Wireless charging non-inductive protection method and device for electronic equipment, equipment and readable medium

Abstract

The embodiment of the invention discloses a wireless charging non-inductive protection method and device for electronic equipment, equipment and a readable medium. A specific embodiment of the method comprises the steps of collecting living body motion data in a target area; generating spatial position prediction probability cloud information based on the collected living body motion data; based on the spatial position prediction probability cloud information, generating to-be-shielded region information; obtaining irradiation surface area information of the wireless charging area; in response to determining that an area represented by the information of the to-be-shielded area overlaps an area represented by the information of the irradiation surface area, generating light field modulation information based on the information of the to-be-shielded area and the information of the irradiation surface area; and based on the light field modulation information, performing adaptive safety modulation processing on the wireless charging light beam. According to the embodiment, the harm of the wireless charging light beam for wireless charging to people during working is reduced.

Description

Technical Field

[0001] The embodiments of this disclosure relate to the field of computer technology, and more specifically to a wireless charging non-contact protection method, apparatus, device, and readable medium for electronic devices. Background Technology

[0002] With the continuous development of wireless charging technology, laser charging has gradually gained attention as an innovative charging method. Wireless charging technology is also widely used in smart homes (for example, charging smart doors using infrared or invisible light). However, the laser beam used in wireless charging may cause harm to people when in operation. This problem urgently needs to be solved.

[0003] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0004] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0005] Some embodiments of this disclosure provide wireless charging non-contact protection methods, apparatuses, electronic devices, and computer-readable media for electronic devices to solve one or more of the technical problems mentioned in the background section above.

[0006] In a first aspect, some embodiments of this disclosure provide a method for seamless wireless charging protection of electronic devices. The method includes: collecting live motion data within a target area; generating spatial location prediction probability cloud information based on the collected live motion data; generating a region to be blocked based on the spatial location prediction probability cloud information; acquiring illumination surface region information of the wireless charging area; in response to determining that the region represented by the region to be blocked overlaps with the region represented by the illumination surface region information, generating light field modulation information based on the region to be blocked and the illumination surface region information; and performing adaptive safety modulation processing on the wireless charging beam based on the light field modulation information.

[0007] Secondly, some embodiments of this disclosure provide a wireless charging non-contact protection device for electronic devices. The device includes: a acquisition unit configured to acquire live motion data within a target area; a first generation unit configured to generate spatial position prediction probability cloud information based on the acquired live motion data; a second generation unit configured to generate a to-be-blocked area information based on the spatial position prediction probability cloud information; an acquisition unit configured to acquire illumination surface area information of the wireless charging area; a third generation unit configured to generate light field modulation information based on the to-be-blocked area information and the illumination surface area information in response to determining that the area represented by the to-be-blocked area information overlaps with the area represented by the illumination surface area information; and a control unit configured to perform adaptive safety modulation processing on the wireless charging beam based on the light field modulation information.

[0008] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0009] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0010] Fifthly, some embodiments of this disclosure provide a door, including the aforementioned electronic device, which is a door lock.

[0011] The present disclosure has the following beneficial effects: The methods of some embodiments of the present disclosure reduce the harm caused to people by the wireless charging beam during operation. Based on this, the wireless charging non-intrusive protection method for electronic devices according to some embodiments of the present disclosure first collects live motion data within the target area; stores the collected live motion data in a preset queue, and generates spatial location prediction probability cloud information based on the collected live motion data. Thus, the spatial location prediction probability cloud information (i.e., dynamically predicting the possible movement trajectory of the live object) can be predicted in real time at different locations in space, realizing a shift from "passive perception" to "active prediction," so as to identify potential obstruction areas in advance. Next, based on the spatial location prediction probability cloud information, information about the area to be obstructed is generated. This allows for the generation of information about the area to be obstructed, enabling early knowledge of the location of the live object and its potential entry into the wireless charging beam irradiation area, providing accurate prediction information for subsequent wireless charging beam modulation, and avoiding blindly shutting down the entire wireless charging beam area. Then, the irradiation surface area information of the wireless charging area is obtained. Next, in response to the determination that the area represented by the area to be blocked overlaps with the area represented by the illumination surface area information, light field modulation information is generated based on the area to be blocked and the illumination surface area information. Thus, when an overlap between the blocked area and the illumination surface area of ​​the wireless charging beam is detected, light field modulation information for modulating the light field of the living person's current and future risk areas can be generated based on the area to be blocked and the illumination surface area information. Finally, based on the light field modulation information, adaptive safety modulation processing is performed on the wireless charging beam. Therefore, adaptive safety modulation processing can be performed on the wireless charging beam in the area represented by the area to be blocked to "carve" a safety cavity for the living person in real time within the wireless charging beam field as the living person moves, causing the wireless charging beam to actively avoid the living person's path rather than simply shutting off, reducing the risk of harm to people from the wireless charging beam during operation. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of a wireless charging contactless protection method for electronic devices according to the present disclosure; Figure 2 This is a schematic diagram of the structure of some embodiments of a wireless charging contactless protection device for electronic devices according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1 A flow 100 of some embodiments of a wireless charging seamless protection method for an electronic device according to the present disclosure is shown. The wireless charging seamless protection method for the electronic device includes the following steps: Step 101: Collect live motion data within the target area.

