Radio frequency power control method and device

Abstract

The invention provides a radio frequency power control method and device. The method comprises the following steps: acquiring first feature information of a power reference signal; obtaining second feature information representing the motion state of the equipment; the first feature information and the second feature information are input into a radio frequency power control model to obtain a first output result or a second output result, the model determines a threshold value selection result comprising a set of threshold values from multiple sets of threshold values based on the second feature information, and each set of threshold values comprises an upper threshold value and a lower threshold value related to the power reference signal; an output layer of the radio frequency power control model determines a first output result under a first threshold value comparison condition or determines a second output result under a second threshold value comparison condition, the first threshold value comparison condition comprises that the minimum value of the power reference signal is less than a lower threshold value, and the second threshold value comparison condition comprises that the minimum value of the power reference signal is less than a lower threshold value. The second threshold comparison condition comprises that the maximum value of the power reference signal is greater than the upper threshold; and controlling the radio frequency power of the antenna according to the output result.

Description

Technical Field

[0001] The present disclosure relates to the field of radio frequency technology, and in particular to a radio frequency power control method and device. Background Art

[0002] In related technologies, the RF power of the antenna on the device is managed. For example, when a user approaches the antenna, the RF power of the antenna is reduced. When identifying the proximity of a user, a SAR sensor (SAR sensor, SAR stands for Specific Absorption Rate, meaning the electromagnetic wave energy absorption ratio of a collection or wireless product) is usually used. A SAR sensor is a sensor used to identify whether a user is approaching.

[0003] When using a SAR sensor to identify whether a user is approaching, space must be provided in the device to deploy the sensor. Furthermore, the deployed SAR sensor will interfere with the antenna, affecting the antenna's transmission and reception efficiency.

[0004] Therefore, a new RF power control method is needed. Summary of the Invention

[0005] In view of this, the present disclosure provides a radio frequency power control method and apparatus.

[0006] One aspect of the present disclosure provides a radio frequency power control method, including: obtaining first characteristic information of a power reference signal, the first characteristic information characterizing a change in the received power reference signal; obtaining second characteristic information characterizing a motion state of a device; inputting the first characteristic information and the second characteristic information into a radio frequency power control model to obtain a first output result or a second output result, wherein the model determines a threshold selection result including a group of thresholds from multiple groups of thresholds based on the second characteristic information, each group of thresholds including an upper threshold and a lower threshold related to the power reference signal; the output layer of the radio frequency power control model determines the first output result under a first threshold comparison condition or determines the second output result under a second threshold comparison condition, the first threshold comparison condition including the minimum value of the power reference signal being less than the lower threshold value, and the second threshold comparison condition including the maximum value of the power reference signal being greater than the upper threshold value; and controlling the radio frequency power of the antenna according to the output result.

[0007] According to an embodiment of the present disclosure, the RF power control model includes: an input layer, used to receive the first characteristic information and the second characteristic information, and determine a threshold selection result including a group of thresholds from multiple groups of thresholds based on the second characteristic information; at least one hidden layer, used to determine a threshold comparison result based on the first characteristic information and the threshold selection result, the threshold comparison result including a first threshold comparison situation or a second threshold comparison situation; an output layer, used to determine a first probability value for reducing the RF power and a second probability value for increasing the RF power based on the threshold comparison situation, and when the first probability value is greater than the first threshold, a first output result is obtained, and when the second probability value is greater than the second threshold, a second output result is obtained.

[0008] According to an embodiment of the present disclosure, the motion state of the device includes a stationary state or a moving state, and the multiple groups of thresholds include a first group of thresholds corresponding to the stationary state, and a second group of thresholds corresponding to the moving state, the second upper limit threshold of the second group of thresholds is higher than the first upper limit threshold of the first group of thresholds, and the second lower limit threshold of the second group of thresholds is lower than the first lower limit threshold of the first group of thresholds.

[0009] According to an embodiment of the present disclosure, the multiple groups of thresholds also include a third group of thresholds, and the method also includes: when it is determined that the motion state of the device is a mobile state, determining the movement mode of the device based on the movement state data of the device; when it is determined that the movement mode of the device is high-speed movement, determining that the threshold selection result includes a third group of thresholds, and the third upper limit threshold in the third group of thresholds is less than the second upper limit threshold and greater than the first upper limit threshold, and the third lower limit threshold is greater than the second lower limit threshold and less than the first lower limit threshold.

[0010] According to an embodiment of the present disclosure, the multiple groups of thresholds also include a fourth group of thresholds, and the method also includes: when it is determined that the movement mode of the device is periodic movement, determining that the threshold selection result includes a fourth group of thresholds, and the fourth upper limit threshold in the fourth group of thresholds is greater than the second upper limit threshold, and the fourth lower limit threshold is less than the second lower limit threshold.

