An indoor personnel positioning method, device, equipment and storage medium

Abstract

The application discloses an indoor personnel positioning method and device, equipment and storage medium, and relates to the technical field of positioning. The method comprises the following steps: collecting a target vital sign signal of a to-be-positioned person through a wearable device; determining a target echo signal from a plurality of echo signals based on the target vital sign signal by using a radio frequency transceiver device installed indoors; positioning the target echo signal by using a preset positioning model to obtain sparse point positioning information; determining inertial positioning information based on inertial information of the to-be-positioned person by using a strapdown inertial navigation system on an inertial measurement unit in the wearable device; and determining indoor positioning information of the to-be-positioned person by using an extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from a plurality of radio frequency transceiver devices. The application combines the sparse point positioning information determined by the radio frequency transceiver device and the inertial positioning information determined by the strapdown inertial navigation system to obtain more accurate indoor positioning information.

Description

Technical Field

[0001] This invention relates to the field of positioning technology, and in particular to an indoor personnel positioning method, device, equipment, and storage medium. Background Technology

[0002] Indoor positioning, as an important branch of positioning technology, has gradually attracted widespread attention and research in recent years with the rise of smart technology, the Internet of Things, and mobile applications. Indoor positioning is used to achieve precise positioning within buildings, providing people with positioning, navigation, and monitoring services in indoor environments, meeting the ever-growing demand for higher accuracy and practicality in indoor positioning.

[0003] Indoor positioning is more challenging due to the complexity of indoor spaces, multipath effects in signal propagation, signal blockage, multi-scale movement, and the requirement for high positioning accuracy. To achieve indoor positioning, various technologies exist, including wireless signal positioning (such as Wi-Fi, Bluetooth, and RFID), inertial sensor positioning (such as accelerometers and gyroscopes), and visual positioning (using camera images). However, all these indoor positioning technologies have inherent biases, and improving the accuracy of indoor positioning remains a problem to be solved. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide an indoor personnel positioning method, apparatus, device, and storage medium, which can combine sparse point positioning information determined by a radio frequency transceiver device and inertial positioning information determined by a strapdown inertial navigation system to obtain more accurate indoor positioning information. The specific solution is as follows:

[0005] Firstly, this application provides an indoor personnel positioning method, including:

[0006] Collect target vital signs signals of the person to be located using wearable devices;

[0007] Using an indoor radio frequency transceiver device and based on the target's vital signs signal, the target echo signal is determined from several echo signals. The preset positioning model in the radio frequency transceiver device is used to locate the person in the target echo signal, so as to obtain the corresponding sparse point positioning information.

[0008] The inertial information of the person to be located is obtained by the strapdown inertial navigation system installed on the inertial measurement unit in the wearable device, and the inertial positioning information is determined based on the inertial information.

[0009] The indoor positioning information of the person to be located is determined by using the extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from the plurality of radio frequency transceivers.

[0010] Optionally, the step of collecting the target vital signs signal of the person to be located through the wearable device includes:

[0011] The target respiratory signal and / or target heart rate signal of the person to be located are collected by wearable devices.

[0012] Optionally, the step of using an indoor radio frequency transceiver and determining the target echo signal from a plurality of echo signals based on the target vital signs signal includes:

[0013] A number of radio frequency signals are transmitted and a number of corresponding echo signals are received by an indoor radio frequency transceiver device, and distance information and vital signs signals to be matched are determined for each of the echo signals; the radio frequency signals are signals whose frequency varies with time.

[0014] The target vital signs signal of the person to be located is acquired from the wearable device through the radio frequency transceiver device, and the matching result of each of the vital signs signals to be matched with the target vital signs signal is determined. Based on the matching result, the target echo signal is determined from the plurality of echo signals.

[0015] Optionally, determining the distance information corresponding to the plurality of echo signals and the vital sign signals to be matched includes:

[0016] The time delay of each echo signal arriving at the radio frequency transceiver is determined, and the corresponding frequency drop value is determined based on each time delay;

[0017] Based on each of the frequency drop values, the frequency of the corresponding echo signal is modulated to obtain the target frequency corresponding to each of the echo signals.

