Method and device for determining electromagnetic field intensity of interferent, terminal equipment and storage medium

Abstract

The invention discloses a method and device for determining the electromagnetic field intensity of an interferent, terminal equipment and a storage medium, and relates to the technical field of electromagnetic field measurement, and the method comprises the steps: collecting the point cloud data of a target region; determining interference characteristic data of an interferent in the target area according to the point cloud data; inputting the interference characteristic data into a pre-trained quantum neural network, and determining an interference coefficient corresponding to the interference characteristic data according to the quantum neural network; and determining the final electromagnetic field intensity of the interferent according to the interference coefficient and the original electromagnetic field data of the interferent. According to the invention, the point cloud data of the target area is collected to distinguish different object types and interference distances of the interferent, the influence of the object types and the interference distances on the electromagnetic field intensity is considered, the interference characteristic data is input into the pre-trained quantum neural network to output the interference coefficient, and the electromagnetic field of the interferent is determined. And the accuracy of determining the electromagnetic field intensity of the interferent is effectively improved.

Description

A method, apparatus, terminal equipment, and storage medium for determining the electromagnetic field strength of an interfering object. Technical Field

[0001] This invention relates to the field of electromagnetic field measurement technology, and in particular to a method, apparatus, terminal device, and storage medium for determining the electromagnetic field strength of an interfering object. Background Technology

[0002] With the continuous development of power systems, communication networks, and industrial automation, accurately determining the electromagnetic field strength of interfering objects is crucial for ensuring system safety, improving measurement accuracy, and optimizing equipment layout. For example, in power systems, metal structures and buildings near high-voltage transmission lines can cause electromagnetic field distortion. Accurately measuring the electromagnetic field strength of these objects helps assess their impact on power equipment and the surrounding environment, thereby enabling the implementation of effective protective measures.

[0003] Existing methods for determining the electromagnetic field strength of interfering objects typically utilize electric field probes and magnetic field coils, outputting electric and magnetic field strengths through direct sampling and conversion circuits. However, these methods do not consider the influence of the interference characteristic data of the interfering objects within the target area on the electromagnetic field strength, making it difficult to accurately determine the electromagnetic field strength of the interfering objects. Summary of the Invention

[0004] This invention provides a method, apparatus, terminal device, and storage medium for determining the electromagnetic field strength of an interfering object. It can solve the technical problem in the prior art that the electric field strength and magnetic field strength are output by directly sampling and converting the electric field and magnetic field strength through an electric field probe and a magnetic field coil without considering the influence of the interference characteristic data of the interfering object in the target area on the electromagnetic field strength, which makes it difficult to accurately determine the electromagnetic field strength of the interfering object.

[0005] This invention provides a method for determining the electromagnetic field strength of an interfering object, comprising: acquiring point cloud data of a target area; determining interference feature data of an interfering object within the target area based on the point cloud data, wherein the interference feature data includes an object type code of the interfering object and an interference distance from the interfering object to a measurement point; inputting the interference feature data into a pre-trained quantum neural network, determining an interference coefficient corresponding to the interference feature data based on the quantum neural network; and determining the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object.

[0006] Furthermore, determining the interference feature data of the interfering object within the target area based on the point cloud data includes: determining the reflection intensity and shape features of the interfering object based on the point cloud data; determining the object type of the interfering object based on the reflection intensity and the shape features; determining the corresponding object type code based on the object type; determining the size of the interfering object based on the shape features; determining the distance calculation point based on the size of the interfering object; and using the distance calculated from the measurement point as the interference distance.

[0007] Furthermore, the training of the quantum neural network includes: setting multiple distance gradients; determining multiple sets of training samples based on various types of interfering objects, multiple distance gradients, and the true coefficients of the interfering objects; initializing the rotation angles of the three quantum rotation gates in the quantum neural network and setting the learning rate; using each set of training samples as an input vector, mapping the input features to a quantum state using the quantum rotation gate, evolving the quantum state using the quantum rotation gate to obtain an evolved quantum state, determining the predicted interference coefficient value corresponding to each set of training samples by measuring the probability amplitude of the evolved quantum state; constructing a loss function based on the predicted interference coefficient value, iteratively optimizing the loss function, the rotation angle of the quantum rotation gate, and the learning rate, and completing the training of the quantum neural network when preset conditions are met.

