Disaster Area Rescue Target Location Method Based on Sparrow Search Algorithm Optimized BP Neural Network

Abstract

The present invention relates to the technical field of target positioning, and discloses a method for positioning disaster relief targets by optimizing a BP neural network based on a sparrow algorithm. The method includes: preprocessing the drone record information during drone cruising; establishing a BP neural network model, initializing the weights and thresholds of the BP neural network model, inputting the table into the BP neural network model, subtracting the output mobile phone longitude and latitude from the actual mobile phone longitude and latitude as the fitness of the sparrow, running the sparrow optimization algorithm, and iteratively finding the optimal fitness value; using the sparrow data corresponding to the optimal fitness value as the final weights and thresholds, using the table as the input to train the BP neural network model, and putting the trained BP neural network model into the drone remote control; inputting the arranged data rows into the trained BP neural network model to obtain the final predicted position longitude and latitude, and marking the predicted mobile phone position on the map. The present invention realizes precise positioning.

Description

Technical Field

[0001] The present invention relates to the technical field of target positioning, and more specifically, to a method for positioning disaster relief targets based on a sparrow algorithm optimized BP neural network. Background Technique

[0002] The sparrow algorithm is a heuristic optimization algorithm based on the behavior of bird flocks, simulating the behavior of sparrows during foraging and reproduction. This algorithm searches for the optimal solution through the interaction between individuals in the group, and has advantages such as strong global search ability and fast convergence speed. Its core idea is to initialize the position and speed of sparrows, calculate the fitness value (such as the error size of the BP neural network) according to the current position, and update the optimal position and the global optimal position according to the fitness value. Finally, the optimal solution is found by continuously adjusting the speed and position. Due to its efficient global search ability and fast convergence speed, the sparrow algorithm is widely used in various optimization problems, including but not limited to the fields of machine learning, data mining, image processing, etc. The BP neural network (Back Propagation Neural Network) is a commonly used machine learning model, which is trained and optimized through the backpropagation algorithm. This network consists of an input layer, a hidden layer, and an output layer, and approximates the mapping relationship between the input and the output by adjusting the weights and bias values between the layers. The BP neural network has advantages such as strong self-adaptability and strong non-linear mapping ability, and is widely used in tasks such as classification and regression.

[0003] However, there are also some problems in the training process of the BP neural network, such as slow convergence speed and easy to fall into local minima. These problems limit the performance and application scope of the BP neural network. GPS positioning has disadvantages such as signal limitation, accuracy problems, dependence problems, energy consumption and cost, as well as privacy and security risks. In disaster scenarios, there are many collapsed objects that have a relatively large impact on GPS positioning, and mobile phones with precise GPS positioning require a relatively high cost. In disaster scenarios, nearby base stations will be damaged and unable to be used. WiFi positioning and Bluetooth positioning are only applicable to indoor scenarios and not to outdoor scenarios. The AOA technology determines the position by the angle of the signal source. Multiple sensors need to be equipped on the device to meet the requirements. The device costs are high and there are great technical difficulties. The TDOA technology determines the position by the time difference of signal arrival. It has good positioning effect in an ideal space. However, when encountering buried terrain, the signal time difference will be greatly affected and the positioning accuracy is poor. Since AOA and TDOA calculate the position of the mobile phone by means of formulas based on the data of signal strength or direction angle, when encountering obstacles, it is very difficult to detect or calculate the interference coefficient of the signal strength. At the same time, there are multipath problems in both of these two technologies. Multipath means that after electromagnetic waves propagate through different paths, the arrival times of each component field at the receiving end are different, and they are superimposed on each other according to their respective phases, resulting in interference, making the original signal distorted or generating errors.

[0004] Therefore, it is necessary to provide a disaster area rescue target positioning method based on the sparrow algorithm to optimize the BP neural network to solve the problems of poor accuracy and easy to be affected by the environment in the existing positioning methods. Summary of the Invention

[0005] In view of this, the present invention proposes a disaster area rescue target positioning method based on the sparrow algorithm to optimize the BP neural network, aiming to solve the problems of poor accuracy and easy to be affected by the environment in the existing positioning methods.

