Antenna position updating method and device, electronic equipment and storage medium

Abstract

The invention provides an antenna position updating method and device, electronic equipment and a storage medium, and relates to the technical field of the Internet of Things, and the method comprises the steps: obtaining target signal data collected by a mobile signal collection device for a target region; generating initial region feature data of the target region based on the target signal data; performing position labeling on the initial region feature data to obtain target region feature data; inputting the target region feature data into a label position prediction model to generate a target label position; and updating the antenna position of the mobile signal acquisition device based on the target label position. According to the invention, high-precision and self-adaptive label positioning can be realized through the mobile signal acquisition device, meanwhile, a sensing-optimization closed loop is constructed, dynamic tuning of antenna deployment is realized, the system robustness is improved, the method adapts to a complex dynamic environment, and compared with a manual antenna adjustment mode in the prior art, the precision and efficiency of antenna adjustment can be greatly improved.

Description

Technical Field

[0001] This disclosure relates to the field of Internet of Things (IoT) technology, and in particular to an antenna position update method, apparatus, electronic device, and storage medium. Background Technology

[0002] Passive IoT terminal devices operate without built-in batteries, powered by energy harvested from the environment to perform sensing, computing, or communication tasks. They offer advantages such as low cost, maintenance-free operation, and zero power consumption, making them suitable for large-scale applications in logistics, warehousing, and asset management. Tag positioning is a key application scenario for passive IoT. Based on the principle of radio wave reflection, a receiver captures the weak signals reflected back from passive tags, and combined with multipath propagation characteristics, a positioning algorithm estimates the tag's location. Currently, antenna deployment schemes rely on manual experience. To achieve optimal positioning results, antenna positions need repeated manual adjustments. When the target tag arrangement changes (e.g., adjusting product shelves or relocating warehouse goods), repeated adjustments are required again, resulting in a large workload and difficulty in guaranteeing global optimization. Summary of the Invention

[0003] This disclosure aims to at least partially address one of the technical problems in the related art.

[0004] Therefore, one objective of this disclosure is to propose an antenna position update method.

[0005] The second objective of this disclosure is to provide an antenna position updating device.

[0006] The third objective of this disclosure is to propose an electronic device.

[0007] The fourth objective of this disclosure is to provide a non-transitory computer-readable storage medium.

[0008] The fifth objective of this disclosure is to provide a computer program product.

[0009] To achieve the above objectives, a first aspect of this disclosure provides an antenna position update method, comprising: acquiring target signal data collected by a mobile signal acquisition device from a target area; generating initial area feature data of the target area based on the target signal data; marking the initial area feature data to obtain target area feature data; inputting the target area feature data into a tag position prediction model to generate a target tag position; and updating the antenna position of the mobile signal acquisition device based on the target tag position.

[0010] According to one embodiment of this disclosure, acquiring target signal data collected by a mobile signal acquisition device from a target area includes: acquiring target positioning accuracy and scene parameters of the target area; dividing the target area into multiple sub-areas based on the target positioning accuracy, and determining a target inventory mode based on the scene parameters; configuring the mobile signal acquisition device based on the target inventory mode and the sub-areas; and acquiring the target signal data, wherein the target signal data is acquired by the configured mobile signal acquisition device during inventory of the target area.

[0011] According to one embodiment of this disclosure, the scene parameters include tag density, the number of reference tags, and the positioning requirement level. Determining the target inventory mode based on the scene parameters includes: in response to the tag density being less than or equal to a first judgment threshold, the number of reference tags being less than or equal to a second judgment threshold, and the positioning requirement level being a large granularity level, determining the target inventory mode as a polling inventory mode, wherein the granularity of the large granularity level is greater than a granularity threshold; or, in response to the tag density being greater than the first judgment threshold, the number of reference tags being greater than the second judgment threshold, and the positioning requirement level being a small granularity level, determining the target inventory mode as an antenna concurrent inventory mode, wherein the granularity of the small granularity level is less than or equal to the granularity threshold.

[0012] According to one embodiment of this disclosure, generating initial regional feature data of the target region based on the target signal data includes: for any tag in the scanned target region, acquiring sub-acquisition data of the tag from the target signal data, and acquiring device information of the tag; determining the tag's RSSI volatility, RSSI change, phase flip correction, and phase-frequency slope based on the sub-acquisition data; generating the tag's feature vector based on the device information, RSSI volatility, RSSI change, phase flip correction, and phase-frequency slope; and generating the initial regional feature data based on the feature vectors of all tags in the target region.

[0013] According to one embodiment of this disclosure, the step of position-labeling the initial region feature data to obtain target region feature data includes: obtaining the tag position of the tag for the feature vector of any tag, and obtaining the antenna acquisition position of the mobile signal acquisition device when collecting sub-acquisition data of the tag; and position-labeling the initial region feature data based on the antenna acquisition position and the tag position to generate target region feature data.

[0014] According to one embodiment of this disclosure, updating the antenna position of the mobile signal acquisition device based on the target tag position includes: acquiring historical tag positions; determining a similarity value based on the historical tag positions and the target tag position; and adjusting the antenna of the mobile signal acquisition device based on the similarity value.