[0008] Furthermore, the step of inputting the interference feature data into a pre-trained quantum neural network and determining the interference coefficient corresponding to the interference feature data based on the quantum neural network includes: using three quantum rotation gates in the quantum hidden layer of the quantum neural network to map the input features into quantum states, using the quantum rotation gates to evolve the quantum states to obtain evolved quantum states, and measuring the interference coefficient of the evolved quantum states.

[0009] Furthermore, determining the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object includes: acquiring the original electromagnetic field strength data of the interfering object; obtaining the reference electromagnetic field data of the target area; determining the initial compensation electromagnetic field strength based on the interference coefficient, the original electromagnetic field strength data, and the interference distance; determining the electromagnetic field error based on the initial compensation electromagnetic field strength and the reference electromagnetic field strength; when the electromagnetic field error is less than a preset threshold, using the initial compensation electromagnetic field strength as the final electromagnetic field strength; when the electromagnetic field error is greater than or equal to the preset threshold, adjusting the parameters in the quantum neural network with a preset step size until the electromagnetic field error is less than the preset threshold, and using the current initial compensation electromagnetic field strength as the final electromagnetic field strength.

[0010] Furthermore, before determining the reflection intensity and shape characteristics of the interfering object based on the point cloud data, determining the object type of the interfering object based on the reflection intensity and the shape characteristics, and determining the corresponding object type code based on the object type, the method further includes: preprocessing the point cloud data, wherein the preprocessing includes denoising processing and downsampling processing.

[0011] The present invention also provides a device for determining the electromagnetic field strength of an interfering object, comprising: a point cloud data acquisition module for acquiring point cloud data of a target area; an interference feature data determination module for determining interference feature data of an interfering object within the target area based on the point cloud data, wherein the interference feature data includes an object type code of the interfering object and an interference distance from the interfering object to a measurement point; an interference coefficient determination module for inputting the interference feature data into a pre-trained quantum neural network and determining the interference coefficient corresponding to the interference feature data based on the quantum neural network; and an electromagnetic field strength determination module for determining the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object.

[0012] Furthermore, determining the interference feature data of the interfering object within the target area based on the point cloud data includes: determining the reflection intensity and shape features of the interfering object based on the point cloud data; determining the object type of the interfering object based on the reflection intensity and the shape features; determining the corresponding object type code based on the object type; determining the size of the interfering object based on the shape features; determining the distance calculation point based on the size of the interfering object; and using the distance calculated from the measurement point as the interference distance.

[0013] The present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the method for determining the electromagnetic field strength of an interfering object as described above.

[0014] 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 in which the computer-readable storage medium is located to perform the electromagnetic field strength determination method for the interference object as described above.

[0015] The present invention has the following beneficial effects: By collecting point cloud data of the target area, the present invention can obtain detailed spatial information of the interfering object, thereby accurately determining the object type code and interference distance of the interfering object. By distinguishing different object types and interference distances, the present invention considers the influence of object type and interference distance on electromagnetic field strength. These interference feature data are then input into a pre-trained quantum neural network. Through the nonlinear fitting ability and data processing ability of the quantum neural network, the interference coefficient corresponding to the interference feature data can be accurately determined, thereby effectively improving the accuracy of determining the electromagnetic field strength of the interfering object.

[0016] Furthermore, the quantum neural network of the present invention utilizes the superposition state characteristic of qubits, enabling a single neuron to process multiple sets of input features in parallel, effectively improving computational efficiency, thereby effectively improving the efficiency and accuracy of determining the electromagnetic field strength of interfering objects. Attached Figure Description