[0006] The present invention proposes a disaster area rescue target positioning method based on the sparrow algorithm to optimize the BP neural network, including:

[0007] Preprocess the continuously numbered mobile phones, collect mobile phone information through the unmanned aerial vehicle (UAV) equipped with a positioning payload, preprocess the UAV record information during the UAV cruise, and record it in a table;

[0008] Establish a BP neural network model, initialize the weights and thresholds of the BP neural network model, substitute the data of each sparrow into the BP neural network model, input the table into the BP neural network model, subtract the output longitude and latitude of the mobile phone of the BP neural network model from the actual longitude and latitude of the mobile phone as the fitness of the sparrow, run the sparrow optimization algorithm, and iteratively find the optimal fitness value;

[0009] Take the sparrow data corresponding to the optimal fitness value as the final weights and thresholds of the BP neural network model, use the table as the input to train the BP neural network model, and put the trained BP neural network model into the drone remote control so that the drone remote control can perform real-time processing on the received data;

[0010] Determine the disaster area of the affected people through remote sensing technology, make the drone carrying the positioning payload automatically cruise over the disaster area of the affected people, collect the mobile phone information, and transmit the mobile phone information and the drone record information back to the drone remote controller;

[0011] Arrange the data of each group of mobile phones collected in groups of three to form data rows, use the arranged data rows as the input, input them into the trained BP neural network model, obtain the final predicted position longitude and latitude, and mark the mobile phone positions predicted by the BP neural network model on the map.

[0012] Further, when preprocessing the continuously registered mobile phones, it includes:

[0013] Place the continuously registered mobile phones in a square flat ground, use concrete bricks to bury the mobile phones in an "inclined" manner, and record the actual longitude and latitude of the mobile phones.

[0014] Further, when collecting mobile phone information through a drone equipped with a positioning payload, it includes:

[0015] Install the positioning payload directly below the drone and keep the signal receiving surface of the payload facing down. Remote control the drone to automatically cruise in the square flat ground and fly around the mobile phone. When the mobile phone is scanned, the drone exchanges data with the mobile phone to obtain the mobile phone information.

[0016] Further, the mobile phone information includes: mobile phone serial number and mobile phone signal strength;

[0017] The drone record information includes: drone altitude, drone longitude and latitude, and mobile phone signal strength.

[0018] Further, when preprocessing the drone record information during the drone cruise and recording it in a table, it includes:

[0019] Record and export the drone record information during the drone cruise through the remote controller, process the drone record information in groups, combine three groups and the actual longitude and latitude of the mobile phone into a large group, and use a computer to put the recorded data into the table to be trained, where the mobile phone signal strengths in the data of the three groups are of the same mobile phone.

[0020] Further, the large group is (drone altitude 1, drone longitude 1, drone latitude 1, mobile phone signal strength 1, drone altitude 2, drone longitude 2, drone latitude 2, mobile phone signal strength 2, drone altitude 3, drone longitude 3, drone latitude 3, mobile phone signal strength 3, actual longitude of the mobile phone, actual latitude of the mobile phone).

[0021] Further, when establishing the BP neural network model and initializing the weights and thresholds of the BP neural network model, substituting the data of each sparrow into the BP neural network model includes:

[0022] If the number of input layer nodes of the BP neural network model is n, the number of hidden layer nodes is m, and the number of output layer nodes is p, then the number of weights is N = n*m + m*p, and the number of thresholds is M = m + p;

[0023] Set a sparrows, each sparrow has M + N data and includes all weights and thresholds, and initialize the data of each sparrow.

[0024] Further, when arranging and combining each group of mobile phone data collected in groups of three to form data rows, and taking the arranged data rows as inputs and inputting them into the trained BP neural network model to obtain the final predicted position longitude and latitude, it includes:

[0025] Arrange and combine each group of mobile phone data collected in groups of three to become a data row of 12 data in one row, and take the arranged data row as an input and input it into the trained BP neural network model. Among them, the data row is (drone altitude 1, drone longitude 1, drone latitude 1, mobile phone signal strength 1, drone altitude 2, drone longitude 2, drone latitude 2, mobile phone signal strength 2, drone altitude 3, drone longitude 3, drone latitude 3, mobile phone signal strength 3).

[0026] Further, when arranging and combining each group of mobile phone data collected in groups of three to form data rows, and taking the arranged data rows as inputs and inputting them into the trained BP neural network model to obtain the final predicted position longitude and latitude, it includes:

[0027] Sort the predicted longitude and latitude output by the BP neural network model according to size, remove a total of 1 / 4 of the largest and smallest data, and perform mean processing on the middle data to obtain the final predicted position longitude and latitude.

