Control method, device and equipment of high-frequency wireless learning remote controller and medium

Abstract

The application relates to a control method, device and equipment of a high-frequency wireless learning type remote controller and a medium, the method comprises the following steps: acquiring a first high-frequency remote control signal, processing the first high-frequency remote control signal based on a preset signal conversion rule to obtain a quantized first high-frequency remote control signal; inputting the quantized first high-frequency remote control signal into a preset signal recognition model to obtain a signal prediction degree; acquiring a second high-frequency remote control signal, processing the second high-frequency remote control signal according to the preset signal conversion rule to obtain a quantized second high-frequency remote control signal; verifying the quantized second high-frequency remote control signal according to the signal prediction degree to obtain a verification result; acquiring a quantized third high-frequency remote control signal according to the verification result, and storing the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal and the quantized third high-frequency remote control signal. The application has the effect of enhancing the intelligent learning function of the wireless learning type remote controller, improving the intelligence of the wireless learning type remote controller product, and further improving the use experience of the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of learning remote controllers, and in particular to a control method, device, equipment and medium of a high-frequency wireless learning remote controller. BACKGROUND

[0002] At present, a wireless learning remote controller refers to a remote controller that can copy the same function by learning the signal of an existing remote controller, so that a user can control the same device through copying without relying on the original remote controller. Wireless learning remote controllers are widely used in the fields of access control systems, garage doors, automatic doors, and electric curtains.

[0003] In related technologies, a wireless learning remote controller can receive a wireless signal from an original remote controller in a learning mode, identify the signal sent by the original remote controller, and store the code of the signal in an internal memory chip. When a user uses the learning remote controller, the remote controller will copy the original signal according to the stored code. The user presses the corresponding button on the remote controller, and the remote controller sends the copied signal at the same frequency through its built-in transmission module. When the key buttons of the original remote controller are numerous, the user needs to manually press each button to send the code of each button to the wireless learning remote controller. Such an operation is very tedious, reduces the intelligence of the wireless learning remote controller product, and greatly reduces the user experience. SUMMARY

[0004] In order to enhance the intelligent learning function of the wireless learning remote controller, improve the intelligence of the wireless learning remote controller product, and further improve the user experience, the present application provides a control method, device, equipment and medium of a high-frequency wireless learning remote controller.

[0005] In a first aspect, the above application aims to achieve the following technical solutions:

[0006] A control method of a high-frequency wireless learning remote controller, the control method of the high-frequency wireless learning remote controller comprising:

[0007] obtaining a first high-frequency remote control signal, processing the first high-frequency remote control signal based on a preset signal conversion rule to obtain a quantized first high-frequency remote control signal;

[0008] inputting the quantized first high-frequency remote control signal into a preset signal identification model to obtain a signal prediction degree;

[0009] obtaining a second high-frequency remote control signal, processing the second high-frequency remote control signal according to a preset signal conversion rule to obtain a quantized second high-frequency remote control signal;

[0010] verifying the quantized second high-frequency remote control signal according to the signal prediction degree to obtain a verification result;

[0011] According to the verification result, a quantized third high-frequency remote control signal is obtained, and the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal and the quantized third high-frequency remote control signal are stored.

[0012] By adopting the technical scheme, the first high-frequency remote control signal refers to the signal of the first original remote controller received by the wireless learning type remote controller. Therefore, when the first high-frequency remote control signal is obtained, it indicates that the wireless learning type remote controller is in a learning mode, and a signal decoder inside the wireless learning type remote controller starts decoding processing on the received signal and converts the first high-frequency remote control signal into a form recognizable by a processor of the wireless learning type remote controller through a signal conversion rule, for example, converts the pulse width and time interval of the first high-frequency remote control signal into a data form, so as to convert the first high-frequency remote control signal, judge the frequency band and type of the original remote control signal and other information, and facilitate further learning of the original remote controller; the signal recognition model is used to specifically recognize the encoding value, encoding format and encoding form of the original remote control signal. Because the signal recognition model is trained by remote control signals of a plurality of different types of remote controllers, the learning degree of the signal recognition model for the remote control signal of the original remote controller is judged, the prediction ability, i.e. the signal prediction degree, for all remote control signals of the current original remote controller is judged based on the learning degree, and the signal prediction degree is verified through the subsequently obtained second high-frequency remote control signal. When the signal prediction degree is verified, the remote control signals of other buttons of the current original remote controller can be predicted and generated based on the signal prediction degree, so as to reduce the key operation of the user, improve the intelligence of the wireless learning type remote controller product, and enhance the intelligent learning function of the wireless learning type remote controller.

[0013] In a preferred example, the application can be further configured as follows:

[0014] A reference high-frequency remote control signal is obtained, and a plurality of groups of comparison high-frequency remote control signals are generated based on the reference high-frequency remote control signal;

[0015] The reference high-frequency remote control signal and the comparison high-frequency remote control signal are input into a signal analysis model, and the signal analysis model is built-in with a plurality of signal analysis rules;

[0016] Based on the signal analysis model, an identification conversion accuracy rate corresponding to each signal analysis rule is obtained;

[0017] The signal analysis rule with the highest identification conversion accuracy rate is selected as the signal conversion rule.

[0018] By adopting the technical scheme, the benchmark high-frequency remote control signal refers to a standard remote control signal of various types of remote controllers, that is, the encoding form of the benchmark high-frequency remote control signal is a basic encoding form commonly used in the industry, and no additional encoding is added, for example, no encryption algorithm is used or a commonly used encryption algorithm in the industry is used, no additional functional encoding and timestamp encoding are added, etc. In this way, the comparison high-frequency remote control signal generated by the benchmark high-frequency remote control signal has the same encoding form as the benchmark high-frequency remote control signal, and is easy to compare. After the benchmark high-frequency remote control signal and the comparison high-frequency remote control signal are input into the signal analysis model, the benchmark high-frequency remote control signal and the comparison high-frequency remote control signal are compared and analyzed based on the signal analysis model, that is, the encoding integrity and detail retention rate of the benchmark high-frequency remote control signal are compared and analyzed, so as to judge the recognition and conversion accuracy of each signal analysis rule, and then select the signal analysis rule with the highest recognition and conversion accuracy as the signal conversion rule, thereby improving the accuracy of recognizing and converting the remote control signal.

