Target positioning method, device and system and electronic equipment

Abstract

The invention provides a target positioning method, device and system, a medium and electronic equipment, and relates to the technical field of positioning, the target positioning method comprises the steps that multiple pieces of sensing data of target equipment for a sensing target in a target space are acquired, and the target equipment comprises a sensor and / or communication equipment; the multiple pieces of sensing data are input into a positioning model, position information of the sensing target is obtained, and the positioning model is used for outputting the position information according to the input multiple pieces of sensing data. The sensing target is sensed through the target device in the target space, the location information is output according to the obtained multiple pieces of sensing data by using the positioning model, different positioning scenes and application requirements can be adapted, and the positioning precision of the sensing target is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of positioning technology, and in particular to a target positioning method, device, system and electronic equipment. Background Art

[0002] With the rapid development of smart terminals and IoT devices, there are many scenarios where electronic devices, people or other objects need to be positioned. Therefore, efficient and accurate positioning of targets is the current research trend. Summary of the invention

[0003] The present disclosure provides a target positioning method, device, system and electronic equipment to adapt to different positioning scenarios and application requirements and improve the positioning accuracy of perceived targets.

[0004] According to a first aspect of an embodiment of the present disclosure, a target positioning method is provided, including: Acquire a plurality of perception data of a target device in a target space on a perception target, wherein the target device includes a sensor and / or a communication device; The multiple perception data are input into a positioning model to obtain the position information of the perception target, wherein the positioning model is used to output the position information based on the input multiple perception data.

[0005] Optionally, the training of the positioning model includes: Acquire multiple sample perception data of a sample device in a sample space for a sample perception target, the sample device comprising a sensor and / or a communication device, the sample perception data being marked with actual positioning information of the sample perception target; Inputting the sample perception data into the positioning model so that the positioning model determines the predicted positioning information of the sample perception target according to the sample perception data; According to the actual positioning information and the predicted positioning information, the network parameters of the positioning model are adjusted.

[0006] Optionally, the distribution positions of the target devices in the target space are the same as the distribution positions of the sample devices in the sample space.

[0007] Optionally, obtaining a plurality of sample perception data of a sample device in a sample space for a sample perception target includes: placing at least one sample sensing target within the sensing range of the sample device; Acquire first perception data perceived by the sample device before placing the sample perception target, and acquire second perception data perceived by the sample device after placing the sample perception target; The plurality of sample perception data are obtained according to the first perception data, the second perception data, and change data between the first perception data and the second perception data.

[0008] Optionally, obtaining a plurality of perception data of the target device on the perception target in the target space includes: Acquire the perception data of the perception target by multiple devices of the same type in the target space to obtain multiple perception data; or, Acquire the perception data of different types of devices in the target space on the perception target to obtain multiple perception data.

[0009] Optionally, the target device is a device of a different type, and the positioning model is used to obtain the position information of the perceived target in the following manner: Extract positioning features from the perception data of each type of device; The positioning features of different types of equipment are fused to obtain fused positioning features; The position information is obtained according to the fused positioning features.

[0010] Optionally, obtaining a plurality of perception data of the target device on the perception target in the target space includes: Acquire the perception data of the perception target by different devices in the target space at the same time to obtain multiple perception data; or, Acquire the perception data of the same device in the target space on the perception target at different times to obtain multiple perception data; or, The perception data of different devices in the target space on the perception target at different times are acquired to obtain a plurality of perception data of each device on the perception target.

[0011] According to a second aspect of the present disclosure, there is provided a target positioning device, comprising: An acquisition module is configured to acquire a plurality of perception data of a target device in a target space on a perception target, wherein the target device includes a sensor and / or a communication device; The acquisition module is configured to input the multiple perception data into a positioning model to obtain the position information of the perception target, wherein the positioning model is used to output the position information based on the input multiple perception data.

[0012] According to a third aspect of the present disclosure, there is provided a target positioning system, comprising: A target device is arranged in the target space, and the target device is used to perceive the perception data of the perception target; The central computing platform is used to execute the target positioning method described in the first aspect of the present disclosure to obtain the position information of the perceived target.