[0028] Further, the loss function of the BP neural network model is MSE, and the activation functions are set as tansig and purelin.

[0029] Compared with the prior art, the beneficial effects of the present invention are as follows: The method of establishing a fitting model by the sparrow-optimized neural network perfectly solves the problems of low accuracy and high cost of the AOA and TDOA methods by establishing a model with existing data to predict application data. Establishing a model through a large amount of data does not require too much cost, and the accuracy is also guaranteed by the data fitting method. The positioning method of the sparrow-optimized BP neural network model can cope with most situations in the training scenario through a large amount of data verification and training, and will not cause positioning deviation due to individual special signal intensities. In terms of the multipath problem, in the method of positioning the sparrow-optimized BP neural network model, the collected data before training the model also has multipath propagation. In the process of fitting and training the model with these data, the multipath propagation problem of the signal is also fitted, so that the model has good anti-interference ability for the multipath propagation of the signal, greatly reducing the influence of the signal multipath propagation. The processing of multiple groups of data output during the prediction process further processes the interference of the signal and improves the positioning accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0031] Figure 1 is a flowchart of the disaster area rescue target positioning method based on the sparrow algorithm-optimized BP neural network provided by the embodiment of the present invention;

[0032] Figure 2 is a flowchart of the sparrow-optimized BP neural network algorithm provided by the embodiment of the present invention;

[0033] Figure 3 is a schematic diagram of the UAV flight route and the mobile phone position provided by the embodiment of the present invention;

[0034] Figure 4 is a network diagram of the BP neural network model provided by the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0036] In some embodiments of the present application, referring to Figure 1 as shown, this embodiment provides a method for locating disaster relief targets based on a sparrow algorithm to optimize a BP neural network, including the following steps:

[0037] S100. Preprocess the continuously numbered mobile phones, collect mobile phone information through drones equipped with positioning payloads, preprocess the drone recording information during the drone cruise, and record it in a table;

[0038] S200. Establish a BP neural network model, initialize the weights and thresholds of the BP neural network model, substitute the data of each sparrow into the BP neural network model, input the table into the BP neural network model, subtract the output mobile phone longitude and latitude of the BP neural network model from the actual mobile phone longitude and latitude as the fitness of the sparrow, run the sparrow optimization algorithm, and iteratively find the optimal fitness value;

[0039] S300. Use the sparrow data corresponding to the optimal fitness value as the final weights and thresholds of the BP neural network model, input the table as the input to train the BP neural network model, and put the trained BP neural network model into the drone remote control so that the drone remote control can perform real-time processing on the received data;

[0040] S400. Determine the disaster-affected area of the personnel through remote sensing technology, automatically cruise the drone equipped with a positioning payload over the disaster-affected area of the personnel, collect the mobile phone information, and transmit the mobile phone information and the drone recording information back to the drone remote control;

[0041] S500. Arrange and combine each group of mobile phone data collected in groups of three to form data rows, input the arranged data rows as the input into the trained BP neural network model to obtain the final predicted position longitude and latitude, and mark the mobile phone positions predicted by the BP neural network model on the map.

[0042] Preferably, the continuously numbered mobile phones refer to mobile phones that can normally receive and send signals.

[0043] Specifically, Figure 2 It is a flow chart of the sparrow-optimized BP neural network algorithm.

[0044] In some embodiments of the present application, when preprocessing the continuously numbered mobile phones, it includes:

[0045] Place the continuously numbered mobile phones on a square flat ground, use concrete bricks to bury the mobile phones in an "inclined type", and record the actual longitude and latitude of the mobile phones.

[0046] Specifically, the post-earthquake buried environment is classified into three types: "inclined type", "collapse type" and "composite type". Among them, the overall survival space of the "inclined type" buried environment is large, the stability is the strongest, and the survival rate of the buried personnel is the highest. Therefore, the "inclined type" environment is used to collect data.

[0047] In some embodiments of the present application, when collecting mobile phone information by a drone equipped with a positioning load, it includes:

[0048] Install the positioning load directly below the drone, and keep the signal receiving surface of the load facing down. Remotely control the drone to perform automatic cruising in the square flat ground and fly around the mobile phone. When the mobile phone is scanned, the drone exchanges data with the mobile phone to obtain the mobile phone information.

