An indoor space positioning system and method based on acoustic wave signals

Abstract

The present invention discloses an indoor space positioning system and method based on acoustic wave signals, which relates to the technical field of wireless positioning. The system includes: a mobile device, which is used to initiate a positioning request and present a space positioning map; a sound emitting module, which is used to emit near-ultrasonic acoustic waves with a fixed positioning period and is composed of an acoustic wave base station array for generating acoustic waves within a fixed frequency range and with a fixed intensity; an acoustic wave analysis module, which is used to receive acoustic wave signals and convert the acoustic wave signals into codewords that can be recognized by the management platform through an encoding method; and a management platform, which is used to control the sound emitting module to emit acoustic wave signals according to the positioning request initiated by the mobile device, and receive and process positioning data. According to the technical solution of the present application, high-precision indoor space positioning can be achieved without time synchronization between the mobile device and the acoustic wave base station, which has high application value.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless positioning, and particularly relates to an indoor space positioning system and method based on acoustic wave signals. Background Art

[0002] With the wide application of the Global Positioning System (GPS) and the BeiDou Navigation Satellite System, significant progress has been made in the accuracy and timeliness of outdoor positioning and navigation technologies. However, due to the obstruction of building structures in indoor spaces, satellite signals cannot effectively penetrate, resulting in the difficulty for traditional satellite positioning means to play their due roles in indoor environments. Therefore, the development of an efficient and reliable indoor space positioning technology has become a current research hotspot.

[0003] Among the existing indoor positioning technologies, the 5G + BeiDou positioning technology is a relatively advanced technical solution. This technology deploys 5G base stations and indoor simulated satellites in indoor spaces, uses precise time synchronization between terminals and base stations to send positioning signals to each other, and calculates the position through the time difference. However, this technology has some obvious deficiencies. First, the deployment process of 5G base stations and simulated satellites is relatively complex, requiring a large amount of infrastructure construction and equipment installation, and the construction cost and maintenance difficulty of the system are relatively high. Second, the user positioning terminal needs to be compatible with 5G and BeiDou positioning signals on the premise of precise time synchronization, which poses high requirements on its performance and limits its application on ordinary consumer-grade devices.

[0004] In addition, most of the existing indoor positioning technologies rely on the transmission of high-frequency signals, such as Wi-Fi, Bluetooth, or ultrasonic waves. Although these technologies can achieve indoor positioning to a certain extent, they have problems such as limited coverage, severe signal interference, and low positioning accuracy. For example, although the ultrasonic positioning system can achieve relatively high positioning accuracy, its coverage range is small and it is easily interfered by environmental noise, making it difficult to be widely applied in large indoor spaces. In view of the deficiencies of the existing technologies, the present application proposes an indoor space positioning system and method based on acoustic wave signals. Summary of the Invention

[0005] Technical Objectives

[0006] To solve the above problems, the object of the present invention is to provide an indoor space positioning system and method based on acoustic wave signals. The system and method use acoustic wave signals in the near-ultrasonic frequency band for positioning, avoiding the problem of precise time synchronization required in traditional indoor positioning technologies, and at the same time reducing the requirements for the performance of terminal devices. In addition, the acoustic wave base stations of the present invention have a large coverage range, can achieve a wider indoor space positioning, and support general-purpose communication devices such as smart phones, with high economy. Through the present invention, efficient and accurate positioning can be achieved in an indoor environment, providing a new solution for fields such as indoor navigation, intelligent logistics, and personnel management.

[0007] Technical solution

[0008] To achieve the above object, the present invention provides an indoor space positioning system and method based on acoustic wave signals, aiming to solve the problems of complex deployment, time synchronization required, and high requirements for terminal devices in existing indoor positioning technologies. The system and method arrange an acoustic wave base station array in an indoor space, distribute it in the form of an equidistant array and emit acoustic wave signals of a fixed intensity. After receiving the acoustic wave signals, the mobile device calculates its own position through the time difference positioning method without time synchronization with the base station, and finally uploads the calculation result to achieve real-time positioning and map display, with the advantages of simplified deployment, reduced terminal requirements, and high-precision positioning.

