing device communication interconnection on the receiving device instruction execution data based on the response optimization instruction to generate multi-device collaborative control interconnection data; performing task coordination and resource allocation on the multi-device collaborative control interconnection data to generate multi-device collaborative control task allocation data; Step S42: performing execution status feedback on the multi-device collaborative control task allocation data to generate execution status feedback data; performing remote control completion rate evaluation on the execution status feedback data to generate the remote control completion rate; Step S43: comparing the remote control completion rate with the preset remote control standard completion rate. When the remote control completion rate is less than the preset remote control standard completion rate, adaptively adjusting the multi-device collaborative control task allocation data until the remote control completion rate is greater than or equal to the preset remote control standard completion rate, so as to execute the remote control operation. The specific steps of performing remote control mode recognition on the lightweight decoded data of the remote control device and performing signal decoding optimization on the lightweight decoded data of the remote control device based on the remote control operation intention data include: Extract dynamic change features from the remote control device lightweight decoding data to obtain dynamic change feature data of the remote control device lightweight decoding; divide the remote control device lightweight decoding dynamic change feature data into data sets to generate a model training set and a model test set; The model training set is trained according to the recurrent neural network algorithm to generate a remote control mode recognition pre-model; the remote control mode recognition pre-model is optimized and iterated based on the model test set to generate a remote control mode recognition model; the remote control device lightweight decoding data is imported into the remote control mode recognition model for label mapping to generate operation label mapping data; The operation label mapping data is classified into operation categories to obtain remote control control intention data; based on the remote control control intention data, the remote control device lightweight decoding data is signal modulated to generate optimized decoding control signal data.

2. The remote control method based on low power consumption Hall sensor according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Obtain remote control device type data; Step S12: selecting a Hall sensor type based on the remote control device type data to obtain the Hall sensor type data of the remote control device; deploying the Hall sensor according to the Hall sensor type data of the remote control device to generate Hall sensor deployment data; Step S13: sensing the magnetic field of the remote control device according to the Hall sensor deployment data to generate the magnetic field sensing data of the remote control device; calibrating the working magnetic field direction of the Hall sensor deployment data according to the magnetic field sensing data of the remote control device to generate the Hall sensor deployment correction data; Step S14: perform real-time signal acquisition on the Hall sensor deployment correction data to obtain the original magnetic field detection signal of the remote control device; perform signal preprocessing on the original magnetic field detection signal of the remote control device to generate a standard remote control device magnetic field detection signal, wherein the signal preprocessing includes signal denoising, signal enhancement and signal normalization.

3. The remote control method based on low power consumption Hall sensor according to claim 2, characterized in that: Calibration of the sensor working magnetic field direction based on the Hall sensor deployment data according to the magnetic field sensing data of the remote control device includes: Confirm the sensor installation coordinates of the Hall sensor deployment data to obtain the sensor installation coordinate data; perform installation angle analysis on the Hall sensor deployment data based on the sensor installation coordinate data to generate the sensor installation angle data; Extracting a single Hall sensor sensing data from the remote control device magnetic field sensing data to obtain Hall sensor sensing data, wherein the Hall sensor sensing data extraction includes magnetic field intensity extraction, magnetic field direction extraction, and magnetic field change extraction; based on the Hall sensor sensing data, the lateral magnetic field orientation is aggregated and compared to generate lateral magnetic field orientation aggregated data; The installation orientation of the Hall sensor deployment data is adjusted according to the lateral magnetic field orientation aggregation data to generate the Hall sensor deployment correction data.

4. The remote control method based on low power consumption Hall sensor according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: extracting magnetic field multi-dimensional features from the magnetic field detection signal of the standard remote control device to obtain multi-dimensional feature data of the magnetic field of the remote control device, wherein the multi-dimensional feature data of the magnetic field of the remote control device includes magnetic field intensity feature data, magnetic field change rate feature data and magnetic field timestamp data; Step S22: performing spatial information association on the magnetic field intensity characteristic data, the magnetic field change rate characteristic data and the magnetic field timestamp data based on the sensor installation coordinate data to generate remote control device magnetic field spatial association data; performing lightweight signal decoding on the standard remote control device magnetic field detection signal according to the remote control device magnetic field spatial association data to generate remote control device lightweight decoding data; Step S23: performing remote control mode recognition on the lightweight decoded data of the remote control device to generate remote control control intention data; performing signal decoding optimization on the lightweight decoded data of the remote control device based on the remote control operation intention data to generate optimized decoding control signal data.