[0017] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 is a flowchart illustrating a method for determining the electromagnetic field strength of an interfering object according to an embodiment of the present invention; Figure 2 is a structural schematic diagram illustrating a device for determining the electromagnetic field strength of an interfering object according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0021] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0024] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0025] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0026] Referring to Figure 1, to address the technical problem in existing technologies that utilize electric field probes and magnetic field coils to output electric and magnetic field strengths via direct sampling and conversion circuits without considering the influence of interference characteristic data of interfering objects within the target area on the electromagnetic field strength, leading to difficulties in accurately determining the electromagnetic field strength of interfering objects, an embodiment of the present invention provides a method for determining the electromagnetic field strength of interfering objects, including: S1, collecting point cloud data of the target area; In this embodiment of the present invention, the target area is the area where the electromagnetic field strength of interfering objects needs to be determined, which can be achieved using a lidar (range range 0.1-10m, angular resolution (0.3°-1.5°) × (0.3°-1.5°), which generates point cloud data by emitting infrared laser and receiving reflected light signals. The object type is distinguished by the reflection intensity of the point cloud (metal reflectivity >80%, concrete reflectivity 30%-50%, vegetation reflectivity <20%); the interference distance between the object and the measuring instrument is calculated based on the time-of-flight (TOF) method (accuracy ±3cm).

[0027] S2. Determine the interference feature data of the interfering objects within the target area based on the point cloud data. The interference feature data includes the object type code of the interfering object and the interference distance from the interfering object to the measurement point. S3. Input the interference feature data into a pre-trained quantum neural network and determine the interference coefficient corresponding to the interference feature data based on the quantum neural network. In this embodiment of the invention, before inputting the interference feature data into the pre-trained quantum neural network, the interference feature data is normalized to the [0,1] interval, specifically: object type code: numerically encode the identified fixed object type, specifically: metal = 1.0, concrete = 0.5, vegetation = 0.2; distance normalization value: normalize the distance between the measuring instrument and the fixed object, calculated by the formula d' = d / 10 (where d is the actual distance in meters); when the distance exceeds 10 meters, it is uniformly processed as 1.0.

[0028] S4. Determine the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object.

[0029] This invention, through the acquisition of point cloud data of the target area, can obtain detailed spatial information of the interfering object, thereby accurately determining the object type code and interference distance, and other interference characteristic data. By distinguishing different object types and interference distances, the influence of object type and interference distance on electromagnetic field strength is considered. These interference characteristic data are then input into a pre-trained quantum neural network. Through the nonlinear fitting and data processing capabilities of the quantum neural network, the interference coefficients corresponding to the interference characteristic data can be accurately determined, thereby effectively improving the accuracy of determining the electromagnetic field strength of the interfering object.

[0030] In one embodiment, step S2, determining the interference feature data of interfering objects within the target area based on point cloud data, includes: S21, determining the reflection intensity and shape characteristics of the interfering objects based on the point cloud data, determining the object type of the interfering objects based on the reflection intensity and shape characteristics, and determining the corresponding object type code based on the object type; in this embodiment of the invention, before determining the interference feature data of interfering objects within the target area based on the point cloud data, the point cloud data is preprocessed, including denoising and downsampling. For example, the lidar point cloud is denoised to remove noise points with a reflection intensity <5%, and downsampling is performed to retain the center point of each (0.3°-1.5°) × (0.3°-1.5°) grid.

[0031] In this embodiment of the invention, metallic interfering objects are typically of regular geometric shape, while vegetation interfering objects are typically of irregular shape, etc.; the reflectivity of the interfering objects can be: metal reflectivity >80%, concrete 30%-50%, vegetation <20%.

[0032] S22. Determine the size of the interfering object based on its shape characteristics, determine the distance calculation point based on the size of the interfering object, and take the distance from the calculated distance to the measurement point as the interference distance.

[0033] In this embodiment of the invention, the object size (e.g., the diameter of a metal pipe = the maximum lateral distance of the clustered point cloud) is calculated using a point cloud clustering algorithm. After determining the size of the interfering object, if the size of the interfering object is less than or equal to 0.5m, the distance closest to the measurement point in the interfering object's point cloud data is taken as the interference distance; if the size of the interfering object is greater than 0.5m, the distance from the center point to the measurement point is taken as the interference distance.

[0034] The embodiments of the present invention utilize point cloud data to accurately obtain the shape features of interfering objects, including their outlines, dimensions, and other information. Based on these detailed shape features, the size of the interfering object can be accurately determined, thereby allowing for a more reasonable selection of distance calculation points and improving the accuracy of determining the electromagnetic field strength of the interfering object.

[0035] In one embodiment, training a quantum neural network includes: S301, setting multiple distance gradients; in this embodiment of the invention, the multiple distance gradients may include five distances: 0.1m, 0.5m, 2m, 5m, and 10m.