[0015] According to one embodiment of this disclosure, adjusting the antenna of the mobile signal acquisition device based on the similarity value includes: comparing the similarity value with a similarity threshold; and adjusting the antenna of the mobile signal acquisition device in response to the similarity value being greater than the similarity threshold.

[0016] According to one embodiment of this disclosure, adjusting the antenna of the mobile signal acquisition device includes: obtaining the true position of any tag in the scanned target area; calculating the positioning error of the tag based on the target tag position and the true position; and adjusting the antenna of the mobile signal acquisition device based on the positioning errors of all tags in the target area.

[0017] According to one embodiment of this disclosure, adjusting the antenna of the mobile signal acquisition device based on the positioning error of all tags in the target area includes: obtaining the area type of the target area; determining an antenna adjustment scheme based on the area type; and adjusting the antenna of the mobile signal acquisition device based on the antenna adjustment scheme.

[0018] According to one embodiment of this disclosure, the step of determining an antenna adjustment scheme based on the region type and adjusting the antenna of the mobile signal acquisition device based on the antenna adjustment scheme includes: in response to the region type being a small-scale region, randomly generating a candidate antenna position set; when the target region is arranged based on the candidate antenna position set, generating a predicted tag position using the tag position prediction model; determining an average error value corresponding to the candidate antenna position set based on the predicted tag position and the actual position; updating the candidate antenna position set based on a gradient descent algorithm and the average error value to generate an updated candidate antenna position set; repeating the above steps of generating the predicted tag position using the tag position prediction model and subsequent steps when the target region is arranged based on the candidate antenna position set, until the adjustment termination condition is met, outputting a target antenna position set, and adjusting the antenna of the mobile signal acquisition device based on the target antenna position set.

[0019] According to one embodiment of this disclosure, the step of determining an antenna adjustment scheme based on the region type and adjusting the antenna of the mobile signal acquisition device based on the antenna adjustment scheme includes: in response to the region type being a large-scale region, randomly generating multiple candidate antenna position sets, and generating a target population based on the multiple candidate antenna position sets; for any candidate antenna position set in the target population, when the target region is arranged based on the candidate antenna position set, generating a predicted tag position using the tag position prediction model; determining the average error value corresponding to the candidate antenna position set based on the predicted tag position and the actual position, and calculating the fitness value of the candidate antenna position set based on the average error value; updating the target population based on a genetic algorithm and the fitness value; repeating the above steps for any candidate antenna position set in the target population, when the target region is arranged based on the candidate antenna position set, generating a predicted tag position using the tag position prediction model and subsequent steps, until the update termination condition is met, outputting the target population, obtaining the target antenna position set in the target population, and adjusting the antenna of the mobile signal acquisition device based on the target antenna position set.

[0020] According to one embodiment of this disclosure, obtaining the target antenna location set in the target population includes: obtaining the average error value corresponding to each candidate antenna location set in the target population; and taking the candidate antenna location set with the smallest average error value as the target antenna location set.

[0021] To achieve the above objectives, a second aspect of this disclosure provides an antenna position update apparatus, comprising: an acquisition module for acquiring target signal data collected by a mobile signal acquisition device from a target area; a generation module for generating initial area feature data of the target area based on the target signal data; an annotation module for annotating the initial area feature data to obtain target area feature data; an input module for inputting the target area feature data into a tag position prediction model to generate a target tag position; and an update module for updating the antenna position of the mobile signal acquisition device based on the target tag position.

[0022] To achieve the above objectives, a third aspect of this disclosure provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to implement the antenna position update method as described in the first aspect of this disclosure.

[0023] To achieve the above objectives, a fourth aspect of this disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the antenna position update method as described in the first aspect of this disclosure.

[0024] To achieve the above objectives, a fifth aspect of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the antenna position update method as described in the first aspect of this disclosure.

[0025] This disclosure enables high-precision, adaptive tag positioning through a mobile signal acquisition device. It also constructs a "perception-optimization" closed loop to achieve dynamic tuning of antenna deployment, improve system robustness, and adapt to complex dynamic environments. Compared with the current technology of manually adjusting antennas, it can greatly improve the accuracy and efficiency of antenna adjustment. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of an antenna position update method according to one embodiment of the present disclosure; Figure 2 This is a schematic diagram of another antenna position update method according to one embodiment of the present disclosure; Figure 3 This is a schematic diagram of another antenna position update method according to one embodiment of the present disclosure; Figure 4 This is a schematic diagram of another antenna position update method according to one embodiment of the present disclosure; Figure 5 This is a schematic diagram of another antenna position update method according to one embodiment of the present disclosure; Figure 6 This is a schematic diagram of an antenna position updating device according to one embodiment of the present disclosure; Figure 7 This is a schematic diagram of an electronic device according to one embodiment of the present disclosure. Detailed Implementation

[0027] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0028] The acquisition, storage, use, and processing of data in this disclosed technical solution all comply with the relevant provisions of relevant laws and regulations.

[0029] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0030] Current antenna deployment methods typically rely on manual experience. To achieve optimal positioning, the antenna position needs to be repeatedly adjusted manually. This adjustment method has the following problems: 1. Reliance on human experience, resulting in low efficiency: Antenna deployment locations are usually designed manually, and repeated manual adjustments are required to achieve the best positioning effect, which is labor-intensive and makes it difficult to guarantee the overall optimal result.