[0011] According to an embodiment of the present disclosure, it further includes: when it is determined that the movement mode of the device is high-speed movement and the first probability value is less than a third threshold, setting the radio frequency power of the antenna to remain unchanged within a preset time.

[0012] According to an embodiment of the present disclosure, it also includes: when the first probability value is greater than a fourth threshold, setting the radio frequency power of the antenna to be reduced according to the first step length; when the first probability value is greater than a fifth threshold, setting the radio frequency power of the antenna to be reduced according to the second step length, the fourth threshold is greater than the fifth threshold, and the first step length is greater than the second step length.

[0013] According to an embodiment of the present disclosure, it also includes: when the second probability value is greater than the sixth threshold, setting the RF power of the antenna to increase according to the third step length; when the first probability value is greater than the seventh threshold, setting the RF power of the antenna to decrease according to the fourth step length, the sixth threshold value is greater than the seventh threshold value, and the third step length is greater than the fourth step length.

[0014] Another aspect of the present disclosure further provides a radio frequency power control model training method, comprising:

[0015] Obtain a training sample, wherein the training sample includes a received power reference signal and motion state data of a device where the antenna is located. The training sample is provided with a first label, a second label, and a third label. The first label includes whether to trigger. If the first label is triggered, it indicates that the user is close to the antenna and the RF power of the antenna needs to be reduced. The second label includes whether to release. If the second label is released, it indicates that the user is far away from the antenna and the RF power of the antenna needs to be increased. The third label includes the motion state of the device where the antenna is located. According to the training sample, the pre-trained model is trained to obtain a RF power control model and multiple sets of thresholds under different motion states of the device.

[0016] Another aspect of the present disclosure also provides a radio frequency power control device, including: a first characteristic information acquisition module, used to obtain first characteristic information of a power reference signal, wherein the first characteristic information characterizes the change of the received power reference signal; a second characteristic information acquisition module, used to obtain second characteristic information characterizing the motion state of the device; an output result determination module, used to input the first characteristic information and the second characteristic information into a radio frequency power control model to obtain a first output result or a second output result, wherein the model determines a threshold selection result including a group of thresholds from multiple groups of thresholds based on the second characteristic information, each group of thresholds including an upper threshold and a lower threshold related to the power reference signal; the output layer of the radio frequency power control model determines the first output result under a first threshold comparison condition or determines the second output result under a second threshold comparison condition, wherein the first threshold comparison condition includes that the minimum value of the power reference signal is less than the lower threshold, and the second threshold comparison condition includes that the maximum value of the power reference signal is greater than the upper threshold; and a radio frequency power setting module, used to control the radio frequency power of the antenna according to the output result.

[0017] Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to perform the above method.

[0018] Another aspect of the present disclosure further provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to perform the above method.

[0019] Another aspect of the present disclosure provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0022] Figure 1 is a schematic diagram of an exemplary system architecture to which the radio frequency power control method and apparatus according to an embodiment of the present disclosure can be applied;

[0023] Figure 2 A schematic diagram of a radio frequency power control model is schematically shown;

[0024] Figure 3a A schematic diagram of a first training sample is schematically shown;

[0025] Figure 3b A schematic diagram of a second training sample is schematically shown;

[0026] Figure 3c A schematic diagram of a third training sample is schematically shown;

[0027] Figure 3d A schematic diagram of a fourth training sample is schematically shown;

[0028] Figure 3e A schematic diagram of a fifth training sample is schematically shown;

[0029] Figure 3f A schematic diagram of a sixth training sample is schematically shown;

[0030] Figure 4 FIG4 is a schematic diagram showing a radio frequency power control method 400 according to an embodiment of the present disclosure;

[0031] Figure 5 Schematically shows a structural block diagram of a device according to an embodiment of the present disclosure;

[0032] Figure 6 A schematic block diagram of an electronic device that can be used to implement the method of the embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0033] Embodiments of the present disclosure are described below with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted from the following description.

[0034] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure and application of the data involved (including but not limited to user personal information) comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0035] Figure 1 This is a schematic diagram of an exemplary system architecture to which the radio frequency power control method and apparatus according to an embodiment of the present disclosure can be applied. It should be noted that: Figure 1 The examples shown are merely examples of system architectures to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure may not be used in other devices, systems, environments or scenarios.

[0036] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0037] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Terminal devices 101, 102, and 103 can be various electronic devices with display screens and support web browsing, including but not limited to smartphones, tablet computers, laptop computers, and desktop computers, etc.

[0038] Server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using terminal devices 101, 102, and 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal device.

[0039] It should be noted that the RF power control method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the RF power control device provided in the embodiment of the present disclosure can generally be set in the server 105. The RF power control method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the RF power control device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0040] According to one embodiment, the present invention constructs a radio frequency power control model for replacing a SAR sensor. The radio frequency power control model obtains a reference power signal and determines whether to control the radio frequency power of the antenna based on the reference power signal.