[0036] This invention also collects interference data from various types of interfering objects, including three types of metals, and metals (based on conductivity ≥ 3.5 × 10⁻⁶). 7 S / m, conductivity 1×10 7 - 3.5×10 7 S / m, conductivity <1×10 7S / m is divided into 3 categories), 3 types of concrete (divided into 3 categories according to strength grade, such as C30-C40-C5), and 2 types of vegetation (herbaceous and woody) with interference data at multiple distance gradients.

[0037] S302. Based on multiple types of interfering objects, multiple distance gradients, and the true coefficients of the interfering objects, multiple sets of training samples are determined. In this embodiment of the invention, a total of 40 combinations can be generated, namely 8 types of interfering objects x 5 distances = 40 combinations. 125 samples are collected for each combination, resulting in a total of 40 × 125 = 5,000 sets of samples.

[0038] In this embodiment of the invention, each sample set includes interference feature data and a pair of true coefficients. The true coefficients include: true electric field coefficients: Magnetic field true coefficient: ;in, , Let be the original electric field strength and the original magnetic field strength of the interfering object, respectively; , The theoretical values ​​obtained from finite element simulation calculations are the reference values ​​of the electric field and magnetic field of the interfering object.

[0039] S303. Initialize the rotation angles of the three quantum rotating gates in the quantum neural network and set the learning rate; In this embodiment of the invention, the rotation angles θ1, θ2, and θ3 of the three quantum rotating gates are randomly initialized, the learning rate η = 0.01 is set, and the number of iterations is not less than 500.

[0040] In this embodiment of the invention, the quantum neural network processes input features through a quantum hidden layer. This quantum hidden layer includes three quantum rotation gates, each using a qubit as its information carrier. Unlike the deterministic state of traditional neural networks, a qubit can simultaneously be in one of three states. and The superposition state, i.e., the quantum state Where α and β are complex probability amplitudes, and |α|² + |β|² = 1. This superposition characteristic of the embodiments of the present invention enables a single neuron to process multiple sets of input features in parallel, greatly improving computational efficiency.

[0041] In this embodiment of the invention, the three quantum rotation gates include an RX rotation gate (rotating about the X-axis), an RY rotation gate (rotating about the Y-axis), and an RZ rotation gate (rotating about the Z-axis), wherein the matrix of the RX rotation gate... The expression is as follows: .

[0042] In this embodiment of the invention, the pre-rotation quantum state is assumed to be... After the RX rotating door effect, the new probability amplitude , for: ; The RX rotary gate operation is primarily used to control the phase relationship between α and β, and is suitable for enhancing the effect of different types of interference (such as metal / concrete). The impact. For example, when When it increases, The real part decreases and the imaginary part increases, making Shift towards higher values ​​(enhance the interference weight of metallic objects).

[0043] RY Revolving Door Matrix The expression is as follows: .

[0044] RY Probability amplitude after the revolving door rotates , for: ; The RY rotating door operation is used to directly change the magnitude ratio of α and β, balancing the weights of interference type and distance. For example, when... When =π / 2, α'≈ -β, β'≈ α, making the distance feature pair and Enhanced impact (applicable to long-range interference scenarios).

[0045] RZ Revolving Door Matrix The expression is as follows: .

[0046] RZ revolving door's probability amplitude after rotation , for: ; ;in, It only changes the phase and does not affect the magnitudes |α| and |β|.

[0047] The RZ rotation gate operation is used to optimize the coherence of quantum states through phase adjustment, improving the model's adaptability to complex disturbance scenarios. For example, in weak disturbance scenarios such as vegetation, fine-tuning... It can align the phase of quantum states and reduce and The predicted fluctuations.

[0048] In this embodiment of the invention, the RX, RY, and RZ rotary gates achieve precise control of the quantum state by changing the magnitude and phase of α and β. The RX and RY rotary gates primarily affect... and The numerical value is used to match the intensity characteristics of different interference objects; the RZ rotating gate improves model stability through phase optimization, ensuring prediction consistency in complex scenarios. This embodiment of the invention utilizes the synergistic effect of three quantum rotating gates to enable the QNN model to efficiently learn the coupling relationship between interference type and distance, providing an accurate coefficient basis for dynamic compensation.