[0013] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the target positioning method described in the first aspect of the present disclosure is implemented.

[0014] According to a fifth aspect of the present disclosure, there is provided an electronic device, including: A storage device for storing a computer program; An execution device is used to execute the computer program to implement the target positioning method described in the first aspect of the present disclosure.

[0015] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects: The present disclosure obtains multiple perception data of a perception target from a target device in a target space, wherein the target device includes a sensor and / or a communication device; and inputs the multiple perception data into a positioning model to obtain location information of the perception target, wherein the positioning model is used to output location information based on the input multiple perception data. In this way, the perception target is perceived by the target device in the target space, and the positioning model is used to output location information based on the obtained multiple perception data, which can adapt to different positioning scenarios and application requirements, and improve the positioning accuracy of the perception target.

[0016] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0018] Figure 1 The figure is a flow chart of a target positioning method according to an exemplary embodiment.

[0019] Figure 2 The figure is a flow chart of a target positioning method according to an exemplary embodiment.

[0020] Figure 3 The figure is a flow chart of a target positioning method according to an exemplary embodiment.

[0021] Figure 4 The figure is a block diagram of a target positioning device according to an exemplary embodiment.

[0022] Figure 5 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0023] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0024] In wireless positioning systems, determining the precise location of a device is a key technical issue.

[0025] In one example, the perceived target can be located through a single data source or device, such as GPS (Global Positioning System) or a single sensor data, and the distance from the single data source or device to the perceived target can be estimated by backpropagating the path of the sent signal, thereby locating the perceived target. However, with the advancement of technology and the complexity of application scenarios, the data source and the perceived target are not a single one-to-one relationship, and there are many interferences. In complex application scenarios, it may be limited by factors such as signal strength and multipath effects, making it difficult to meet the needs of precise positioning.

[0026] See also Figure 1 , Figure 1 is a flow chart of a target positioning method according to an exemplary embodiment. Figure 1 As shown, a target positioning method is used in a terminal, including the following steps.

[0027] In step S101, a plurality of perception data of a target device on a perception target in a target space is obtained, where the target device includes a sensor and / or a communication device.

[0028] In step S102, a plurality of perception data are input into a positioning model to obtain position information of a perception target, wherein the positioning model is used to output position information according to the plurality of input perception data.

[0029] For example, the target space can be a fixed space, such as an office, a living room, a shopping mall, etc., and the target space can also be a mobile space, such as an interior space of a car, a train, an airplane, etc. In addition, the target space can also be an open space, a semi-open space, or a closed space. The target device is a device with perception capabilities, such as a Bluetooth communication device, a lidar sensor, a camera sensor, an ultrasonic communication device, a Wi-Fi (Wireless Fidelity) communication device, an UWB (Ultra Wide Band, wireless carrier communication technology) communication device, and the like. The Bluetooth communication device here can be a device with Bluetooth communication function, not a device dedicated to providing Bluetooth connection. Correspondingly, an ultrasonic communication device can be a device with ultrasonic transmitting and receiving functions; a Wi-Fi communication device can be a device with Wi-Fi communication function; and a UWB communication device can be a device with Wi-Fi wireless carrier communication function.

[0030] For example, the sensing target can be a person, an object, or an electronic device. When the sensing target is a person or an object, multiple sensing data can be obtained through a camera device and positioned using a positioning model. The positioning model is a pre-trained model. The positioning model can comprehensively utilize these multi-source data through deep learning or other machine learning technologies to accurately calculate the location information of the target.

[0031] Specifically, in the training stage of the positioning model, one or more target devices can be placed in different positions of the target space at the same time to obtain a large amount of sensor perception data and the actual positioning information of the perceived target, which can be used as a training data set for training. Among them, the target device can be a device of the same type or a variety of devices with different sensing capabilities. The initial positioning model can adopt a deep learning model, which is obtained by training through a preset deep learning algorithm. Among them, any deep learning model that can output position information based on multiple input perception data can be used as the positioning model of the present disclosure, and the type of deep learning model is not limited here.