[0041] According to one embodiment, the RF power control model includes: an input layer for receiving first characteristic information and second characteristic information, and determining a threshold selection result including a group of thresholds from multiple groups of thresholds based on the second characteristic information; at least one hidden layer for determining a threshold comparison result based on the first characteristic information and the threshold selection result, the threshold comparison result including a first threshold comparison situation or a second threshold comparison situation; an output layer for determining a first probability value for reducing the RF power and a second probability value for increasing the RF power based on the threshold comparison situation, and obtaining a first output result when the first probability value is greater than the first threshold, and obtaining a second output result when the second probability value is greater than the second threshold.

[0042] Figure 2 A schematic diagram of the RF power control model is shown schematically. Figure 2 As shown, the RF power control model includes an input layer, a first Dropout layer, a second Dropout layer, a second Dropout layer, a third Dropout layer, a fourth Dropout layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer connected in sequence.

[0043] According to one embodiment, to balance recognition accuracy, training time, and response speed, and to enable the RF power control model to be deployed in low-cost MCUs, the RF power control model can be implemented as a lightweight MLP structure. The model's input layer can be implemented as a fully connected layer and may include 64 neurons. The input layer may also include a ReLU (Rectified Linear Unit) activation function. The ReLU activation function is used to introduce nonlinearity into the neural network model, allowing the model to gradually learn more effective feature representations. Because the ReLU activation function does not activate all neurons simultaneously, activating a small number of neurons at a time makes sparse neural networks efficient and computationally easy. The first hidden layer may include 32 neurons, the second hidden layer may include 16 neurons, and the third hidden layer may include 8 neurons. The first, second, third, and fourth hidden layers may include the ReLU activation function. The first, second, third, and fourth dropout layers may be implemented with a dropout rate of 0.2. The dropout layer ignores randomly selected neurons during training, preventing model overfitting. The output layer may be implemented with 2 neurons and a softmax activation function. Softmax is used in the model's output layer. This softmax function is used to construct a multi-classification model, assigning probabilities to each target class. The class with the highest probability score becomes the final output. The RF power control model also uses the cross-entropy loss function, categorical_crosentropy, to estimate the model's loss and update weights to reduce the loss in the next evaluation. The RF power control model also uses an Adam optimizer with an adaptive learning rate to handle sparse gradients in the presence of noise.

[0044] According to one embodiment, when training the model, a training sample is obtained, and the training sample includes a received power reference signal and the motion state data of the device where the antenna is located, and may also include a first feature information determined based on the received power reference signal and a second feature information determined based on the device motion data. The training sample is provided with a first label, a second label and a third label. The first label includes whether it is triggered. If the first label is triggered, it means that the user is close to the antenna and the RF power of the antenna needs to be reduced. The second label includes whether it is released. If the second label is released, it means that the user is far away from the antenna and the RF power of the antenna needs to be increased. The third label includes the motion state of the device where the antenna is located. Based on the training sample, the pre-trained model is trained to obtain a RF power control model and multiple sets of thresholds under different motion states of the device. This application does not impose any restrictions on the specific selection of the pre-selected model.

[0045] According to one embodiment, the training sample includes first characteristic information and second characteristic information for training. The first characteristic information is determined based on a power reference signal. The power reference signal includes the RSSI of the wireless network signal reception strength during a preset time period, or a signal change rate determined based on the wireless network signal reception strength. This application does not limit the specific setting method of the preset time period, such as 500ms, 1000ms, etc. The signal change rate is determined based on the rate at which the wireless network signal reception strength changes over time, such as:

[0046] a(RSSI)=Diff(RSSI) / Δt

[0047] Where a(RSSI) is the signal change rate, Diff(RSSI) is the change in the wireless network signal receiving strength RSSI within a time interval of Δt, and Δt is the time interval.

[0048] When determining the first characteristic information based on the power reference signal, the first characteristic information may be determined based on the rate of change of the signal over a preset time period: at least one of an average value, a maximum value, a minimum value, the sum of the average value and the standard deviation, the difference between the average value and the standard deviation, and the rate of change of the signal at one or more time points. This application does not limit the specific method for determining the first characteristic information from the power reference signal.

[0049] The second characteristic information is used to characterize the motion state of the device. The motion state of the device can be determined based on data from a gyroscope, an accelerometer, or the like. The motion state of the device includes moving or stationary. When the motion state of the device is moving, the device motion state data includes at least one of gyroscope data and accelerometer data. The second characteristic information can be determined based on data from a gyroscope, an accelerometer, or the like, such as by extracting and processing data from the gyroscope and accelerometer to obtain the second characteristic information. This application does not limit the specific method for determining the second characteristic information.

[0050] According to one embodiment, the present application trains multiple sets of thresholds for multiple operating states, and each set of thresholds includes an upper threshold and a lower threshold related to a power reference signal. Multiple motion states include stationary and mobile. Device mobile states include high-speed movement and periodic movement, etc. The present application does not limit the specific types of device mobile states. The present application trains a first set of thresholds for the stationary state and sets a second set of thresholds for the mobile state. The second set of thresholds can also be set to more accurate thresholds in different scenarios, such as a third set of thresholds set in a high-speed movement state and a fourth set of thresholds set in a periodic movement case.