[0031] 2. Poor adaptability and high maintenance costs: When the display of target labels (quantity, location, density) changes, manual deployment is required again, and it cannot be adapted and adjusted quickly.

[0032] 3. Limited features and insufficient model generalization: The localization model needs to model the channel-location mapping relationship with diversified features, but the channel features obtained by antennas with fixed positions and numbers are limited, and it lacks the ability to dynamically expand the signal features under hardware constraints.

[0033] To address the aforementioned problems, this disclosure proposes an antenna position update method. Figure 1 This is a schematic diagram of an antenna position update method according to one embodiment of the present disclosure, as shown below. Figure 1 As shown, the antenna position update method includes the following steps: S101, acquire target signal data collected by the mobile signal acquisition device in the target area.

[0034] The antenna position update method of this application embodiment can be applied to the scenario of automated tag inventory. The execution subject of the antenna position update in this application embodiment can be the antenna position update device of this application embodiment, which can be installed on an electronic device.

[0035] It should be noted that the mobile signal acquisition device in this embodiment consists of a movable signal acquisition device (such as a rail-mounted mobile platform with an antenna) and a control unit, used to acquire reflected signals from passive tags at a preset initial position within the target area. The movable device supports autonomous movement along a grid path to achieve multi-location signal acquisition; the control unit can configure inventory parameters and switch inventory modes.

[0036] It should be noted that the mobile signal acquisition device is equipped with an antenna for transmitting radio frequency signals and receiving reflected signals from passive radio frequency identification (RFID) tags.

[0037] The mobile signal acquisition device in this embodiment may be multiple, and each mobile signal acquisition device may have multiple antennas, which can be specifically limited according to actual design needs.

[0038] The position of the antenna (including its height, angle, distance from the tag, and orientation) directly affects signal strength, read rate, and positioning accuracy. Therefore, adjusting the antenna position can improve the tag's reading efficiency and accuracy.

[0039] It should be noted that the rules for determining the type and size of the target area are not limited here and can be determined according to actual design needs or actual signal acquisition scenarios. In this embodiment, the mobile signal acquisition device can be set according to actual inventory requirements. For example, if the area to be inventoried is a specific area of ​​a warehouse, then that specific area can be set as the target area in the mobile signal acquisition device, and the mobile signal acquisition device will only perform inventory operations on that specific area.

[0040] It should be noted that target signal data may include a variety of data, without any limitation here. For example, target signal data may include antenna location, tag location, port number, device number, acquisition timestamp, etc.

[0041] S102, Generate initial regional feature data of the target area based on the target signal data.

[0042] In this embodiment of the disclosure, the initial regional feature data of the target area generated based on the target signal data is used to transform the original collected tag signal data into a structured feature model that can characterize the physical space characteristics, providing a basis for subsequent positioning, classification and optimization.

[0043] It should be noted that there are various methods for generating initial regional feature data of the target area based on the target signal data, and no limitation is made here.

[0044] In one possible implementation, the target signal data can be calculated using a pre-defined data generation algorithm to generate initial regional feature data.

[0045] In another possible implementation, the target signal data can be processed using a pre-trained initial region feature data generation model to generate initial region feature data. This initial region feature data generation model is pre-trained and can be stored in the storage space of an electronic device for easy retrieval when needed.

[0046] In this embodiment of the disclosure, before processing the target signal data, the target signal data can be preprocessed to transform the raw RFID signal into clean, structured feature data with spatial semantics, laying a solid foundation for subsequent intelligent analysis, precise positioning and global optimization.

[0047] It should be noted that preprocessing can take many forms, and no specific limitations are made here. For example, preprocessing may include data cleaning, data completion, and normalization.

[0048] S103, mark the location of the initial region feature data to obtain the target region feature data.

[0049] It should be noted that the target area feature data assigns its corresponding physical coordinates to each initial area feature data, establishing a mapping relationship between "signal features and physical location".

[0050] By establishing target area feature data, a mapping relationship of "a certain combination of signal features → a corresponding physical location" can be established, providing a data foundation for subsequent automatic positioning and data tracing.

[0051] S104. Input the target region feature data into the label location prediction model to generate the target label location.

[0052] It should be noted that the label location prediction model in this embodiment is a pre-trained model used to predict the target label location based on the target region feature data.

[0053] Tag location prediction models can be stored in the storage space of electronic devices for easy retrieval when needed.

[0054] In this embodiment, a mapping model can be trained to learn the feature propagation patterns from antennas at different locations to the actual tag location, providing predictive capabilities for subsequent active sampling and location optimization. This solution can employ various deep learning models, including but not limited to fully connected neural networks and transformer network architectures. The network input is a feature vector and antenna position, and the output is the predicted tag location. By minimizing the error between the predicted and actual tag locations, the network parameters are optimized, iterating until the model converges to generate the final tag location prediction model.

[0055] S105, update the antenna position of the mobile signal acquisition device based on the target tag position.

[0056] It should be noted that there are various methods for updating the antenna position of the mobile signal acquisition device based on the target tag location, and no limitation is made here. For example, the target tag position can be processed according to a preset position update rule to determine the optimal position of the mobile signal acquisition device.