[0018] Based on the target frequency, speed of light, and slope of the radio frequency signal corresponding to each echo signal, the distance information corresponding to each echo signal is determined, and the corresponding vital sign signal to be matched is determined based on the phase shift signal and phase signal corresponding to each echo signal.

[0019] Optionally, before using the preset positioning model in the radio frequency transceiver to locate personnel in the target echo signal to obtain the corresponding sparse point positioning information, the method further includes:

[0020] An initial localization model is constructed based on a dual-hidden-layer neural network, and the initial localization model is configured using a particle swarm optimization algorithm to obtain a configured localization model.

[0021] Acquire several historical echo signals and extract historical multi-dimensional features corresponding to each of the historical echo signals to construct a training set; the multi-dimensional features include distance information, vital signs signals, phase shift signals, and phase signals.

[0022] The configured localization model is trained using the training set to obtain a trained preset localization model.

[0023] Optionally, the step of using a preset positioning model in the radio frequency transceiver to locate personnel in the target echo signal to obtain corresponding sparse point positioning information includes:

[0024] Extract the multi-dimensional features of the target corresponding to the target echo signal, and use the preset positioning model in the radio frequency transceiver to locate the person based on the multi-dimensional features of the target. Combine the return orientation information of the target echo signal to determine the sparse point positioning information of the person to be located.

[0025] Optionally, determining the indoor positioning information of the person to be located using the extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from the plurality of radio frequency transceivers includes:

[0026] The extended Kalman filter in the wearable device determines whether the sparse point positioning information is obtained from the plurality of radio frequency transceivers;

[0027] If the sparse point positioning information is not obtained from any radio frequency transceiver, the indoor positioning information of the person to be located is determined based on the inertial positioning information.

[0028] If the sparse point positioning information is obtained from any of the radio frequency transceivers, the target sparse point positioning information is determined based on the obtained sparse point positioning information, and the target sparse point positioning information is fused with the inertial positioning information to obtain the indoor positioning information of the person to be located.

[0029] Secondly, this application provides an indoor personnel positioning device, comprising:

[0030] The vital sign acquisition module is used to acquire the target vital sign signals of the person to be located through wearable devices;

[0031] The radio frequency echo positioning module is used to determine the target echo signal from several echo signals based on the target's vital signs signal using an indoor radio frequency transceiver device, and to perform personnel positioning on the target echo signal using a preset positioning model in the radio frequency transceiver device, so as to obtain the corresponding sparse point positioning information.

[0032] An inertial positioning module is used to acquire the inertial information of the person to be located through a strapdown inertial navigation system installed on the inertial measurement unit in the wearable device, and to determine inertial positioning information based on the inertial information.

[0033] An indoor positioning determination module is used to determine the indoor positioning information of the person to be located by utilizing the extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from the plurality of radio frequency transceivers respectively.

[0034] Thirdly, this application provides an electronic device, comprising:

[0035] Memory, used to store computer programs;

[0036] A processor is used to execute the computer program to implement the aforementioned indoor personnel positioning method.

[0037] Fourthly, this application provides a computer-readable storage medium for storing a computer program that, when executed by a processor, implements the aforementioned indoor personnel positioning method.

[0038] In this application, a wearable device is used to collect the target vital signs signal of the person to be located; an indoor radio frequency transceiver is used to determine the target echo signal from several echo signals based on the target vital signs signal, and a preset positioning model in the radio frequency transceiver is used to locate the person using the target echo signal to obtain the corresponding sparse point positioning information; the inertial information of the person to be located is obtained through a strapdown inertial navigation system installed on the inertial measurement unit in the wearable device, and inertial positioning information is determined based on the inertial information; the indoor positioning information of the person to be located is determined using an extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from several radio frequency transceivers respectively. Therefore, this application can determine the target echo signal corresponding to the person to be located from several echo signals by using the target vital sign signal of the person to be located, and input the target echo signal into a preset positioning model to perform indoor personnel positioning, thereby obtaining the corresponding sparse point positioning information. Then, by combining the sparse point positioning information determined by the preset positioning model in the radio frequency transceiver device and the inertial positioning information determined by the strapdown inertial navigation system, more accurate indoor positioning information can be obtained, thereby improving the accuracy of indoor personnel positioning. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0040] Figure 1 This application discloses a flowchart of an indoor personnel positioning method.