[0051] Figure 3a Schematic diagram of the first training sample is shown schematically. Figure 3aAs shown, the first, second, and third labels of the first training sample are static, no trigger, and no release, respectively. The red and blue curves represent the wireless network signal reception strength and the signal change rate determined based on the wireless network signal reception strength, respectively. The green and black lines represent the upper and lower thresholds of the first set of training thresholds, respectively. In this state, the wireless network signal reception strength is stable, and the corresponding signal change rate fluctuation is low. The user is not close to the antenna, and the antenna's RF power reduction is not triggered.

[0052] Figure 3b Schematic diagram of the second training sample is shown schematically. Figure 3b As shown, the first, second, and third labels of the second training sample are stationary, triggered, and not released, respectively. The red and blue curves represent the wireless network signal reception strength and the signal change rate determined by the wireless network signal reception strength, respectively. The green and black lines represent the upper and lower thresholds of the first set of thresholds to be trained, respectively. In this state, the device is stationary. If the user approaches the antenna, such as holding their hand, the wireless network signal reception strength deteriorates rapidly, and the corresponding signal change rate reaches the lower threshold. However, the subsequent stable network signal reception strength indicates that the user has not removed their hand from the device, such as when playing a game. In this case, the hand has not been released and the device remains in the triggered state.

[0053] Figure 3c Schematic diagram of the third training sample is shown schematically. Figure 3c As shown, the first, second, and third labels of the third training sample are stationary, triggered, and released, respectively. The red and blue curves represent the wireless network signal reception strength and the signal change rate determined based on the wireless network signal reception strength, respectively. The green and black lines represent the upper and lower thresholds of the first set of thresholds to be trained, respectively. In this state, the device is stationary. If the user approaches the antenna, such as holding their hand, the wireless network signal reception strength deteriorates rapidly, and the corresponding signal change rate reaches the lower threshold, indicating a triggered state. If the user then moves away from the antenna, such as removing their hand, the wireless network signal reception strength increases rapidly, and the corresponding signal change rate reaches the upper threshold, indicating a released state.

[0054] Figure 3d Schematic diagram of the fourth training sample is shown schematically. Figure 3dAs shown, the first, second, and third labels of the fourth training sample are motion, no trigger, and no release, respectively. The red and blue curves represent the wireless network signal reception strength and the signal change rate determined based on the wireless network signal reception strength, respectively. The green and black lines represent the upper and lower thresholds of the second set of thresholds to be trained, respectively. In this state, the device is in motion. The user can hold the device but is not close to the antenna, for example, holding the hand away from the antenna. The wireless network signal fluctuates with the movement, but the corresponding signal change rate does not fluctuate dramatically, and the upper or lower thresholds are not reached, indicating neither trigger nor release.

[0055] Figure 3e Schematic diagram of the fifth training sample is shown schematically. Figure 3e As shown, the first label, second label, and third label of the fifth training sample are motion, triggering, and non-release, respectively. The red curve and blue curve represent the wireless network signal reception strength and the signal change rate determined based on the wireless network signal reception strength, respectively. The green line and black line represent the upper and lower thresholds of the second set of thresholds to be trained, respectively. In this state, the device is in motion. The user can hold the device and bring it close to the antenna. If the hand is held on the antenna, the wireless network signal reception strength deteriorates rapidly, and the corresponding signal change rate touches the lower threshold. However, the subsequent stable network signal reception strength indicates that the user's hand has not left the device. At this time, there is no release state and it will continue to be in the triggered state. Since the movement of the device will affect the wireless network signal reception strength, a separate set of thresholds needs to be trained to identify whether the user is close to the device in motion scenarios.

[0056] Figure 3f Schematic diagram of the sixth training sample is shown schematically. Figure 3f As shown, the first, second, and third labels of the sixth training sample are motion, triggering, and release, respectively. The red and blue curves represent the wireless network signal reception strength and the signal change rate determined based on the wireless network signal reception strength, respectively. The green and black lines represent the upper and lower thresholds of the second set of thresholds to be trained, respectively. In this state, the device is in motion. The user can hold the device close to the antenna. For example, if the user holds the device with their hand on the antenna, the wireless network signal reception strength deteriorates rapidly, and the corresponding signal change rate reaches the lower threshold, corresponding to the trigger state. Subsequently, if the user moves away from the antenna, for example, if the user removes their hand from the antenna, the wireless network signal reception strength increases rapidly, and the corresponding signal change rate reaches the upper threshold, indicating the release state.