[0019] In a preferred example, the application can be further configured to generate the signal recognition model by the following method:

[0020] Obtain a historical high-frequency remote control signal group, the historical high-frequency remote control signal group including historical high-frequency remote control signal groups of various types of remote controllers, and each type of remote controller including a plurality of different high-frequency remote control signals;

[0021] Input the historical high-frequency remote control signal into a machine learning model, and the machine learning model is provided with the signal conversion rule;

[0022] Obtain prediction accuracy data based on the machine learning model;

[0023] Obtain signal prediction data corresponding to each type of remote controller based on the prediction accuracy data;

[0024] Generate a signal recognition model based on the signal prediction data.

[0025] By adopting the technical solution, the signal recognition model is used to judge the characteristics of various types of remote control signals, the historical high-frequency remote control signal group includes historical high-frequency remote control signal groups of various types of remote controllers, and the historical high-frequency remote control signal group of each type of remote controller includes various different high-frequency remote control signals. Therefore, by learning the historical high-frequency remote control signals, the characteristics of each type of remote control signal are obtained and predicted. By comparing the predicted remote control signal with the original historical high-frequency remote control signal, the prediction accuracy data of the high-frequency remote control signal of each type of remote controller is obtained. The prediction accuracy data represents the learning ability of the machine learning model for each type of remote control signal. The higher the degree of mastery of the machine learning model for the characteristics of the remote control signal, the more accurate the predicted remote control signal. In this way, the signal recognition model generated based on the signal prediction degree can realize the prediction generation of the collected remote control signal, realize intelligent learning of the remote control signal, and further enhance the intelligent learning function of the wireless learning type remote controller and improve the intelligence of the wireless learning type remote controller product.

[0026] In a preferred example, the application can be further configured to: verifying the quantized second high-frequency remote control signal according to the signal prediction degree to obtain a verification result, specifically including:

[0027] generating a predicted high-frequency remote control signal according to the signal prediction degree;

[0028] comparing the predicted high-frequency remote control signal with the quantized second high-frequency remote control signal to obtain a verification result.

[0029] By adopting the above technical solution, after obtaining the signal prediction degree and the quantized second high-frequency remote control signal, a predicted high-frequency remote control signal is generated based on the signal prediction degree. At this time, the signal prediction degree represents the prediction degree of the signal recognition model for the waveform characteristics of the quantized first high-frequency remote control signal. For example, when the signal prediction degree is 80%, it means that the signal recognition model can predict 80% of the waveform characteristics of the quantized second high-frequency remote control signal. Therefore, based on the signal recognition model, a predicted high-frequency remote control signal is generated. At this time, the characteristics of the part corresponding to the signal prediction degree in the predicted high-frequency remote control signal are predicted and generated. The remaining part of the predicted high-frequency remote control signal is generated according to the signals with the same characteristics as the first high-frequency remote control signal and the remote control function represented by the second high-frequency remote control signal, and the standard code conforming to the current remote control signal coding form. When verifying, the part corresponding to the signal prediction degree in the predicted high-frequency remote control signal is compared with the corresponding part of the second high-frequency remote control signal. At this time, the signal prediction degree represents the similarity of the comparison between the predicted high-frequency remote control signal and the quantized second high-frequency remote control signal. Therefore, the predicted high-frequency remote control signal is verified based on the signal prediction degree, which guarantees the accuracy of the generated predicted high-frequency remote control signal.

[0030] The application can be further configured in a preferred example as follows: the third high-frequency remote control signal is obtained according to the verification result, specifically including:

[0031] If the verification result indicates that the verification is passed, the predicted high-frequency remote control signal is taken as the quantized third high-frequency remote control signal.

[0032] If the verification result indicates that the verification is not passed, the third high-frequency remote control signal is obtained, and the third high-frequency remote control signal is processed based on the signal conversion rule to obtain the quantized third high-frequency remote control signal.

[0033] By using the above technical solution, when the part corresponding to the signal prediction degree in the predicted high-frequency remote control signal is the same as the corresponding part of the second high-frequency remote control signal, the verification result indicates that the verification is passed, the signal recognition model accurately recognizes the features of the current original remote controller, and therefore, the predicted high-frequency remote control signal is taken as the quantized third high-frequency remote control signal. At this time, the user does not need to continue pressing the remaining buttons to send the remote control signal, and the current wireless learning type remote controller can send an indication signal to inform the user. When the part corresponding to the signal prediction degree in the predicted high-frequency remote control signal is not the same as the corresponding part of the second high-frequency remote control signal, it indicates that the signal recognition model does not have enough accuracy in recognizing the features of the current original remote controller, and the generated predicted high-frequency remote control signal cannot realize the function of the third high-frequency remote control signal of the original remote controller. Therefore, the verification result indicates that the verification is not passed, and the user needs to press the buttons to send the remote control signal for the wireless learning type remote controller to learn. Based on this, under the premise of realizing the basic learning function of the wireless learning type remote controller, the intelligent learning function of the wireless learning type remote controller is enhanced through signal learning of the signal recognition model, the intelligence of the wireless learning type remote controller product is improved, and the user's experience is improved.

[0034] In a second aspect, the above application aims to achieve the following technical solutions:

[0035] A control device of a high-frequency wireless learning type remote controller, the control device of the high-frequency wireless learning type remote controller comprising:

[0036] A first signal processing module configured to obtain a first high-frequency remote control signal, process the first high-frequency remote control signal based on a preset signal conversion rule, and obtain a quantized first high-frequency remote control signal;

[0037] A signal recognition module configured to input the quantized first high-frequency remote control signal into a preset signal recognition model and obtain a signal prediction degree;

[0038] A second signal processing module configured to obtain a second high-frequency remote control signal, process the second high-frequency remote control signal according to a preset signal conversion rule, and obtain a quantized second high-frequency remote control signal;

[0039] A prediction verification module is configured to verify the quantized second high-frequency remote control signal according to the signal prediction degree, and obtain a verification result.

[0040] A third signal acquisition module is configured to acquire a quantized third high-frequency remote control signal according to the verification result, and store the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal and the quantized third high-frequency remote control signal.

[0041] Optionally, the control device of the high-frequency wireless learning-type remote controller further comprises:

[0042] A comparison signal module is configured to acquire a reference high-frequency remote control signal, and generate a plurality of groups of comparison high-frequency remote control signals based on the reference high-frequency remote control signal.

[0043] A signal analysis module is configured to input the reference high-frequency remote control signal and the comparison high-frequency remote control signal into a signal analysis model, and the signal analysis model is internally provided with a plurality of signal analysis rules.