[0049] In some embodiments of the present application, the mobile phone information includes: the mobile phone serial number and the mobile phone signal strength;

[0050] The information recorded by the drone includes: the drone altitude, the drone longitude and latitude, and the mobile phone signal strength.

[0051] Specifically, the serial number of the SIM card in the mobile phone can distinguish different mobile phone cards, and the data will not be confused.

[0052] In some embodiments of the present application, when preprocessing the information recorded by the drone during the drone cruising and recording it in a table, it includes:

[0053] Record and export the information recorded by the drone during the drone cruising through the remote controller, process the information recorded by the drone in groups, combine three groups and the actual longitude and latitude of the mobile phone into a large group, and use a computer to put the recorded data into the table to be trained. Among them, the mobile phone signal strengths in the data of the three groups are of the same mobile phone.

[0054] In some embodiments of the present application, the large group is (drone altitude 1, drone longitude 1, drone latitude 1, mobile phone signal strength 1, drone altitude 2, drone longitude 2, drone latitude 2, mobile phone signal strength 2, drone altitude 3, drone longitude 3, drone latitude 3, mobile phone signal strength 3, actual longitude of the mobile phone, actual latitude of the mobile phone).

[0055] Specifically, three small groups plus the actual longitude and latitude of the mobile phone are combined into a large group. The form of the large group is: drone altitude 1, drone longitude 1, drone latitude 1, mobile phone signal strength 1, drone altitude 2, drone longitude 2, drone latitude 2, mobile phone signal strength 2, drone altitude 3, drone longitude 3, drone latitude 3, mobile phone signal strength 3, actual longitude of the mobile phone, actual latitude of the mobile phone. Each set of data is for one mobile phone. The principle is that the actual position of a mobile phone can be determined through the signal data at three points.

[0056] Refer to Figure 3 As shown: (x, y) represents the position of the mobile phone, (xi, yi) represents the longitude and latitude of the drone at point i, where i = 1, 2, 3; di represents the distance from the drone at point i to the mobile phone. There is a mapping relationship between the signal strength ei received by the drone and the distance si from the two signal sources. The mapping relationship is denoted as si = a * ei + b, where a and b are conversion coefficients and are affected by the signal strength consumption during signal transmission. Through the fitting function of the neural network, a and b can be fitted into specific data, so as to achieve the effect of converting the signal strength ei received by the drone into the distance si. According to the Pythagorean theorem of the triangle, the plane distance di can be obtained through the distance si between the drone and the mobile phone and the drone altitude hi. Finally, the specific position (x, y) of the mobile phone can be obtained through the schematic diagram of the three-point positioning principle in the above figure. The specific formula is as follows:

[0057] si = a * ei + b

[0058] di 2 + hi 2 = si 2

[0059] (x - x1) 2 +(y - y1) 2 = d1 2

[0060] (x - x2) 2 +(y - y2) 2 = d2 2

[0061] (x - x3) 2 +(y - y3) 2 = d3 2 .

[0062] In some embodiments of the present application, when establishing the BP neural network model and initializing the weights and thresholds of the BP neural network model, substituting the data of each sparrow into the BP neural network model includes:

[0063] If the number of input layer nodes of the BP neural network model is n, the number of hidden layer nodes is m, and the number of output layer nodes is p, then the number of weights is N = n * m + m * p, and the number of thresholds is M = m + p;

[0064] Set a sparrows, each sparrow has M + N data and contains all weights and thresholds, and initialize the data of each sparrow.

[0065] Specifically, Figure 4 For the BP neural network diagram, the UAV altitude 1, UAV longitude 1, UAV latitude 1, mobile phone signal strength 1, UAV altitude 2, UAV longitude 2, UAV latitude 2, mobile phone signal strength 2, UAV altitude 3, UAV longitude 3, UAV latitude 3, mobile phone signal strength 3. Therefore, the input layer is set to 12 nodes, the output is the actual longitude and actual latitude of the mobile phone, so the output layer is set to 2 nodes, and the number of hidden layer nodes can be set to 5 - 12. The number of input layer nodes n (here is 12), the number of hidden layer nodes m, and the output layer p (here is 2). Then the number of weights is: N = n * m + m * p, and the number of thresholds is: M = m + p. Set a sparrows, each sparrow has M + N data, and contains all weights and thresholds, and initialize the data of each sparrow to maintain randomness.