[0057] According to one embodiment, in order to further more accurately judge whether the user is close to the antenna and whether the RF power needs to be controlled in a variety of mobile scenarios in motion scenarios, the present application obtains data in high-speed mobile scenarios and periodic mobile scenarios, such as the wireless network signal reception strength in high-speed mobile scenarios and periodic mobile scenarios, or the signal change rate determined based on the wireless network signal reception strength, and can also determine the first characteristic information; obtain data from the gyroscope and acceleration sensor, and can also determine the second characteristic information, generate training samples from the training data in the corresponding scenario, input the RF power control model, train the model, and obtain the third set of thresholds corresponding to the high-speed mobile scenario and the fourth set of thresholds corresponding to the periodic mobile scenario.

[0058] According to one embodiment, because motion can cause disturbances to the wireless network signal reception strength, or the signal change rate determined based on the wireless network signal reception strength, the threshold used by the RF power control model to determine whether to trigger or release will be higher. Therefore, in the second set of thresholds trained in a motion scenario, the second upper threshold is higher than the first upper threshold of the first set of thresholds, and the second lower threshold of the second set of thresholds is lower than the first lower threshold of the first set of thresholds. The first upper threshold is, for example, 100, and the second lower threshold is, for example, -100; the second upper threshold is, for example, 110, and the second lower threshold is, for example, -110.

[0059] According to one embodiment, in a sports scenario, if the user is in a high-speed movement scenario, such as when riding in a vehicle or other means of transportation, the disturbance caused by the wireless network signal reception strength, or the signal change rate determined based on the wireless network signal reception strength, will be less than that in a low-speed, normal sports scenario. In the high-speed movement scenario, the third upper threshold value of the third set of thresholds obtained by training is less than the second upper threshold value and greater than the first upper threshold value, and the third lower threshold value is greater than the second lower threshold value and less than the first lower threshold value. For example, the third upper threshold value can be set to 105, and the third lower threshold value can be set to -105.

[0060] According to one embodiment, in a periodic movement scenario, such as when a user walks or runs, the user's periodic movement may cause disturbances to the wireless network signal reception strength, or the signal change rate determined based on the wireless network signal reception strength. This disturbance may be compounded by the effect of the user's proximity to the antenna on the wireless network signal reception strength, or the signal change rate determined based on the wireless network signal reception strength. Therefore, the upper threshold of the fourth set of thresholds obtained through training may be lowered, while the lower threshold may be raised. In the fourth set of thresholds, the fourth upper threshold is greater than the second upper threshold, and the fourth lower threshold is less than the second lower threshold. For example, the fourth upper threshold may be set to 115, and the fourth lower threshold may be set to -115.

[0061] According to one embodiment, the input layer further determines a threshold selection result including a set of thresholds from multiple sets of thresholds based on the second feature information; the device motion state includes a stationary state or a mobile state, and the multiple sets of thresholds include a first set of thresholds corresponding to the stationary state and a second set of thresholds corresponding to the mobile state, wherein the second upper limit threshold of the second set of thresholds is higher than the first upper limit threshold of the first set of thresholds, and the second lower limit threshold of the second set of thresholds is lower than the first lower limit threshold of the first set of thresholds. Furthermore, the multiple sets of thresholds also include a third set of thresholds and a fourth set of thresholds. When the device motion state is determined to be a mobile state, the device's movement mode is determined based on the device's movement state data; when the device's movement mode is determined to be high-speed movement, the threshold selection result is determined to include the third set of thresholds, wherein the third upper limit threshold of the third set of thresholds is less than the second upper limit threshold and greater than the first upper limit threshold, and the third lower limit threshold is greater than the second lower limit threshold and less than the first lower limit threshold. When the device's movement mode is determined to be periodic movement, the threshold selection result is determined to include a fourth set of thresholds, wherein the fourth upper limit threshold of the fourth set of thresholds is greater than the second upper limit threshold, and the fourth lower limit threshold is less than the second lower limit threshold.

[0062] According to one embodiment, at least one hidden layer determines a threshold comparison result based on the first feature information and the threshold selection result. The threshold comparison result includes a first threshold comparison condition or a second threshold comparison condition. The first threshold comparison condition includes a minimum value of the power reference signal being less than a lower threshold, and the second threshold comparison condition includes a maximum value of the power reference signal being greater than an upper threshold. The power reference signal can be implemented as wireless network signal reception strength or a signal change rate determined based on the wireless network signal reception strength.