[0057] In this embodiment, target signal data collected by the mobile signal acquisition device from the target area is first acquired. Then, initial area feature data of the target area is generated based on the target signal data. Next, the initial area feature data is labeled with its location to obtain target area feature data. Then, the target area feature data is input into the tag location prediction model to generate the target tag location. Finally, the antenna position of the mobile signal acquisition device is updated based on the target tag location. Therefore, this disclosure enables high-precision, adaptive tag positioning through the mobile signal acquisition device. Simultaneously, it constructs a "perception-optimization" closed loop to achieve dynamic tuning of antenna deployment, improve system robustness, and adapt to complex dynamic environments. Compared to the current method of manual antenna adjustment, this significantly improves the accuracy and efficiency of antenna adjustment.

[0058] In the above embodiments, the target signal data collected by the mobile signal acquisition device in the target area can also be obtained through... Figure 2 To further explain, the method includes: S201, obtain the target positioning accuracy and scene parameters of the target area.

[0059] It should be noted that the target positioning accuracy refers to the expected positioning error range. The target positioning accuracy determines the mesh granularity; for example, higher accuracy results in a smaller mesh. It also determines whether to enable the high complexity mode.

[0060] The target positioning accuracy can be set according to the actual design needs. For example, the target positioning accuracy at the regional level can be ±2m (warehouse zoning), the target positioning accuracy at the shelf level can be ±0.5m (store merchandise positioning), and the target positioning accuracy at the centimeter level can be ±10cm (high-value assets).

[0061] Scene parameters can include a variety of data, without any limitations here. For example, they can include tag density, number of reference tags, area, shape, distribution of occlusions, and whether there is metal / liquid interference.

[0062] S202, the target area is divided into multiple sub-areas based on the target positioning accuracy, and the target inventory mode is determined based on the scene parameters.

[0063] In this embodiment of the disclosure, the target area is divided into a grid according to the positioning accuracy requirements: [ ] represents rounding up, N is the number of grids, sets the initial position (grid vertices) number, and the movable antenna moves sequentially.

[0064] In this embodiment of the disclosure, the target inventory mode can be determined based on scene parameters according to preset rules.

[0065] In one possible implementation, in response to the tag density being less than or equal to a first judgment threshold, the number of reference tags being less than or equal to a second judgment threshold, and the positioning requirement level being large granularity, the target inventory mode is determined to be a polling inventory mode, wherein the granularity of the large granularity level is greater than the granularity threshold.

[0066] Alternatively, in response to a tag density greater than the first judgment threshold, a reference tag number greater than the second judgment threshold, and a positioning requirement level of small granularity, the target inventory mode is determined to be the antenna concurrent inventory mode, wherein the granularity of the small granularity level is less than or equal to the granularity threshold.

[0067] In another possible implementation, when the target area is a large and complex scenario, or when the current inventory requirement is a combination of multiple positioning services, a combination of the above two methods can be used, alternating between polling inventory mode and antenna concurrent inventory mode.

[0068] It should be noted that the first judgment threshold, the second judgment threshold, and the granularity threshold are pre-designed and can be changed according to actual design needs; no restrictions are imposed here.

[0069] S203, configures the mobile signal acquisition device based on the target inventory mode and sub-region.

[0070] S204, Acquire target signal data. The target signal data is acquired by the configured mobile signal acquisition device by taking stock of the target area.

[0071] In this embodiment, the target positioning accuracy and scene parameters of the target area are first obtained. Then, the target area is divided into multiple sub-areas based on the target positioning accuracy, and the target inventory mode is determined based on the scene parameters. Next, the mobile signal acquisition device is configured based on the target inventory mode and the sub-areas. Finally, target signal data is acquired, which is obtained by the configured mobile signal acquisition device during the inventory of the target area. Therefore, based on adaptive configuration of accuracy and scene, on-demand positioning can be achieved, avoiding resource waste, while improving system flexibility and versatility, and optimizing inventory efficiency.

[0072] In the above embodiments, initial regional feature data of the target region is generated based on the target signal data, and can also be generated through... Figure 3 To further explain, the method includes: S301, for any tag in the scanned target area, acquires the tag's sub-collection data from the target signal data minute, and obtains the tag's device information.

[0073] S302 determines the tag's RSSI volatility, RSSI change, phase reversal correction, and phase-frequency slope based on the sub-acquisition data.

[0074] It should be noted that RSSI volatility refers to the magnitude of change in Received Signal Strength Indication (RSSI) per unit time, usually measured by standard deviation or range. Experiments show that RSSI fluctuates linearly with distance during lateral movement.

[0075] The change in RSSI represents the amount of change in the absolute value of RSSI.

[0076] Phase flipping occurs when the tag and reader antenna are in certain relative positions. Due to the polarization characteristics of electromagnetic waves, the phase of the received signal may undergo a sudden change of π. Phase correction is required. By obtaining phase flip correction, the phase jump can be eliminated and the true distance can be restored.

[0077] The phase-frequency slope describes the linear relationship between phase and frequency changes. In RFID, when a tag is moved uniformly, the phase value changes linearly with distance, and the slope reflects the signal characteristics.

[0078] In this embodiment of the disclosure, the RSSI volatility, RSSI change, phase reversal correction, and phase-frequency slope of the tag, determined based on sub-acquisition data, can be determined by the following formula: RSSI volatility: For each label, calculate the standard deviation of the RSSI over a fixed time window. , where n is the number of samples taken within the time window.