[0041] Figure 2 This application discloses a specific indoor personnel positioning method flowchart;

[0042] Figure 3 This is a schematic diagram of an indoor personnel positioning device disclosed in this application;

[0043] Figure 4 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Due to the complexity of indoor spaces, multipath effects in signal propagation, signal blockage, multi-scale movement, and the requirements for positioning accuracy, many current indoor positioning technologies suffer from inaccuracies. Therefore, this application provides an indoor personnel positioning method that combines sparse point positioning information determined by a radio frequency transceiver with inertial positioning information determined by a strapdown inertial navigation system to obtain more accurate indoor positioning information.

[0046] See Figure 1 As shown, an embodiment of the present invention discloses an indoor personnel positioning method, including:

[0047] Step S11: Collect the target vital signs signals of the person to be located using wearable devices.

[0048] In this embodiment, a wearable device capable of collecting vital sign signals is worn by the person to be located, thereby collecting the target respiratory signal and / or target heart rate signal of the person to be located. The wearable device includes, but is not limited to, smartwatches, smart bracelets, etc.

[0049] Step S12: Using an indoor radio frequency transceiver device and based on the target vital signs signal, determine the target echo signal from several echo signals, and use the preset positioning model in the radio frequency transceiver device to locate the person in the target echo signal, so as to obtain the corresponding sparse point positioning information.

[0050] In this embodiment, an indoor radio frequency transceiver is installed. The transceiver's radio frequency chip transmits radio frequency signals whose frequency varies over time, and the receiving antenna of the transceiver receives the echo signals. The received echo signals are then stored and preprocessed. The preprocessing of the echo signals includes Kalman filtering in the time domain and mean filtering in the frequency domain to remove echo signals caused by noise, leaving mostly echo signals reflected or scattered by the human body. Furthermore, a communication connection is established between a wearable device and the transceiver. The wearable device transmits the target vital signs signal of the person to be located to the transceiver. After receiving the target vital signs signal, the transceiver determines the target echo signal from the preprocessed echo signals based on the target vital signs signal. Then, a preset positioning model in the transceiver is used to locate the person indoors using the target echo signal, obtaining corresponding sparse point positioning information.

[0051] In this embodiment, before using a preset positioning model in the radio frequency transceiver device to locate personnel from the target echo signal and obtain the corresponding sparse point positioning information, the method further includes: constructing an initial positioning model based on a dual-hidden-layer neural network, and configuring the initial positioning model using a particle swarm optimization algorithm to obtain a configured positioning model; acquiring several historical echo signals and extracting historical multi-dimensional features corresponding to the historical echo signals to construct a training set; the multi-dimensional features include distance information, vital signs, phase shift signals, and phase signals; and training the configured positioning model using the training set to obtain a trained preset positioning model. It is understood that, in order to achieve a lightweight recognition algorithm with small training data samples, this application uses a dual-hidden-layer neural network to construct the initial positioning model; and in order to reduce the memory consumption of Neural Architecture Search (NAS), a particle swarm optimization algorithm (PSO) is used to configure the initial positioning model to obtain a configured positioning model. Several historical echo signals were acquired, and historical multi-dimensional features corresponding to each historical echo signal were extracted. Sparse point localization information was also labeled for each historical multi-dimensional feature to construct a training set. The distance information reflects the distance between the target person and the radio frequency transceiver. The configured localization model was trained using the training set to obtain a pre-trained preset localization model.

[0052] After determining the target echo signal corresponding to the person to be located, the target multi-dimensional features corresponding to the target echo signal are extracted. The target multi-dimensional features include target distance information, target vital signs signal, target phase shift signal and target phase signal. The preset positioning model in the radio frequency transceiver device is used to locate the person based on the target multi-dimensional features, and the sparse point positioning information of the person to be located is determined by combining the return orientation information of the target echo signal.

[0053] Step S13: Obtain the inertial information of the person to be located through the strapdown inertial navigation system installed on the inertial measurement unit in the wearable device, and determine the inertial positioning information based on the inertial information.