[0021] In some embodiments, the execution subject of the wireless charging non-contact protection method for electronic devices (e.g., a computing device such as a control chip) collects live motion data within a target area. In practice, a human motion data acquisition device can be triggered to collect human motion data in real time as live motion data. This human motion data acquisition device can be a depth sensor (such as a depth camera) or a laser scanner. The human motion data includes human point cloud data and the acquisition time. The human point cloud data can be a dataset of points captured by a depth sensor (such as a depth camera) or a laser scanner, reflecting the position and shape of the human body in three-dimensional space. Each point data represents a location in space. For example, the point data can be (X, Y, Z, R, G, B). X can be the X coordinate value, representing the position of the point on the horizontal plane. Y can be the Y coordinate value, representing the height of the point. Z can be the Z coordinate value, representing the depth of the point (or the relative distance to the sensor). R, G, and B represent the color value (in RGB values) of the point. The target area can be the acquisition area covered by an image acquisition device. The aforementioned electronic device can be a smart door lock. The wireless charging protection method for the electronic device disclosed herein can be applied to charging a smart door lock using infrared or invisible light during the charging process of an indoor door lock.

[0022] In some optional implementations of certain embodiments, the aforementioned execution entity may collect live motion data within the target area through the following steps: The first step is to acquire images of the target area using an image acquisition device. This image acquisition device can be installed outside the edge of the charging area, maintaining a preset safe distance from it. The target area can be the area covered by the image acquisition device, which can be a monitoring area located spatially outside the hazardous wireless charging area and at a preset safe distance. The image acquisition device can be a camera.

[0023] The second step is to perform liveness detection processing on the above images to obtain liveness detection information. This liveness detection information can be the recognition result obtained from person identification within the image. It should be noted that when no person is identified, the liveness detection information can be empty. When a person is identified, the liveness detection information is a person identifier (e.g., elderly person, cleaning staff, maintenance personnel, or pedestrian).

[0024] The third step is to collect live motion data in real time based on the liveness detection information. In practice, in response to the determination that the liveness detection information is not empty, the human motion data acquisition device can be triggered to collect human motion data in the target area in real time as live motion data.

[0025] In some optional implementations of certain embodiments, the aforementioned execution entity may perform liveness detection processing on the aforementioned image through the following steps to obtain liveness detection information: The first step involves performing preliminary human detection on the aforementioned image to obtain preliminary detection information. In practice, the executing entity can input the image into a pre-trained YOLO series model (such as YOLOv5, YOLOv8, YOLO-NAS, etc.) to obtain at least one identification identifier. In response to determining that a preset identifier (e.g., the "person" category) exists among the at least one identification identifier, the information representing the presence of a person in the image is determined as preliminary detection information. This preliminary detection information can be textual information representing the presence or absence of a person (e.g., true or a person exists in the image).

[0026] The second step is to determine that a person exists in the image characterized by the preliminary detection information mentioned above, and then identify the image as a person to be identified.

[0027] The third step is to perform fine-grained personnel identification processing on the images of the personnel to be identified, and obtain personnel identification information as liveness detection information.

[0028] In some optional implementations of certain embodiments, the aforementioned executing entity can perform fine-grained person identification processing on the image of the person to be identified through the following steps to obtain person identification information: The first step involves sending the images of the individuals to be identified to a pre-defined cloud server. This server then inputs these images into a deployed teacher model to obtain a human body focus heatmap. The teacher model can be a pre-trained bottom-up model that takes the images of the individuals to be identified as input and outputs the human body focus heatmap. The human body focus heatmap can be an attention heatmap indicating the degree of attention received by relevant parts of the human body (such as the head, upper limbs, legs, etc.) in the image.

[0029] The second step involves inputting the aforementioned image of the person to be identified into the visual feature extraction layer of a pre-trained fine-grained person recognition student model to obtain visual feature information. This fine-grained person recognition student model includes the aforementioned visual feature extraction layer, heatmap fusion layer, flattening layer, and person recognition layer. This fine-grained person recognition student model can be a neural network model that takes the image of the person to be identified as input and outputs person recognition information (e.g., HRNet (High-Resolution Network) or SENet (Squeeze-and-Excitation Networks)). The aforementioned visual feature extraction layer can be a convolutional layer that takes the image of the person to be identified as input and outputs visual feature information. The aforementioned visual feature information can be a feature map representing the image of the person to be identified.

[0030] The third step involves inputting the aforementioned visual feature information and the aforementioned human body focal point heatmap into the aforementioned heatmap fusion layer to obtain weighted feature information. The aforementioned heatmap fusion layer can be an attention layer that fuses the visual feature information and the human body focal point heatmap. As an example, the visual feature information of the image and the human body focal point heatmap are fused. The fusion method can be: weighted fusion: using the human body focal point heatmap as a weighting factor, each pixel value of the human body focal point heatmap is multiplied by the value of the corresponding region of the visual feature, thereby emphasizing the regions that the teacher considers important, resulting in a fused attention-weighted feature map as weighted feature information.

[0031] The fourth step involves inputting the weighted feature information into the flattening layer to obtain flattened feature information. This flattening layer can be a layer that converts the feature map into a one-dimensional vector. The flattened feature information can be a vector obtained by flattening the feature map represented by the weighted feature information into a one-dimensional vector.

[0032] The fifth step involves inputting the aforementioned flattened feature information into the personnel identification layer to obtain personnel identification information. This personnel identification layer can be a classification layer that takes the flattened feature information as input and outputs the personnel identification information. The personnel identification information can be personnel identifiers (e.g., cleaning staff, maintenance personnel, or pedestrians).

[0033] Step 102: Based on the collected live motion data, generate spatial location prediction probability cloud information.

[0034] In some embodiments, the aforementioned executing entity may generate spatial location prediction probability cloud information based on the collected live motion data.