[0049] S304. Each training sample is used as an input vector. The input features are mapped to quantum states using a quantum rotation gate. The quantum states are evolved using the quantum rotation gate to obtain the evolved quantum states. The predicted interference coefficient value corresponding to each training sample is determined by measuring the probability amplitude of the evolved quantum states. In this embodiment of the invention, the input vector is processed by a quantum hidden layer to generate a quantum state |ψ>, and the predicted interference coefficient value is output after measurement.

[0050] S305. Construct a loss function based on the predicted value of the interference coefficient, and perform iterative optimization based on the loss function, the rotation angle of the quantum rotating gate, and the learning rate. When the preset conditions are met, complete the training of the quantum neural network.

[0051] In this embodiment of the invention, the expression for the loss function is as follows: in, This is a predicted value for the electric field interference coefficient, used to quantify the interference intensity of the interfering object on the electric field measurement, reflecting the original electric field strength. The degree of distortion caused by the presence of interfering objects. A higher value indicates a stronger influence of the interfering object on the electric field (e.g., the distortion caused by a metallic object). (usually larger than concrete); The predicted value of the magnetic field interference coefficient is directly related to the conductivity, magnetism, and other properties of the object (such as highly conductive metals). (significantly higher than non-metals) and It is the predicted value output by the QNN model after calculating the input features (type of interference, distance), and its accuracy directly determines the compensation effect (the closer the predicted value is to the true interference coefficient). and The smaller the error after compensation, the better. N represents the total number of samples participating in the iteration, used to balance the error of a single iteration with the overall optimization effect, and to ensure the stability of model training.

[0052] In this embodiment of the invention, during the iterative optimization process, the rotation angle can be adjusted synchronously using the quantum gradient descent method until the loss function L < 0.001.

[0053] By setting multiple distance gradients and collecting interference data from various types of interference objects, this invention can generate a large number of diverse training samples, enabling the quantum neural network to learn in a wide range of interference scenarios. These samples cover different types of interference objects (such as metal, concrete, vegetation, etc.) and interference characteristics at different distances, effectively improving the model's generalization ability and thus accurately predicting the interference coefficients of interference objects in various real-world complex environments.

[0054] Furthermore, in this embodiment of the invention, the quantum neural network utilizes the superposition characteristics of qubits, enabling a single neuron to process multiple sets of input features in parallel, effectively improving computational efficiency and thus significantly enhancing the accuracy of determining the electromagnetic field strength of interfering objects.

[0055] In one embodiment, step S3, determining the interference coefficient corresponding to the interference feature data based on the quantum neural network, includes: mapping the interference features to quantum states using three quantum rotation gates in the quantum hidden layer of the quantum neural network, using the quantum rotation gates to evolve the quantum states to obtain the evolved quantum states, and outputting the interference coefficient by measuring the evolved quantum states.

[0056] In this embodiment of the invention, the evolution of a quantum state refers to the change of a quantum state over time. By manipulating the quantum state through a quantum rotation gate, the state of the quantum state can be changed, causing it to evolve in quantum space. After multiple operations by the quantum rotation gate, the quantum state will reach a new state, which is the evolved quantum state. This embodiment of the invention obtains a classical measurement value, namely the interference coefficient, by measuring the evolved quantum state. The interference coefficient includes both electric field strength interference coefficient and magnetic field strength interference coefficient.

[0057] The embodiments of the present invention use quantum rotation gate operation to evolve the interference characteristics mapped to quantum states, which can accurately determine the interference coefficient, thereby making it applicable to complex environments and effectively improving the accuracy of electromagnetic field strength determination.

[0058] In one embodiment, step S4, determining the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object, includes: S41, collecting the original electromagnetic field strength data of the interfering object; In one embodiment, during monitoring under a high-voltage transmission line, a lidar detected a highly conductive metal tower (type code = 1.0) 1m away from the distance measuring instrument, and the three-dimensional electromagnetic field sensor collected the following original electromagnetic field strength data: Original electromagnetic field strength Original magnetic field strength .

