Antenna signal coverage control method and system of RFID tag

Abstract

The invention relates to the technical field of signal control, and discloses an RFID tag antenna signal coverage control method and system, and the method comprises the steps: obtaining tag distribution density data and environment interference data; constructing a label spatial distribution diagram through kernel density estimation and quadtree spatial indexes; identifying the boundary of the abnormal region by adopting hierarchical scanning and acquiring coordinates; inputting the abnormal area data into a power optimization model to generate a power distribution matrix; calibrating a node power state through backscatter communication to obtain an adjustment amplitude; allocating communication time slots by using a time slot ALOHA protocol, and performing data verification in combination with a neighbor discovery algorithm to obtain a power coordination result; and finally, generating a final resource scheduling scheme through weighted polling and a Nash equilibrium algorithm. According to the method, accurate label signal coverage control and resource optimization allocation are realized.

Description

Technical Field

[0001] This invention relates to the field of signal control technology, and in particular to an antenna signal coverage control method and system for RFID tags. Background Technology

[0002] Currently, in the fields of modern logistics, warehouse management, and intelligent identification, Radio Frequency Identification (RFID) technology, as a crucial component of IoT chips, enables efficient tracking and management of goods through contactless methods, becoming one of the core technologies driving digital transformation. However, although the integration of RFID chips with sensor network chips, radio frequency chips, and other technologies provides a foundation for applications, it still faces numerous challenges in real-world scenarios. Dynamic changes in complex environments make precise control of signal coverage a difficult problem.

[0003] In one existing technology employing a fixed-power transmission method, the reader / writer, equipped with an RF chip, continuously transmits signals at a preset power value. When a tag enters the coverage area, a millimeter-wave chip receives the reflected signal, and the MCU controller polls and scans the tag at fixed time intervals. The system implements a static time-division multiple access mechanism via an FPGA, pre-allocating a fixed number of communication time slots to all tags, and the time slot allocation scheme remains unchanged after initialization. The environmental interference detection module uses a fixed threshold comparison method; when interference exceeds the threshold, the GPU proportionally attenuates the transmission power of all areas. Tag power adjustment is entirely centrally controlled by the reader / writer, with no local coordination between adjacent tags. The resource allocation module executes a preset fixed scheduling algorithm, and the microcontroller periodically calls the same resource allocation strategy. Environmental parameters collected by the sensor chip are only stored in a local cache and do not participate in power control decisions. Control commands output by the processor chip directly act on the RF chip. However, existing technologies employ fixed-power transmission and static time slot allocation, which cannot dynamically adapt to changes in tag distribution, resulting in uneven signal coverage; centralized control lacks inter-tag coordination, and interference handling uses simple proportional attenuation, which cannot be accurately optimized; preset resource allocation strategies do not adjust with load, high-frequency components operate in fixed modes, and the system has poor adaptability.

[0004] Therefore, existing technologies have the problem of failing to achieve accurate tag signal coverage control and optimal resource allocation. Summary of the Invention

[0005] This invention provides a method and system for controlling the antenna signal coverage of RFID tags, so as to achieve precise tag signal coverage control and optimized resource allocation.

[0006] In a first aspect, to solve the above-mentioned technical problems, the present invention provides an antenna signal coverage control method for RFID tags, comprising: Acquire distribution density data and environmental interference data of RFID tags within the coverage area, wherein the distribution density data includes tag signal strength, signal occurrence frequency and tag coordinates; Based on the distribution density data, a label spatial distribution map is constructed using a kernel density estimation algorithm and a quadtree spatial indexing algorithm. Based on the spatial distribution map of the tags, a layered scanning of signal strength is performed, and the boundaries of abnormal regions are identified to obtain the coordinates of the abnormal regions. The distribution density data and environmental disturbance data corresponding to the coordinates of the abnormal region are input into a pre-constructed power optimization model to obtain a power allocation matrix; Based on the power allocation matrix, node power state calibration is performed via tag backscatter communication to obtain the power adjustment amplitude of each tag node; Based on the power adjustment amplitude, communication time slots are allocated through the time slot ALOHA protocol, and data consistency between tags is checked through the neighbor discovery synchronization algorithm to obtain the power coordination result; Based on the power coordination results, communication resources are allocated using a weighted round-robin algorithm, and resource reallocation decisions are made using a Nash equilibrium algorithm to obtain the final resource scheduling scheme.

[0007] In one optional implementation, the step of constructing a label spatial distribution map based on the distribution density data using a kernel density estimation algorithm and a quadtree spatial indexing algorithm includes: The distribution density data is spatially interpolated using a kernel density estimation algorithm to generate a label density heatmap. The label density heatmap is divided into grid cells and high-density variation areas are marked using a quadtree spatial index to obtain gridded data. The spatial hashing algorithm is used to spatially correlate and match the gridded data with the label coordinates to generate a label spatial distribution map.