[0035] In some optional implementations of certain embodiments, the aforementioned execution entity can generate spatial location prediction probability cloud information based on the collected live motion data through the following steps: The collected live motion data is stored as human motion data in a preset queue. Based on at least one human motion data point in the preset queue, spatial location prediction probability cloud information and a corresponding time period are generated. The preset queue can be a queue storing a preset number of data points. This preset queue can be used to store human motion data (if the queue is not full, human motion data is inserted at the end of the queue; if the queue is full, the oldest human motion data at the head of the queue is discarded, and newly collected human motion data is inserted at the end of the queue).

[0036] In some optional implementations of certain embodiments, the aforementioned execution entity can generate spatial location prediction probability cloud information and a time period corresponding to the spatial location prediction probability cloud information based on at least one human motion data in a preset queue through the following steps: The first step, in response to determining that there is a human motion data enqueue operation in the aforementioned preset queue and that the number of human motion data in the preset queue after the enqueue operation is equal to the length of the aforementioned preset queue, is to execute the following steps: The first sub-step involves determining at least one human motion data from the aforementioned preset queue as a human motion data sequence.

[0037] The second sub-step involves adding a preset instantaneous velocity to the first human motion data point in the aforementioned human motion data sequence to update the human motion data sequence. The preset instantaneous velocity can be 0.

[0038] The third sub-step involves generating the instantaneous velocity corresponding to each human motion data point (excluding the first human motion data point) based on the aforementioned human motion data sequence, and adding the instantaneous velocities to the human motion data to update the human motion data sequence. In practice, for each human motion data point (excluding the first human motion data point) in the human motion data sequence, the executing entity can determine the average of the X-coordinate values ​​included in the human motion data as the first center point X-coordinate value, the average of the Z-coordinate values ​​included in the human motion data as the first center point Y-coordinate value, and the average of the Z-coordinate values ​​included in the human motion data as the first center point Z-coordinate value. The acquisition time included in the human motion data is determined as the first time. Then, the executing entity can determine (first center point X-coordinate value, first center point Y-coordinate value, first center point Z-coordinate value) as the first position coordinate. Finally, the executing entity can determine the preceding human motion data point in the human motion data sequence as the target human motion data. Next, for the human point cloud data included in the target human motion data, the aforementioned executing entity can determine the average of each X-coordinate value included in the human point cloud data as the second center point X-coordinate value, the average of each Z-coordinate value included in the human point cloud data as the second center point Z-coordinate value, and the average of each Z-coordinate value included in the human point cloud data as the second center point Z-coordinate value. The acquisition time included in the human motion data is determined as the second time. Then, the aforementioned executing entity can determine (second center point X-coordinate value, second center point Y-coordinate value, second center point Z-coordinate value) as the second position coordinates. Then, the distance between the first position coordinates and the second position coordinates can be determined as the target distance. Then, the time difference between the first time and the second time is determined as the target time difference. Then, the ratio of the target distance to the target time difference is determined as the instantaneous velocity corresponding to the aforementioned human motion data. Wherein, the aforementioned distance is the Euclidean distance.

[0039] The fourth sub-step involves generating spatial location prediction probability cloud information and the corresponding time period based on the updated human motion data sequence.

[0040] In addressing the aforementioned technical problems by employing technical solutions, the application scenario—charging smart door locks via wireless charging beams in a home setting—often presents the following technical challenges: To prevent harm from the wireless charging beam when a person passes through its area, the common practice is to predict the person's future location by collecting their current position information and then controlling the closure of the wireless charging beam in that area. However, human movement patterns are complex and varied, with frequent changes in direction and speed. Knowing only the person's current location without understanding their movement trends (changes in direction and speed) leads to low accuracy in predicting possible locations, increasing the risk of harm from the wireless charging beam and compromising security. Therefore, this application scenario requires the following characteristics: high-precision, real-time location prediction.

[0041] In some optional implementations of certain embodiments, the aforementioned executing entity can generate spatial location prediction probability cloud information and a time period corresponding to the spatial location prediction probability cloud information based on the updated human motion data sequence through the following steps: The first step is to convert each human motion data point in the updated human motion data sequence into a motion feature vector. In practice, the aforementioned execution entity can use a data vectorization method to convert each human motion data point in the updated human motion data sequence into a motion feature vector. This motion feature vector can be a vectorized representation of the human motion data.

[0042] The second step is to arrange the obtained motion feature vectors according to the order of their corresponding human motion data in the human motion data sequence to obtain the motion feature vector sequence.

[0043] The third step involves inputting the aforementioned motion feature vector sequence into the spatiotemporal graph convolutional layer of a pre-trained spatiotemporal trajectory prediction model to obtain historical human spatial trajectory feature information. This spatiotemporal trajectory prediction model includes the aforementioned spatiotemporal graph convolutional layer, temporal convolutional layer, feature fusion layer, global context feature extraction layer, and prediction layer. The aforementioned spatiotemporal graph convolutional layer can be an ST-GCN model that takes the motion feature vector sequence as input and outputs historical human spatial trajectory feature information. This spatiotemporal graph convolutional layer can extract the relationship between spatial location and time steps from the motion feature vector sequence. The aforementioned historical human spatial trajectory feature information can be a multi-dimensional vector containing the relationship between the human body's spatial trajectory and time steps over a past period.

[0044] The fourth step involves inputting the aforementioned motion feature vector sequence into a temporal convolutional layer to obtain human temporal dynamic characteristic information. This temporal convolutional layer can be a Temporal Convolutional Network (TCN), which takes the motion feature vector sequence as input and outputs human temporal dynamic characteristic information. The aforementioned human temporal dynamic characteristic information can be feature vectors describing the changes in human motion over time (e.g., vectors containing physical motion features such as velocity and acceleration, as well as features including dependencies between time steps, periodicity, and trend patterns).