[0009] In the first aspect, the present invention provides an indoor space positioning system based on acoustic wave signals, including:

[0010] A mobile device, used to initiate a positioning request and present a space positioning map;

[0011] A sound generation module, used to emit near-ultrasonic acoustic waves with a fixed positioning period, which consists of an acoustic wave base station array for generating acoustic waves in a fixed frequency range and with a fixed intensity;

[0012] An acoustic wave analysis module, used to receive acoustic wave signals and convert the acoustic wave signals into codewords that can be recognized by the management platform through TDMA, FDMA, and CDMA coding methods. The codewords include mobile device information, the frequency, intensity, and reception time of the acoustic wave signals;

[0013] A management platform, used to control the sound generation module to emit acoustic wave signals according to the positioning request initiated by the mobile device, and receive and process positioning data.

[0014] Further, one of the acoustic wave base stations in the acoustic wave base station array is used as the coordinate origin, and the other base stations are distributed in the coordinate system in the form of an equidistant array. The fixed frequency of each acoustic wave base station is unique and the intensity of the emitted acoustic wave signals is the same.

[0015] Further, the frequency range of the acoustic wave signal is 19KHz - 23KHz.

[0016] Further, the acoustic wave base stations within the square area where the frequency band points are located are determined to emit acoustic wave signals according to the screening of the acoustic wave frequency and intensity.

[0017] Further, the mobile device is equipped with supporting positioning software for processing the received acoustic wave signals and outputting the position coordinates of the mobile device according to the processing results.

[0018] Further, the positioning software calculates the position coordinates of the mobile device through the following formula:

[0019]

[0020]

[0021] In the formula, and are the horizontal and vertical coordinates of the mobile device respectively; and are the horizontal and vertical coordinates of acoustic wave base station A respectively; and are the horizontal and vertical coordinates of acoustic wave base station B respectively; and are the horizontal and vertical coordinates of acoustic wave base station C respectively; is the distance difference between the mobile device and acoustic wave base stations A and B; is the distance difference between the mobile device and acoustic wave base stations A and C.

[0022] Further, the calculation formula of the position coordinates of the mobile device is analyzed by the iterative method, Newton method or least squares method.

[0023] Further, the management platform performs transcoding positioning on the spatial positioning map according to the position coordinates of the mobile device.

[0024] This method does not require complex infrastructure construction, significantly reducing the deployment difficulty and cost of the system; it does not require time synchronization between the mobile terminal and the base station, greatly reducing the performance requirements for terminal devices, enabling general-purpose communication devices to directly support the positioning function, and improving the versatility and applicability of the system.

[0025] Further, the mobile device is equipped with an inertial sensor for maintaining positioning accuracy through inertial navigation in the case of a short-term loss of the acoustic wave signal, performing coordinate positioning according to the received acoustic wave signal, and fusing the inertial sensor data after preprocessing operations such as denoising and filtering through a Kalman filter to estimate the displacement and attitude changes of the mobile device. The calculation formula of the Kalman filter is:

[0026]

[0027]

[0028] Wherein, is the position vector updated based on the measurement value at the th moment; is the position vector predicted based on the information at the th moment; is the Kalman gain matrix at the th moment; is the measurement vector at the th moment; is the measurement matrix; is the position covariance matrix updated based on the measurement value at the th moment; is the position covariance matrix predicted based on the information at the th moment; is the identity matrix consistent with the dimension of the position vector.

[0029] The continuous motion information provided by the inertial sensor can effectively reduce the error of the acoustic wave signal and improve the positioning accuracy; the inertial sensor is not affected by the interference of the acoustic wave signal. Even when the acoustic wave signal is lost or severely interfered, it can still provide relatively accurate position information and improve the anti-interference ability of the system in a complex environment.

[0030] Furthermore, the system further includes a multi-layer perceptron module for performing predictive spatial positioning by learning the relationship between the acoustic wave signal and the spatial position, specifically including: receiving the acoustic wave signals from multiple known and unknown acoustic wave base stations, annotating the acoustic wave signals as the training data set; extracting the features of the acoustic wave signals and combining them with the coordinates of the acoustic wave base stations as the input data for training the multi-layer perceptron model; constructing the multi-layer perceptron model, inputting the input data into the multi-layer perceptron model, and outputting the predicted position information.

[0031] By learning the complex non-linear relationship between the acoustic wave signal features and the position coordinates, the positioning accuracy is improved, and the system can handle the acoustic wave signals containing noise, making the system have a certain robustness. Even in the case of poor signal quality, it can provide relatively accurate positioning results through the non-linear fitting ability of the multi-layer perceptron.