[0079] RSSI Change: For each tag, calculate the change in the average RSSI as the antenna moves one grid vertex (A->B). .

[0080] Phase wrapping correction: For each tag, if the initial phase and the ending phase are in the range (180, 360), subtract 180.

[0081] Phase-frequency slope: For each label, calculate the average of the initial and final phases at different frequency points, fit a straight line between the frequency point and the corresponding phase mean, and record the slope of the line. .

[0082] S303 generates feature vectors for tags based on device information, RSSI volatility, RSSI change, phase reversal correction, and phase-frequency slope, and generates initial regional feature data based on the feature vectors of all tags in the target region.

[0083] In this embodiment, firstly, for any tag in the scanned target area, sub-acquisition data of the tag is obtained from the target signal data, and the tag's device information is acquired. Then, based on the sub-acquisition data, the tag's RSSI volatility, RSSI change, phase flip correction, and phase-frequency slope are determined. Finally, based on the device information, RSSI volatility, RSSI change, phase flip correction, and phase-frequency slope, a feature vector of the tag is generated. Based on the feature vectors of all tags in the target area, initial area feature data is generated. Therefore, compared to the current technology that only uses the magnitude of RSSI positioning error for calibration, this solution, by establishing feature vectors for the tags, has stronger spatial sensitivity, generates structured initial area feature data, and supports subsequent intelligent processing.

[0084] In the above embodiments, the initial region feature data is marked with positions to obtain the target region feature data. First, for the feature vector of any tag, the tag position of the tag is obtained, and when the sub-collection data of the tag is collected, the antenna collection position of the mobile signal acquisition device is obtained. Then, the initial region feature data is marked with positions based on the antenna collection position and the tag position to generate the target region feature data.

[0085] In the above embodiments, the antenna position of the mobile signal acquisition device is updated based on the target tag position, and can also be updated by... Figure 4 To further explain, the method includes: S401, Get historical tag positions.

[0086] In this embodiment of the disclosure, the historical tag location can be obtained by calling the historical feature library.

[0087] S402, determine the similarity value based on the historical tag position and the target tag position.

[0088] In one possible implementation, the similarity value can be calculated by measuring the Jensen-Shannon Divergence (JS divergence) between the historical tag location set and the target tag location set. The JS divergence is a metric that measures the degree of similarity between two probability distributions. The historical tag location set is the set of historical tag locations, and the target tag location set is the set of target tag locations.

[0089] S403, Adjust the antenna of the mobile signal acquisition device based on the similarity value.

[0090] In this embodiment of the disclosure, a similarity value can be compared with a similarity threshold, and the antenna of the mobile signal acquisition device can be adjusted in response to the similarity value being greater than the similarity threshold.

[0091] It should be noted that the similarity threshold is a critical value for determining whether the conditions for adjusting the antenna of the mobile signal acquisition device are met. The similarity threshold can be changed according to actual design needs, and no restrictions are imposed here.

[0092] In the above embodiments, the antenna of the mobile signal acquisition device can also be adjusted by... Figure 5 To further explain, the method includes: S501, obtain the region type of the target region.

[0093] S502 determines the antenna adjustment scheme based on the area type, and adjusts the antenna of the mobile signal acquisition device based on the antenna adjustment scheme.

[0094] In this embodiment, the area type can be divided into small-scale areas and large-scale areas, and the specific division rules can be various, without any limitation here. For example, the area can be divided according to the actual area of ​​the target area, or according to the actual inventory area of ​​the target area, without any limitation here.

[0095] In this embodiment of the disclosure, in response to the region type being a small-scale region, a candidate antenna position set is randomly generated. Then, with the target region arranged based on the candidate antenna position set, the predicted tag position is generated by the tag position prediction model. Then, based on the predicted tag position and the actual position, the average error value corresponding to the candidate antenna position set is determined. Then, the candidate antenna position set is updated based on the gradient descent algorithm and the average error value to generate an updated candidate antenna position set. The above steps of generating the predicted tag position by the tag position prediction model and subsequent steps with the target region arranged based on the candidate antenna position set are repeated until the end adjustment condition is met, the target antenna position set is output, and the antenna of the mobile signal acquisition device is adjusted based on the target antenna position set.

[0096] It should be noted that the conditions for ending the adjustment are pre-designed and can be changed according to actual design needs; no restrictions are imposed here.

[0097] In one possible implementation, the gradient descent algorithm can be calculated using the following formula: (1) Randomly initialize a set of candidate antenna locations. Calculate the objective function .

[0098] It should be noted that the objective function for M is the number of tags. For the actual location, To predict the label location.

[0099] (2) Calculate the objective function Gradient of S (i.e., the coordinates of each antenna) This gradient indicates which direction the antenna position should be adjusted to reduce the error the fastest; (3) Update antenna position ,in The learning rate; (4) Repeat steps (1)-(3) until If the change is less than a preset threshold or the maximum number of iterations is reached, the output S is the set of target antenna positions.