[0045] Fifth, the aforementioned historical human spatial trajectory feature information and the aforementioned human temporal dynamic characteristic information are input into the aforementioned feature fusion layer to obtain global feature information. The aforementioned feature fusion layer can be a feature fusion layer that fuses historical human spatial trajectory feature information and human temporal dynamic characteristic information. The aforementioned global feature information can be a vector obtained by fusing historical human spatial trajectory feature information and human temporal dynamic characteristic information.

[0046] The sixth step involves inputting the aforementioned global feature information into the global context feature extraction layer to obtain the extracted global feature information. This global context feature extraction layer can be a convolutional layer that takes the global feature information as input and outputs the extracted global feature information. The extracted global feature information can be the global feature vector obtained by performing a convolution operation on the global feature information.

[0047] Step 7: Input the globally extracted feature information into the prediction layer to obtain the spatial location prediction probability cloud information and the corresponding time period. The prediction layer can be a multi-task output head that takes the globally extracted feature information as input and outputs the spatial location prediction probability cloud information and the corresponding time period. The spatial location prediction probability cloud information describes the probability of a moving target (such as a person) appearing at every possible location in three-dimensional space within a future time period. This information includes information about individual spatial points, each of which includes spatial location information and a probability value. The spatial location information can be three-dimensional coordinates.

[0048] The above technical solution, combined with steps 103 to 106 and related content, serves as an inventive point of this disclosure, solving the technical problem of "low security of protection." Factors leading to low security of protection often include: In a home setting, during the charging of a smart door lock using a wireless charging beam, to prevent harm from the beam when a person passes through the area, it is common practice to predict the person's future location by collecting their current position information, and then control the closure of the wireless charging beam in that area. However, human movement patterns are complex and diverse, with frequent changes in direction and speed. Knowing only the person's current location does not reveal their movement trend (changes in direction and speed), resulting in low accuracy in predicting possible locations and increasing the risk of harm from the wireless charging beam, thus lowering the security of protection. Solving these factors can improve the security of protection. To achieve this, firstly, each human motion data point in the updated human motion data sequence is converted into a motion feature vector. Then, the obtained motion feature vectors are arranged according to the order of their corresponding human motion data points in the human motion data sequence, resulting in a motion feature vector sequence. Thus, a motion feature vector sequence reflecting the historical movement trajectory of the human body can be obtained. Next, the aforementioned motion feature vector sequence is input into the spatiotemporal graph convolutional layer of a pre-trained spatiotemporal trajectory prediction model to obtain historical human spatial trajectory feature information. This spatiotemporal trajectory prediction model includes the aforementioned spatiotemporal graph convolutional layer, temporal convolutional layer, feature fusion layer, global context feature extraction layer, and prediction layer. Thus, historical human spatial trajectory feature information, i.e., how the human body moves, is distributed, and its movement patterns in space, can be extracted through spatiotemporal convolution. Next, the aforementioned motion feature vector sequence is input into the temporal convolutional layer to obtain human temporal dynamic characteristic information. Thus, the temporal convolutional layer can better capture the temporal dynamic characteristics of human movement (e.g., the human body may rapidly change its direction of movement or accelerate / decelerate within a short period). Then, the aforementioned historical human spatial trajectory feature information and the aforementioned human temporal dynamic characteristic information are input into the aforementioned feature fusion layer to obtain global feature information. Thus, historical spatial trajectory features and temporal dynamic characteristics can be combined to form global feature information. Finally, the aforementioned global feature information is input into the aforementioned global context feature extraction layer to obtain globally extracted feature information. Subsequently, the globally extracted feature information is input into the prediction layer to obtain spatial location prediction probability cloud information and the corresponding time period. Thus, the output of the prediction layer can more accurately predict the possible location of personnel, providing precise spatial location prediction probability cloud information and time period for the wireless charging beam control system.Because features are extracted and fused from both spatial and temporal dimensions, the method takes into account the complexity and diversity of human movement patterns and the fact that movement trends (changes in direction and speed) are not limited to the person's current location as the basis for prediction. Combining steps 103 to 106, based on more accurate spatial location prediction probability cloud information, adaptive safety modulation processing can be applied to the wireless charging beam, improving safety while ensuring charging efficiency.

[0049] Step 103: Based on spatial location, predict probabilistic cloud information to generate information about the area to be occluded.

[0050] In some embodiments, the aforementioned execution entity can generate information about the area to be occluded based on spatial location-predicted probabilistic cloud information.

[0051] In some optional implementations of certain embodiments, the aforementioned execution entity can generate information about the area to be occluded by predicting probabilistic cloud information based on spatial location through the following steps: The first step is to determine the spatial point information set by including all spatial point information that meets the preset conditions from the aforementioned spatial location prediction probability cloud information. The preset conditions can include a probability value that is not equal to 0.

[0052] The second step is to identify the spatial point information sets containing spatial point information whose occurrence probability values ​​are less than or equal to a first preset probability value as the first spatial point information group. For example, the first preset probability value can be 0.3.

[0053] The third step is to identify the spatial point information groups whose occurrence probability values ​​are greater than the first preset probability value in the above spatial point information set as the second spatial point information group.

[0054] The fourth step is to determine the spatial location information of each spatial point information group included in the first spatial point information group as the first area to be occluded information.