[0032] For example, the corresponding perception data may be different according to different target devices. For example, the perception data obtained by the laser radar sensor may be the distance information, angle information and signal reflection intensity of the perception target relative to the laser radar sensor, etc.; the target image is obtained by the camera sensor, and the target image is processed by computer vision technology, and the perception data corresponding to the camera sensor may be the distance information of the perception target relative to the camera, and the environmental characteristics of the space that may have the perception target; the perception data obtained by the ultrasonic wave emitted by the ultrasonic communication device and the reflected sound wave received may be the sound wave reflection time, distance and / or signal strength of the perception target; the perception data obtained by the Bluetooth communication device and / or Wi-Fi communication device may be the distance of the perception target relative to the Bluetooth anchor point or Wi-Fi access point, signal transmission strength, whether there are obstacles, etc.; the perception data obtained by the UWB communication device may be the accurate distance of the perception target relative to the UWB communication device after timing measurement or multipath signal processing.

[0033] For example, the ambient temperature information and ambient humidity information around the sensing target may have an impact on the signal transmission process between the sensing target and other devices. Therefore, in addition to the target device in the above example, a temperature sensor and a humidity sensor can also be used as the target device, and the sensing data obtained by the thermometer and the hygrometer can be the current temperature data and humidity data in the target space.

[0034] For example, Figure 2 As shown in the figure, the positioning model can perform complex data processing and pattern recognition based on the positioning information, time series changes of information, spatial distribution and communication signal strength in the perception data perceived by various sensors and communication devices. This method not only improves the accuracy of positioning, but also enhances the robustness to environmental changes and interference, and can effectively locate targets in a variety of scenarios, such as indoor navigation, smart home control, lost item search and other application scenarios.

[0035] The present disclosure obtains multiple perception data of a perception target from a target device in a target space, wherein the target device includes a sensor and / or a communication device; and inputs the multiple perception data into a positioning model to obtain location information of the perception target, wherein the positioning model is used to output location information based on the input multiple perception data. In this way, the perception target is perceived by the target device in the target space, and the positioning model is used to output location information based on the obtained multiple perception data, which can adapt to different positioning scenarios and application requirements, and improve the positioning accuracy of the perception target.

[0036] As an optional embodiment, the training of the positioning model includes: Acquire multiple sample perception data of a sample device in a sample space for a sample perception target, where the sample device includes a sensor and / or a communication device, and the sample perception data is marked with actual positioning information of the sample perception target; Inputting the sample perception data into the positioning model so that the positioning model determines the predicted positioning information of the sample perception target according to the sample perception data; Adjust the network parameters of the positioning model according to the actual positioning information and the predicted positioning information.

[0037] For example, one or more target devices can be placed in different positions of the target space at the same time to obtain a large amount of sensor perception data and actual positioning information of the perceived target, which can be used as a training data set for training. The actual positioning information of the perceived target is used as a label for sample perception data for supervised training. The gap between the actual positioning information and the predicted positioning information is used to perform back propagation to adjust the network parameters of the positioning model.

[0038] For example, when the positioning model meets the preset convergence condition, the training process can be stopped to obtain a trained positioning model. The preset convergence condition can be that the gap between the actual positioning information and the predicted positioning information is less than a preset gap threshold, or that a preset number of iterations is reached. The preset number of iterations is, for example, 1000 times.

[0039] In addition, the training methods corresponding to the positioning model may be inconsistent. For example, when the sample perception data corresponding to the positioning model does not include a label, that is, does not include actual location information, an unsupervised method can be used to train the positioning model. Alternatively, after the positioning model is trained using the forward propagation method, when the positioning accuracy of the output positioning information is higher than that of the positioning model trained using the back propagation method, the positioning model can be trained using the forward propagation method, which is not limited here.

[0040] As an optional embodiment, the distribution positions of the target devices in the target space are the same as the distribution positions of the sample devices in the sample space.