[0044] A correctness rate judgment module is configured to obtain an identification conversion correctness rate corresponding to each signal analysis rule based on the signal analysis model.

[0045] A rule selection module is configured to select a signal analysis rule with the highest identification conversion correctness rate as a signal conversion rule.

[0046] Optionally, the control device of the high-frequency wireless learning-type remote controller further comprises:

[0047] A historical signal acquisition module is configured to acquire a historical high-frequency remote control signal group, and the historical high-frequency remote control signal group comprises historical high-frequency remote control signal groups of a plurality of types of remote controllers, and each type of remote controller's historical high-frequency remote control signal group comprises a plurality of different high-frequency remote control signals.

[0048] A model conversion module is configured to input the historical high-frequency remote control signal into a machine learning model, and the machine learning model is provided with the signal conversion rule.

[0049] A model analysis module is configured to obtain prediction accuracy data based on the machine learning model.

[0050] A prediction degree acquisition module is configured to obtain a signal prediction degree corresponding to each type of remote controller based on the prediction accuracy data.

[0051] A model generation module is configured to generate a signal identification model based on the signal prediction degree.

[0052] In a third aspect, the above-mentioned application objectives of the present application are achieved by the following technical solutions:

[0053] A computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the control method of the high-frequency wireless learning remote controller when executing the computer program.

[0054] In a fourth aspect, the above-mentioned application objectives of the present application are achieved by the following technical solutions:

[0055] A computer-readable storage medium stores a computer program, and the computer program implements the steps of the control method of the high-frequency wireless learning remote controller when executed by a processor.

[0056] In summary, the present application includes at least one of the following beneficial technical effects:

[0057] 1、The first high-frequency remote control signal refers to the first original remote control signal received by the wireless learning remote controller. Therefore, when the first high-frequency remote control signal is acquired, it indicates that the wireless learning remote controller is in learning mode. The signal decoder inside the wireless learning remote controller starts decoding the received signal and converts the first high-frequency remote control signal into a form that the processor of the wireless learning remote controller can recognize through signal conversion rules, such as converting the pulse width and time interval of the first high-frequency remote control signal into data form. In this way, the first high-frequency remote control signal is converted, and the frequency band and type of the original remote control signal are determined, etc. This facilitates further learning of the original remote control. The signal recognition model is used to specifically recognize the encoding value, encoding format, and encoding form of the original remote control signal. Because the signal recognition model has been trained by a variety of different types of remote control signals, the learning degree of the signal recognition model for the original remote control signal is determined, and the prediction ability of the signal prediction degree based on the learning degree is determined. The signal prediction degree is verified through the subsequent acquisition of the second high-frequency remote control signal. When the signal prediction degree is verified, the signal prediction degree can be used to predict and generate the remote control signals of other buttons of the current original remote control. In this way, the user's key operation is reduced, the intelligence of the wireless learning remote controller product is improved, and the intelligent learning function of the wireless learning remote controller is enhanced.

[0058] 2. The reference high-frequency remote control signal refers to the standard remote control signal for various types of remote controls. This means the encoding format of the reference high-frequency remote control signal is the industry-standard basic encoding format, without any additional encoding. For example, it does not use encryption algorithms or uses industry-standard encryption algorithms, and does not add additional functional encoding or timestamp encoding. Therefore, the comparison high-frequency remote control signal generated from the reference high-frequency remote control signal has the same encoding format as the reference high-frequency remote control signal, making comparison easy. After inputting the reference high-frequency remote control signal and the comparison high-frequency remote control signal into the signal analysis model, the model compares and analyzes them, comparing the encoding completeness and detail retention rate of the reference high-frequency remote control signal. This determines the recognition and conversion accuracy of each signal analysis rule, and then selects the signal analysis rule with the highest recognition and conversion accuracy as the signal conversion rule, thereby improving the accuracy of remote control signal recognition and conversion.

[0059] 3. The signal recognition model is used to determine the characteristics of various types of remote control signals. The historical high-frequency remote control signal group includes historical high-frequency remote control signal groups of various types of remote controls. Each type of remote control's historical high-frequency remote control signal group includes multiple different high-frequency remote control signals. Therefore, by learning from the historical high-frequency remote control signals, the characteristics of each type of remote control signal are obtained and predicted. By comparing the predicted remote control signal with the original historical high-frequency remote control signal, the prediction accuracy data for the high-frequency remote control signal of each type of remote control is obtained. This prediction accuracy data represents the learning ability of the machine learning model for each type of remote control signal. The higher the degree to which the machine learning model grasps the characteristics of this type of remote control signal, the more accurate the predicted remote control signal will be. Thus, the signal recognition model based on signal prediction accuracy can realize the prediction and generation of collected remote control signals, realizing intelligent learning of remote control signals, thereby enhancing the intelligent learning function of wireless learning remote control and improving the intelligence of wireless learning remote control products. Attached Figure Description

[0060] Figure 1 This is a flowchart illustrating an implementation of the control method for a high-frequency wireless learning remote controller in this application.

[0061] Figure 2 This is a flowchart illustrating the implementation of the signal conversion rule generation method in the embodiments of this application;

[0062] Figure 3 This is a flowchart illustrating the implementation of the signal recognition model generation method in this application embodiment;

[0063] Figure 4 This is a flowchart illustrating the implementation of S40 of the control method for a high-frequency wireless learning remote controller in this application embodiment;

[0064] Figure 5 is a realization flow chart of S50 of the control method of the high-frequency wireless learning type remote controller in the embodiments of the present application;

[0065] Figure 6 is a principle block diagram of the control platform device of the high-frequency wireless learning type remote controller in the embodiments of the present application;

[0066] Figure 7 is an internal structure diagram of the control computer equipment of the high-frequency wireless learning type remote controller in the embodiments of the present application. DETAILED DESCRIPTION

[0067] The following will be further explained in detail with reference to the accompanying drawings. Figures 1-7 The present application is further explained in detail.

[0068] In an embodiment, as shown in the drawings, the present application discloses a control method of a high-frequency wireless learning type remote controller, specifically comprising the following steps: Figure 1

[0069] S10: obtaining a first high-frequency remote control signal, processing the first high-frequency remote control signal based on a preset signal conversion rule to obtain a quantized first high-frequency remote control signal.