5. The remote control method based on low power consumption Hall sensor according to claim 4, characterized in that: Lightweight signal decoding of standard remote control device magnetic field detection signals based on remote control device magnetic field spatial correlation data includes: Perform fast Fourier transform on the magnetic field detection signal of the standard remote control device according to the spatial correlation data of the magnetic field of the remote control device to generate the frequency domain data of the magnetic field of the remote control device; perform signal morphology analysis on the frequency domain data of the magnetic field of the remote control device to generate a decoding feature data set; A dictionary is constructed for the magnetic field detection signal of the standard remote control device by decoding the feature data set to generate a signal representation dictionary; based on the signal representation dictionary, the decoded feature data set is signal sparsified to generate sparse remote control device signal data, where the signal sparsification formula is as follows: In the formula, Represented as a decoding feature dataset, Represented as a matrix of basis vectors in the dictionary, Represented as a sparse coefficient vector, It is represented as reconstruction error; Based on the L1 norm, the sparse remote control device signal data is minimized to obtain a sparse coefficient matrix, where the formula for minimizing the target calculation is as follows: In the formula, Represented as a sparse coefficient matrix, is represented as the regularization parameter; The sparse coefficient matrix is ​​used to optimize the signal decoding of the lightweight decoding data of the remote control device to generate optimized decoding control signal data.

6. The remote control method based on low power consumption Hall sensor according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: encapsulating the optimized decoded control signal data into a data packet to generate a decoded control signal packet; performing signal packet remote transmission on the decoded control signal packet based on a low-power communication protocol to generate decoded control signal packet transmission data; Step S32: performing receiving device instruction execution on the decoded control signal packet transmission data to obtain receiving device instruction execution data; performing instruction response time analysis on the receiving device instruction execution data to generate the receiving device instruction execution response time; Step S33: Optimize the response delay of the receiving device instruction execution data by the receiving device instruction execution response time, and generate a response optimization instruction.

7. The remote control method based on low power consumption Hall sensor according to claim 1, characterized in that: Step S33 includes the following steps: Step S331: identifying response influencing factors of the received device instruction execution data by receiving the device instruction execution response time, and generating response influencing factor identification data, wherein the response influencing factor identification includes network delay identification, device performance identification and environmental interference identification; Step S332: performing a minimum delay optimization target setting on the instruction execution response time of the receiving device according to the response influencing factor identification data, and obtaining the minimum delay optimization target setting data; performing a network path optimization on the instruction execution data of the receiving device based on the minimum delay optimization target setting data, and generating the network path optimization data; Step S333: Utilize the network path optimization data to optimize the response delay of the receiving device instruction execution data and generate a response optimization instruction.

8. A remote control device based on a low-power Hall sensor, characterized in that: Used to execute the remote control method based on the low power consumption Hall sensor as claimed in claim 1, the remote control device based on the low power consumption Hall sensor comprises: The sensor deployment module is used to obtain the remote control device type data; deploy the Hall sensor based on the remote control device type data to generate the Hall sensor deployment data; calibrate the sensor working magnetic field direction on the Hall sensor deployment data to generate the Hall sensor deployment correction data; perform real-time signal acquisition on the Hall sensor deployment correction data to obtain the standard remote control device magnetic field detection signal; The decoding optimization module is used to perform lightweight signal decoding on the magnetic field detection signal of the standard remote control device to generate lightweight decoding data of the remote control device; perform remote control mode recognition on the lightweight decoding data of the remote control device to generate remote control control intention data; perform signal decoding optimization on the lightweight decoding data of the remote control device based on the remote control operation intention data to generate optimized decoding control signal data; The response optimization module is used to perform signal packet remote transmission of the optimized decoded control signal data to generate decoded control signal packet transmission data; perform command reception response analysis on the decoded control signal packet transmission data to generate receiving device command execution data and receiving device command execution response time; perform response delay optimization on the receiving device command execution data through the receiving device command execution response time to generate response optimization instructions; The control comparison module is used to evaluate the remote control completion rate of the receiving device instruction execution data based on the response optimization instruction to generate the remote control completion rate; compare the remote control completion rate with the preset remote control standard completion rate. When the remote control completion rate is less than the preset remote control standard completion rate, the multi-device collaborative control task allocation data is adaptively adjusted until the remote control completion rate is greater than or equal to the preset remote control standard completion rate to execute the remote control operation.

Images