[0008] In one optional implementation, the step of performing signal strength layered scanning based on the tag spatial distribution map and identifying abnormal region boundaries to obtain abnormal region coordinates includes: The DBSCA clustering algorithm is used to perform a hierarchical scanning of the label spatial distribution map based on signal strength, resulting in a hierarchical distribution map. Anomalies are identified based on the hierarchical distribution map and a preset signal strength threshold to obtain abnormal regions. Based on the abnormal region, a region growing algorithm is used to extract the boundary of the abnormal region. The label coordinates within the boundary of the abnormal region are extracted as the abnormal region coordinates.

[0009] In one optional implementation, the process of constructing the power optimization model includes: Obtain historical distribution density data, historical environmental interference data, and corresponding standard power allocation matrix corresponding to the coordinates of historical anomaly areas; and perform data cleaning and feature extraction on the historical distribution density data and the historical environmental interference data to obtain anomaly features. The abnormal features are input into the input layer of the initially constructed power optimization model for training, and the predicted power allocation matrix output by the output layer of the power optimization model is obtained. Substitute the predicted power allocation matrix and the standard power allocation matrix into the loss function to calculate the loss value; The gradient of the output layer of the power optimization model is calculated based on the loss value, and the gradient is passed forward layer by layer through the chain rule to calculate the gradient of the parameters of each layer and obtain the gradient data. Based on the gradient data and the preset learning rate, the parameters of each layer of the neural network model are updated using the gradient descent method. The parameters of each layer are iteratively updated until the number of training iterations of the power optimization model is greater than the preset number of iterations, or the loss value of the power optimization model is less than the preset loss threshold. At this point, the training is considered complete, and the trained power optimization model is obtained.

[0010] In one optional implementation, the step of calibrating the node power state via tag backscatter communication based on the power allocation matrix to obtain the power adjustment amplitude of each tag node includes: Based on the power allocation matrix, tag node data is distributed using a time-division multiple access protocol to obtain tag response signals; Based on the tag response signal, power status is collected through an electronic tag polling mechanism to obtain tag power data; Based on the tag power data, a fuzzy adaptive control algorithm is used to calculate the power deviation, and combined with a preset power threshold range, the power adjustment range of each tag is obtained.

[0011] In one optional implementation, the step of adjusting the power amplitude, allocating communication time slots via the time slot ALOHA protocol, and verifying inter-tag data consistency via a neighbor discovery synchronization algorithm to obtain the power coordination result includes: Based on the power adjustment amplitude, communication time slots are dynamically divided using the time slot ALOHA protocol to obtain a time slot allocation table with priority markings; Based on the time slot allocation table, the overlap of adjacent tag time slots is analyzed by the collision detection algorithm. When a time slot conflict is found, the non-overlapping time slots are reallocated to obtain an optimized time slot scheme. According to the optimized time slot scheme, the data synchronization status between tags is detected by the neighbor discovery synchronization algorithm, and the data is calibrated by the retransmission compensation mechanism for tags that have not completed synchronization, so as to obtain a synchronization status report. Based on the synchronization status report, the final power values ​​of each tag are collected through a distributed power coordination algorithm, and a power coordination command is generated by combining the preset power tolerance range, and the power coordination result is finally output.

[0012] In one optional implementation, the step of allocating communication resources using a weighted round-robin algorithm based on power coordination results, and making resource reallocation decisions using a Nash equilibrium algorithm to obtain the final resource scheduling scheme includes: Power data for each tag region is extracted based on the power coordination results. When the power data exceeds a preset power threshold, a resource adjustment signal is generated to obtain a list of regions to be optimized. Based on the list of resources to be optimized, a weighted round-robin algorithm is used to allocate communication resources and obtain a preliminary resource allocation scheme. According to the preliminary resource allocation scheme, when the power data still exceeds the preset power threshold, the Nash equalization algorithm is triggered to perform secondary communication resource allocation and generate the final resource scheduling scheme table.

[0013] Secondly, the present invention provides an antenna signal coverage control system for RFID tags, comprising: The data acquisition module is used to acquire the distribution density data and environmental interference data of RFID tags within the coverage area, wherein the distribution density data includes tag signal strength, signal occurrence frequency and tag coordinates; The spatial construction module is used to construct a label spatial distribution map based on the distribution density data using a kernel density estimation algorithm and a quadtree spatial indexing algorithm. An anomaly identification module is used to perform signal strength layer scanning based on the tag spatial distribution map, identify the boundaries of abnormal regions, and obtain the coordinates of the abnormal regions; The power allocation module is used to input the distribution density data and environmental interference data corresponding to the coordinates of the abnormal area into a pre-built power optimization model to obtain a power allocation matrix; The power adjustment module is used to perform node power state calibration through tag backscatter communication based on the power allocation matrix to obtain the power adjustment amplitude of each tag node; The power coordination module is used to adjust the amplitude according to the power, allocate communication time slots through the time slot ALOHA protocol, and perform data consistency verification between tags through the neighbor discovery synchronization algorithm to obtain the power coordination result. The resource scheduling module is used to allocate communication resources based on the power coordination results, using a weighted round-robin algorithm, and to make resource reallocation decisions using a Nash equilibrium algorithm, thus obtaining the final resource scheduling scheme.

[0014] Thirdly, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the antenna signal coverage control method for RFID tags as described in any one of the above.

[0015] Fourthly, the present invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the antenna signal coverage control method for RFID tags described in any one of the above-described methods.