[0032] In a second aspect, the present invention further provides an indoor space positioning method based on acoustic wave signals. The method is based on the system described in the first aspect above and includes:

[0033] The mobile device initiates a positioning request;

[0034] The management platform controls the sound emission module to emit near-ultrasonic waves with a fixed positioning period according to the positioning request initiated by the mobile device;

[0035] The sound wave analysis module converts the near-ultrasonic waves into codewords that can be recognized by the management platform through an encoding method;

[0036] The mobile device calculates its own position coordinates based on the time difference of the received sound wave signals;

[0037] The management platform receives and processes the positioning data uploaded by the mobile device and outputs the positioning result.

[0038] In a third aspect, the present invention further provides a computer device, including a management platform and a memory. The management platform is connected to the memory. The memory is used to store a computer program, and the management platform is used to execute the computer program stored in the memory so that the computer device executes at least one step of the indoor space positioning method based on sound wave signals described above.

[0039] In a fourth aspect, the present invention further provides a computer-readable storage medium. A computer program is stored in the computer-readable storage medium. When the computer program is executed by the management platform, it realizes at least one step of the indoor space positioning method based on sound wave signals described above.

[0040] In the present invention, a sound wave base station array is arranged in the indoor space, distributed in the form of an equidistant array and emits sound wave signals with a fixed intensity. After receiving the sound wave signals, the mobile device calculates its own position through the time difference positioning method, and finally uploads the calculation result to realize real-time positioning and map display. The application scenarios of the system and method are extensive, and it can achieve efficient and accurate positioning in the indoor environment, providing a new solution for indoor navigation, intelligent logistics, personnel management and other fields.

[0041] Beneficial effects

[0042] By implementing the indoor space positioning system and method based on sound wave signals provided by the present invention, the following technical effects are achieved:

[0043] (1) The present invention arranges an acoustic wave base station array in an indoor space, distributes it in the form of an equidistant array, and emits acoustic wave signals of a fixed intensity. After receiving the acoustic wave signals, the mobile device calculates its own position through the time difference positioning method. Without the need for complex infrastructure construction, it significantly reduces the deployment difficulty and cost of the system; without the need for time synchronization between the mobile terminal and the base station, it greatly reduces the performance requirements for terminal devices, enabling general-purpose communication devices to directly support the positioning function, and improving the versatility and applicability of the system; due to the relatively stable propagation speed of acoustic wave signals and the known frequency and position of each base station, this method can achieve high positioning accuracy and meet the requirements of application scenarios such as indoor navigation and personnel positioning.

[0044] (2) It is equipped with an inertial sensor, which is used to maintain the positioning accuracy through inertial navigation in the case of a short-term loss of acoustic wave signals, and combines the acoustic wave positioning information with the inertial sensor data through a Kalman filter. The continuous motion information provided by the inertial sensor can effectively reduce the error of acoustic wave signals and improve the positioning accuracy; the inertial sensor is not affected by the interference of acoustic wave signals, and can still provide relatively accurate position information even in the case of loss or severe interference of acoustic wave signals, improving the anti-interference ability of the system in complex environments.

[0045] (3) Predictive spatial positioning is carried out by learning the relationship between acoustic wave signals and spatial positions. By learning the complex non-linear relationship between the characteristics of acoustic wave signals and position coordinates, the positioning accuracy is improved, and it can process acoustic wave signals containing noise, enabling the system to have a certain degree of robustness. Even in the case of poor signal quality, it can provide relatively accurate positioning results through the non-linear fitting ability of a multi-layer perceptron. Description of the Drawings

[0046] To make the above indoor space positioning system and method based on acoustic wave signals of the present invention more clearly understandable, the following will briefly introduce the drawings required for the specific implementation of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings without creative efforts.

[0047] Figure 1 It represents a schematic flow chart of the indoor space positioning method based on acoustic wave signals;

[0048] Figure 2 It represents a schematic principle diagram of the indoor space positioning method based on acoustic wave signals. Detailed Description of the Invention

[0049] Example 1:

[0050] Provided is an indoor space positioning system and method based on acoustic wave signals. The indoor space positioning system based on acoustic wave signals includes: a mobile device, a sound emitting module, an acoustic wave analysis module, and a management platform. The flow of the indoor space positioning method based on acoustic wave signals is as Figure 1 shown, specifically for the indoor space positioning system and method in the following steps.

[0051] The mobile device is used to initiate a positioning request and present a space positioning map.

[0052] The sound emitting module is used to emit near-ultrasonic acoustic waves with a fixed positioning period and is composed of an acoustic wave base station array for generating acoustic waves with a fixed frequency range and a fixed intensity.