[0054] In this embodiment, the inertial information of the person to be located is collected by the inertial measurement unit in the wearable device and transmitted to the strapdown inertial navigation system (SINS) installed on the inertial measurement unit, so that the SINS can determine the inertial positioning information of the person to be located based on the angular motion information and linear motion information contained in the inertial information.

[0055] Step S14: Using the extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from the plurality of radio frequency transceivers, determine the indoor positioning information of the person to be located.

[0056] In this embodiment, because the signal transmission process is easily affected by multipath effects, signal blockage, and other factors, the wearable device may not be able to receive the sparse point positioning information sent by the radio frequency transceiver. Therefore, this application determines the final indoor positioning information of the person to be located by combining the sparse point positioning information determined by the preset positioning model in the radio frequency transceiver and the inertial positioning information determined by the strapdown inertial navigation system. Specifically, the extended Kalman filter in the wearable device determines whether sparse point positioning information is obtained from several radio frequency transceivers. If no sparse point positioning information is obtained from any radio frequency transceiver, the indoor positioning information of the person to be located is determined based on the inertial positioning information. If sparse point positioning information is obtained from any radio frequency transceiver, the target sparse point positioning information is determined based on the obtained sparse point positioning information, and the target sparse point positioning information is fused with the inertial positioning information to obtain the indoor positioning information of the person to be located.

[0057] Therefore, this application can determine the target echo signal corresponding to the person to be located from several echo signals by using the target vital sign signal of the person to be located, and input the target echo signal into a preset positioning model to perform indoor personnel positioning, thereby obtaining the corresponding sparse point positioning information. Then, by combining the sparse point positioning information determined by the preset positioning model in the radio frequency transceiver device and the inertial positioning information determined by the strapdown inertial navigation system, more accurate indoor positioning information can be obtained, thereby improving the accuracy of indoor personnel positioning.

[0058] As described in the previous embodiment, this application describes the overall process of indoor personnel positioning. Next, this application will elaborate on how to determine the target echo signal from several echo signals based on the target vital sign signals of the person to be located. See also... Figure 2 As shown, this embodiment of the invention discloses a process for determining a target echo signal, including:

[0059] Step S21: Transmit several radio frequency signals and receive several corresponding echo signals through an indoor radio frequency transceiver device, and determine the distance information and the vital signs signal to be matched corresponding to the several echo signals respectively; the radio frequency signal is a signal whose frequency changes with time.

[0060] In this embodiment, an indoor radio frequency transceiver transmits radio frequency signals with frequencies varying over time within a corresponding range based on the propagation radius. Several consecutively received echo signals are stored, and each echo signal undergoes Kalman filtering in the time domain and mean filtering in the frequency domain to remove noise-generated echo signals, resulting in several echo signals reflected or scattered by the human body. Then, distance information corresponding to each echo signal is determined, and the corresponding vital sign signals to be matched are determined based on the phase shift and phase signals corresponding to each echo signal.

[0061] Specifically, determining the distance information corresponding to each echo signal includes: determining the time delay of each echo signal arriving at the radio frequency transceiver, and determining the corresponding frequency drop value based on each time delay; modulating the frequency of the corresponding echo signal based on each frequency drop value to obtain the target frequency corresponding to each echo signal; and determining the distance information corresponding to each echo signal based on the target frequency, the speed of light, and the slope of the radio frequency signal corresponding to each echo signal. It can be understood that the time delay of different echo signals arriving at the radio frequency transceiver varies depending on the distance between the person to be located and the radio frequency transceiver. Therefore, the frequency drop value can be determined based on the time delay, and the frequency of the echo signal can be reduced accordingly using the frequency drop value to obtain the target frequency; the higher the target frequency, the farther the person to be located is from the radio frequency transceiver; then, the distance information corresponding to the echo signal is determined based on the target frequency, the speed of light, and the slope of the radio frequency signal emitted by the radio frequency transceiver; the formulas involved are as follows:

[0062]

[0063] Where f represents the target frequency, S represents the slope of the radio frequency signal corresponding to the echo signal, c represents the speed of light, and d represents the distance information corresponding to the echo signal.