[0016] Compared with the prior art, the present invention has the following beneficial effects: (1) This invention generates a heatmap by spatially interpolating tag distribution density data using a kernel density estimation algorithm, divides the data into dynamic grid cells using a quadtree spatial index, and marks high-density variation areas. Then, it constructs a spatial distribution map by associating tag coordinates using a spatial hash algorithm. This method accurately reflects the spatial characteristics of tag distribution through dynamic modeling, thereby improving signal coverage uniformity and accurately locating the boundaries of abnormal areas.

[0017] (2) This invention inputs abnormal region data into a power optimization model built on a neural network. This model learns the coupling relationship between historical abnormal features and environmental interference through training, and outputs a power allocation matrix that matches the complex scene. This method achieves adaptive adjustment to multi-source interference through machine learning, significantly enhancing the system's anti-interference capability.

[0018] (3) This invention uses the slotted ALOHA protocol for dynamic slot allocation and introduces priority marking. It establishes tag-cooperative groups through a neighbor discovery algorithm, combines a conflict detection mechanism to solve slot overlap problems, and finally employs a distributed power coordination algorithm to achieve power balancing. This method effectively avoids multi-tag communication conflicts through distributed coordination, improving system coordination efficiency.

[0019] (4) Based on the power coordination results, this invention first performs preliminary resource allocation through a weighted round-robin algorithm, and then triggers a Nash equilibrium algorithm for secondary optimization in areas that do not meet the standards, finally generating a global resource scheduling scheme. This method achieves dynamic adjustment of resource allocation through a hierarchical optimization mechanism, achieving the best balance between coverage quality and resource consumption. Attached Figure Description

[0020] Figure 1This is a schematic flowchart of the antenna signal coverage control method for RFID tags provided in the first embodiment of the present invention; Figure 2 This is a schematic diagram of the antenna signal coverage control system structure of the RFID tag provided in the second embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Reference Figure 1 The first embodiment of the present invention provides a method for controlling the antenna signal coverage of an RFID tag, comprising the following steps: S11, acquire the distribution density data and environmental interference data of RFID tags within the coverage area, wherein the distribution density data includes tag signal strength, signal occurrence frequency and tag coordinates; S12, Based on the distribution density data, construct a label spatial distribution map using a kernel density estimation algorithm and a quadtree spatial indexing algorithm; S13, Perform a layered scanning of signal strength based on the label spatial distribution map, identify the boundaries of abnormal regions, and obtain the coordinates of the abnormal regions; S14, input the distribution density data and environmental interference data corresponding to the coordinates of the abnormal area into the pre-built power optimization model to obtain the power allocation matrix; S15, perform node power state calibration through tag backscatter communication based on the power allocation matrix to obtain the power adjustment amplitude of each tag node; S16, adjust the amplitude according to the power, allocate communication time slots through the time slot ALOHA protocol, and verify the data consistency between tags through the neighbor discovery synchronization algorithm to obtain the power coordination result; S17. Based on the power coordination results, communication resources are allocated using a weighted round-robin algorithm, and resource reallocation decisions are made using a Nash equilibrium algorithm to obtain the final resource scheduling scheme.

[0023] In step S11, the distribution density data and environmental interference data of RFID tags within the coverage area are obtained, wherein the distribution density data includes tag signal strength, signal occurrence frequency and tag coordinates.

[0024] Specifically, the tag signal strength (i.e., RSSI value) is collected by a radio frequency signal receiving module deployed on the reader. This module records the intensity fluctuations of the tag's reflected signal at millisecond sampling intervals. The number of times each tag is successfully identified per unit time is accumulated by the reader's time slot statistical counter, generating signal occurrence frequency data. The real-time three-dimensional coordinates of each tag are calculated by coordinating ranging between a UWB positioning base station installed at a fixed reference point and the tag's built-in positioning module, combined with a trilateration algorithm. Environmental interference data is collected by electromagnetic field strength sensors distributed throughout the coverage area to obtain background noise spectrum, while environmental parameters are obtained through temperature and humidity sensors and metal object detectors. The final output includes tag signal strength, signal occurrence frequency, and tag coordinate distribution density data, as well as environmental interference data composed of environmental electromagnetic noise intensity, temperature and humidity values, and metal reflection coefficient.

[0025] In step S12, a label spatial distribution map is constructed based on the distribution density data using a kernel density estimation algorithm and a quadtree spatial indexing algorithm.

[0026] In one specific implementation, the step of constructing a label spatial distribution map based on the distribution density data using a kernel density estimation algorithm and a quadtree spatial indexing algorithm includes: The distribution density data is spatially interpolated using a kernel density estimation algorithm to generate a label density heatmap. The label density heatmap is divided into grid cells and high-density variation areas are marked using a quadtree spatial index to obtain gridded data. The spatial hashing algorithm is used to spatially correlate and match the gridded data with the label coordinates to generate a label spatial distribution map.

[0027] Specifically, taking the tag coordinates and corresponding signal strength output in step S11 as input, the Gaussian kernel function (kernel density estimation algorithm) is first used to perform spatial interpolation on the discrete tag coordinates: the density contribution value of neighboring points within a preset bandwidth radius around each coordinate point is calculated, and the values ​​are superimposed to generate a continuous tag density heatmap. The pixel values ​​of this heatmap represent the tag distribution density per unit area.