[0053] One of the acoustic wave base stations in the acoustic wave base station array is used as the coordinate origin, and the other base stations are distributed in the coordinate system in the form of an equidistant array. The fixed frequency of each acoustic wave base station is unique and the intensity of the emitted acoustic wave signals is the same.

[0054] The frequency range of the acoustic wave signals is 19KHz - 23KHz.

[0055] According to the acoustic wave frequency and intensity screening, determine the acoustic wave base stations within the square area where the frequency band points are located to emit acoustic wave signals.

[0056] The acoustic wave analysis module is used to receive the acoustic wave signals and convert the acoustic wave signals into codewords that can be recognized by the management platform through TDMA, FDMA, and CDMA coding methods. The codewords include mobile device information, the frequency, intensity, and reception time of the acoustic wave signals.

[0057] The mobile device is equipped with a supporting positioning software for processing the received acoustic wave signals and outputting the position coordinates of the mobile device according to the processing results.

[0058] As Figure 2 shown, the mobile device P is within the square area where the three nearest acoustic wave base stations A, B, and C are located. Assume the coordinates of acoustic wave base station A are ( , ), the coordinates of acoustic wave base station B are ( , ), the coordinates of acoustic wave base station C are ( , ), the coordinates of the mobile device P are ( , ), the specific time points when the mobile device P receives the acoustic wave signals from the three acoustic wave base stations are , and , the time when the acoustic wave signals are emitted is , and the propagation speed of the acoustic wave in space is ;

[0059] The distances between the mobile device P and three acoustic wave base stations , and as well as the distance differences and are expressed as:

[0060]

[0061]

[0062]

[0063]

[0064]

[0065] The calculation formula for the position coordinates of the mobile device P is:

[0066]

[0067]

[0068] The calculation formula for the position coordinates of the mobile device is analyzed by the iterative method, Newton's method or least squares method.

[0069] The management platform is used to control the sound - emitting module to emit acoustic wave signals according to the positioning request initiated by the mobile device, and receive and process positioning data.

[0070] The management platform performs transcoding positioning on the spatial positioning map according to the position coordinates of the mobile device.

[0071] Embodiment 2:

[0072] On the basis of the foregoing embodiment, the mobile device is equipped with an inertial sensor for maintaining positioning accuracy through inertial navigation in the case of a short - term loss of acoustic wave signals.

[0073] The inertial sensor includes an accelerometer, a gyroscope and a magnetometer.

[0074] Acceleration, angular velocity and magnetic field intensity data are collected by the inertial sensor at a certain frequency, and the timestamps of the inertial sensor data are recorded to ensure time synchronization with the acoustic wave signals.

[0075] The collected acoustic wave signals and inertial sensor data are packed, including the frequency and arrival time of the acoustic wave signals, the acceleration, angular velocity, magnetic field intensity of the inertial sensor, and the timestamps.

[0076] Perform coordinate positioning based on the received acoustic wave signal, and fuse the inertial sensor data after preprocessing operations such as denoising and filtering through a Kalman filter to estimate the displacement and attitude changes of the mobile device. The calculation formula of the Kalman filter is as follows:

[0077]

[0078]

[0079] In the formula, is the position vector updated based on the measurement value at the th moment; is the position vector predicted based on the information at the th moment; is the Kalman gain matrix at the th moment, which is used to determine the weight between the measurement value and the predicted value; is the measurement vector at the th moment, including the time difference of arrival of acoustic wave information and the acceleration and angular velocity of the inertial sensor; is the measurement matrix, which is used to describe how to obtain the measurement value from the position vector , and includes the mapping relationship from acoustic wave signals and inertial sensor data to position coordinates; is the position covariance matrix updated based on the measurement value at the th moment; is the position covariance matrix predicted based on the information at the th moment; is the identity matrix with the same dimension as the position vector.

[0080] Ensure the accuracy of spatial positioning in the case of a short-term loss of acoustic wave signals through the continuous position and attitude information provided by the inertial sensor, and be able to provide auxiliary positioning when the acoustic wave signal is blocked, improving the anti-interference ability of the system. Verification shows that when obtaining an average error similar to that of the above embodiment, the positioning accuracy can be improved by about 10% on the basis of the original positioning accuracy, indicating that adding an inertial sensor helps to improve the positioning accuracy on the basis of ensuring positioning accuracy, especially in an environment with strong signal interference, and provides auxiliary positioning when the acoustic wave signal is blocked or the acoustic wave base station array is abnormal.