[0100] In this embodiment of the disclosure, in response to the region type being a large-scale region, multiple candidate antenna position sets are randomly generated, and a target population is generated based on these candidate antenna position sets. For any candidate antenna position set in the target population, when the target region is arranged based on the candidate antenna position set, a predicted tag position is generated by a tag position prediction model. Then, based on the predicted tag position and the actual position, the average error value corresponding to the candidate antenna position set is determined, and the fitness value of the candidate antenna position set is calculated based on the average error value. Subsequently, the target population is updated based on a genetic algorithm and the fitness value. The above process of generating the predicted tag position by a tag position prediction model and subsequent steps for any candidate antenna position set in the target population, when the target region is arranged based on the candidate antenna position set, is repeated until the update termination condition is met. The target population is then output, and the target antenna position set in the target population is obtained. The antenna of the mobile signal acquisition device is adjusted based on the target antenna position set.

[0101] It should be noted that the update termination condition is pre-designed and can be changed according to actual design needs; no restrictions are imposed here.

[0102] It should be noted that the target antenna position set in the target population can be determined based on the average error value. In one possible implementation, the average error value corresponding to each candidate antenna position set in the target population can be obtained, and then the candidate antenna position set with the smallest average error value can be used as the target antenna position set.

[0103] In one possible implementation, the genetic algorithm can be calculated using the following formula: (1) Randomly generate a set of N candidate antenna locations This constitutes the initial population; (2) Calculate the fitness of each candidate antenna location set. The smaller the positioning error, the higher the adaptability; (3) Select schemes with higher fitness scores from the current population, randomly swap some of their antenna position coordinates, or randomly change the coordinates of some antennas to form a new population; Repeat steps (2)-(3) until the maximum number of generations is reached or the fitness tends to stabilize. Finally, the optimal antenna deployment scheme is S, which has the highest fitness among all generations of the population.

[0104] Corresponding to the antenna position update methods provided in the above embodiments, an embodiment of this disclosure also provides an antenna position update device. Since the antenna position update device provided in this disclosure corresponds to the antenna position update methods provided in the above embodiments, the implementation methods of the above antenna position update methods are also applicable to the antenna position update device provided in this disclosure, and will not be described in detail in the following embodiments.

[0105] Figure 6 Figure 6 is a schematic diagram of an antenna position update device according to one embodiment of the present disclosure. As shown in Figure 6, the antenna position update device 600 includes: an acquisition module 610, a generation module 620, a labeling module 630, an input module 640, and an update module 650.

[0106] The acquisition module 610 is used to acquire target signal data collected by the mobile signal acquisition device from the target area; Generation module 620 is used to generate initial regional feature data of the target area based on the target signal data; The annotation module 630 is used to annotate the initial region feature data to obtain the target region feature data; The input module 640 is used to input the target region feature data into the label location prediction model to generate the target label location; The update module 650 is used to update the antenna position of the mobile signal acquisition device based on the target tag position.

[0107] According to one embodiment of this disclosure, acquiring target signal data collected by a mobile signal acquisition device from a target area includes: acquiring target positioning accuracy and scene parameters of the target area; dividing the target area into multiple sub-areas based on the target positioning accuracy, and determining a target inventory mode based on the scene parameters; configuring the mobile signal acquisition device based on the target inventory mode and the sub-areas; and acquiring target signal data, wherein the target signal data is acquired by the configured mobile signal acquisition device during inventory of the target area.

[0108] According to one embodiment of this disclosure, the scene parameters include tag density, the number of reference tags, and the positioning requirement level. Determining the target inventory mode based on the scene parameters includes: in response to a tag density less than or equal to a first judgment threshold, a reference tag number less than or equal to a second judgment threshold, and a positioning requirement level of large granularity, determining the target inventory mode as a polling inventory mode, wherein the granularity of the large granularity level is greater than the granularity threshold; or, in response to a tag density greater than the first judgment threshold, a reference tag number greater than the second judgment threshold, and a positioning requirement level of small granularity, determining the target inventory mode as an antenna concurrent inventory mode, wherein the granularity of the small granularity level is less than or equal to the granularity threshold.

[0109] According to one embodiment of this disclosure, generating initial regional feature data of a target area based on target signal data includes: for any tag in the scanned target area, acquiring sub-acquisition data of the tag from the target signal data and acquiring the tag's device information; determining the tag's RSSI volatility, RSSI change, phase reversal correction, and phase-frequency slope based on the sub-acquisition data; generating the tag's feature vector based on the device information, RSSI volatility, RSSI change, phase reversal correction, and phase-frequency slope; and generating initial regional feature data based on the feature vectors of all tags in the target area.

[0110] According to one embodiment of this disclosure, initial region feature data is labeled with location to obtain target region feature data, including: obtaining the tag position of the tag for the feature vector of any tag, and obtaining the antenna acquisition position of the mobile signal acquisition device when acquiring sub-acquisition data of the tag; and labeling the initial region feature data with location based on the antenna acquisition position and the tag position to generate target region feature data.

[0111] According to one embodiment of this disclosure, updating the antenna position of a mobile signal acquisition device based on the target tag position includes: acquiring historical tag positions; determining a similarity value based on the historical tag positions and the target tag position; and adjusting the antenna of the mobile signal acquisition device based on the similarity value.