[0028] Next, the heatmap is divided into dynamic grid cells using a quadtree spatial index: the heatmap region is recursively split until the density variance in each cell is lower than the preset density change threshold (the density change threshold is set according to the standard deviation of normal density fluctuations in historical data), high density change regions with density gradients exceeding twice the mean of adjacent cells are marked, and gridded data and cell attribute tables are output.

[0029] Finally, a spatial hashing algorithm is used to establish the mapping relationship between grid cells and label coordinates: each label coordinate is converted into a hash key value, associated with the center coordinates and density level of the grid cell to which it belongs, and a label spatial distribution map containing the grid spatial topology and the list of label coordinates within the cell is generated.

[0030] This step eliminates data sparsity through kernel density interpolation, captures clustered features through quadtree dynamic partitioning, and quickly associates coordinates with grids using spatial hashing, thus constructing a spatial model that accurately reflects the label distribution and providing a data structure foundation for anomaly region identification.

[0031] In step S13, a layered scanning of signal strength is performed based on the label spatial distribution map, and the boundaries of abnormal regions are identified to obtain the coordinates of the abnormal regions.

[0032] In one specific implementation, the step of performing signal strength layered scanning based on the tag spatial distribution map, identifying abnormal region boundaries, and obtaining abnormal region coordinates includes: The DBSCA clustering algorithm is used to perform a hierarchical scanning of the label spatial distribution map based on signal strength, resulting in a hierarchical distribution map. Anomalies are identified based on the hierarchical distribution map and a preset signal strength threshold to obtain abnormal regions. Based on the abnormal region, a region growing algorithm is used to extract the boundary of the abnormal region. The label coordinates within the boundary of the abnormal region are extracted as the abnormal region coordinates.

[0033] Specifically, the tag spatial distribution map generated in step S12 (including the center coordinates of grid cells, cell density levels, and a list of tag coordinates within the cells) and the tag signal strength data collected in step S11 are used as inputs. First, the DBSCAN clustering algorithm is used to process the grid cells: using the center coordinates of the grid cells as data points and the arithmetic mean of the tag signal strength within the cell as the attribute value, a core point distance threshold (which is determined based on the average intra-cluster distance of historical normal signal strength distribution) and a minimum number of neighboring cells are set. Continuous grid cells with similar attribute values ​​are clustered into signal strength layers, generating a hierarchical distribution map containing high, medium, and low signal strength layers.

[0034] Then, anomaly identification is performed on each strength layer according to the preset signal strength threshold (the signal strength threshold is set according to the 99th percentile of the statistical distribution of historical normal operation data): when the average signal strength of a certain grid cell exceeds the threshold of its respective strength layer, the cell is marked as an abnormal cell, and all abnormal cells constitute the initial abnormal region. Next, the region growth algorithm is used to process the initial abnormal region: the abnormal cell with the highest signal strength is selected as the seed point and expanded to the adjacent eight directions (including the up, down, left, right and four diagonal directions). If the signal strength difference between adjacent cells is less than the preset gradient tolerance (set according to the standard deviation of the signal strength difference between adjacent cells in historical data), it is included in the current abnormal region; for non-contiguous but isolated abnormal cells within the preset merging radius (determined according to 3 times the average spacing of the labels), merging is performed when the following conditions are met: (1) the signal strength difference is less than 1.5 times the gradient tolerance; (2) there is no normal cell blocking between cells. The iterative growth process continues until the intensity difference between the boundary cells and normal cells exceeds the tolerance. Finally, the boundary of the abnormal region is output as a closed polygon, and the coordinates of the discontinuous abnormal cells inside the region are recorded.

[0035] Finally, extract all the label coordinates contained within the geometric boundary of the polygon to form the coordinates of the abnormal region.

[0036] This step achieves precise location of signal coverage anomalies by dividing signal strength into hierarchical levels using density clustering, identifying anomalous units using statistical thresholds, and determining precise boundaries using region growing, thus providing spatial target input for power optimization.

[0037] In step S14, the distribution density data and environmental interference data corresponding to the coordinates of the abnormal area are input into the pre-constructed power optimization model to obtain the power allocation matrix.

[0038] In one specific implementation, the process of constructing the power optimization model includes: Obtain historical distribution density data, historical environmental interference data, and corresponding standard power allocation matrix corresponding to the coordinates of historical anomaly areas; and perform data cleaning and feature extraction on the historical distribution density data and the historical environmental interference data to obtain anomaly features. The abnormal features are input into the input layer of the initially constructed power optimization model for training, and the predicted power allocation matrix output by the output layer of the power optimization model is obtained. Substitute the predicted power allocation matrix and the standard power allocation matrix into the loss function to calculate the loss value; The gradient of the output layer of the power optimization model is calculated based on the loss value, and the gradient is passed forward layer by layer through the chain rule to calculate the gradient of the parameters of each layer and obtain the gradient data. Based on the gradient data and the preset learning rate, the parameters of each layer of the neural network model are updated using the gradient descent method. The parameters of each layer are iteratively updated until the number of training iterations of the power optimization model is greater than the preset number of iterations, or the loss value of the power optimization model is less than the preset loss threshold. At this point, the training is considered complete, and the trained power optimization model is obtained.