[0059] S42. Obtain the reference electromagnetic field data of the target area; in this embodiment of the invention, the reference electromagnetic field data under interference-free conditions can be obtained through finite element simulation calculation: electric field reference value. ; Magnetic field reference value .

[0060] S43. Based on the interference coefficient, the original electromagnetic field strength data, and the interference distance, determine the initial compensation electromagnetic field strength; in this embodiment of the invention, the relevant interference characteristic data are input into the quantum neural network to obtain the interference coefficient as follows: Electric field interference coefficient (Within the range of 0.25-0.35 for the metallicity coefficient); Magnetic field interference coefficient (Within the range of 0.35-0.45 for the metal coefficient).

[0061] Please refer to Table 1, which is a physical interpretation interval table of the interference coefficient provided in an embodiment of the present invention.

[0062] Table 1: Physical Intervals of Interference Coefficients. The expression for the initial compensation electromagnetic field strength is as follows: Initial compensation electric field strength : Initial compensation magnetic field strength : .

[0063] S44. Determine the electromagnetic field error based on the initial compensated electromagnetic field strength and the reference electromagnetic field strength. When the electromagnetic field error is less than a preset threshold, use the initial compensated electromagnetic field strength as the final electromagnetic field strength. When the electromagnetic field error is greater than or equal to the preset threshold, adjust the parameters in the quantum neural network with a preset step size until the electromagnetic field error is less than the preset threshold, and use the current initial compensated electromagnetic field strength as the final electromagnetic field strength.

[0064] In this embodiment of the invention, the error formula is as follows: Electric field error : ; Magnetic field error : In this embodiment of the invention, both the electric field error and the magnetic field error are less than a preset threshold of 5%, so there is no need to adjust the parameters in the quantum neural network with a preset step size; that is, the final compensated electric field strength is... The magnetic field strength is .

[0065] In this embodiment of the invention, when the electromagnetic field error is greater than or equal to a preset threshold, the rotation angle in the quantum neural network is adjusted with a preset step size. If the value is too large, increase the rotation angle θ1 to make Increase (enhance electric field compensation); when If the value is too large, increase the rotation angle θ2 to make Increase (enhance magnetic field compensation). In this embodiment of the invention, the step size can be adjusted to Δθ = 0.02π in each iteration until... , ,in The electric field error threshold, The electric field error threshold and the magnetic field error threshold u are determined and adjusted through experimental data. For example, the electric field error threshold can be set to 0.01 or 0.02, and the magnetic field error threshold can be set to 0.005 or 0.006.

[0066] Implementing the embodiments of the present invention has the following beneficial effects: By collecting point cloud data of the target area, the embodiments of the present invention can obtain detailed spatial information of the interfering object, thereby accurately determining the object type code and interference distance of the interfering object, and considering the influence of object type and interference distance on electromagnetic field strength. These interference feature data are then input into a pre-trained quantum neural network. Through the nonlinear fitting ability and data processing ability of the quantum neural network, the interference coefficient corresponding to the interference feature data can be accurately determined, thereby effectively improving the accuracy of determining the electromagnetic field strength of the interfering object.

[0067] Furthermore, in this embodiment of the invention, the quantum neural network utilizes the superposition characteristics of qubits, enabling a single neuron to process multiple sets of input features in parallel, effectively improving computational efficiency and thus significantly enhancing the accuracy of determining the electromagnetic field strength of interfering objects.

[0068] As shown in Figure 2, based on the above method embodiments, corresponding device embodiments are provided; one embodiment of the present invention provides a device for determining the electromagnetic field strength of an interfering object, including: a point cloud data acquisition module 10, used to acquire point cloud data of a target area; an interference feature data determination module 20, used to determine interference feature data of an interfering object in the target area based on the point cloud data, wherein the interference feature data includes the object type code of the interfering object and the interference distance from the interfering object to the measurement point; an interference coefficient determination module 30, used to input the interference feature data into a pre-trained quantum neural network and determine the interference coefficient corresponding to the interference feature data based on the quantum neural network; and an electromagnetic field strength determination module 40, used to determine the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object.