[0112] According to one embodiment of the present disclosure, adjusting the antenna of a mobile signal acquisition device based on a similarity value includes: comparing the similarity value with a similarity threshold; and adjusting the antenna of the mobile signal acquisition device in response to a similarity value being greater than the similarity threshold.

[0113] According to one embodiment of this disclosure, adjusting the antenna of a mobile signal acquisition device includes: acquiring the true position of any tag in a scanned target area; calculating the positioning error of the tag based on the target tag position and the true position; and adjusting the antenna of the mobile signal acquisition device based on the positioning errors of all tags in the target area.

[0114] According to one embodiment of this disclosure, adjusting the antenna of a mobile signal acquisition device based on the positioning error of all tags in a target area includes: obtaining the area type of the target area; determining an antenna adjustment scheme based on the area type; and adjusting the antenna of the mobile signal acquisition device based on the antenna adjustment scheme.

[0115] According to one embodiment of this disclosure, an antenna adjustment scheme is determined based on the region type, and the antenna of a mobile signal acquisition device is adjusted based on the antenna adjustment scheme, including: in response to the region type being a small-scale region, a candidate antenna position set is randomly generated; when the target region is arranged based on the candidate antenna position set, a predicted tag position is generated by a tag position prediction model; the average error value corresponding to the candidate antenna position set is determined based on the predicted tag position and the actual position; the candidate antenna position set is updated based on a gradient descent algorithm and the average error value to generate an updated candidate antenna position set; the above steps of generating the predicted tag position by a tag position prediction model and subsequent steps when the target region is arranged based on the candidate antenna position set are repeated until the adjustment termination condition is met, the target antenna position set is output, and the antenna of the mobile signal acquisition device is adjusted based on the target antenna position set.

[0116] According to one embodiment of this disclosure, an antenna adjustment scheme is determined based on the region type, and the antenna of a mobile signal acquisition device is adjusted based on the antenna adjustment scheme. This includes: in response to the region type being a large-scale region, randomly generating multiple candidate antenna position sets, and generating a target population based on the multiple candidate antenna position sets; for any candidate antenna position set in the target population, predicting tag positions using a tag position prediction model when the target region is arranged based on the candidate antenna position sets; determining the average error value corresponding to the candidate antenna position set based on the predicted tag position and the actual position, and calculating the fitness value of the candidate antenna position set based on the average error value; updating the target population based on a genetic algorithm and the fitness value; repeating the above steps for any candidate antenna position set in the target population, predicting tag positions using a tag position prediction model when the target region is arranged based on the candidate antenna position sets, and subsequent steps, until the update termination condition is met, outputting the target population, obtaining the target antenna position set in the target population, and adjusting the antenna of the mobile signal acquisition device based on the target antenna position set.

[0117] According to one embodiment of this disclosure, obtaining the target antenna location set in the target population includes: obtaining the average error value corresponding to each candidate antenna location set in the target population; and taking the candidate antenna location set with the smallest average error value as the target antenna location set.

[0118] This disclosure enables high-precision, adaptive tag positioning through a mobile signal acquisition device. It also constructs a "perception-optimization" closed loop to achieve dynamic tuning of antenna deployment, improve system robustness, and adapt to complex dynamic environments. Compared with the current technology of manually adjusting antennas, it can greatly improve the accuracy and efficiency of antenna adjustment.

[0119] To implement the above embodiments, this disclosure also proposes an electronic device 700. Figure 7 This is a schematic diagram of an electronic device according to one embodiment of the present disclosure, such as... Figure 7 As shown, the electronic device 700 includes: a processor 701 and a memory 702 communicatively connected to the processor. The memory 702 stores instructions executable by at least one processor. The instructions are executed by at least one processor 701 to implement the functions described in this disclosure. Figures 1-5 Antenna position update method of the embodiment.

[0120] To implement the above embodiments, this disclosure also proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to implement the present disclosure. Figures 1-5 Antenna position update method of the embodiment.

[0121] To implement the above embodiments, this disclosure also proposes a computer program product, including a computer program, which, when executed by a processor, implements the features of this disclosure. Figures 1-5 Antenna position update method of the embodiment.

[0122] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0123] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0124] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0125] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0126] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0127] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that contains, stores, communicates, propagates, or transmits programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0128] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0129] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0130] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0131] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. An antenna position update method, characterized in that, include: Acquire target signal data collected by the mobile signal acquisition device in the target area; Initial regional feature data of the target region is generated based on the target signal data; The initial region feature data is labeled with locations to obtain the target region feature data; The target region feature data is input into the label location prediction model to generate the target label location; The antenna position of the mobile signal acquisition device is updated based on the target tag location.

2. The method according to claim 1, characterized in that, The acquisition of target signal data collected by the mobile signal acquisition device in the target area includes: Obtain the target positioning accuracy and scene parameters of the target area; Based on the target positioning accuracy, the target area is divided into multiple sub-areas, and the target inventory mode is determined based on the scene parameters; Configure the mobile signal acquisition device based on the target inventory pattern and the sub-region; The target signal data is acquired by the configured mobile signal acquisition device by taking stock of the target area.