[0070] In the embodiments, the wireless learning type remote controller is composed of an MCU (Microcontroller Unit, single-chip microcomputer), a wireless receiving part, a wireless transmitting part, an external storage part and a key. The wireless receiving part and the wireless transmitting part share the MCU, and the wireless receiving part and the wireless transmitting part are welded with the key. The MCU processes data internally. The wireless receiving part is composed of an internal storage, a receiving antenna, a key and the MCU. The wireless receiving part is responsible for receiving a remote control signal, converting a high-frequency remote control signal to be learned into a signal available for the MCU, and performing a specified learning key operation by the key part, and then storing and expanding by the external storage part. The overall data is processed by the MCU, which is mainly used for identifying and analyzing the waveform of the remote control signal. The wireless transmitting part shares the MCU, the external storage part and the key. The wireless transmitting part can call the stored code value data through the MCU by key operation, and then control the wireless transmitting output through the IO port. The remote control signal frequency band of the original remote controller and the wireless learning type remote controller is 433MHz or 315MHz high-frequency remote control signal. The first high-frequency remote control signal refers to the first remote control signal sent by the original remote controller. The quantized first high-frequency remote control signal refers to the first high-frequency remote control signal after form conversion.

[0071] ​Specifically, when learning is needed to be performed using the wireless learning remote controller, the user opens the learning mode of the wireless learning remote controller, and presses the button on the original remote controller to send the remote control signal of the original remote controller to the wireless learning remote controller, so that the wireless learning remote controller acquires the first remote control signal, i.e., the first high-frequency remote control signal, sent by the original remote controller. At this time, the first high-frequency remote control signal is a high-frequency wireless carrier signal, and the first high-frequency remote control signal needs to be decoded and converted into a signal that can be processed by the MCU. Therefore, based on the preset signal conversion rule, the decoded first high-frequency remote control signal is converted into waveform information that can be processed by the MCU. The decoded waveform information reflects the logical state change of the remote control signal coding, such as a binary sequence, which corresponds to a specific command or data. In addition, the decoded waveform information also includes the waveform characteristics of the first high-frequency remote control signal, such as the carrier frequency (e.g., 433 MHz or 315 MHz), the signal strength, the wideband or narrowband characteristics of the signal, etc. Therefore, the quantized first high-frequency remote control signal includes the remote control signal coding, the binary sequence of the remote control signal coding, the waveform diagram of the remote control signal, and the waveform distribution data of the remote control signal, etc.

[0072] In this embodiment, the first high-frequency remote control signal is decoded after being processed (such as filtering, noise reduction, etc.).

[0073] S20: input the quantized first high-frequency remote control signal into a preset signal recognition model to obtain a signal prediction degree.

[0074] In this embodiment, the signal prediction degree refers to the degree to which the remote control signal of the current original remote controller can be predicted.

[0075] Specifically, the quantized first high-frequency remote control signal is input into the preset signal recognition model, which is used to specifically identify the quantized first high-frequency remote control signal, judge the coding value, coding format and coding form of the original remote control signal, and the waveform characteristics of the quantized first high-frequency remote control signal. In addition, since the remote control signals of different function instructions on the same remote controller adopt the same signal coding mode and signal modulation mode, the waveforms of the remote control signals of different function instructions on the same remote controller generally have the same characteristics. The signal recognition model is trained by a large number of remote control signals, and the signal recognition model can judge the waveform characteristics of the remote control signals of various function instructions of different types of remote controllers. Therefore, through the signal recognition model, after the signal recognition model identifies the quantized first high-frequency remote control signal, the signal prediction degree of the remote control signal type corresponding to the quantized first high-frequency remote control signal is queried and acquired. The signal prediction degree represents the learning degree of the signal recognition model to the waveform characteristics of the remote control signal of the type corresponding to the quantized first high-frequency remote control signal. The higher the learning degree, the higher the accuracy of the predicted remote control signal. Therefore, the signal prediction degree refers to the degree to which the remote control signal of the current original remote controller can be predicted.

[0076] S30: Obtain the second high-frequency remote control signal, process the second high-frequency remote control signal according to the preset signal conversion rule, and obtain the quantized second high-frequency remote control signal.

[0077] In this embodiment, the second high-frequency remote control signal refers to the remote control signal sent by the original remote control subsequently obtained. The quantized second high-frequency remote control signal refers to the second high-frequency remote control signal after form conversion.

[0078] Specifically, after the user presses the button on the original remote control to send the first high-frequency remote control signal to the wireless learning remote control, the user needs to continue pressing other buttons on the original remote control. Therefore, when the user continues to press other buttons on the original remote control, the second high-frequency remote control signal is obtained. In this embodiment, the second high-frequency remote control signal does not only refer to the remote control signal sent by the second button pressed by the user, but refers to at least one remote control signal obtained after the first high-frequency remote control signal and before the quantized third high-frequency remote control signal is obtained. The same as the first high-frequency remote control signal, the same preset signal conversion rule is used to process the second high-frequency remote control signal to obtain the quantized second high-frequency remote control signal. The format and form of the quantized second high-frequency remote control signal are the same as those of the quantized first high-frequency remote control signal.

[0079] S40: Verify the quantized second high-frequency remote control signal according to the signal prediction degree, and obtain a verification result.

[0080] In this embodiment, the verification result refers to the verification result of the quantized second high-frequency remote control signal.

[0081] Specifically, the signal prediction degree represents the learning degree of the signal recognition model on the waveform features of the remote control signal of the type corresponding to the quantized first high-frequency remote control signal. Specifically, the signal prediction degree includes the waveform features of the remote control signal of the type corresponding to the quantized first high-frequency remote control signal learned by the signal recognition model. Therefore, according to the waveform features represented by the signal prediction degree, the quantized second high-frequency remote control signal is verified, for example, the waveform features represented by the signal prediction degree are compared with the waveform features of the corresponding part in the quantized second high-frequency remote control signal to obtain the verification result. In this embodiment, the compared waveform features include signal amplitude, pulse number, coding structure, pulse width, pulse position, waveform shape, pulse width, arrangement order, interval and height, as well as period length, frequency and phase of two signals and other features.

[0082] S50: According to the verification result, obtain the quantized third high-frequency remote control signal, and store the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal and the quantized third high-frequency remote control signal.

[0083] In this embodiment, the quantized third high-frequency remote control signal refers to the remote control signal obtained after the quantized second high-frequency remote control signal is generated.