[0064] Step S22: Obtain the target vital signs signal of the person to be located from the wearable device through the radio frequency transceiver device, determine the matching result of each of the vital signs signals to be matched with the target vital signs signal, and determine the target echo signal from the plurality of echo signals based on the matching result.

[0065] In this embodiment, the wearable device wirelessly transmits the target vital sign signals of the person to be located to a radio frequency transceiver. After the radio frequency transceiver receives the target vital sign signals, it matches each potential vital sign signal with the target vital sign signal to obtain a matching result. Based on the matching result, the vital sign signal with the highest matching degree and a matching degree greater than a preset matching threshold is determined from several potential vital sign signals. Then, the target echo signal corresponding to the vital sign signal with the highest matching degree and a matching degree greater than the preset matching threshold is determined from several echo signals. At this time, the distance information corresponding to the target echo signal is the target distance information corresponding to the person to be located.

[0066] It should be noted that this application can also collect the target vital signs signals of the person to be located using a wearable device and send them to a radio frequency transceiver. The radio frequency transceiver performs Kalman filtering in the time domain and mean filtering in the frequency domain on the acquired echo signals, and determines the distance information corresponding to each of the filtered echo signals. Based on the correlation between each distance information and the phase information and energy density of the target vital signs signal, the radio frequency transceiver determines the distance information with the highest correlation, which serves as the target distance information corresponding to the person to be located. Thus, based on the target distance information, the corresponding target echo signal can be determined from the several echo signals. Then, a preset positioning model in the radio frequency transceiver is used to locate the person using the target echo signal to obtain the corresponding sparse point positioning information. Finally, the inertial information of the person to be located is acquired through a strapdown inertial navigation system installed on the inertial measurement unit of the wearable device, and inertial positioning information is determined based on this inertial information. By utilizing the extended Kalman filter in the wearable device and based on inertial positioning information and sparse point positioning information obtained from several radio frequency transceivers, the final indoor positioning information of the person to be located is determined.

[0067] Therefore, this application removes noise-generated echo signals by performing Kalman filtering in the time domain and mean filtering in the frequency domain. Furthermore, by determining the distance information corresponding to several echo signals and the vital signs signals to be matched, the target echo signal corresponding to the vital sign signal with the highest matching degree and a matching degree greater than a preset matching threshold is determined from several echo signals based on the matching results between the vital sign signals to be matched and the target vital sign signals of the person to be located. Further, after determining the target echo signal, indoor personnel positioning using the target echo signal via a preset positioning model in the radio frequency transceiver device can obtain more accurate sparse point positioning information, thereby improving the accuracy of indoor personnel positioning.

[0068] See Figure 3 As shown, an embodiment of the present invention discloses an indoor personnel positioning device, comprising:

[0069] The vital sign acquisition module 11 is used to acquire the target vital sign signals of the person to be located through a wearable device;

[0070] The radio frequency echo positioning module 12 is used to determine the target echo signal from several echo signals based on the target vital signs signal using an indoor radio frequency transceiver device, and to perform personnel positioning on the target echo signal using a preset positioning model in the radio frequency transceiver device, so as to obtain the corresponding sparse point positioning information.

[0071] The inertial positioning module 13 is used to acquire the inertial information of the person to be located through the strapdown inertial navigation system installed on the inertial measurement unit in the wearable device, and to determine the inertial positioning information based on the inertial information.

[0072] The indoor positioning determination module 14 is used to determine the indoor positioning information of the person to be located by using the extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from the plurality of radio frequency transceivers respectively.

[0073] Therefore, this application can determine the target echo signal corresponding to the person to be located from several echo signals by using the target vital sign signal of the person to be located, and input the target echo signal into a preset positioning model to perform indoor personnel positioning, thereby obtaining the corresponding sparse point positioning information. Then, by combining the sparse point positioning information determined by the preset positioning model in the radio frequency transceiver device and the inertial positioning information determined by the strapdown inertial navigation system, more accurate indoor positioning information can be obtained, thereby improving the accuracy of indoor personnel positioning.

[0074] In some specific embodiments, the vital signal acquisition module 11 includes:

[0075] The signal acquisition unit is used to acquire the target respiratory signal and / or target heart rate signal of the person to be located through a wearable device.