[0063] According to one embodiment, the output layer is configured to determine a first probability value indicating a need to reduce RF power and a second probability value indicating a need to increase RF power based on a threshold comparison. A first output result is obtained when the first probability value is less than a lower threshold, and a second output result is obtained when the second probability value is greater than an upper threshold. Specifically, if the threshold comparison is a first threshold comparison result, this indicates a trigger condition, i.e., it is determined that the user is approaching the antenna in the motion scene and the antenna's RF power needs to be reduced, thereby obtaining a first probability value indicating a need to reduce RF power. If the threshold comparison is a second threshold comparison result, this indicates a release condition, i.e., it is determined that the user has moved from being close to the antenna to being away from the antenna in the motion scene and the antenna's RF power can be increased, thereby obtaining a second probability value indicating a need to increase RF power. When the first probability value is greater than the first threshold, a first output result is obtained, including: determining that the user is approaching the antenna and the antenna's RF power needs to be reduced; when the second probability value is greater than the second threshold, a second output result is obtained, including: determining that the user is away from the antenna and the antenna's RF power can be increased. For example, if the first threshold is set to 50%, and the second threshold is set to 50%, this application does not limit the specific settings of the first and second thresholds.

[0064] According to one embodiment, the absolute value of the received signal strength (RSSI) varies, regardless of whether the user is moving or stationary, moving the device or holding it, or changing the position of the hand. However, this RSSI cannot be used to directly determine whether the user is close to the antenna. For example, the RSSI value may be the same when the user is far away from the router and when the user's hand is close to the antenna. Since SAR triggering is based on the user's body being close to the device, performance degradation is inevitable due to absorption and scattering of the wireless signal by the body. Therefore, the signal change rate determined based on the wireless network signal receiving strength enters a negative range, reaching the lower threshold, which is the SAR triggering range. When the body moves away from the antenna, the signal gradually improves, and the signal change rate falls into a positive range, reaching the upper threshold, which is the SAR release range. This application proposes a simple MLP model as a classifier for SAR detection. When the input signal enters the classification model, the classifier outputs probabilities corresponding to two categories: triggering SAR and not triggering SAR (or releasing SAR). In the recognition decision stage, whether the output probability exceeds the threshold is used as a judgment condition to derive the final result.

[0065] Figure 4 FIG. 4 is a schematic diagram showing a radio frequency power control method 400 according to an embodiment of the present disclosure. Figure 4As shown, step 410 is first performed to obtain first characteristic information of a power reference signal. The first characteristic information represents changes in the received power reference signal. The rate reference model includes the wireless network signal received strength RSSI (Received Signal Strength Index) for a preset time period, or a signal change rate determined based on the wireless network signal received strength. The first characteristic information may include at least one of an average value, a maximum value, a minimum value, a sum of the average value and the standard deviation, a difference between the average value and the standard deviation, and a signal change rate at one or more time points.

[0066] Then, step 420 is executed to obtain second characteristic information representing the motion state of the device. The second characteristic information is determined based on the motion state data of the device, such as data from a gyroscope or an acceleration sensor.

[0067] Subsequently, step 430 is executed to input the first feature information and the second feature information into the RF power control model to obtain a first output result or a second output result, wherein the model determines a threshold selection result including a set of thresholds from multiple threshold groups based on the second feature information, each threshold group including an upper threshold and a lower threshold related to the power reference signal; the output layer of the RF power control model determines the first output result under a first threshold comparison condition or determines the second output result under a second threshold comparison condition, wherein the first threshold comparison condition includes the minimum value of the power reference signal being less than the lower threshold, and the second threshold comparison condition includes the maximum value of the power reference signal being greater than the upper threshold. According to one embodiment, when the model determines the threshold selection result including a set of thresholds from multiple threshold groups based on the second feature information, the motion state of the device where the antenna is located is obtained, and the threshold selection result is determined based on the operating state of the device. The first threshold comparison condition includes the minimum value of the power reference signal being less than the lower threshold, and the first output result includes the user approaching the antenna in the determined motion scenario, and the antenna's RF power needs to be reduced; the second threshold comparison condition includes the maximum value of the power reference signal being greater than the upper threshold, and the second output result includes the user being away from the antenna, and the antenna's RF power can be increased.

[0068] Finally, step 440 is executed to control the antenna's RF power based on the output result, including reducing the antenna's RF power based on the first output result and increasing the antenna's RF power based on the second output result. This application utilizes the real-time monitoring of wireless network signal reception strength, or the signal change rate determined based on the wireless network signal reception strength, when a terminal device such as a tablet is wirelessly connected. By extracting and processing these two parameters, the user's actual SAR triggering condition is identified and the corresponding power backoff or increase is performed.

[0069] According to one embodiment, when it is determined that the device is moving at high speed and the first probability value is less than a third threshold, the RF power of the target antenna is set to remain unchanged for a preset time. The third threshold can be set to 30%, and this application does not limit the specific setting method of the third threshold. If the device is moving at high speed and the first probability value is less than the third threshold, it indicates that the user is unlikely to be close to the antenna at this time. In this case, the RF power of the antenna can be maintained to maintain the optimal performance of the antenna.