[0081] Embodiment 3:

[0082] On the basis of the foregoing embodiment, the system adds a multi-layer perceptron module for predictive spatial positioning by learning the relationship between acoustic wave signals and spatial positions.

[0083] Select multiple acoustic wave base stations at known locations, receive the acoustic wave signals from the acoustic wave base stations through the microphone equipped on the mobile device, and record the arrival time of each acoustic wave signal.

[0084] Pack the collected acoustic wave signals, including information such as frequency, arrival time, timestamp, etc., as well as the coordinates of the corresponding acoustic wave base station.

[0085] Annotate the collected acoustic wave signals. The annotation content includes the frequency of the acoustic wave signal, the arrival time, the position coordinates of the reference point, etc., and store the annotated data as a training data set.

[0086] Clean the collected acoustic wave signals and remove noise and outliers.

[0087] Extract the features of the acoustic wave signals, such as time difference of arrival, signal strength, etc., and combine the feature data with the coordinates of the corresponding acoustic wave base station at the known location to obtain the input data for training the multi-layer perceptron model.

[0088] The architecture design of the multi-layer perceptron model includes: the number of neurons in the input layer is the same as the number of features; the number of neurons in the output layer is the same as the dimension of the target position coordinates.

[0089] The training process of the multi-layer perceptron model involves two stages: forward propagation and backward propagation. Among them, the formula for forward propagation is:

[0090]

[0091] In the formula, is the output vector of the th layer; is the weight matrix of the th layer, representing the connection weight from the th layer to the th layer; is the output vector of the th layer, that is, the input vector of the th layer; is the bias vector of the th layer, used to adjust the activation value of the neuron; is the weight vector of the th layer, used to perform element-wise weighting on the input features; is the activation function; is the element-wise multiplication operation.

[0092] The formula for backward propagation is:

[0093]

[0094]

[0095]

[0096] In the formula, is the gradient of the weight matrix of the th layer; represents the output vector of the th layer, that is, the input vector of the th layer; is the error term of the th layer; is the regularization coefficient; is the weight matrix of the th layer; is the gradient of the bias vector of the th layer; represents the gradient of the weight vector of the th layer; is the element-wise multiplication operation.

[0097] Input the input data into the multi-layer perceptron model to output the predicted position information. After adding the multi-layer perceptron module described in this embodiment and optimizing the algorithm, the inventors found that it can significantly suppress the positioning error caused by multiple propagation paths generated by sound waves due to refraction, reflection, diffraction, and diffraction in the indoor environment, thereby significantly improving the positioning accuracy.

[0098] For example, assume there is a multi-layer perceptron model, including an input layer, a hidden layer, and an output layer, each layer having one neuron, and assume there is a training sample;

[0099] In the forward propagation, assume the input vector , the weight matrix , the bias vector , the weight vector ;

[0100] From the input layer to the hidden layer, calculate the output of the hidden layer:

[0101]

[0102] From the hidden layer to the output layer, calculate the output of the output layer:

[0103]

[0104] In the backpropagation, assume the loss function , where is the true value, is the predicted value;

[0105] Calculate the gradient of the loss function:

[0106]

[0107] Calculate the weight gradient of the output layer. Assume the regularization coefficient :

[0108]

[0109] Calculate the bias gradient of the output layer:

[0110]

[0111] Calculate the weight gradient of the hidden layer:

[0112]

[0113] The effect of the multi-layer perceptron module is shown in Table 1.

[0114] Table 1. Summary of the multi-layer perceptron module

[0115]

[0116] According to the experimental table, the error between the predicted position and the actual position of the multi-layer perceptron model is very small, and the maximum error is only 0.07 meters. This indicates that the multi-layer perceptron model can effectively learn the relationship between the acoustic wave signal and the position, thereby achieving high-precision indoor positioning and being applicable to various indoor positioning application scenarios.

[0117] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable non-transitory storage media containing computer-usable program code.

[0118] The present invention can provide computer program instructions to the management platform of a general computer, a special computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the management platform of the computer or other programmable data processing devices generate a device for implementing the system.

[0119] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices 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 of the system.

[0120] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing steps for implementing the functions of the system in the instructions executed on the computer or other programmable apparatus.