[0084] Specifically, the verification result refers to the comparison between the waveform characteristics represented by the signal predictivity and the waveform characteristics of the corresponding part in the quantized second high-frequency remote control signal. Therefore, when the waveform characteristics represented by the signal predictivity are the same as the waveform characteristics of the corresponding part in the quantized second high-frequency remote control signal, the verification result indicates that the verification is successful. A quantized third high-frequency remote control signal is then generated based on the waveform characteristics represented by the signal predictivity, eliminating the need for the user to press the remote control button to send a signal. When the waveform characteristics represented by the signal predictivity are different from the waveform characteristics of the corresponding part in the quantized second high-frequency remote control signal, the verification result indicates that the verification is unsuccessful. The user then needs to press the remote control button to send a signal to obtain the third high-frequency remote control signal. The third high-frequency remote control signal is then processed based on a preset signal conversion rule to obtain the quantized third high-frequency remote control signal. The quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal, and the quantized third high-frequency remote control signal are stored in corresponding locations in the external storage unit; that is, each of the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal, and the quantized third high-frequency remote control signal has a corresponding remote control button.

[0085] Furthermore, the external storage unit has corresponding storage space for the first high-frequency remote control signal, the second high-frequency remote control signal, the third high-frequency remote control signal, the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal, and the quantized third high-frequency remote control signal.

[0086] In one embodiment, such as Figure 2 As shown, the signal conversion rules are generated in the following way:

[0087] S01: Acquire a reference high-frequency remote control signal, and generate several sets of comparative high-frequency remote control signals based on the reference high-frequency remote control signal.

[0088] In this embodiment, the reference high-frequency remote control signal refers to the standard remote control signal of various types of remote controls. The comparison high-frequency remote control signal refers to a remote control signal with a different encoding value than the reference high-frequency remote control signal.

[0089] Specifically, a reference high-frequency remote control signal is obtained, that is, the encoding form of the reference high-frequency remote control signal is the basic encoding form commonly used in the industry, and no additional encodings are added. For example, no encryption algorithm is used or an industry-standard encryption algorithm is used, and no additional functional encodings and timestamp encodings are added. Based on the encoding form and encoding format of the reference high-frequency remote control signal, multiple sets of remote control signals with the same encoding form and encoding format but different encoding values ​​are randomly generated, that is, the high-frequency remote control signals are compared.

[0090] S02: Input the reference high-frequency remote control signal and the comparison high-frequency remote control signal into the signal analysis model. The input signal analysis model has several built-in signal analysis rules.

[0091] Specifically, the reference high-frequency remote control signal and the comparison high-frequency remote control signal are input into a signal analysis model, the signal analysis model is built-in with a plurality of signal analysis rules, each signal analysis rule is different, and therefore, the reference high-frequency remote control signal and the comparison high-frequency remote control signal are processed by each signal analysis rule based on the plurality of different signal analysis rules in the signal analysis model. It should be noted that the reference high-frequency remote control signal and the comparison high-frequency remote control signal are both decoded high-frequency remote control signals, and after the reference high-frequency remote control signal and the comparison high-frequency remote control signal are processed by each signal analysis rule, the waveform information of the reference high-frequency remote control signal corresponding to each signal analysis rule and the waveform information of the high-frequency remote control signal corresponding to each signal analysis rule are obtained, which can be processed by the MCU.

[0092] S03: Based on the signal analysis model, the recognition conversion accuracy corresponding to each signal analysis rule is obtained.

[0093] In this embodiment, the recognition conversion accuracy refers to the accuracy of remote control signal conversion.

[0094] Specifically, based on the signal analysis model, the comparison between the waveform information of the reference high-frequency remote control signal corresponding to each signal analysis rule and the waveform information of the high-frequency remote control signal corresponding to each signal analysis rule is analyzed, and then the accuracy of converting the reference high-frequency remote control signal into the comparison high-frequency remote control signal corresponding to each signal analysis rule, i.e., the recognition conversion accuracy, is obtained. In this embodiment, the signal analysis rule includes directly sampling the high-frequency remote control signal into digital form after the high-frequency remote control signal is filtered and amplified, directly converting the remote control signal by measuring the width or time interval of the pulse, extracting the characteristics (such as peak value, energy, spectral component, etc.) of the through-hole signal, converting the waveform of the remote control signal into a set of feature vectors, obtaining the frequency distribution characteristics of the signal by performing Fourier transform (for example, fast Fourier transform) on the received remote control signal, and converting the remote control signal into time series data, etc.

[0095] Further, the accuracy of converting the reference high-frequency remote control signal into the comparison high-frequency remote control signal can be judged by the completeness of the code value, and can also be judged by the details of the waveform characteristics (such as pulse duration and pulse width, etc.).

[0096] S04: Selecting the signal analysis rule with the highest recognition conversion accuracy as the signal conversion rule.

[0097] Specifically, according to the recognition conversion accuracy of converting the reference high-frequency remote control signal into the comparison high-frequency remote control signal corresponding to each signal analysis rule, the signal analysis rule with the highest recognition conversion accuracy is selected as the signal conversion rule.

[0098] In an embodiment, as Figure 3As shown, the signal recognition model is generated in the following manner:

[0099] S001: Obtain a historical high-frequency remote control signal group, the historical high-frequency remote control signal group including historical high-frequency remote control signal groups of multiple types of remote controllers, each type of remote controller including multiple different high-frequency remote control signals.

[0100] In this embodiment, the historical high-frequency remote control signal group refers to a historical remote controller remote control signal group.

[0101] Specifically, the historical high-frequency remote control signal group is obtained, wherein the historical high-frequency remote control signal group includes historical high-frequency remote control signal groups of multiple different types of remote controllers, each type of remote controller including multiple high-frequency remote control signals with different encoding values and multiple high-frequency remote control signals with different encoding forms.

[0102] S002: Input the historical high-frequency remote control signal into a machine learning model, the machine learning model being provided with a signal conversion rule.

[0103] Specifically, the historical high-frequency remote control signal is input into the machine learning model, which is provided with a signal conversion rule, so that the machine learning model is used to convert each remote control signal in the historical high-frequency remote control signal and learn the waveform characteristics of various types of remote control signals.

[0104] S003: Obtain prediction accuracy data based on the machine learning model.

[0105] In this embodiment, the prediction accuracy data refers to the accuracy data of the predicted generated remote control signal.