[0039] Specifically, the construction process of the power optimization model is as follows: Historical datasets corresponding to the coordinates of historical anomaly areas are collected, including historical tag signal strength, signal frequency, and historical distribution density data composed of tag coordinates, as well as historical environmental interference data composed of historical environmental electromagnetic noise intensity, temperature and humidity values, and metal reflection coefficients. Simultaneously, a standard power allocation matrix verified through system testing and experiments under this historical scenario is obtained. This matrix represents the stable optimal power configuration obtained through multiple tests under the same environmental conditions. Outlier removal and standardization are performed on the historical distribution density data, and the tag density variation coefficient, signal strength range, and coordinate dispersion within the anomaly area are extracted as density features. The coordinate dispersion is characterized by calculating the average distance between each tag coordinate point within the area and the center point of the area; a larger distance indicates a more dispersed distribution. Electromagnetic noise peak values, temperature and humidity variation gradients, and the mean value of metal reflection intensity are extracted from the environmental interference data as interference features. Density features and interference features are merged into an anomaly feature vector, which is then input into a fully connected neural network. The input layer receives 12-dimensional anomaly features (3-dimensional density features + 3-dimensional interference features, each feature group containing mean and variance, totaling 12 dimensions). This vector undergoes a non-linear transformation through three hidden layers (32, 64, and 32 neurons respectively), and the output layer generates a predicted power allocation matrix with the same dimensions as the standard power allocation matrix. The difference between the predicted matrix and the standard matrix is ​​calculated using the mean squared error loss function, and the gradient of the output layer is calculated using backpropagation, passing the gradient data layer by layer from back to front. Based on the gradient data and the learning rate (initial value 0.01, using an exponential decay strategy), the weight parameters of each layer are updated using gradient descent. Training is stopped when the number of training iterations reaches 2000 or the loss value is below 0.005 for 10 consecutive iterations, and the final network parameters are saved as a power optimization model.

[0040] Finally, the distribution density data and environmental disturbance data corresponding to the coordinates of the abnormal region are input into the pre-built power optimization model to obtain the power allocation matrix.

[0041] This model solves the problem that fixed power rules are difficult to adapt to complex interference environments by dynamically learning the optimal power allocation strategy in historical scenarios, and provides a precise basis for power regulation in abnormal areas.

[0042] In step S15, node power state calibration is performed through tag backscatter communication based on the power allocation matrix to obtain the power adjustment amplitude of each tag node.

[0043] In one specific implementation, the step of calibrating the node power state through tag backscatter communication based on the power allocation matrix to obtain the power adjustment amplitude of each tag node includes: Based on the power allocation matrix, tag node data is distributed using a time-division multiple access protocol to obtain tag response signals; Based on the tag response signal, power status is collected through an electronic tag polling mechanism to obtain tag power data; Based on the tag power data, a fuzzy adaptive control algorithm is used to calculate the power deviation, and combined with a preset power threshold range, the power adjustment range of each tag is obtained.

[0044] Specifically, the process first distributes power adjustment instructions to each tag node according to the target power value of each tag stored in the power allocation matrix through the time division multiple access transmission protocol: the reader divides the time axis into time slots of fixed length and writes the target power value data packet to each time slot in order of tag ID. The tag confirms the signal by backscattering modulation in the specified time slot, forming a tag response signal containing the tag ID and the reception status code.

[0045] Next, the electronic tag polling mechanism is activated: the reader sends power query commands in ascending order of ID. After receiving the dedicated command, the tag returns the current actual transmit power value through load modulation. The reader records valid data where the response delay of each tag does not exceed the preset timeout threshold (this threshold is determined based on the 99th percentile of the historical average response time distribution) and generates a tag power data table consisting of tag ID and actual power value.

[0046] Based on the tag power data, power deviation is calculated using a fuzzy control algorithm: Based on historical power sampling data of the tags (such as power records from recent periods), typical fluctuation characteristics are statistically analyzed, and multi-level evaluation intervals are established. An adjustable membership function (such as a trapezoidal or trigonometric function) is used to dynamically map the current power deviation to preset fuzzy levels (such as "negative large," "negative small," "zero," "positive small," and "positive large"). The boundary parameters of each level interval are automatically adapted according to historical fluctuation characteristics—when increased power volatility is detected, the range of each level interval is widened accordingly; conversely, the range is appropriately narrowed. Combined with a preset power threshold range, the final power adjustment range for each tag is obtained.

[0047] This step achieves closed-loop dynamic calibration of tag node power by accurately distributing instructions through time-division communication, polling to collect real-time status, and fuzzy adaptive calculation of adjustment amounts.

[0048] In step S16, the power adjustment amplitude is adjusted, communication time slots are allocated through the time slot ALOHA protocol, and data consistency between tags is checked through the neighbor discovery synchronization algorithm to obtain the power coordination result.