[0070] According to one embodiment, when the first probability value is greater than the fourth threshold value, the RF power of the antenna is set to be reduced according to the first step length; when the first probability value is greater than the fifth threshold value, the RF power of the antenna is set to be reduced according to the second step length, the fourth threshold value is greater than the fifth threshold value, and the first step length is greater than the second step length. The fourth threshold value can be set to 80%, and the fifth threshold value can be set to 50%. This application does not limit the specific setting method of the fourth threshold value and the fifth threshold value. If the first probability value is greater than the fourth threshold value, it can be more accurately and clearly determined that the user is close to the antenna. At this time, the antenna RF power can be set to be reduced more quickly, that is, the higher the possibility that the user is close to the antenna, the faster the antenna RF power can be reduced.

[0071] According to one embodiment, when the second probability value is greater than the sixth threshold value, the RF power of the antenna is set to increase according to the third step length; when the first probability value is greater than the seventh threshold value, the RF power of the antenna is set to decrease according to the fourth step length, the sixth threshold value is greater than the seventh threshold value, and the third step length is greater than the fourth step length. The sixth threshold value can be set to 80%, and the seventh threshold value can be set to 50%. This application does not limit the specific setting method of the sixth and seventh threshold values. If the first probability value is greater than the sixth threshold value, it can be more accurately and clearly determined that the user is away from the antenna. At this time, the antenna RF power can be set to increase more quickly, that is, the higher the possibility that the user is away from the antenna, the faster the antenna RF power can be increased.

[0072] Figure 5 The structural block diagram of the device according to the embodiment of the present disclosure is schematically shown.

[0073] like Figure 5 As shown, the device 500 of this embodiment includes:

[0074] The first characteristic information acquisition module 510 is configured to obtain first characteristic information of the power reference signal, wherein the first characteristic information represents a change in the received power reference signal. In one embodiment, the first characteristic information acquisition module 510 may be configured to perform the operation 410 described above, which will not be described in detail here.

[0075] The second feature information acquisition module 520 is configured to obtain second feature information representing the motion state of the device. In one embodiment, the second feature information acquisition module 520 may be configured to perform the aforementioned operation 420, which will not be described in detail herein.

[0076] The second characteristic information acquisition module 530 is used to input the first characteristic information and the second characteristic information into the radio frequency power control model to obtain a first output result or a second output result, wherein the model determines a threshold selection result including a group of thresholds from multiple groups of thresholds based on the second characteristic information, and each group of thresholds includes an upper threshold and a lower threshold related to the power reference signal; the output layer of the radio frequency power control model determines the first output result under the first threshold comparison condition or determines the second output result under the second threshold comparison condition, the first threshold comparison condition includes that the minimum value of the power reference signal is less than the lower threshold, and the second threshold comparison condition includes that the maximum value of the power reference signal is greater than the upper threshold. In one embodiment, the second characteristic information acquisition module 530 can be used to perform the operation 430 described above, which will not be repeated here.

[0077] The RF power setting module 540 is configured to control the RF power of the antenna according to the output result. In one embodiment, the RF power setting module 540 may be configured to perform the operation 440 described above, which will not be described in detail here.

[0078] Figure 6 A schematic block diagram of an electronic device that can be used to implement the method of the embodiment of the present disclosure is schematically shown.

[0079] like Figure 6 As shown, an electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0080] Various programs and data required for the operation of the electronic device 600 are stored in the RAM 603. The processor 601, ROM 602, and RAM 603 are connected to each other via a bus 604. The processor 601 executes the various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than the ROM 602 and RAM 603. The processor 601 may also implement the method provided by the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0081] According to an embodiment of the present disclosure, electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to bus 604. Electronic device 600 may also include one or more of the following components connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 608 including a hard disk; and a communication section 609 including a network interface card such as a LAN card or modem. Communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. Removable media 611, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 610 as needed, so that computer programs read from the removable media can be installed into storage section 608 as needed.

[0082] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0083] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 602 and / or RAM 603 described above, and / or one or more memories other than ROM 602 and RAM 603.

[0084] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiments of the present disclosure.

[0085] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the processor 601 executes the computer program. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0086] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 609, and / or installed from a removable medium 611. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0087] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from a removable medium 611. When the computer program is executed by the processor 601, the above-described functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0088] It should be noted that the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information in the technical solutions disclosed herein comply with relevant laws and regulations, employ necessary confidentiality measures, and do not violate public order and good morals. In the technical solutions disclosed herein, user authorization or consent is obtained before obtaining or collecting user personal information.

[0089] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] Those skilled in the art will appreciate that the features described in the various embodiments and / or claims of this disclosure may be combined and / or coupled in various ways, even if such combinations and / or couplings are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or couplings fall within the scope of this disclosure.