[0041] For example, the target space can be a sample space, and the target device can also be a sample device. That is, after the sample device corresponding to the sample space collects sample perception data to train the positioning model, the trained positioning model can be directly applied to the sample space. Alternatively, the target space can be different from the sample space, and the distribution position of the target device in the target space is the same as the distribution position of the sample device in the sample space. Figure 3 , the position in the target space is described by a spatial coordinate system, and the same distribution position means that the coordinate point of the target device in the target space is the same as the coordinate point of the sample device in the sample space.

[0042] For example, see Figure 3 In the model training phase, the sample space can be segmented by spatial coordinates. In the training phase, one or more target devices can be placed in different coordinate points in the space at the same time, and then deep learning training can be performed. In the application phase of the trained positioning model, spatial coordinate segmentation can also be performed with the same coordinate origin. When there is a perceived target in the target space, the positioning model can output the coordinate point where the perceived target is located. This coordinate point is the predicted positioning position of the perceived target.

[0043] For example, after the model training is completed, the positioning model can be deployed in the target space, wherein the distribution positions of the target devices in the target space are the same as the distribution positions of the sample devices in the sample space, so that the perception data of the sample devices in the sample space on the perceived targets during the training process and the perception data of the target devices in the target space in actual use can be as similar as possible. For example, the knowledge learned by the positioning model in the training stage about the correlation between signal transmission and space, the changes in sensing parameters of different target devices when the perceived targets are at various positions in the target space, etc., can all be smoothly transferred to the target space to locate the perceived targets, which can further increase the positioning accuracy.

[0044] It should be noted that the sample positioning model can also be used in other scenarios, but there may be situations where the positioning accuracy is low. A large amount of perception data can be obtained by using different spaces and different sample devices for multiple training. Compared with the scenario where the position of the perceived target is calculated only through the signal return path and is affected by factors such as multipath effects, the positioning model trained in the sample space is used in a space completely different from the sample space. Because the mutual influence between different sample devices in different spaces is learned, the positioning model still has a high positioning accuracy.

[0045] As an optional embodiment, obtaining a plurality of sample perception data of a sample device in a sample space for a sample perception target includes: placing at least one sample sensing target within the sensing range of the sample device; Acquire first perception data sensed by the sample device before placing the sample perception target, and acquire second perception data sensed by the sample device after placing the sample perception target; A plurality of sample perception data are obtained according to the first perception data, the second perception data, and the change data between the first perception data and the second perception data.

[0046] For example, the perception data may be a single perception feature or a time series feature. For example, the perception data may include the first perception data perceived by the sample device before the sample perception target is placed, the second perception data perceived by the sample device after the sample perception target is placed, and the change data between the first perception data and the second perception data. The perception data includes not only the location or state information of the target, but also the changes in environmental conditions, the improvement of the device perception accuracy, etc. Among them, the change data not only reflects the state change of the target itself, but also reflects the changes in the perception ability of the sensing device or the changes in environmental conditions.

[0047] For example, by placing sample sensing targets within the sensing range of the sensing device and acquiring sensing data at different time points, richer and more diverse sensing data can be obtained. Furthermore, the positioning model can be better adapted to complex real-world environments, the robustness and reliability of the positioning model can be improved, and the positioning accuracy of the positioning model can be further improved.

[0048] As an optional embodiment, obtaining a plurality of perception data of a target device in a target space on a perception target includes: Acquire the perception data of the perception target by multiple devices of the same type in the target space to obtain multiple perception data; or, The perception data of different types of devices in the target space on the perception target are obtained to obtain multiple perception data.

[0049] For example, multiple perception data can be obtained through multiple devices of the same type in the target space. For example, 5 Bluetooth communication devices can be set in the target space. Multiple perception data can also be obtained through different types of devices in the target space. Among them, different types of devices can include the same number of devices corresponding to each type, or different numbers of devices corresponding to each type. For example, 1 Bluetooth communication device, 1 Wi-Fi communication device, and 1 camera sensor can be set in the target space, or 3 Bluetooth communication devices, 1 Wi-Fi communication device, 2 UWB communication devices, and so on can be set in the target space.