[0049] In one specific implementation, the process of adjusting the power amplitude, allocating communication time slots via the time-slot ALOHA protocol, and verifying inter-tag data consistency via a neighbor discovery synchronization algorithm to obtain the power coordination result includes: Based on the power adjustment amplitude, communication time slots are dynamically divided using the time slot ALOHA protocol to obtain a time slot allocation table with priority markings; Based on the time slot allocation table, the overlap of adjacent tag time slots is analyzed by the collision detection algorithm. When a time slot conflict is found, the non-overlapping time slots are reallocated to obtain an optimized time slot scheme. According to the optimized time slot scheme, the data synchronization status between tags is detected by the neighbor discovery synchronization algorithm, and the data is calibrated by the retransmission compensation mechanism for tags that have not completed synchronization, so as to obtain a synchronization status report. Based on the synchronization status report, the final power values ​​of each tag are collected through a distributed power coordination algorithm, and a power coordination command is generated by combining the preset power tolerance range, and the power coordination result is finally output.

[0050] Specifically, firstly, based on the power adjustment amplitude, communication time slots are dynamically divided using the ALOHA time slot protocol: the time slot length setting comprehensively considers the typical response characteristics of the tags (such as average response time and its fluctuation range), dividing the communication cycle into several time slot segments; priority evaluation is based on the degree of tag power adjustment needs (such as the adjustment magnitude or urgency), concentrating high-priority tags in a dedicated time slot area at the beginning of the communication cycle. This area reserves a wider time slot interval (such as adding several protection time slots compared to ordinary areas), and the risk of transmission overlap between adjacent tags is reduced by staggering the time slots. Finally, a time slot allocation table with priority markings is generated, where each time slot segment is marked with the applicable priority level and recommended transmission power range.

[0051] Next, the tag location coordinates and time slot allocation information in the time slot allocation table are read, and a dual detection algorithm of geometric distance and time slot overlap is adopted: the Euclidean distance between adjacent tags is calculated. If it is less than the preset critical communication radius (this radius is determined based on the typical signal coverage distance of the system and can be obtained by actually measuring the maximum stable communication distance between the reader and the tag) and the allocated time slots overlap, it is determined to be a conflict. Non-overlapping time slots are reallocated to the conflicting tags to generate an optimized time slot scheme. Then, according to the optimized time slot scheme, a tag cooperation group is established through a neighbor discovery synchronization algorithm: with each tag as the center, neighboring tags within its critical communication radius are searched as neighbor nodes. Each tag broadcasts its own power adjustment amplitude to its neighbors within the allocated time slot and receives confirmation signals from its neighbors. If not all neighbor confirmations are received within the preset synchronization timeout window (determined based on twice the maximum signal round-trip delay), a retransmission compensation mechanism is triggered—automatically increasing the transmission power by 5dB and reserving a dedicated retransmission time slot for data retransmission until a report containing the synchronization status of all tags is generated.

[0052] Finally, based on the synchronization status report, a distributed power coordination algorithm is used to collect the final confirmed power values ​​of each tag, calculate the power difference between adjacent tags, and if it exceeds the preset power tolerance range (the lower limit is the chip's minimum adjustable power step value, and the upper limit is the chip's maximum allowable power difference, both determined according to the device technical manual), a coordination instruction is generated: attenuation compensation is performed on high-power tags, gain compensation is performed on low-power tags, and a power coordination result that meets the tolerance requirements is output.

[0053] This step ensures communication reliability through time slot allocation and conflict resolution, implements distributed data verification through a neighbor discovery mechanism, and ensures regional power balance through a power coordination algorithm, thus solving the signal interference problem in multi-tag collaboration.

[0054] In step S17, based on the power coordination results, communication resources are allocated using a weighted round-robin algorithm, and resource reallocation decisions are made using a Nash equilibrium algorithm to obtain the final resource scheduling scheme.

[0055] In one specific implementation, the step of allocating communication resources based on power coordination results using a weighted round-robin algorithm and making resource reallocation decisions using a Nash equilibrium algorithm to obtain the final resource scheduling scheme includes: Power data for each tag region is extracted based on the power coordination results. When the power data exceeds a preset power threshold, a resource adjustment signal is generated to obtain a list of regions to be optimized. Based on the list of resources to be optimized, a weighted round-robin algorithm is used to allocate communication resources and obtain a preliminary resource allocation scheme. According to the preliminary resource allocation scheme, when the power data still exceeds the preset power threshold, the Nash equalization algorithm is triggered to perform secondary communication resource allocation and generate the final resource scheduling scheme table.

[0056] Specifically, the average power value of each labeled region in the power coordination result output in step S16 is used as input. When the average power value of a certain region exceeds the preset power threshold limit (this threshold is determined based on 90% of the chip's maximum safe power), a resource adjustment signal containing the region ID and the power exceeding the limit is generated, forming a list to be optimized.

[0057] Based on the region ID in the list to be optimized, the number of tags, historical communication load weights, and power adjustment ranges of the corresponding regions are read. Communication resources are allocated through a weighted round-robin algorithm: the number of tags is used as the base weight (accounting for 60%) and the adjustment range is used as the dynamic weight (accounting for 40%). Reader channel resources are allocated according to the total weight ratio to generate a preliminary resource allocation scheme that includes the channel allocation duration for each region.