[0055] The fifth step is to determine the spatial location information of each element in the second spatial point information group as the second area to be occluded.

[0056] Step 6: Determine the first area to be occluded and the second area to be occluded as the area to be occluded information. The area to be occluded information includes both the first and second areas to be occluded, with the first area to be occluded information including spatial location information and the second area to be occluded information including spatial location information.

[0057] Step 104: Obtain the illumination area information of the wireless charging area.

[0058] In some embodiments, the execution entity can obtain illumination surface area information of the wireless charging area. This illumination surface area information includes various two-dimensional coordinates of the illumination surface of the wireless charging beam (e.g., the various two-dimensional coordinates within a rectangular illumination surface with dimensions of 2 can be (1,1), (1,2), (2,1), (2,2)). Each of these two-dimensional coordinates can be the two-dimensional coordinates of the illumination surface through which the wireless charging beam passes. In practice, the execution entity can obtain the illumination surface area information from a local storage device. The illumination surface of the wireless charging beam can be a surface through which infrared or laser light passes.

[0059] Step 105: In response to the determination that the region represented by the information of the region to be occluded overlaps with the region represented by the information of the irradiated surface region, light field modulation information is generated based on the information of the region to be occluded and the information of the irradiated surface region.

[0060] In some embodiments, the execution entity may generate light field modulation information based on the information of the area to be occluded and the information of the irradiated surface area in response to determining that the area represented by the information of the area to be occluded overlaps with the area represented by the information of the irradiated surface area.

[0061] In some optional implementations of certain embodiments, the execution entity may generate light field modulation information based on the information of the area to be occluded and the information of the irradiated surface area through the following steps: Based on the above-mentioned information on the area to be blocked, the above-mentioned information on the illuminated surface area, and the above-mentioned personnel identification information, light field modulation information is generated.

[0062] In addressing the technical challenges of specific application scenarios using the aforementioned solutions, the following technical issues arise regarding the intended application scenario: a home environment where smart devices are charged via wireless charging beams, and where slow-moving individuals (such as the elderly, people with disabilities, and cleaning staff) are present. If modulation is only applied to high-probability areas, the unpredictable movement (such as falls or sudden stops) of slow-moving individuals in low-probability (but not zero-probability) areas poses an unprotected safety risk, resulting in low overall safety during the wireless charging process. Therefore, this application scenario requires the following characteristics: suitability for providing safety protection for slow-moving individuals during wireless charging beam charging.

[0063] In some optional implementations of certain embodiments, the aforementioned execution entity may generate light field modulation information based on the aforementioned information about the area to be occluded, the aforementioned information about the irradiated surface area, and the aforementioned personnel identification information through the following steps: The first step is to obtain the illumination area information of the wireless charging area. This illumination area information includes the two-dimensional coordinates of each illumination point on the wireless charging beam's illumination surface.

[0064] The second step, in response to determining that the personnel identifier included in the personnel identification information belongs to a slow-moving personnel identifier, is to perform the following steps for the first area information to be obscured included in the aforementioned area information to be obscured: The first sub-step involves determining the two-dimensional projection coordinates of each spatial location information included in the first area to be obscured onto the surface illuminated by the wireless charging beam as the respective first obscuration projection coordinates. In practice, the executing entity can identify the personnel identifiers (e.g., elderly, cleaning staff, or maintenance personnel) included in the personnel identification information as the personnel identifiers to be compared. In response to determining that the personnel identifier to be compared is the same as one of the preset slow-moving personnel identifiers, the executing entity can determine that the personnel identifiers included in the personnel identification information belong to the slow-moving personnel identifiers.

[0065] The second sub-step involves deduplicating the aforementioned first occlusion projection coordinates and determining the deduplicated first occlusion projection coordinates as the deduplicated first coordinates.

[0066] The third sub-step is to determine the first deduplication coordinate that is the same as one of the first deduplication coordinates and the first two-dimensional irradiation coordinates, and to determine the first deduplication coordinate that is the same as one of the first two-dimensional irradiation coordinates as the first target coordinate.

[0067] The fourth sub-step involves determining, for each of the at least one determined first target coordinates, first preset control information and the aforementioned first target coordinates as first modulation information. The first preset control information can be control information for controlling the output power of the wireless charging beam emitted from a coordinate point in the spatial light modulator to be within a safe and acceptable range for humans. For example, the first preset control information can be a target power percentage that sets the amplitude to its maximum value (e.g., target amplitude = sqrt(31.6%)), so that the output power of the wireless charging beam emitted from the first target coordinate is within a safe and acceptable range for humans. The first modulation information can be information for controlling the output power of the wireless charging beam emitted from the first target coordinate in the spatial light modulator to be within a safe and acceptable range for humans.

[0068] The fifth sub-step involves determining at least one first modulation information as a first modulation information set.

[0069] Third, for the second area information to be occluded included in the above-mentioned area information to be occluded, perform the following steps: Sub-step one: Determine the two-dimensional coordinates of the projection of each spatial location information included in the above-mentioned second area to be blocked onto the surface of the wireless charging beam as each second blocking projection coordinate.

[0070] Sub-step two involves deduplicating the aforementioned second occlusion projection coordinates and determining the deduplicated second occlusion projection coordinates as the deduplicated second coordinates.

[0071] Sub-step three: In response to determining that each of the above-mentioned second deduplication coordinates has the same coordinate as each of the above-mentioned irradiation two-dimensional coordinates, the second deduplication coordinate that is the same as one of the above-mentioned irradiation two-dimensional coordinates is determined as the second target coordinate.