[0050] For example, by acquiring data on the perceived target from multiple devices of the same or different types, more diverse and comprehensive perception information can be obtained. Multiple devices of the same type may obtain different data at different positions or angles, thereby providing a more comprehensive perception perspective. For example, three camera sensors with different orientations are set in the target space. Different types of devices may obtain complementary information through different sensing technologies or perception methods, further enhancing the comprehensiveness and accuracy of perception. By merging multiple perception data from different devices, errors or blind spots that may exist in a single device can be eliminated, thereby improving the accuracy and reliability of overall perception.

[0051] As an optional embodiment, the target device is a device of a different type, and the positioning model is used to obtain the position information of the perceived target in the following manner: Extract positioning features from the perception data of each type of device; The positioning features of different types of equipment are fused to obtain fused positioning features; According to the fused positioning features, the location information is obtained.

[0052] For example, the positioning model can extract features from the perception data obtained by different types of devices, fuse features at the feature level, and then calculate and predict based on the fused positioning features to obtain the location information of the perceived target. Among them, the fusion of the extracted positioning features corresponding to different types of devices can not only integrate and complement the information of different types of devices, but also capture more of the spatial correlation of different types of devices in the target space, that is, the impact that the signal sent by each type of device may have on other devices, so that the perceived target can be more accurately located based on the spatial correlation information.

[0053] As an optional embodiment, obtaining a plurality of perception data of a target device in a target space on a perception target includes: Acquire the perception data of the perception target by different devices in the target space at the same time to obtain multiple perception data; or, Acquire the perception data of the same device in the target space on the perception target at different times to obtain multiple perception data; or, The perception data of different devices in the target space on the perception target at different times are obtained, and multiple perception data of each device on the perception target are obtained.

[0054] For example, multiple perception data can be obtained based on data acquired by different devices at the same time. For example, the multiple perception data are obtained based on the first data, the second data and the third data respectively acquired by the Bluetooth communication device, the lidar sensor and the camera sensor at the same time. Multiple perception data can also be obtained based on data acquired by the same device at different times. For example, for the same Bluetooth device, the multiple perception data can be determined based on the data respectively perceived by it at the first moment, the second moment and the third moment. Multiple perception data can also be obtained based on data acquired by different devices at different times. For example, at time 1, time 2 and time 3, the data acquired by the lidar sensor and the camera sensor are respectively obtained, that is, the corresponding data perceived by the lidar sensor at time 1, time 2 and time 3, and the data perceived by the camera sensor at time 1, time 2 and time 3.

[0055] For example, different combinations of perception devices and data collection strategies can be selected according to specific needs to adapt to different environments and application scenarios. Among them, the perception data of different devices on the perception target at the same time is obtained. Different types of devices may have different perception capabilities. Therefore, the perception data obtained at the same time can be complementary. Then, the integration of these data can enhance the understanding of the state of the perception target and the environment in which it is located. The final positioning accuracy can also be improved through data fusion technology to improve the comprehensiveness and accuracy of perception.

[0056] For example, by acquiring data of a perceived target at different times by the same device or by different devices at different times, it is possible to obtain information on the dynamic changes of the perceived target over time, and based on the changes in the perceived data of the target device on the perceived target, it is possible to monitor and / or predict the motion trajectory of the perceived target and changes in the surrounding environment, thereby accurately locating the perceived target.

[0057] like Figure 2 and 3 As shown, the present disclosure also provides a target positioning system, comprising: A target device is arranged in the target space, and the target device is used to perceive the perception data of the perception target; The central computing platform is used to execute the target positioning method provided by the present invention to obtain the position information of the perceived target.

[0058] The present disclosure also provides a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the target positioning method provided by the present disclosure is implemented.