[0069] In one embodiment, determining interference feature data of interfering objects within a target area based on point cloud data includes: determining the reflection intensity and shape features of the interfering objects based on point cloud data; determining the object type of the interfering objects based on the reflection intensity and shape features; determining the corresponding object type code based on the object type; determining the size of the interfering objects based on the shape features; determining the distance calculation point based on the size of the interfering objects; and using the distance calculated to the measurement point as the interference distance.

[0070] In one embodiment, training a quantum neural network includes: setting multiple distance gradients; determining multiple sets of training samples based on various types of interfering objects, multiple distance gradients, and the true coefficients of the interfering objects; initializing the rotation angles of three quantum rotation gates in the quantum neural network and setting the learning rate; using each set of training samples as input vectors, mapping the input features to quantum states using quantum rotation gates, evolving the quantum states using quantum rotation gates to obtain evolved quantum states, determining the predicted interference coefficient value corresponding to each set of training samples by measuring the probability amplitude of the evolved quantum states; constructing a loss function based on the predicted interference coefficient value, iteratively optimizing the loss function, the rotation angles of the quantum rotation gates, and the learning rate, and completing the training of the quantum neural network when preset conditions are met.

[0071] In one embodiment, determining the interference coefficient corresponding to the interference feature data based on the quantum neural network includes: mapping the input features to quantum states using three quantum rotation gates in the quantum hidden layer of the quantum neural network, using the quantum rotation gates to evolve the quantum states to obtain the evolved quantum states, and measuring the evolved quantum states to output the interference coefficient.

[0072] In one embodiment, determining the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object includes: collecting the original electromagnetic field strength data of the interfering object; acquiring the reference electromagnetic field data of the target area; determining the initial compensation electromagnetic field strength based on the interference coefficient, the original electromagnetic field strength data, and the interference distance; determining the electromagnetic field error based on the initial compensation electromagnetic field strength and the reference electromagnetic field strength; when the electromagnetic field error is less than a preset threshold, using the initial compensation electromagnetic field strength as the final electromagnetic field strength; when the electromagnetic field error is greater than or equal to the preset threshold, adjusting the parameters in the quantum neural network with a preset step size until the electromagnetic field error is less than the preset threshold, and using the current initial compensation electromagnetic field strength as the final electromagnetic field strength.

[0073] In one embodiment, before determining the reflection intensity and shape characteristics of the interfering object based on the point cloud data, determining the object type of the interfering object based on the reflection intensity and shape characteristics, and determining the corresponding object type code based on the object type, the method further includes: preprocessing the point cloud data, the preprocessing including denoising processing and downsampling processing.

[0074] It is understood that the above-described device embodiments correspond to the method embodiments of the present invention, and can implement the method for determining the electromagnetic field strength of an interfering object provided by any of the above-described method embodiments of the present invention.

[0075] It should be noted that the device embodiments described above are merely illustrative, and 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 specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0076] Based on the above embodiments of the method for determining the electromagnetic field strength of interfering objects, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for determining the electromagnetic field strength of interfering objects according to any embodiment of the present invention.

[0077] For example, in this embodiment, the computer program can be divided into one or more modules, one or more modules are stored in memory and executed by a processor to complete the present invention. One or more module elements can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0078] Terminal devices can be computing devices such as desktop computers, laptops, handheld computers, and cloud servers. Terminal devices may include, but are not limited to, processors and memory.

[0079] 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 terminal device, connecting all parts of the terminal device through various interfaces and lines.

[0080] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the method for determining the electromagnetic field strength of an interfering object according to any of the above-described method embodiments of the present invention.

[0081] The modules / units integrated into the device / terminal equipment, if implemented as software functional units and sold or used as independent products, 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 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.

[0082] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for determining the electromagnetic field strength of an interfering object, characterized in that, include: Collect point cloud data of the target area; The interference feature data of the interfering object within the target area is determined based on the point cloud data, wherein the interference feature data includes the object type code of the interfering object and the interference distance from the interfering object to the measurement point; the interference feature data is input into a pre-trained quantum neural network, and the interference coefficient corresponding to the interference feature data is determined based on the quantum neural network; the final electromagnetic field strength of the interfering object is determined based on the interference coefficient and the original electromagnetic field data of the interfering object.