[0072] Sub-step four: For each of the at least two determined first target coordinates and the second target coordinate, the second preset control information and the second target coordinate are determined as the second modulation information. The first preset control information can be control information that controls the output power of the wireless charging beam at a coordinate point in the spatial light modulator to be zero. For example, the second preset control information can be a target power percentage that sets the amplitude to its maximum value (e.g., target amplitude = 0), so that the output power of the wireless charging beam emitted at the second target coordinate is zero. The second modulation information can be the control information that controls the output power of the wireless charging beam at the second target coordinate in the spatial light modulator to be zero.

[0073] Sub-step five: Determine at least one second modulation information as the second modulation information set.

[0074] The fourth step is to determine the first modulation information set and the second modulation information set as optical field modulation information.

[0075] The above technical solution, combined with step 104 and related content, serves as an inventive point of this disclosure, solving the technical problem of "low safety during the wireless charging beam charging process." Factors leading to low safety during the wireless charging beam charging process often include: if modulation is only applied to high-probability areas, for slow-moving individuals (such as the elderly, cleaning staff, etc.), unexpected movement (such as falls or sudden stops) in low-probability (but not zero-probability) areas can easily pose unprotected safety risks, thus resulting in low safety during the entire wireless charging beam charging process. Solving these factors can improve the safety of the wireless charging beam charging process. To achieve this, firstly, the illumination surface area information of the wireless charging area is obtained, including the illumination surface area information of each two-dimensional coordinate of the wireless charging beam illumination surface. Thus, the precise distribution coordinates characterizing the energy of the wireless charging beam on the two-dimensional illumination surface, i.e., each two-dimensional illumination coordinate, can be obtained. Then, in response to determining that the personnel identifier included in the personnel identification information belongs to a slow-moving personnel identifier, for the first unblocked area information included in the aforementioned unblocked area information, the following steps are performed: First sub-step: Determine the two-dimensional projection coordinates of each spatial location information included in the aforementioned first unblocked area information onto the wireless charging beam illumination surface as each first blocking projection coordinate. Thus, the first blocking projection coordinates of each low-probability area, i.e., areas with a probability value less than or equal to a first preset probability value, can be determined. Second sub-step: Perform deduplication processing on the aforementioned first blocking projection coordinates, and determine the deduplicated first blocking projection coordinates as each first deduplicated coordinate. Then, in response to determining that each of the aforementioned first deduplicated coordinates has the same coordinate as each of the aforementioned illumination two-dimensional coordinates, determine the first deduplicated coordinate that is the same as one of the aforementioned illumination two-dimensional coordinates as a first target coordinate. Thus, the first target coordinate of a slow-moving person in a low-probability area can be tracked. Afterwards, for each of the at least one determined first target coordinates, first preset control information and the aforementioned first target coordinate are determined as first modulation information. Therefore, first modulation information can be generated to prevent slow-moving personnel from being irradiated by the wireless charging beam in low-probability areas, thus reducing potential safety hazards. Then, at least one of the determined first modulation information is defined as a first modulation information set. This allows the generation of a first modulation information set for protection of slow-moving personnel in low-probability areas. Then, for the second area information to be blocked included in the aforementioned area information to be blocked, the following steps are performed: First sub-step: determining the two-dimensional coordinates of the projection of each spatial location information included in the second area information to be blocked onto the surface irradiated by the wireless charging beam as each second blocking projection coordinate. Second sub-step: performing deduplication processing on the aforementioned second blocking projection coordinates, and determining the deduplicated second blocking projection coordinates as each second deduplicated coordinate.The third sub-step involves determining the second deduplication coordinates that share the same coordinates as the aforementioned second deduplication coordinates and the aforementioned illumination two-dimensional coordinates, and identifying the second deduplication coordinate that shares the same coordinate with one of the aforementioned illumination two-dimensional coordinates as the second target coordinate. The fourth sub-step involves defining the second preset control information and the second target coordinate as second modulation information for each of the at least two determined first target coordinates. The fifth sub-step involves defining the at least one determined second modulation information as a second modulation information set. This generates a second modulation information set for modulating high-probability regions. The first modulation information set and the second modulation information set are defined as optical field modulation information. This allows for the simultaneous generation of optical field modulation information that modulates high-probability and low-probability regions, respectively. Combined with step 104, adaptive security modulation processing is performed on the wireless charging beam based on the optical field modulation information. Thus, adaptive security modulation processing can be performed using optical field modulation information containing the first and second modulation information sets to achieve security protection for high-probability and low-probability regions. Because it adopts a strategy of modulating the wireless charging beam in both high- and low-probability risk areas for slow-moving individuals, it ensures that slow-moving individuals (such as the elderly and cleaning staff) can still maintain a high level of safety in the event of accidental movement (such as falls or sudden stops) in low-probability (but not zero-probability) areas, thus improving the safety of the wireless charging beam charging process.

[0076] Step 106: Based on the light field modulation information, perform adaptive safety modulation processing on the wireless charging beam.