[0076] In some specific embodiments, the radio frequency echo positioning module 12 includes:

[0077] The signal determination submodule is used to transmit several radio frequency signals and receive several corresponding echo signals through an indoor radio frequency transceiver, and determine the distance information and the vital signs signal to be matched corresponding to the several echo signals respectively; the radio frequency signal is a signal whose frequency changes with time.

[0078] The vital sign matching unit is used to acquire the target vital sign signal of the person to be located from the wearable device through the radio frequency transceiver device, determine the matching result of each of the vital sign signals to be matched with the target vital sign signal, and determine the target echo signal from the plurality of echo signals based on the matching result.

[0079] In some specific embodiments, the signal determination submodule includes:

[0080] A drop value determination unit is used to determine the time delay of each of the echo signals arriving at the radio frequency transceiver, and to determine the corresponding frequency drop value based on each of the time delays.

[0081] A frequency modulation unit is used to modulate the frequency of the corresponding echo signal based on each of the frequency drop values ​​to obtain a target frequency corresponding to each of the echo signals.

[0082] The information determination unit is used to determine the distance information corresponding to each of the echo signals based on the target frequency, the speed of light, and the slope of the radio frequency signal corresponding to each of the echo signals, and to determine the corresponding vital sign signal to be matched based on the phase shift signal and phase signal corresponding to each of the echo signals.

[0083] In some specific embodiments, the indoor personnel positioning device further includes:

[0084] The model configuration unit is used to construct an initial localization model based on a dual-hidden-layer neural network and to configure the initial localization model using a particle swarm optimization algorithm to obtain a configured localization model.

[0085] The training set construction unit is used to acquire several historical echo signals and extract historical multi-dimensional features corresponding to the several historical echo signals respectively to construct a training set; the multi-dimensional features include distance information, vital signs signals, phase shift signals and phase signals;

[0086] The model training unit is used to train the configured localization model using the training set to obtain a trained preset localization model.

[0087] In some specific embodiments, the radio frequency echo positioning module 12 includes:

[0088] The sparse point localization determination unit is used to extract the target multi-dimensional features corresponding to the target echo signal, and use the preset localization model in the radio frequency transceiver device to locate the personnel based on the target multi-dimensional features, and combine the return orientation information of the target echo signal to determine the sparse point localization information of the personnel to be located.

[0089] In some specific embodiments, the indoor positioning determination module 14 includes:

[0090] The information acquisition and judgment unit is used to determine whether the sparse point positioning information is acquired from the plurality of radio frequency transceivers through the extended Kalman filter in the wearable device;

[0091] An indoor positioning determination unit is used to determine the indoor positioning information of the person to be located based on the inertial positioning information if the sparse point positioning information is not obtained from any radio frequency transceiver device.

[0092] The information fusion unit is configured to, if the sparse point positioning information is obtained from any of the radio frequency transceivers, determine the target sparse point positioning information based on the obtained sparse point positioning information, and fuse the target sparse point positioning information with the inertial positioning information to obtain the indoor positioning information of the person to be located.

[0093] Furthermore, embodiments of this application also disclose an electronic device, Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0094] Figure 4 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the indoor personnel positioning method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0095] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0096] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0097] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the indoor personnel positioning method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include a computer program capable of performing other specific tasks.

[0098] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned indoor personnel positioning method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0099] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0100] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0101] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0102] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0103] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for locating people indoors, characterized in that, include: Collect target vital signs signals of the person to be located using wearable devices; Using an indoor radio frequency transceiver device and based on the target's vital signs signal, the target echo signal is determined from several echo signals. The preset positioning model in the radio frequency transceiver device is used to locate the person in the target echo signal, so as to obtain the corresponding sparse point positioning information. The inertial information of the person to be located is obtained by the strapdown inertial navigation system installed on the inertial measurement unit in the wearable device, and the inertial positioning information is determined based on the inertial information. The indoor positioning information of the person to be located is determined by using the extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from the plurality of radio frequency transceivers.

2. The indoor personnel positioning method according to claim 1, characterized in that, The process of collecting target vital sign signals of the person to be located via wearable devices includes: The target respiratory signal and / or target heart rate signal of the person to be located are collected by wearable devices.