2. The method for determining the electromagnetic field strength of an interfering object as described in claim 1, characterized in that, The step of determining the interference feature data of the interfering object within the target area based on the point cloud data includes: determining the reflection intensity and shape features of the interfering object based on the point cloud data; determining the object type of the interfering object based on the reflection intensity and the shape features; determining the corresponding object type code based on the object type; determining the size of the interfering object based on the shape features; determining the distance calculation point based on the size of the interfering object; and using the distance calculated from the measurement point as the interference distance.

3. The method for determining the electromagnetic field strength of an interfering object as described in claim 1, characterized in that, The training of the quantum neural network includes: setting multiple distance gradients; determining multiple sets of training samples based on various types of interfering objects, multiple distance gradients, and the true coefficients of the interfering objects; initializing the rotation angles of the three quantum rotation gates in the quantum neural network and setting the learning rate; using each set of training samples as an input vector, mapping the input features to a quantum state using the quantum rotation gates, evolving the quantum state using the quantum rotation gates to obtain an evolved quantum state, determining the predicted interference coefficient value corresponding to each set of training samples by measuring the probability amplitude of the evolved quantum state; constructing a loss function based on the predicted interference coefficient value, iteratively optimizing the loss function, the rotation angles of the quantum rotation gates, and the learning rate, and completing the training of the quantum neural network when preset conditions are met.

4. The method for determining the electromagnetic field strength of an interfering object as described in claim 3, characterized in that, The step of determining the interference coefficient corresponding to the interference feature data based on the quantum neural network includes: mapping the input feature to a quantum state using three quantum rotation gates of the quantum hidden layer in the quantum neural network, evolving the quantum state using the quantum rotation gates to obtain the evolved quantum state, and measuring the interference coefficient of the evolved quantum state.

5. The method for determining the electromagnetic field strength of an interfering object as described in claim 1, characterized in that, The step of determining the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object includes: collecting the original electromagnetic field strength data of the interfering object; acquiring the reference electromagnetic field data of the target area; determining the initial compensation electromagnetic field strength based on the interference coefficient, the original electromagnetic field strength data, and the interference distance; determining the electromagnetic field error based on the initial compensation electromagnetic field strength and the reference electromagnetic field strength; when the electromagnetic field error is less than a preset threshold, using the initial compensation electromagnetic field strength as the final electromagnetic field strength; when the electromagnetic field error is greater than or equal to the preset threshold, adjusting the parameters in the quantum neural network with a preset step size until the electromagnetic field error is less than the preset threshold, and using the current initial compensation electromagnetic field strength as the final electromagnetic field strength.

6. The method for determining the electromagnetic field strength of an interfering object as described in claim 2, characterized in that, Before determining the reflection intensity and shape characteristics of the interfering object based on the point cloud data, determining the object type of the interfering object based on the reflection intensity and the shape characteristics, and determining the corresponding object type code based on the object type, the method further includes: preprocessing the point cloud data, wherein the preprocessing includes denoising processing and downsampling processing.

7. A device for determining the electromagnetic field strength of an interfering object, characterized in that, include: The point cloud data acquisition module is used to collect point cloud data of the target area; An interference feature data determination module is used to determine interference feature data of an interfering object within the target area based on the point cloud data. The interference feature data includes the object type code of the interfering object and the interference distance from the interfering object to the measurement point. An interference coefficient determination module is used to input the interference feature data into a pre-trained quantum neural network and determine the interference coefficient corresponding to the interference feature data based on the quantum neural network. An electromagnetic field strength determination module is used to determine the final electromagnetic field strength of the interfering object based on the interference coefficient and the original electromagnetic field data of the interfering object.

8. The device for determining the electromagnetic field strength of an interfering object as described in claim 7, characterized in that, The step of determining the interference feature data of the interfering object within the target area based on the point cloud data includes: determining the reflection intensity and shape features of the interfering object based on the point cloud data; determining the object type of the interfering object based on the reflection intensity and the shape features; determining the corresponding object type code based on the object type; determining the size of the interfering object based on the shape features; determining the distance calculation point based on the size of the interfering object; and using the distance calculated from the measurement point as the interference distance.

9. A terminal 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 when the processor executes the computer program, it implements the method for determining the electromagnetic field strength of an interfering object as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, include: A stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform the method for determining the electromagnetic field strength of an interfering object as described in any one of claims 1-6.

Images