[0092] The embodiments of the present disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be advantageously used in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A radio frequency power control method, comprising: Obtaining first characteristic information of a power reference signal, where the first characteristic information represents a change in a received power reference signal; Obtaining second characteristic information representing a motion state of the device; Inputting the first characteristic information and the second characteristic information into a radio frequency power control model to obtain a first output result or a second output result, wherein the model determines a threshold selection result including a group of thresholds from multiple groups of thresholds based on the second characteristic information, each group of thresholds including an upper threshold and a lower threshold related to the power reference signal; the output layer of the radio frequency power control model determines the first output result under a first threshold comparison condition or determines the second output result under a second threshold comparison condition, the first threshold comparison condition including that the minimum value of the power reference signal is less than the lower threshold, and the second threshold comparison condition including that the maximum value of the power reference signal is greater than the upper threshold; The radio frequency power of the antenna is controlled according to the output result.

2. The method according to claim 1, wherein the radio frequency power control model comprises: an input layer, configured to receive the first feature information and the second feature information, and determine a threshold selection result including a set of thresholds from a plurality of sets of thresholds based on the second feature information; at least one hidden layer, configured to determine a threshold comparison result based on the first feature information and the threshold selection result, the threshold comparison result including a first threshold comparison condition or a second threshold comparison condition; The output layer is used to determine a first probability value for reducing the radio frequency power and a second probability value for increasing the radio frequency power based on the threshold comparison. When the first probability value is greater than the first threshold, a first output result is obtained; when the first probability value is greater than the second threshold, a second output result is obtained.

3. The method as claimed in claim 1, wherein the motion state of the device includes a stationary state or a moving state, and the multiple groups of thresholds include a first group of thresholds corresponding to the stationary state and a second group of thresholds corresponding to the moving state, the second upper limit threshold of the second group of thresholds is higher than the first upper limit threshold of the first group of thresholds, and the second lower limit threshold of the second group of thresholds is lower than the first lower limit threshold of the first group of thresholds.

4. The method of claim 3, wherein the plurality of threshold groups further include a third threshold group, and the method further includes: When it is determined that the motion state of the device is a moving state, determining the movement mode of the device according to the movement state data of the device; When it is determined that the movement mode of the device is high-speed movement, it is determined that the threshold selection result includes a third group of thresholds, in which the third upper limit threshold is less than the second upper limit threshold and greater than the first upper limit threshold, and the third lower limit threshold is greater than the second lower limit threshold and less than the first lower limit threshold.

5. The method of claim 4, wherein the plurality of threshold groups further include a fourth threshold group, and the method further includes: When it is determined that the movement mode of the device is periodic movement, it is determined that the threshold selection result includes a fourth group of thresholds, in which the fourth upper limit threshold is greater than the second upper limit threshold, and the fourth lower limit threshold is less than the second lower limit threshold.

6. The method of claim 4, further comprising: When it is determined that the movement mode of the device is high-speed movement and the first probability value is less than a third threshold, the radio frequency power of the antenna is set to remain unchanged within a preset time.

7. The method of claim 2, further comprising: When the first probability value is greater than a fourth threshold, setting the radio frequency power of the antenna to be reduced according to the first step; When the first probability value is greater than the fifth threshold, the radio frequency power of the antenna is set to be reduced according to the second step length, the fourth threshold is greater than the fifth threshold, and the first step length is greater than the second step length.

8. The method of claim 2, further comprising: When the second probability value is greater than a sixth threshold, setting the radio frequency power of the antenna to increase according to a third step size; When the first probability value is greater than the seventh threshold, the radio frequency power of the antenna is set to be reduced according to the fourth step length, the sixth threshold is greater than the seventh threshold, and the third step length is greater than the fourth step length.

9. A radio frequency power control model training method, comprising: Obtaining a training sample, the training sample including a received power reference signal and motion state data of a device where the antenna is located, the training sample being provided with a first tag, a second tag, and a third tag, the first tag including whether it is triggered, where the first tag being triggered indicates that a user is close to the antenna and the antenna's radio frequency power needs to be reduced, the second tag including whether it is released, where the second tag being released indicates that a user is far away from the antenna and the antenna's radio frequency power needs to be increased, and the third tag including the motion state of the device where the antenna is located; The pre-trained model is trained based on the training samples to obtain the RF power control model and multiple sets of thresholds under different motion states of the device.

10. A radio frequency power control device, comprising: A first characteristic information acquisition module is used to obtain first characteristic information of the power reference signal, where the first characteristic information represents a change in the received power reference signal; A second characteristic information acquisition module is used to obtain second characteristic information representing the motion state of the device; an output result determination module, configured to input the first characteristic information and the second characteristic information into a radio frequency power control model to obtain a first output result or a second output result, wherein the model determines a threshold selection result including a group of thresholds from multiple groups of thresholds based on the second characteristic information, each group of thresholds including an upper threshold and a lower threshold associated with the power reference signal; an output layer of the radio frequency power control model determines the first output result under a first threshold comparison condition or determines the second output result under a second threshold comparison condition, wherein the first threshold comparison condition includes that the minimum value of the power reference signal is less than the lower threshold, and the second threshold comparison condition includes that the maximum value of the power reference signal is greater than the upper threshold; The radio frequency power setting module is used to control the radio frequency power of the antenna according to the output result.

Images