[0066] In some embodiments of the present application, when arranging and combining each group of mobile phone data collected in rows of three to form data rows, and using the arranged data rows as inputs and inputting them into the trained BP neural network model to obtain the final predicted position longitude and latitude, it includes:

[0067] Arrange and combine each group of mobile phone data collected in rows of three to become a data row of 12 data in one row, and use the arranged data row as an input and input it into the trained BP neural network model, where the data row is (UAV altitude 1, UAV longitude 1, UAV latitude 1, mobile phone signal strength 1, UAV altitude 2, UAV longitude 2, UAV latitude 2, mobile phone signal strength 2, UAV altitude 3, UAV longitude 3, UAV latitude 3, mobile phone signal strength 3).

[0068] Specifically, due to the large number of training data, the influence of multipath signals can be avoided as much as possible. The number of training rounds and step size of the neural network can be set by oneself, the loss function is MSE, and the activation functions are set to 'tansig' and 'purelin' to achieve good training effects.

[0069] In some embodiments of the present application, when arranging and combining the collected data of each group of mobile phones in rows of three to form data rows, and taking the arranged data rows as inputs and inputting them into the trained BP neural network model to obtain the final predicted position longitude and latitude, it includes:

[0070] Sort the predicted longitude and latitude output by the BP neural network model according to their magnitudes, remove a total of 1 / 4 of the largest and smallest data, and perform mean processing on the intermediate data to obtain the final predicted position longitude and latitude.

[0071] Specifically, since there will be multiple groups of outputs after the collected data is input into the model through arrangement and combination, and we only need one predicted position, we need to process the output data. Sort the longitude and latitude according to their magnitudes, remove 1 / 4 of the largest and smallest data, and perform mean processing on the intermediate data to obtain the final predicted position longitude and latitude. This data processing step is mainly used to remove the influence of signal strength outliers and enhance the anti-interference ability of the model.

[0072] In some embodiments of the present application, the loss function of the BP neural network model is MSE, and the activation functions are set as tansig and purelin.

[0073] In summary, the method for establishing a fitting model by the sparrow optimization neural network perfectly solves the difficulties of low accuracy and high cost of the AOA and TDOA methods by establishing a model with existing data to predict application data. Establishing a model with a large amount of data does not require too much cost, and the method of data fitting also ensures the accuracy. The sparrow optimization BP neural network model positioning method is verified and trained through a large amount of data, enabling the model to handle most situations in the training scenario and not causing positioning deviation due to individual special signal strengths. In terms of the multipath problem, for the sparrow optimization BP neural network model positioning method, there will also be multipath propagation in the data collected before training the model. During the process of fitting and training the model with these data, the multipath propagation problem of the signal is also fitted, enabling the model to have good anti-interference ability against the multipath propagation of the signal and greatly reducing the influence of signal multipath propagation. The processing of multiple groups of data outputs during the prediction process further processes the interference of the signal and improves the positioning accuracy.

[0074] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0075] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more of the processes Figure 1 or multiple processes and / or blocks.

[0076] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one or more of the processes Figure 1 or multiple processes and / or blocks.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Therefore, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the processes Figure 1 or multiple processes and / or blocks.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still modifications or equivalent replacements can be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A method for locating disaster relief targets by optimizing a BP neural network based on a sparrow algorithm, characterized in that, Including: Preprocess the continuously numbered mobile phones. Collect mobile phone information through a drone equipped with a positioning payload. Preprocess the drone recording information during the drone's cruise and record it in a table. Here, the continuously numbered mobile phones refer to mobile phones that can normally receive and send signals. Establish a BP neural network model, initialize the weights and thresholds of the BP neural network model. Substitute the data of each sparrow into the BP neural network model. Input the table into the BP neural network model. Subtract the output mobile phone longitude and latitude of the BP neural network model from the actual mobile phone longitude and latitude as the fitness of the sparrow. Run the sparrow optimization algorithm to iteratively find the optimal fitness value. Use the sparrow data corresponding to the optimal fitness value as the final weights and thresholds of the BP neural network model. Use the table as the input to train the BP neural network model. Put the trained BP neural network model into the drone remote control so that the drone remote control can perform real-time processing on the received data. Determine the disaster-affected area of personnel through remote sensing technology. Automatically cruise the drone with a positioning payload over the disaster-affected area of personnel, collect the mobile phone information, and transmit the mobile phone information and drone recording information back to the drone remote control. Arrange the collected mobile phone data in groups of three rows for permutation and combination to form data rows. Use the arranged data rows as the input and input them into the trained BP neural network model to obtain the final predicted position longitude and latitude. Mark the mobile phone positions predicted by the BP neural network model on the map. When establishing the BP neural network model, initializing the weights and thresholds of the BP neural network model, and substituting the data of each sparrow into the BP neural network model, it includes: If the number of input layer nodes of the BP neural network model is n, the number of hidden layer nodes is m, and the number of output layer nodes is p, then the number of weights is N = n * m + m * p, and the number of thresholds is M = m + p. Set a sparrows, each sparrow has M + N data and includes all weights and thresholds, and initialize the data of each sparrow.