[0058] After implementing the initial plan, regional power data is monitored in real time. If any region's power value still exceeds the upper limit of the power threshold, the Nash equilibrium algorithm is triggered for secondary allocation. The reader channel resources are treated as limited public resources, and each region is treated as an independent participant. A utility function is constructed based on regional signal quality (weight 50%) and resource utilization (weight 50%), and the Pareto optimal solution is found through iterative game theory. The calculation terminates when the difference between the utility functions of two adjacent iterations is less than the convergence threshold (set to 0.01), and the final resource scheduling scheme table that satisfies Nash equilibrium is output, specifying the optimal channel occupancy period and power compensation value for each region.

[0059] This step, through a hierarchical resource allocation mechanism, optimizes global resources while ensuring basic needs in high-load areas, thus resolving signal coverage conflicts in complex scenarios.

[0060] Reference Figure 2 The second embodiment of the present invention provides an antenna signal coverage control system for RFID tags, comprising: The data acquisition module is used to acquire the distribution density data and environmental interference data of RFID tags within the coverage area, wherein the distribution density data includes tag signal strength, signal occurrence frequency and tag coordinates; The spatial construction module is used to construct a label spatial distribution map based on the distribution density data using a kernel density estimation algorithm and a quadtree spatial indexing algorithm. An anomaly identification module is used to perform signal strength layer scanning based on the tag spatial distribution map, identify the boundaries of abnormal regions, and obtain the coordinates of the abnormal regions; The power allocation module is used to input the distribution density data and environmental interference data corresponding to the coordinates of the abnormal area into a pre-built power optimization model to obtain a power allocation matrix; The power adjustment module is used to perform node power state calibration through tag backscatter communication based on the power allocation matrix to obtain the power adjustment amplitude of each tag node; The power coordination module is used to adjust the amplitude according to the power, allocate communication time slots through the time slot ALOHA protocol, and perform data consistency verification between tags through the neighbor discovery synchronization algorithm to obtain the power coordination result. The resource scheduling module is used to allocate communication resources based on the power coordination results, using a weighted round-robin algorithm, and to make resource reallocation decisions using a Nash equilibrium algorithm, thus obtaining the final resource scheduling scheme.

[0061] It should be noted that the antenna signal coverage control device for an RFID tag provided in this embodiment of the invention is used to execute all the process steps of the antenna signal coverage control method for an RFID tag in the above embodiment. The working principle and beneficial effects of the two are one-to-one, so they will not be described again.

[0062] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an antenna signal coverage control program for RFID tags. When the processor executes the computer program, it implements the steps in the various RFID tag antenna signal coverage control method embodiments described above, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiments, such as the antenna signal coverage control module for RFID tags.

[0063] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0064] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0065] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0066] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0067] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0068] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0069] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for controlling antenna signal coverage of an RFID tag, characterized in that, include: Acquire distribution density data and environmental interference data of RFID tags within the coverage area, wherein the distribution density data includes tag signal strength, signal occurrence frequency and tag coordinates; Based on the distribution density data, a label spatial distribution map is constructed using a kernel density estimation algorithm and a quadtree spatial indexing algorithm. Based on the spatial distribution map of the tags, a layered scanning of signal strength is performed, and the boundaries of abnormal regions are identified to obtain the coordinates of the abnormal regions. The distribution density data and environmental disturbance data corresponding to the coordinates of the abnormal region are input into a pre-constructed power optimization model to obtain a power allocation matrix; Based on the power allocation matrix, node power state calibration is performed via tag backscatter communication to obtain the power adjustment amplitude of each tag node; Based on the power adjustment amplitude, communication time slots are allocated through the time slot ALOHA protocol, and data consistency between tags is checked through the neighbor discovery synchronization algorithm to obtain the power coordination result; Based on the power coordination results, communication resources are allocated using a weighted round-robin algorithm, and resource reallocation decisions are made using a Nash equilibrium algorithm to obtain the final resource scheduling scheme.

2. The antenna signal coverage control method for RFID tags according to claim 1, characterized in that, The step of constructing a label spatial distribution map based on the distribution density data using a kernel density estimation algorithm and a quadtree spatial indexing algorithm includes: The distribution density data is spatially interpolated using a kernel density estimation algorithm to generate a label density heatmap. The label density heatmap is divided into grid cells and high-density variation areas are marked using a quadtree spatial index to obtain gridded data. The spatial hashing algorithm is used to spatially correlate and match the gridded data with the label coordinates to generate a label spatial distribution map.

3. The antenna signal coverage control method for RFID tags according to claim 1, characterized in that, The step of performing a layered scanning of signal strength based on the tag spatial distribution map, identifying the boundaries of abnormal regions, and obtaining the coordinates of the abnormal regions includes: The DBSCA clustering algorithm is used to perform a hierarchical scanning of the label spatial distribution map based on signal strength, resulting in a hierarchical distribution map. Anomalies are identified based on the hierarchical distribution map and a preset signal strength threshold to obtain abnormal regions. Based on the abnormal region, a region growing algorithm is used to extract the boundary of the abnormal region. The label coordinates within the boundary of the abnormal region are extracted as the abnormal region coordinates.