Claims

1. An indoor space positioning system based on acoustic signals, including a mobile device for initiating a positioning request and presenting a spatial positioning map, characterized in that, It further includes a sound - emitting module, a sound - wave analysis module, a management platform, and a multi - layer perceptron module; The sound - emitting module is used to emit near - ultrasonic sound waves with a fixed positioning period, and is composed of an array of sound - wave base stations for generating sound waves within a fixed frequency range and with a fixed intensity. Among them, one of the sound - wave base stations in the sound - wave base - station array is used as the coordinate origin, and the other base stations are distributed in the coordinate system in the form of an equidistant array. The fixed frequency of each sound - wave base station is unique and the intensity of the emitted sound - wave signal is the same; The sound - wave analysis module is used to receive sound - wave signals and convert the sound - wave signals into codewords that can be recognized by the management platform through an encoding method. The codewords include the frequency, intensity, and reception time of the sound - wave signals; The management platform is used to receive and process positioning data, and control the sound - emitting module to emit sound - wave signals according to the positioning request initiated by the mobile device; The multi-layer perceptron module is used to perform predictive spatial positioning by learning the relationship between acoustic signals and spatial positions. Its training process involves two stages: forward propagation and backward propagation. Among them, the formula for forward propagation is: ; In the formula, is the output vector of the th layer; is the weight matrix of the th layer; is the output vector of the th layer; is the bias vector of the th layer; is the weight vector of the th layer; is the activation function; is the element-wise multiplication operation; The formula for backward propagation is: ; ; ; In the formula, is the gradient of the weight matrix of the th layer; is the error term of the th layer; is the regularization coefficient; is the gradient of the bias vector of the th layer; represents the gradient of the weight vector of the th layer.

2. The system according to claim 1, wherein: The frequency range of the sound - wave signal is 19KHz - 23KHz.

3. The system according to claim 1, wherein: The mobile device is deployed with supporting positioning software, which is used to process the received sound - wave signals and output the position coordinates of the mobile device according to the processing results.

4. The system according to claim 3, wherein: The positioning software calculates the position coordinates of the mobile device through the following formula: Wherein, and are the horizontal and vertical coordinates of the mobile device respectively; and are the horizontal and vertical coordinates of acoustic wave base station A respectively; and are the horizontal and vertical coordinates of acoustic wave base station B respectively; and are the horizontal and vertical coordinates of acoustic wave base station C respectively; is the distance difference between the mobile device and acoustic wave base stations A and B; is the distance difference between the mobile device and acoustic wave base stations A and C.

5. The system according to claim 1, wherein: The mobile device is equipped with an inertial sensor, which is used to maintain positioning accuracy through inertial navigation in the case of a short - term loss of sound - wave signals, perform coordinate positioning according to the received sound - wave signals, and fuse the inertial - sensor data after denoising and filtering pre - processing operations through a Kalman filter to estimate the displacement and attitude changes of the mobile device. The calculation formula of the Kalman filter is: Wherein, is the position vector updated based on the measurement value at the th moment; is the position vector predicted based on the information at the th moment; is the Kalman gain matrix at the th moment; is the measurement vector at the th moment; is the measurement matrix; is the position covariance matrix updated based on the measurement value at the th moment; is the position covariance matrix predicted based on the information at the th moment; is the identity matrix consistent with the dimension of the position vector.

6. The system according to claim 1, wherein: The multi - layer perceptron module specifically includes: receiving sound - wave signals from multiple sound - wave base stations at known positions, annotating the sound - wave signals as a training data set; extracting the features of the sound - wave signals and combining them with the coordinates of the sound - wave base stations as the input data for training the multi - layer perceptron model; constructing a multi - layer perceptron model, inputting the input data into the multi - layer perceptron model, and outputting predicted position information.

7. An indoor space positioning method based on sound - wave signals, wherein: The implementation of the method is based on the system according to any one of claims 1 - 6: The method includes: The mobile device initiates a positioning request; The management platform controls the sound - emitting module to emit near - ultrasonic sound waves with a fixed positioning period according to the positioning request initiated by the mobile device; The sound - wave analysis module converts the near - ultrasonic sound waves into codewords that can be recognized by the management platform through an encoding method; The mobile device calculates its own position coordinates according to the time difference of the received sound - wave signals; The management platform receives and processes the positioning data uploaded by the mobile device and outputs the positioning result.

8. A computer device, comprising a management platform and a memory, the management platform being connected to the memory, the memory being used for storing a computer program, characterized in that: The management platform is used to execute the computer program stored in the memory so that the computer device executes at least one step in the method according to claim 7.

9. A computer-readable storage medium storing a computer program therein, characterized in that: When the computer program is run, at least one step of the method recited in claim 7 is implemented.

Images