2. The disaster area rescue target positioning method based on optimizing the BP neural network by the sparrow algorithm according to claim 1, characterized in that, When preprocessing the continuously numbered mobile phones, it includes: Place the continuously numbered mobile phones in a square flat ground, use concrete bricks to bury the mobile phones in an "inclined type", and record the actual longitude and latitude of the mobile phones.

3. The disaster area rescue target positioning method based on the sparrow algorithm optimized BP neural network according to claim 2, characterized in that, When collecting mobile phone information through a drone equipped with a positioning payload, it includes: Install the positioning payload directly below the drone and keep the signal receiving surface of the payload facing down. Remotely control the drone to automatically cruise in the square flat ground and fly around the mobile phone. When the mobile phone is scanned, the drone interacts with the mobile phone to obtain the mobile phone information.

4. The method for locating disaster relief targets based on optimizing a BP neural network by a sparrow algorithm according to claim 3, wherein, The mobile phone information includes: mobile phone serial number and mobile phone signal strength. The drone recording information includes: drone altitude, drone longitude and latitude, and mobile phone signal strength.

5. The method for locating disaster relief targets based on optimizing a BP neural network by a sparrow algorithm according to claim 4, wherein When preprocessing the drone recording information during the drone's cruise and recording it in a table, it includes: Record and export the drone recording information during drone cruising through the remote controller, process the drone recording information in groups, combine three groups and the actual longitude and latitude of the mobile phone into a large group, and use a computer to put the recorded data into a table to be trained, where the mobile phone signal strength in the data of the three groups is the same mobile phone.

6. The method for positioning disaster relief targets based on a sparrow algorithm-optimized BP neural network according to claim 5, wherein, The large group is (drone altitude 1, drone longitude 1, drone latitude 1, mobile phone signal strength 1, drone altitude 2, drone longitude 2, drone latitude 2, mobile phone signal strength 2, drone altitude 3, drone longitude 3, drone latitude 3, mobile phone signal strength 3, actual longitude of the mobile phone, actual latitude of the mobile phone).

7. The method for positioning disaster relief targets based on a sparrow algorithm-optimized BP neural network according to claim 6, wherein, When arranging and combining the collected mobile phone data in groups of three as a row to form data rows, and using the arranged data rows as input into the trained BP neural network model to obtain the final predicted position longitude and latitude, it includes: Arrange and combine the collected mobile phone data in groups of three as a row to become a data row with 12 data in a row, and use the arranged data row as input into the trained BP neural network model, where the data row is (drone altitude 1, drone longitude 1, drone latitude 1, mobile phone signal strength 1, drone altitude 2, drone longitude 2, drone latitude 2, mobile phone signal strength 2, drone altitude 3, drone longitude 3, drone latitude 3, mobile phone signal strength 3).

8. The method for positioning disaster relief targets based on optimizing BP neural network by sparrow algorithm according to claim 7, characterized in that, When arranging and combining the collected mobile phone data in groups of three as a row to form data rows, and using the arranged data rows as input into the trained BP neural network model to obtain the final predicted position longitude and latitude, it includes: Sort the predicted longitude and latitude output by the BP neural network model by size, remove a total of 1 / 4 of the largest and smallest data, and take the average of the middle data to obtain the final predicted position longitude and latitude.

9. The method for locating disaster relief targets based on optimizing BP neural network by sparrow algorithm according to claim 8, characterized in that, The loss function of the BP neural network model is MSE, and the activation functions are set as tansig and purelin.

Images