4. The antenna signal coverage control method for RFID tags according to claim 1, characterized in that, The process of constructing the power optimization model includes: Obtain historical distribution density data, historical environmental interference data, and corresponding standard power allocation matrix corresponding to the coordinates of historical anomaly areas; and perform data cleaning and feature extraction on the historical distribution density data and the historical environmental interference data to obtain anomaly features. The abnormal features are input into the input layer of the initially constructed power optimization model for training, and the predicted power allocation matrix output by the output layer of the power optimization model is obtained. Substitute the predicted power allocation matrix and the standard power allocation matrix into the loss function to calculate the loss value; The gradient of the output layer of the power optimization model is calculated based on the loss value, and the gradient is passed forward layer by layer through the chain rule to calculate the gradient of the parameters of each layer and obtain the gradient data. Based on the gradient data and the preset learning rate, the parameters of each layer of the neural network model are updated using the gradient descent method. The parameters of each layer are iteratively updated until the number of training iterations of the power optimization model is greater than the preset number of iterations, or the loss value of the power optimization model is less than the preset loss threshold. At this point, the training is considered complete, and the trained power optimization model is obtained.

5. The antenna signal coverage control method for RFID tags according to claim 1, characterized in that, The step of calibrating the node power state through tag backscatter communication based on the power allocation matrix to obtain the power adjustment amplitude of each tag node includes: Based on the power allocation matrix, tag node data is distributed using a time-division multiple access protocol to obtain tag response signals; Based on the tag response signal, power status is collected through an electronic tag polling mechanism to obtain tag power data; Based on the tag power data, a fuzzy adaptive control algorithm is used to calculate the power deviation, and combined with a preset power threshold range, the power adjustment range of each tag is obtained.

6. The antenna signal coverage control method for RFID tags according to claim 1, characterized in that, The process of adjusting the amplitude based on power, allocating communication time slots through the time-slotted ALOHA protocol, and verifying inter-tag data consistency through a neighbor discovery synchronization algorithm to obtain the power coordination result includes: Based on the power adjustment amplitude, communication time slots are dynamically divided using the time slot ALOHA protocol to obtain a time slot allocation table with priority markings; Based on the time slot allocation table, the overlap of adjacent tag time slots is analyzed by the collision detection algorithm. When a time slot conflict is found, the non-overlapping time slots are reallocated to obtain an optimized time slot scheme. According to the optimized time slot scheme, the data synchronization status between tags is detected by the neighbor discovery synchronization algorithm, and the data is calibrated by the retransmission compensation mechanism for tags that have not completed synchronization, so as to obtain a synchronization status report. Based on the synchronization status report, the final power values ​​of each tag are collected through a distributed power coordination algorithm, and a power coordination command is generated by combining the preset power tolerance range, and the power coordination result is finally output.

7. The antenna signal coverage control method for RFID tags according to claim 1, characterized in that, The process of allocating communication resources using a weighted round-robin algorithm based on power coordination results, and making resource reallocation decisions using a Nash equilibrium algorithm, to obtain the final resource scheduling scheme includes: Power data for each tag region is extracted based on the power coordination results. When the power data exceeds a preset power threshold, a resource adjustment signal is generated to obtain a list of regions to be optimized. Based on the list of resources to be optimized, a weighted round-robin algorithm is used to allocate communication resources and obtain a preliminary resource allocation scheme. According to the preliminary resource allocation scheme, when the power data still exceeds the preset power threshold, the Nash equalization algorithm is triggered to perform secondary communication resource allocation and generate the final resource scheduling scheme table.

8. An antenna signal coverage control system for RFID tags, characterized in that, include: The data acquisition module is used to acquire the distribution density data and environmental interference data of RFID tags within the coverage area, wherein the distribution density data includes tag signal strength, signal occurrence frequency and tag coordinates; The spatial construction module is used to construct a label spatial distribution map based on the distribution density data using a kernel density estimation algorithm and a quadtree spatial indexing algorithm. An anomaly identification module is used to perform signal strength layer scanning based on the tag spatial distribution map, identify the boundaries of abnormal regions, and obtain the coordinates of the abnormal regions; The power allocation module is used to input the distribution density data and environmental interference data corresponding to the coordinates of the abnormal area into a pre-built power optimization model to obtain a power allocation matrix; The power adjustment module is used to perform node power state calibration through tag backscatter communication based on the power allocation matrix to obtain the power adjustment amplitude of each tag node; The power coordination module is used to adjust the amplitude according to the power, allocate communication time slots through the time slot ALOHA protocol, and perform data consistency verification between tags through the neighbor discovery synchronization algorithm to obtain the power coordination result. The resource scheduling module is used to allocate communication resources based on the power coordination results, using a weighted round-robin algorithm, and to make resource reallocation decisions using a Nash equilibrium algorithm, thus obtaining the final resource scheduling scheme.

9. An electronic device, characterized in that, The method includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the antenna signal coverage control method for an RFID tag as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the antenna signal coverage control method for an RFID tag as described in any one of claims 1 to 7.

Images