[0106] Specifically, the machine learning model is used to learn the features of various types of remote control signals and to predict the generation of remote control signals based on the learned features of the remote control signals. In this embodiment, the machine learning model can learn and predict the generation in the following manner: first, a plurality of historical high-frequency remote control signals of each encoding form are divided into two groups, one group is used for learning, and the other group is used to judge the accuracy of the predicted generation, that is, after training the machine learning model with a group of historical high-frequency remote control signals of the same encoding form, the trained machine learning model predicts the generation of a plurality of predicted high-frequency remote control signals based on the learned waveform features of the remote control signals, the number of predicted high-frequency remote control signals is the same as the number of historical high-frequency remote control signals used to judge the accuracy of the predicted generation, and then each predicted high-frequency remote control signal is compared with all historical high-frequency remote control signals used to judge the accuracy of the predicted generation in terms of waveform features, so as to obtain prediction accuracy data. In addition, the machine learning model can learn and predict the generation in the following manner: first, a plurality of historical high-frequency remote control signals of each encoding form are arranged in sequence, and the machine learning model is trained in the following manner: learning-predicting generation-learning-predicting generation, that is, after training the machine learning model with a plurality of historical high-frequency remote control signals as the initial minimum training sample number, the trained machine learning model predicts the generation of a predicted high-frequency remote control signal based on the learned waveform features of the remote control signals, compares the predicted high-frequency remote control signal with the next sequential historical high-frequency remote control signal in terms of waveform features, obtains a prediction accuracy data, adjusts the historical high-frequency remote control signal with the prediction accuracy data, and then trains the machine learning model again, and then predicts the generation of a predicted high-frequency remote control signal based on the learned waveform features of the remote control signals, obtains the next prediction accuracy data, and so on, to obtain a plurality of prediction accuracy data corresponding to each encoding form.

[0107] Further, the prediction accuracy data includes prediction accuracy data for different waveform features of the remote control signal, that is, a remote control signal has multiple waveform features, and the prediction accuracy data includes prediction accuracy data for multiple different waveform features of a remote control signal.

[0108] S004: Based on the prediction accuracy data, obtain the signal prediction degree corresponding to each type of remote control.

[0109] Specifically, the prediction accuracy data is processed to obtain the signal prediction accuracy for each encoding form of each type of remote control. For example, when the machine learning model learns and predicts by first dividing multiple historical high-frequency remote control signals of each encoding form into two groups, the corresponding prediction accuracy data is the comparison similarity data of waveform features of each predicted high-frequency remote control signal of each encoding form with all historical high-frequency remote control signals used to judge the accuracy of the prediction. Therefore, the corresponding data processing methods can be variance analysis, regression analysis, or calculating the average or harmonic mean of all comparison similarity data, or forming a data matrix from all comparison similarity data and calculating the output value or matrix norm of the data matrix, etc. When the machine learning model learns and predicts by first arranging multiple historical high-frequency remote control signals of each encoding form in sequence, the corresponding prediction accuracy data is the comparison similarity data of waveform features compared multiple times for each encoding form. Therefore, the corresponding data processing methods can be the geometric mean or mean calculation of the comparison similarity data, or forming a data matrix from the comparison similarity data of waveform features compared multiple times and calculating the output value or matrix norm of the data matrix, etc.

[0110] S005: Generate a signal recognition model based on signal predictability.

[0111] Specifically, a signal recognition model is generated based on the signal prediction degree of each encoding form corresponding to each type of remote control. Thus, when the quantized first high-frequency remote control signal is input into the signal recognition model, the signal prediction degree of the encoding form of the quantized first high-frequency remote control signal and the remote control type can be obtained.

[0112] In one embodiment, such as Figure 4 As shown, in step S40, the second high-frequency remote control signal is verified and quantized based on the signal predictivity to obtain the verification result, specifically including:

[0113] S41: Generate a predictive high-frequency remote control signal based on the signal predictability.

[0114] In this embodiment, predicting the high-frequency remote control signal refers to predicting the generated high-frequency remote control signal.

[0115] Specifically, after obtaining the signal prediction degree and quantizing the second high-frequency remote control signal, based on the signal prediction degree, at this time, the signal prediction degree represents the prediction degree of the waveform characteristics of the remote control signal such as the quantized first high-frequency remote control signal by the signal recognition model, for example, when the signal prediction degree is 80%, it means that the signal recognition model can predict 80% of the waveform characteristics of the quantized second high-frequency remote control signal, therefore, based on the signal recognition model, a prediction high-frequency remote control signal corresponding to 80% of the waveform characteristics of the remote control signal type of the quantized first high-frequency remote control signal is generated, at this time, the feature prediction of the part corresponding to the signal prediction degree in the prediction high-frequency remote control signal is generated, and the remaining part of the prediction high-frequency remote control signal is the standard code generated according to the remote control function represented by the second high-frequency remote control signal, which conforms to the current remote control signal coding form. In this way, the prediction high-frequency remote control signal is generated.

[0116] S42: Comparing the prediction high-frequency remote control signal and the quantized second high-frequency remote control signal, a verification result is obtained.

[0117] Specifically, comparing the prediction high-frequency remote control signal and the quantized second high-frequency remote control signal, at this time, the signal prediction degree represents the comparison similarity of the waveform characteristics of the prediction high-frequency remote control signal and the quantized second high-frequency remote control signal, for example, when the signal prediction degree is 80%, the waveform characteristic similarity of the prediction high-frequency remote control signal and the quantized second high-frequency remote control signal should be 80%, therefore, the comparison similarity of the waveform characteristics of the prediction high-frequency remote control signal and the quantized second high-frequency remote control signal is taken as the verification result.

[0118] In an embodiment, as shown in Figure 5 In step S50, according to the verification result, the quantized third high-frequency remote control signal is obtained, specifically including:

[0119] S51: If the verification result indicates that the verification is passed, the prediction high-frequency remote control signal is taken as the quantized third high-frequency remote control signal.

[0120] Specifically, when the part corresponding to the signal prediction degree in the prediction high-frequency remote control signal is the same as the corresponding part of the quantized second high-frequency remote control signal, that is, the comparison similarity of the waveform characteristics of the prediction high-frequency remote control signal and the quantized second high-frequency remote control signal reaches the signal prediction degree, the verification result indicates that the verification is passed, the feature recognition of the current original remote controller by the signal recognition model is accurate, therefore, the prediction high-frequency remote control signal is taken as the quantized third high-frequency remote control signal, at this time, the user does not need to continue pressing the remaining keys to send the remote control signal, and the current wireless learning type remote controller can send an indication signal to inform the user, for example, sending an indication reminding sound or a light reminding.

