Signal positioning method, device, system, program product, and storage medium

Abstract

This invention discloses a signal positioning method, device, system, program product, and storage medium, relating to the field of signal testing technology. During the signal positioning process, the server acquires first signal data of the site and images of different areas within the site. The server compares the visual features of the first image among multiple images with a feature library of the site, and determines the first network signal value of a first location point in the three-dimensional spatial model of the site based on the first signal data. A first label is then rendered at the first location point in the three-dimensional spatial model to display the first network signal value. The server does not use satellite signals during signal positioning; instead, it utilizes the visual features of the compared images and a feature library to align the signal value with the location point. This improves the accuracy of signal testing and signal positioning. Furthermore, the server's rendering of the network signal value of the location point in the three-dimensional spatial model provides a visual representation of the site's network signal.

Description

Technical Field

[0001] This application relates to the field of signal testing technology, and in particular to a signal positioning method, device, system, program product, and storage medium. Background Technology

[0002] Signal measurement involves collecting signal values ​​at each measurement location in the real physical space. Based on the signal values ​​at each measurement location, testers or maintenance personnel adjust the distribution of network devices in the real physical space to ensure network quality.

[0003] In an indoor venue, testing or maintenance personnel move along a pre-set trajectory and test the signal value at each planned test point. Weak satellite signals within the venue can lead to inaccurate positioning, resulting in a mismatch between signal values ​​and location, thus reducing the accuracy of the test results. Summary of the Invention

[0004] This application provides a signal positioning method, device, system, program product, and storage medium to improve the accuracy of test results in scenarios with weak satellite signals.

[0005] Firstly, this application provides a signal localization method applied to a server. The server stores a three-dimensional spatial model of the site and a feature library of the site; the feature library includes multiple location points in the site and the visual features of each location point. During the signal localization process performed on the server, the server acquires first signal data of the site and images of different areas in the site. For the first image among multiple images, the server compares the visual features of the first image with the feature library, determines the first network signal value of the first location point in the three-dimensional spatial model based on the first signal data, and renders a first label at the first location point in the three-dimensional spatial model. This allows the first network signal value of the first location point to be displayed in the three-dimensional spatial model using the first label.

[0006] Based on the first aspect, the server does not use satellite signals during signal localization. Instead, it utilizes images and a feature library to align the region corresponding to the image with the location points in the scene. Based on the image and the initial signal data, it determines the network signal value corresponding to the location point, thus achieving alignment between the signal value and the location point. In this way, even when satellite signals are weak, the matching degree between the network signal value and the location point can still be ensured, thereby improving the accuracy of signal testing and signal localization. Furthermore, the server renders labels for the network signal values ​​of the location points in a 3D spatial model, providing a visual representation of the signal test data.

[0007] In one optional implementation, the server renders the first label at a first location point in the 3D spatial model. Specifically, the server determines the coordinate data of the first label based on the coordinates of the first location point and the shape of the first label, and determines the distance between the first label and the rendering camera based on the coordinate data of the first label. Furthermore, the server determines the position information of the first label in the 3D spatial model according to the distance between the first label and the rendering camera, and renders the first label at the first location point in the 3D spatial model according to the position information.

[0008] The coordinate data of the first label includes the coordinate values ​​of the vertex of the first label in the rendering camera coordinate system.

[0009] Based on this optional implementation, the server uses the coordinates of the first location point and its distance from the rendering camera to determine the size and position of the first label for that location point. Then, based on the size and position of the first label and the first network signal value of the first location point, it renders the data in a 3D spatial model. In this way, users can observe the distribution of network signal values ​​at different locations in the field without having to physically be there, simply by viewing the labels on the 3D spatial model, thus improving the visualization of signal testing results.

[0010] In one optional implementation, the server renders the first label at a first location point in the 3D spatial model. Specifically, the server determines the distance between the first label and the rendering camera based on the coordinates of the first location point. If the distance is less than the depth value of the 3D spatial model, the server renders the first label at the first location point in the 3D spatial model.

[0011] Optionally, if the distance is greater than the depth value of the 3D spatial model, the server will not render the first label at the first location point in the 3D spatial model.