[0059] For example, the target device includes a sensor and / or a communication device, and the target device can perceive the data and data changes of various current sensing parameters of the target space through its own different perception capabilities. Specifically, the target device includes but is not limited to Bluetooth communication devices, laser radar sensors, camera sensors, ultrasonic communication devices, Wi-Fi (Wireless Fidelity, wireless fidelity technology) communication devices, UWB (Ultra Wide Band, wireless carrier communication technology) communication devices, etc.

[0060] For example, the central computing platform deploys a positioning model, which is a deep learning neural network. The central computing platform obtains the perception data of all target devices on the perceived target and inputs it into the input layer network of the positioning model. The output layer of the positioning model outputs the positioning information, and the output positioning information can be passed to applications deployed locally or remotely, so that the application can obtain the positioning information of the perceived target. Among them, the central computing platform can be a part of an electronic device with computing capabilities in the target space. Or the central computing platform may not be in the target space, for example, it can be a computer in another space, a cloud server, etc., which is not limited here.

[0061] For example, the positioning model uses a deep learning neural network, which can pre-divide the target space into spatial coordinates. During the training phase, one or more target devices are placed in different coordinates of the space at the same time to obtain a large amount of perception data collected by the target devices for deep learning training. Among them, the target device can include a variety of devices with different perception capabilities. The positioning model finally trained and the target device in the target space can form a target positioning system that can output the coordinate positioning of the perception object when the perception object is placed. The positioning model is deployed to the same space as in the training phase, that is, the target devices are arranged in the same position in the space. When the perception target enters the space, the positioning information of the perception target can be obtained through deep learning neural network calculation.

[0062] The present invention realizes high-precision spatial positioning of target devices through the combination of multiple sensors / communication equipment, a central computing platform and a deep learning neural network, and performs deep learning training through perception data, thus solving the problems of low accuracy, high cost and narrow scope of application in traditional positioning solutions.

[0063] Figure 4 is a block diagram of a target positioning device according to an exemplary embodiment. Figure 4 The target positioning device includes an acquisition module 401 and an obtaining module 402.

[0064] The acquisition module 401 is configured to acquire a plurality of perception data of a target device in a target space on a perception target, where the target device includes a sensor and / or a communication device; The acquisition module 402 is configured to input multiple perception data into a positioning model to obtain position information of the perception target, wherein the positioning model is used to output position information based on the input multiple perception data.

[0065] As an optional embodiment, the training of the positioning model includes: Acquire multiple sample perception data of a sample device in a sample space for a sample perception target, where the sample device includes a sensor and / or a communication device, and the sample perception data is marked with actual positioning information of the sample perception target; Inputting the sample perception data into the positioning model so that the positioning model determines the predicted positioning information of the sample perception target according to the sample perception data; Adjust the network parameters of the positioning model according to the actual positioning information and the predicted positioning information.

[0066] As an optional embodiment, the distribution positions of the target devices in the target space are the same as the distribution positions of the sample devices in the sample space.

[0067] As an optional embodiment, the acquisition module 401 is further configured to: placing at least one sample sensing target within the sensing range of the sample device; Acquire first perception data sensed by the sample device before placing the sample perception target, and acquire second perception data sensed by the sample device after placing the sample perception target; A plurality of sample perception data are obtained according to the first perception data, the second perception data, and the change data between the first perception data and the second perception data.

[0068] As an optional embodiment, the acquisition module 401 is further configured to: Acquire the perception data of the perception target by multiple devices of the same type in the target space to obtain multiple perception data; or, The perception data of different types of devices in the target space on the perception target are obtained to obtain multiple perception data.

[0069] As an optional embodiment, the target device is a device of a different type, and the positioning model is used to obtain the position information of the perceived target in the following manner: Extract positioning features from the perception data of each type of device; The positioning features of different types of equipment are fused to obtain fused positioning features; According to the fused positioning features, the location information is obtained.

[0070] As an optional embodiment, the acquisition module 401 is further configured to: Acquire the perception data of the perception target by different devices in the target space at the same time to obtain multiple perception data; or, Acquire the perception data of the same device in the target space on the perception target at different times to obtain multiple perception data; or, The perception data of different devices in the target space on the perception target at different times are obtained, and multiple perception data of each device on the perception target are obtained.