[0077] In some embodiments, the aforementioned execution entity can perform adaptive safety modulation processing on the wireless charging beam based on optical field modulation information. In practice, the spatial light modulator can be controlled to perform adaptive safety modulation processing on the wireless charging beam passing through the region characterized by the area to be obstructed, based on the optical field modulation information. In practice, the aforementioned execution entity can determine a time period corresponding to the spatial location prediction probability cloud information. For each first modulation information included in the aforementioned optical field modulation information, the aforementioned execution entity can, through the first preset control information included in the first modulation information, control the output power of the wireless charging beam output by the spatial light modulator at the first target coordinate included in the first modulation information to be within a range acceptable to human safety during the aforementioned time period (i.e., control the output rate of the wireless charging beam output from the low-probability region to be within a range acceptable to human safety). For each second modulation information included in the aforementioned optical field modulation information, the aforementioned execution entity can, through the second preset control information included in the second modulation information, control the output power of the wireless charging beam output by the spatial light modulator at the second target coordinate included in the second modulation information to be zero during the aforementioned time period (i.e., control the output rate of the wireless charging beam output from the high-probability region to be zero). It should be noted that the spatial light modulator outputs the wireless charging beam normally at points other than the coordinates of the first and second targets. This wireless charging beam can be either infrared or laser.

[0078] The above-described embodiments of this disclosure have the following beneficial effects: the methods of some embodiments of this disclosure improve the charging speed of wireless charging beam charging and the living comfort of the home environment in which wireless charging beam charging is applied. Specifically, the reason for the decrease in charging efficiency and living comfort of the home environment in which wireless charging beam charging is applied is that: using ordinary cameras or infrared sensors to monitor a preset area, immediately shutting down the wireless charging beam and issuing an early warning upon intrusion, cannot predict the movement path of people, requiring the entire wireless charging beam area to be shut down, wasting the area that could have continued to charge safely, resulting in a decrease in charging efficiency and a slower charging speed. Moreover, in a home environment, there may be frequent interference behaviors, such as children, pets, or even curtains being blown by the wind, which may be mistakenly identified as "intrusion" by ordinary cameras or infrared sensors, leading to frequent shutdowns and early warnings of the wireless charging beam, thus reducing the living comfort of the home environment in which wireless charging beam charging is applied. Based on this, the wireless charging non-intrusive protection method for electronic devices in some embodiments of this disclosure first collects live motion data within the target area. Based on the collected live motion data, spatial location prediction probability cloud information is generated. This allows for real-time prediction of the spatial location probability cloud information of potential intruders in different locations within a future timeframe (i.e., dynamically predicting possible movement trajectories), shifting from "passive perception" to "active prediction," enabling early identification of potential obstruction areas. Next, based on the spatial location prediction probability cloud information, information about areas to be obstructed is generated. This allows for early knowledge of the location of individuals and their potential entry into the wireless charging beam's illumination area, providing accurate predictive information for subsequent wireless charging beam modulation and avoiding the blind closure of the entire wireless charging beam area. Then, the illumination surface area information of the wireless charging area is acquired. Following this, in response to the determination that the area represented by the area to be obstructed overlaps with the area represented by the illumination surface area information, light field modulation information is generated based on both the area to be obstructed and the illumination surface area information. Thus, when an overlap between an obstruction area and the wireless charging beam's illumination surface area is detected, light field modulation information is generated to modulate the light field in the current and future risk areas of individuals, based on the area to be obstructed and the illumination surface area information. Finally, based on the light field modulation information, adaptive safety modulation processing is performed on the wireless charging beam. Thus, within the predicted time window (i.e., the predicted time period), adaptive safety modulation processing is applied to the wireless charging beam passing through the area characterized by the information of the area to be blocked. This allows a human-shaped safety hole to be "carved" in real time within the wireless charging beam field as people move, enabling the wireless charging beam to actively avoid the person's path rather than simply shutting off.This is because, on the one hand, it employs predictive, localized, and dynamic light field modulation information. Within the predicted time window (i.e., the predicted time period), it performs adaptive safety modulation processing on the wireless charging beam passing through the area characterized by the information of the area to be blocked. This achieves the goal of shielding the wireless charging beam to the minimum extent necessary, maximizing the continuity of the charging process and improving the charging efficiency of the wireless charging beam while ensuring personnel safety. On the other hand, it uses personnel recognition processing on the aforementioned images to obtain personnel identification information, effectively avoiding false shutdowns and false warnings caused by interference, thereby improving the living comfort of the home environment where wireless charging beam charging is applied.

[0079] Further reference Figure 2 As an implementation of the methods shown in the figures, this disclosure provides some embodiments of a wireless charging contactless protection device for electronic devices. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0080] like Figure 2 As shown, a wireless charging contactless protection device 200 for electronic devices in some embodiments includes: a data acquisition unit 201, a first generation unit 202, a second generation unit 203, an acquisition unit 204, a third generation unit 205, and a control unit 206. The data acquisition unit 201 is configured to acquire live motion data within a target area; the first generation unit 202 is configured to generate spatial location prediction probability cloud information based on the acquired live motion data; the second generation unit 203 is configured to generate a region to be blocked based on the spatial location prediction probability cloud information; the acquisition unit 204 is configured to acquire illumination surface region information of the wireless charging area; the third generation unit 205 is configured to generate light field modulation information based on the region to be blocked and the illumination surface region information in response to determining that the region represented by the region to be blocked overlaps with the region represented by the illumination surface region information; and the control unit 206 is configured to perform adaptive safety modulation processing on the wireless charging beam based on the light field modulation information.

[0081] It is understandable that the units described in the device 200 are related to the reference. Figure 1 The steps in the method described above correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 200 and the units contained therein, and will not be repeated here.

[0082] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0083] like Figure 3 As shown, the electronic device 300 may include a spatial light modulator and a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0084] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0085] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0086] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0087] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0088] The computer-readable medium may be included in an electronic device or may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire live motion data within a target area; generate spatial location prediction probability cloud information based on the acquired live motion data; generate a region to be blocked based on the spatial location prediction probability cloud information; acquire illumination surface region information of the wireless charging area; in response to determining that the region represented by the region to be blocked overlaps with the region represented by the illumination surface region information, generate light field modulation information based on the region to be blocked and the illumination surface region information; and perform adaptive safety modulation processing on the wireless charging beam based on the light field modulation information.