[0121] S52: If the verification result indicates that the verification is not passed, the third high-frequency remote control signal is obtained, the third high-frequency remote control signal is processed based on the signal conversion rule, and the quantized third high-frequency remote control signal is obtained.

[0122] Specifically, when the part corresponding to the signal prediction degree in the predicted high-frequency remote control signal is not similar to the corresponding part of the second high-frequency remote control signal, i.e., the waveform feature of the predicted high-frequency remote control signal is not similar to the waveform feature of the quantized second high-frequency remote control signal, the verification result indicates that the verification fails, and the user needs to press the button to send the remote control signal for the wireless learning type remote controller to learn, so as to obtain the third high-frequency remote control signal, and then process the third high-frequency remote control signal based on the signal conversion rule to obtain the quantized third high-frequency remote control signal.

[0123] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0124] In an embodiment, a control device of a high-frequency wireless learning type remote controller is provided, which corresponds to the control method of the high-frequency wireless learning type remote controller in the above embodiment. As shown in the figure, the control device of the high-frequency wireless learning type remote controller includes a first signal processing module, a first signal processing module, a second signal processing module, a prediction verification module, and a third signal acquisition module. The functions of each functional module are described in detail as follows: Figure 6

[0125] The first signal processing module is configured to obtain a first high-frequency remote control signal, process the first high-frequency remote control signal based on a preset signal conversion rule, and obtain a quantized first high-frequency remote control signal;

[0126] The signal recognition module is configured to input the quantized first high-frequency remote control signal into a preset signal recognition model to obtain a signal prediction degree;

[0127] The second signal processing module is configured to obtain a second high-frequency remote control signal, process the second high-frequency remote control signal according to the preset signal conversion rule, and obtain a quantized second high-frequency remote control signal;

[0128] The prediction verification module is configured to verify the quantized second high-frequency remote control signal according to the signal prediction degree to obtain a verification result;

[0129] The third signal acquisition module is configured to obtain a quantized third high-frequency remote control signal according to the verification result, and store the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal, and the quantized third high-frequency remote control signal.

[0130] Optionally, the control device of the high-frequency wireless learning type remote controller further includes:

[0131] The comparison signal module is configured to obtain a reference high-frequency remote control signal, and generate a plurality of groups of comparison high-frequency remote control signals based on the reference high-frequency remote control signal; ​

[0132] a signal analysis module, configured to input the reference high-frequency remote control signal and the comparison high-frequency remote control signal into a signal analysis model, the signal analysis model being provided with a plurality of signal analysis rules;

[0133] a correctness rate determination module, configured to determine, based on the signal analysis model, a recognition conversion correctness rate corresponding to each signal analysis rule;

[0134] a rule selection module, configured to select, as a signal conversion rule, a signal analysis rule with the highest recognition conversion correctness rate.

[0135] Optionally, the control device of the high-frequency wireless learning type remote controller further comprises:

[0136] a historical signal acquisition module, configured to acquire a historical high-frequency remote control signal group, the historical high-frequency remote control signal group including historical high-frequency remote control signal groups of a plurality of types of remote controllers, and each historical high-frequency remote control signal group including a plurality of different high-frequency remote control signals;

[0137] a model conversion module, configured to input the historical high-frequency remote control signal into a machine learning model, the machine learning model being provided with the signal conversion rule;

[0138] a model analysis module, configured to acquire prediction accuracy data based on the machine learning model;

[0139] a prediction degree acquisition module, configured to acquire, based on the prediction accuracy data, a signal prediction degree corresponding to each type of remote controller;

[0140] a model generation module, configured to generate a signal recognition model based on the signal prediction degree.

[0141] Optionally, the prediction verification module comprises:

[0142] a predicted signal generation submodule, configured to generate a predicted high-frequency remote control signal according to the signal prediction degree;

[0143] a signal comparison submodule, configured to compare the predicted high-frequency remote control signal with the quantized second high-frequency remote control signal to obtain a verification result.

[0144] Optionally, the third signal acquisition module comprises:

[0145] a verification passing submodule, configured to, if the verification result indicates passing the verification, take the predicted high-frequency remote control signal as the quantized third high-frequency remote control signal;

[0146] a verification failing submodule, configured to, if the verification result indicates failing the verification, acquire a third high-frequency remote control signal, process the third high-frequency remote control signal based on the signal conversion rule, and obtain a quantized third high-frequency remote control signal.

[0147] The specific definition of the control device of the high-frequency wireless learning type remote controller can refer to the definition of the control method of the high-frequency wireless learning type remote controller, which will not be repeated here. Each module in the control device of the high-frequency wireless learning type remote controller can be realized by software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0148] In one embodiment, a computer device, which can be a server, has an internal structure diagram as shown in Figure 7 The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is used to store quantized first high-frequency remote control signals, signal prediction degrees, quantized second high-frequency remote control signals, verification results, and quantized third high-frequency remote control signals. The network interface of the computer device is used to communicate with external terminals through network connections. The computer program is executed by the processor to implement a control method for a high-frequency wireless learning type remote controller.

[0149] In one embodiment, a computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the following steps:

[0150] Obtain a first high-frequency remote control signal, process the first high-frequency remote control signal based on a preset signal conversion rule, and obtain a quantized first high-frequency remote control signal;

[0151] Input the quantized first high-frequency remote control signal into a preset signal recognition model to obtain a signal prediction degree;

[0152] Obtain a second high-frequency remote control signal, process the second high-frequency remote control signal according to the preset signal conversion rule, and obtain a quantized second high-frequency remote control signal;

[0153] Verify the quantized second high-frequency remote control signal according to the signal prediction degree to obtain a verification result;

[0154] According to the verification result, obtain a quantized third high-frequency remote control signal, and store the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal, and the quantized third high-frequency remote control signal.

[0155] In one embodiment, a computer readable storage medium is provided, having stored thereon a computer program, which when executed by a processor implements the following steps:

[0156] The first high-frequency remote control signal is acquired, and the first high-frequency remote control signal is processed based on a preset signal conversion rule to obtain a quantized first high-frequency remote control signal.

[0157] The quantized first high-frequency remote control signal is input into a preset signal recognition model to obtain a signal prediction degree.