[0071] Regarding the target positioning device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the target positioning method, and will not be elaborated here.

[0072] The present disclosure also provides an electronic device, comprising: A storage device for storing a computer program; The execution device is used to execute the computer program to implement the target positioning method provided by the present disclosure.

[0073] Figure 5 8 is a block diagram of an electronic device 800 according to an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0074] Reference Figure 5 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output interface 812 , a sensor component 814 , and a communication component 816 .

[0075] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned target positioning method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0076] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0077] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0078] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0079] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0080] The input / output interface 812 provides an interface between the processing component 802 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0081] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of the components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0082] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0083] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-mentioned target positioning method.

[0084] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by a processor 820 of an electronic device 800 to complete the above-mentioned target positioning method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0085] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a programmable device. The computer program has a code portion for executing the above target positioning method when executed by the programmable device.

[0086] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0087] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A target positioning method, characterized in that: include: Acquire a plurality of perception data of a target device in a target space on a perception target, wherein the target device includes a sensor and / or a communication device; The multiple perception data are input into a positioning model to obtain the position information of the perception target, wherein the positioning model is used to output the position information based on the input multiple perception data.

2. The method according to claim 1, characterized in that The training of the positioning model includes: Acquire multiple sample perception data of a sample device in a sample space for a sample perception target, the sample device comprising a sensor and / or a communication device, the sample perception data being marked with actual positioning information of the sample perception target; Inputting the sample perception data into the positioning model so that the positioning model determines the predicted positioning information of the sample perception target according to the sample perception data; According to the actual positioning information and the predicted positioning information, the network parameters of the positioning model are adjusted.

3. The method according to claim 2, characterized in that The distribution positions of the target devices in the target space are the same as the distribution positions of the sample devices in the sample space.

4. The method according to claim 2, characterized in that: Acquire multiple sample perception data of the sample device in the sample space for the sample perception target, including: placing at least one sample sensing target within the sensing range of the sample device; Acquire first perception data perceived by the sample device before placing the sample perception target, and acquire second perception data perceived by the sample device after placing the sample perception target; The plurality of sample perception data are obtained according to the first perception data, the second perception data, and change data between the first perception data and the second perception data.

5. The method according to any one of claims 1 to 4, characterized in that: Obtain multiple perception data of the target device in the target space on the perception target, including: Acquire the perception data of the perception target by multiple devices of the same type in the target space to obtain multiple perception data; or, Acquire the perception data of different types of devices in the target space on the perception target to obtain multiple perception data.

6. The method according to any one of claims 1 to 4, characterized in that: The target device is a device of different types, and the positioning model is used to obtain the location information of the perceived target in the following manner: Extract positioning features from the perception data of each type of device; The positioning features of different types of equipment are fused to obtain fused positioning features; The position information is obtained according to the fused positioning features.

7. The method according to any one of claims 1 to 4, characterized in that: Obtain multiple perception data of the target device in the target space on the perception target, including: Acquire the perception data of the perception target by different devices in the target space at the same time to obtain multiple perception data; or, Acquire the perception data of the same device in the target space on the perception target at different times to obtain multiple perception data; or, The perception data of different devices in the target space on the perception target at different times are acquired to obtain a plurality of perception data of each device on the perception target.

8. A target positioning device, characterized in that: include: An acquisition module is configured to acquire a plurality of perception data of a target device in a target space on a perception target, wherein the target device includes a sensor and / or a communication device; The acquisition module is configured to input the multiple perception data into a positioning model to obtain the position information of the perception target, wherein the positioning model is used to output the position information based on the input multiple perception data.

9. A target positioning system, characterized in that: include: A target device is arranged in the target space, and the target device is used to perceive the perception data of the perception target; A central computing platform is used to execute the target positioning method described in any one of claims 1-7 to obtain the position information of the perceived target.

10. An electronic device, characterized in that: include: A storage device for storing a computer program; An execution device is used to execute the computer program to implement the target positioning method described in any one of claims 1-7.

Images