[0089] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0091] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including a data acquisition unit, a first generation unit, a second generation unit, an acquisition unit, a third generation unit, and a control unit. The names of these units do not necessarily limit the specific unit; for example, a data acquisition unit may also be described as a "unit that acquires live motion data within a target area."

[0092] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0093] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of technical features, but should also cover other technical solutions formed by arbitrary combinations of technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for seamless wireless charging protection of electronic devices, comprising: Collect live animal motion data within the target area; Based on the collected live motion data, spatial location prediction probability cloud information is generated; Based on spatial location, predict probabilistic cloud information to generate information about areas to be obscured; Obtain information about the illuminated surface area of ​​the wireless charging zone; In response to the determination that the region represented by the region to be occluded overlaps with the region represented by the illumination surface region information, light field modulation information is generated based on the region to be occluded and the illumination surface region information. Based on the light field modulation information, the wireless charging beam is subjected to adaptive safety modulation processing.

2. The method of claim 1, wherein, The live motion data collected within the target area includes: Images of the target area are acquired using an image acquisition device; Perform liveness detection processing on the image to obtain liveness detection information; Based on liveness detection information, liveness motion data is collected in real time.

3. The method of claim 2, wherein, The process of performing liveness detection on the image to obtain liveness detection information includes: Preliminary human detection is performed on the image to obtain preliminary detection information; In response to determining that a person exists in the image represented by the preliminary detection information, the image is identified as a person to be identified; Fine-grained personnel identification processing is performed on the images of the personnel to be identified, and the personnel identification information is used as liveness detection information.

4. The method of claim 3, wherein, The process of performing fine-grained person recognition processing on the image of the person to be identified to obtain person recognition information includes: The image of the person to be identified is sent to a preset cloud server, so that the preset cloud server can input the image of the person to be identified into the deployed teacher model to obtain a human body focal point heat map; The image of the person to be identified is input into the visual feature extraction layer of a pre-trained fine-grained person recognition student model to obtain visual feature information. The fine-grained person recognition student model includes the visual feature extraction layer, the heatmap fusion layer, the flattening layer, and the person recognition layer. The visual feature information and the human body focal point heatmap are input into the heatmap fusion layer to obtain weighted feature information; The weighted feature information is input into the flattening layer to obtain flattened feature information; The flattened feature information is input into the personnel identification layer to obtain personnel identification information.

5. The method of claim 3, wherein, The generation of spatial location prediction probability cloud information based on the collected live motion data includes: The collected live motion data is stored as human motion data in a preset queue, and based on at least one human motion data in the preset queue, spatial location prediction probability cloud information and the time period corresponding to the spatial location prediction probability cloud information are generated.

6. The method of claim 5, wherein, Each human motion data in at least one human motion data in the preset queue includes human point cloud data and acquisition time, and the generation of spatial location prediction probability cloud information and the time period corresponding to the spatial location prediction probability cloud information based on at least one human motion data in the preset queue includes: In response to determining that there is a human motion data enqueue operation in the preset queue and that the number of human motion data in the preset queue after the enqueue operation is equal to the length of the preset queue, the following steps are performed: At least one human motion data in the preset queue is determined as a human motion data sequence; The first human motion data in the human motion data sequence is updated by adding a preset instantaneous velocity to the human motion data. Based on the human motion data sequence, the instantaneous velocity corresponding to each human motion data point except the first human motion data point in the human motion data sequence is generated, and the instantaneous velocity is added to the human motion data to update the human motion data sequence. Based on the updated human motion data sequence, spatial location prediction probability cloud information and the time period corresponding to the spatial location prediction probability cloud information are generated.

7. The method of any one of claims 1 to 6, wherein, The spatial location prediction probability cloud information includes information on various spatial points. Each spatial point includes spatial location information and an occurrence probability value. The step of generating to-be-occluded area information based on the spatial location prediction probability cloud information includes: The spatial location prediction probability cloud information includes each spatial point information that meets the preset conditions, which is determined as the spatial point information set; Each spatial point information in the spatial point information set whose occurrence probability value is less than or equal to a first preset probability value is determined as the first spatial point information group; Each spatial point information in the spatial point information set whose occurrence probability value is greater than the first preset probability value is determined as the second spatial point information group; The spatial location information included in the first spatial point information group is determined as the first area to be occluded; The spatial location information included in the second spatial point information group is determined as the second area to be occluded; The first area to be occluded and the second area to be occluded are determined as the area to be occluded.

8. A wireless charging contactless protection device for electronic devices, comprising: The acquisition unit is configured to acquire live motion data within the target area; The first generation unit is configured to generate spatial location prediction probability cloud information based on the collected live motion data; The second generation unit is configured to generate information about the area to be occluded based on spatial location-predicted probabilistic cloud information. The acquisition unit is configured to acquire information about the irradiated surface area of ​​the wireless charging area. The third generation unit is configured to generate light field modulation information based on the information of the area to be occluded and the information of the irradiated surface area in response to determining that the area represented by the information of the area to be occluded overlaps with the area represented by the information of the irradiated surface area. The control unit is configured to perform adaptive safety modulation processing on the wireless charging beam based on the light field modulation information.

9. An electronic device, comprising: Spatial light modulator, one or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 7.

11. A door, comprising the electronic device of claim 9, wherein the electronic device is a door lock.

Images