3. The indoor personnel positioning method according to claim 1, characterized in that, The method of determining the target echo signal from several echo signals based on the target's vital signs signal using an indoor-installed radio frequency transceiver includes: A number of radio frequency signals are transmitted and a number of corresponding echo signals are received by an indoor radio frequency transceiver device, and distance information and vital signs signals to be matched are determined for each of the echo signals; the radio frequency signals are signals whose frequency varies with time. The target vital signs signal of the person to be located is acquired from the wearable device through the radio frequency transceiver device, and the matching result of each of the vital signs signals to be matched with the target vital signs signal is determined. Based on the matching result, the target echo signal is determined from the plurality of echo signals.

4. The indoor personnel positioning method according to claim 3, characterized in that, The determination of the distance information corresponding to the plurality of echo signals and the vital sign signals to be matched includes: The time delay of each echo signal arriving at the radio frequency transceiver is determined, and the corresponding frequency drop value is determined based on each time delay; Based on each of the frequency drop values, the frequency of the corresponding echo signal is modulated to obtain the target frequency corresponding to each of the echo signals. Based on the target frequency, speed of light, and slope of the radio frequency signal corresponding to each echo signal, the distance information corresponding to each echo signal is determined, and the corresponding vital sign signal to be matched is determined based on the phase shift signal and phase signal corresponding to each echo signal.

5. The indoor personnel positioning method according to claim 1, characterized in that, Before using the preset positioning model in the radio frequency transceiver device to locate personnel in the target echo signal and obtain the corresponding sparse point positioning information, the method further includes: An initial localization model is constructed based on a dual-hidden-layer neural network, and the initial localization model is configured using a particle swarm optimization algorithm to obtain a configured localization model. Acquire several historical echo signals and extract historical multi-dimensional features corresponding to each of the historical echo signals to construct a training set; the multi-dimensional features include distance information, vital signs signals, phase shift signals, and phase signals. The configured localization model is trained using the training set to obtain a trained preset localization model.

6. The indoor personnel positioning method according to claim 5, characterized in that, The step of using a preset positioning model in the radio frequency transceiver to locate personnel in the target echo signal, in order to obtain corresponding sparse point positioning information, includes: Extract the multi-dimensional features of the target corresponding to the target echo signal, and use the preset positioning model in the radio frequency transceiver to locate the person based on the multi-dimensional features of the target. Combine the return orientation information of the target echo signal to determine the sparse point positioning information of the person to be located.

7. The indoor personnel positioning method according to any one of claims 1 to 6, characterized in that, The process of determining the indoor positioning information of the person to be located using the extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from the plurality of radio frequency transceivers includes: The extended Kalman filter in the wearable device determines whether the sparse point positioning information is obtained from the plurality of radio frequency transceivers; If the sparse point positioning information is not obtained from any radio frequency transceiver, the indoor positioning information of the person to be located is determined based on the inertial positioning information. If the sparse point positioning information is obtained from any of the radio frequency transceivers, the target sparse point positioning information is determined based on the obtained sparse point positioning information, and the target sparse point positioning information is fused with the inertial positioning information to obtain the indoor positioning information of the person to be located.

8. An indoor personnel positioning device, characterized in that, include: The vital sign acquisition module is used to acquire the target vital sign signals of the person to be located through wearable devices; The radio frequency echo positioning module is used to determine the target echo signal from several echo signals based on the target's vital signs signal using an indoor radio frequency transceiver device, and to perform personnel positioning on the target echo signal using a preset positioning model in the radio frequency transceiver device, so as to obtain the corresponding sparse point positioning information. An inertial positioning module is used to acquire the inertial information of the person to be located through a strapdown inertial navigation system installed on the inertial measurement unit in the wearable device, and to determine inertial positioning information based on the inertial information. An indoor positioning determination module is used to determine the indoor positioning information of the person to be located by utilizing the extended Kalman filter in the wearable device and based on the inertial positioning information and the sparse point positioning information obtained from the plurality of radio frequency transceivers respectively.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the indoor personnel positioning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program, which, when executed by a processor, implements the indoor personnel positioning method as described in any one of claims 1 to 7.

Images