[0012] Based on this optional implementation method, the server can filter the labels that can be displayed based on the depth value of the 3D spatial model. This can avoid the problem of poor visual effect of the target 3D spatial model caused by displaying a large number of labels in the target 3D spatial model, improve the visual effect of the target 3D spatial model, and increase the visualization effect of the target 3D spatial model.

[0013] In one optional implementation, the process is as follows: after the server renders the first label at the first location point in the 3D spatial model, and after rendering at multiple locations in the 3D spatial model, the server outputs the target 3D spatial model. The target 3D spatial model is a 3D model with labels displayed at multiple locations within the 3D spatial model.

[0014] In this way, the server can use the target 3D spatial model to display the labels of signal values ​​at different locations, which can intuitively display the signal test results.

[0015] In one optional implementation, the server compares the visual features of the first image with a feature library and determines the first network signal value of the first location point in the 3D spatial model based on the first signal data. Specifically, the server determines the first location point corresponding to the first image based on the feature library and the visual features of the first image. The server obtains a target signal value whose sampling time matches the acquisition time of the first image based on the sampling time corresponding to each signal value in the first signal and the acquisition time of the first image, and uses the target signal value as the first network signal value corresponding to the first location point.

[0016] Based on this optional implementation method, the server uses a 3D spatial model and local images of the site to achieve location, and then uses the network signal value to locate the location by correlating the images with the network signal value. This improves positioning accuracy and ensures location accuracy even in situations with weak satellite signals.

[0017] In one optional implementation, the server determines the first location point corresponding to the first image based on the feature library and the visual features of the first image. Specifically, the server queries the feature library based on the visual features of the first image, obtains the first visual feature in the feature library that matches the visual features of the first image, and determines the location point corresponding to the first visual feature as the first location point.

[0018] Based on this optional implementation method, the first location point corresponding to the first image is determined by retrieving a feature library using the visual features of the first image. In this way, the server uses a 3D spatial model and local images of the site to achieve location positioning, which is simple. Furthermore, the use of visual feature comparison can improve positioning accuracy.

[0019] In one optional implementation, the server obtains 3D map data and a feature library of the site based on panoramic video data. The server then inputs the 3D map data into a neural radiation fields (NeRF) model to train the NeRF model, resulting in a trained NeRF model. Finally, the trained NeRF model is used to generate a rendering image, thus creating a 3D spatial model.

[0020] Based on this optional implementation method, the server uses the NeRF model for training to create a 3D spatial model of the target site, reconstructing and rendering the environmental reality of the target site. This improves rendering quality while ensuring the realism of the 3D spatial model, thereby ensuring that the final signal test results are more intuitive.

[0021] In one optional implementation, the server performs panoramic pose calculations based on the panoramic video data of the site to obtain 3D map data of the target site. This 3D map data includes the coordinates of each location point in the real-world location and the corresponding camera pose of the panoramic image. The server then inputs the 3D map data into a NeRF model for training, resulting in a trained NeRF model. Finally, the trained NeRF model is used to generate a rendered image, thus creating a 3D spatial model.

[0022] Based on this optional implementation method, the server uses the sequence of panoramic pose calculations to obtain 3D map data, ensuring that the 3D map data can provide the pose of the panoramic image, thereby ensuring the degree of matching between the 3D map data and the real environment of the target site, and thus ensuring the reliability of the subsequently generated 3D spatial model.

[0023] In one optional implementation, the process involves the server acquiring 3D map data of the target site and then extracting features from the panoramic image of each location point to obtain the visual features of each point. The server then associates and stores multiple location points in the target site with the visual features of each point to create a feature library.

[0024] In this way, the server can then use the visual features of the acquired images to retrieve a feature library for spatial positioning of the signal value. Even when satellite signals are weak, the server can still ensure the degree of matching between the signal value and the location point, thereby improving the accuracy of signal positioning.

[0025] In one optional implementation, the specific implementation involves the server acquiring point cloud data of the site and a second signal data set. The second signal data set includes the analog network signal value for each of the multiple location points within the site. For a first point cloud coordinate in the point cloud data, the server determines the corresponding analog network signal value based on the second signal data, and renders a second label for the first point cloud coordinate in the point cloud data.