[0158] The second high-frequency remote control signal is acquired, and the second high-frequency remote control signal is processed according to a preset signal conversion rule to obtain a quantized second high-frequency remote control signal.

[0159] The quantized second high-frequency remote control signal is verified according to the signal prediction degree to obtain a verification result.

[0160] According to the verification result, a quantized third high-frequency remote control signal is acquired, and the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal, and the quantized third high-frequency remote control signal are stored.

[0161] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0162] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0163] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A control method for a high-frequency wireless learning remote controller, characterized in that, The control method of the high-frequency wireless learning remote controller includes: Acquire a first high-frequency remote control signal, process the first high-frequency remote control signal based on a preset signal conversion rule, and obtain a quantized first high-frequency remote control signal; The quantized first high-frequency remote control signal is input into a preset signal recognition model to obtain the signal predictability. Acquire a second high-frequency remote control signal, process the second high-frequency remote control signal according to a preset signal conversion rule, and obtain a quantized second high-frequency remote control signal; Based on the signal predictivity, the quantized second high-frequency remote control signal is verified to obtain the verification result, specifically including: Based on the signal predictability, a second high-frequency remote control signal is generated; By comparing the predicted second high-frequency remote control signal and the quantized second high-frequency remote control signal, the verification result is obtained; Based on the verification results, a quantized third high-frequency remote control signal is obtained, and the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal, and the quantized third high-frequency remote control signal are stored, specifically including: If the verification result indicates that the verification is passed, then a predicted third high-frequency remote control signal is generated based on the signal predictivity, and the predicted third high-frequency remote control signal is used as the quantized third high-frequency remote control signal. If the verification result indicates that the verification failed, then the third high-frequency remote control signal is obtained, and the third high-frequency remote control signal is processed based on the signal conversion rule to obtain a quantized third high-frequency remote control signal.

2. The control method for the high-frequency wireless learning remote controller according to claim 1, characterized in that, The signal conversion rules are generated in the following manner: Acquire a reference high-frequency remote control signal, and generate several sets of comparative high-frequency remote control signals based on the reference high-frequency remote control signal; The reference high-frequency remote control signal and the comparison high-frequency remote control signal are input into a signal analysis model, which has several built-in signal analysis rules. Based on the signal analysis model, the recognition and conversion accuracy for each of the signal analysis rules is obtained; The signal analysis rule with the highest recognition and conversion accuracy is selected as the signal conversion rule.

3. The control method for the high-frequency wireless learning remote controller according to claim 1, characterized in that, The signal recognition model is generated in the following way: Acquire historical high-frequency remote control signal groups, which include historical high-frequency remote control signal groups of various types of remote controllers, and each type of remote controller includes a variety of different high-frequency remote control signals. The historical high-frequency remote control signal is input into a machine learning model, which is configured with the signal conversion rules. Based on the machine learning model, obtain prediction accuracy data; Based on the prediction accuracy data, the signal prediction accuracy for each type of remote control is obtained; Based on the signal predictability, a signal recognition model is generated.

4. A control device for a high-frequency wireless learning remote controller, characterized in that, The control device of the high-frequency wireless learning remote controller includes: The first signal processing module is used to acquire a first high-frequency remote control signal, process the first high-frequency remote control signal based on a preset signal conversion rule, and obtain a quantized first high-frequency remote control signal. The signal recognition module is used to input the quantized first high-frequency remote control signal into a preset signal recognition model to obtain the signal predictability. The second signal processing module is used to acquire the second high-frequency remote control signal, process the second high-frequency remote control signal according to the preset signal conversion rules, and obtain the quantized second high-frequency remote control signal. A prediction verification module is used to verify the quantized second high-frequency remote control signal based on the signal prediction degree and obtain a verification result. The prediction verification module includes: The prediction signal generation submodule is used to generate a predicted second high-frequency remote control signal based on the predictability of the signal. The signal comparison submodule is used to compare the predicted second high-frequency remote control signal and the quantized second high-frequency remote control signal to obtain the verification result. The third signal acquisition module is used to acquire a quantized third high-frequency remote control signal based on the verification result, and to store the quantized first high-frequency remote control signal, the quantized second high-frequency remote control signal, and the quantized third high-frequency remote control signal. The third signal acquisition module includes: The verification passed submodule is used to generate a predicted third high-frequency remote control signal based on the signal predictivity if the verification result indicates that the verification is passed, and to use the predicted third high-frequency remote control signal as the quantized third high-frequency remote control signal. The verification failure submodule is used to obtain a third high-frequency remote control signal if the verification result indicates that the verification has failed, and to process the third high-frequency remote control signal based on the signal conversion rules to obtain a quantized third high-frequency remote control signal.

5. The control device for the high-frequency wireless learning remote controller according to claim 4, characterized in that, The control device of the high-frequency wireless learning remote controller also includes: The comparison signal module is used to acquire a reference high-frequency remote control signal and generate several sets of comparison high-frequency remote control signals based on the reference high-frequency remote control signal. The signal analysis module is used to input the reference high-frequency remote control signal and the comparison high-frequency remote control signal into the signal analysis model, and the input signal analysis model has several built-in signal analysis rules. The accuracy judgment module is used to obtain the recognition and conversion accuracy corresponding to each of the signal analysis rules based on the signal analysis model; The rule selection module is used to select the signal analysis rule with the highest recognition and conversion accuracy as the signal conversion rule.

6. The control device for the high-frequency wireless learning remote controller according to claim 4, characterized in that, The control device of the high-frequency wireless learning remote controller also includes: The historical signal acquisition module is used to acquire historical high-frequency remote control signal groups, which include historical high-frequency remote control signal groups of various types of remote controllers, and each type of remote controller's historical high-frequency remote control signal group includes multiple different high-frequency remote control signals. The model conversion module is used to input the historical high-frequency remote control signal into a machine learning model, wherein the machine learning model is configured with the signal conversion rules. The model analysis module is used to obtain prediction accuracy data based on the machine learning model. The prediction accuracy acquisition module is used to obtain the signal prediction accuracy for each type of remote controller based on the prediction accuracy data. The model generation module is used to generate a signal recognition model based on the signal predictivity.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the control method of the high-frequency wireless learning remote controller as described in any one of claims 1 to 3.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the control method of the high-frequency wireless learning remote controller as described in any one of claims 1 to 3.

Images