3. The method according to claim 2, characterized in that, The scene parameters include tag density, number of reference tags, and positioning requirement level. Determining the target inventory mode based on the scene parameters includes: In response to the tag density being less than or equal to a first judgment threshold, the number of reference tags being less than or equal to a second judgment threshold, and the positioning requirement level being a large granularity level, the target inventory mode is determined to be a polling inventory mode, wherein the granularity of the large granularity level is greater than the granularity threshold; or, In response to the tag density being greater than the first judgment threshold, the number of reference tags being greater than the second judgment threshold, and the positioning requirement level being small granularity, the target inventory mode is determined to be the antenna concurrent inventory mode, wherein the granularity of the small granularity level is less than or equal to the granularity threshold.

4. The method according to any one of claims 1-3, characterized in that, The process of generating initial regional feature data for the target region based on the target signal data includes: For any tag in the scanned target area, sub-collection data of the tag is obtained from the target signal data minute, and the device information of the tag is obtained; Based on the sub-acquisition data, determine the tag's RSSI volatility, RSSI change, phase flip correction, and phase-frequency slope; Based on the device information, RSSI volatility, RSSI change, phase flip correction, and phase-frequency slope, the feature vector of the tag is generated, and based on the feature vectors of all tags in the target area, the initial area feature data is generated.

5. The method according to claim 4, characterized in that, The step of labeling the initial region feature data to obtain the target region feature data includes: For any tag's feature vector, obtain the tag's location, and obtain the antenna acquisition location of the mobile signal acquisition device when collecting sub-acquisition data of the tag; Based on the antenna acquisition location and the tag location, the initial area feature data is labeled to generate target area feature data.

6. The method according to claim 1, characterized in that, The step of updating the antenna position of the mobile signal acquisition device based on the target tag position includes: Get historical tag locations; A similarity value is determined based on the historical tag location and the target tag location; The antenna of the mobile signal acquisition device is adjusted based on the similarity value.

7. The method according to claim 6, characterized in that, The adjustment of the antenna of the mobile signal acquisition device based on the similarity value includes: The similarity value is compared with a similarity threshold; In response to the similarity value being greater than the similarity threshold, the antenna of the mobile signal acquisition device is adjusted.

8. The method according to claim 7, characterized in that, The adjustment of the antenna of the mobile signal acquisition device includes: For any tag in the scanned target area, obtain the true location of the tag; The positioning error of the tag is calculated based on the target tag position and the actual position of the tag; The antenna of the mobile signal acquisition device is adjusted based on the positioning error of all tags in the target area.

9. The method according to claim 8, characterized in that, The adjustment of the antenna of the mobile signal acquisition device based on the positioning error of all tags in the target area includes: Obtain the region type of the target region; An antenna adjustment scheme is determined based on the region type, and the antenna of the mobile signal acquisition device is adjusted based on the antenna adjustment scheme.

10. The method according to claim 9, characterized in that, The step of determining an antenna adjustment scheme based on the region type and adjusting the antenna of the mobile signal acquisition device based on the antenna adjustment scheme includes: In response to the region type being a small-scale region, a set of candidate antenna locations is randomly generated; When the target area is arranged based on the set of candidate antenna locations, the predicted tag location is generated by the tag location prediction model. The average error value corresponding to the candidate antenna location set is determined based on the predicted tag location and the actual location. The candidate antenna location set is updated based on the gradient descent algorithm and the average error value to generate an updated candidate antenna location set. Repeat the above steps, which involve generating the predicted tag position using the tag position prediction model and subsequent steps, based on the candidate antenna position set in the target area, until the adjustment end condition is met. Output the target antenna position set and adjust the antenna of the mobile signal acquisition device based on the target antenna position set.

11. The method according to claim 9, characterized in that, The step of determining an antenna adjustment scheme based on the region type and adjusting the antenna of the mobile signal acquisition device based on the antenna adjustment scheme includes: In response to the region type being a large-scale region, multiple candidate antenna location sets are randomly generated, and a target population is generated based on the multiple candidate antenna location sets; For any set of candidate antenna locations in the target population, and given that the target area is arranged based on the set of candidate antenna locations, the predicted tag location is generated by the tag location prediction model. The average error value corresponding to the candidate antenna location set is determined based on the predicted tag location and the actual location, and the fitness value of the candidate antenna location set is calculated based on the average error value. The target population is updated based on the genetic algorithm and the fitness value; Repeat the above steps for any candidate antenna location set in the target population. When the target area is arranged based on the candidate antenna location set, use the predicted tag location generated by the tag location prediction model and subsequent steps until the update termination condition is met. Output the target population and obtain the target antenna location set in the target population. Adjust the antenna of the mobile signal acquisition device based on the target antenna location set.

12. The method according to claim 11, characterized in that, The step of obtaining the set of target antenna locations in the target population includes: Obtain the average error value corresponding to each candidate antenna position set in the target population; The set of candidate antenna positions with the smallest average error value is taken as the target antenna position set.

13. An antenna position updating device, characterized in that, include: The acquisition module is used to acquire target signal data collected by the mobile signal acquisition device from the target area; The generation module is used to generate initial regional feature data of the target region based on the target signal data; The annotation module is used to annotate the initial region feature data to obtain the target region feature data; The input module is used to input the feature data of the target region into the label location prediction model to generate the target label location; The update module is used to update the antenna position of the mobile signal acquisition device based on the target tag position.

14. An electronic device, characterized in that, Including memory and processor; The processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the method as described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-12.

Images