[0026] The second label is used to indicate the simulated network signal value corresponding to the coordinates of the first point cloud.

[0027] In this optional implementation, during the site network planning phase, a three-dimensional model of the site network is formed by simulating network signal values ​​at multiple locations within the site, visually demonstrating the network signal performance and improving user interaction.

[0028] Secondly, this application provides a signal positioning device, which is set on a server. The server stores a three-dimensional spatial model of the site and a feature library of the site. The feature library of the site includes multiple location points in the site and the visual features of each location point.

[0029] Optionally, the signal positioning device can be a server, a chip or system-on-a-chip within the server, or a functional module within the server for implementing the method of the first aspect or any possible implementation thereof. This signal positioning device can implement the functions performed by the server in the first aspect or possible implementations thereof, and these functions can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the aforementioned functions. For example, the signal positioning device may include a storage module, a processing module, and a communication module.

[0030] The storage module is used to store executable program code and data (such as feature library, three-dimensional spatial model, first signal data, etc.) of the signal positioning device during the signal positioning process.

[0031] The communication module is used to acquire first signal data and multiple images of the site; the first signal data includes multiple network signal values ​​and the sampling time corresponding to each network signal value; different images correspond to different areas in the site.

[0032] The processing module is used to compare the visual features of the first image with a feature library for a first image among multiple images, and determine the first network signal value of the first location point in the three-dimensional spatial model based on the first signal data; and to render the first label at the first location point in the three-dimensional spatial model.

[0033] Wherein, the first location point is used to indicate the location information of the area captured by the first image in the three-dimensional spatial model; the first label is used to indicate the first network signal value corresponding to the first location point.

[0034] In one alternative implementation, the processing module is specifically used to: determine the coordinate data of the first label based on the coordinates of the first position point and the shape of the first label; the coordinate data of the first label includes the coordinate values ​​of the vertices of the first label in the rendering camera coordinate system;

[0035] The distance between the first label and the rendering camera is determined based on the coordinate data of the first label;

[0036] Determine the position information of the first label in the 3D spatial model based on the distance between the first label and the rendering camera;

[0037] The first label is rendered based on the first position point in the 3D spatial model according to the location information.

[0038] In one alternative implementation, the processing module is specifically used to determine the distance between the first label and the rendering camera based on the coordinates of the first location point;

[0039] If the distance is less than the depth value of the 3D spatial model, execute the step of rendering the first label at the first position point in the 3D spatial model.

[0040] In one alternative implementation, the processing module is further configured to output a target 3D spatial model after rendering of multiple location points in the 3D spatial model is complete; the target 3D spatial model displays labeled 3D models of multiple location points in the 3D spatial model.

[0041] In one optional implementation, the processing module is specifically used to: determine the first location point corresponding to the first image based on the feature library and the visual features of the first image;

[0042] Based on the sampling time corresponding to each signal value in the first signal and the acquisition time of the first image, a target signal value whose sampling time matches the acquisition time of the first image is obtained;

[0043] The target signal value is used as the first network signal value corresponding to the first location point.

[0044] In one optional implementation, the processing module is specifically used for: the server querying the feature library based on the visual features of the first image to obtain the first visual feature in the feature library that matches the visual features of the first image;

[0045] The location point corresponding to the first visual feature is determined as the first location point.

[0046] In one alternative implementation, the processing module is further configured to: obtain three-dimensional map data and a feature library of the site based on the panoramic video data of the site;

[0047] The 3D map data is input into the NeRF model, the NeRF model is trained, and the trained NeRF model is used to generate a rendering map to obtain a 3D spatial model.

[0048] In one alternative implementation, the communication module is further configured to acquire point cloud data of the site and second signal data; the second signal data includes the analog network signal value of each of the multiple location points of the site.

[0049] The processing module is also used to determine the analog network signal value corresponding to the first point cloud coordinates in the point cloud data based on the second signal data.

[0050] Render a second label for the first point cloud coordinates in the point cloud data; the second label is used to indicate the analog network signal value corresponding to the first point cloud coordinates.

[0051] Thirdly, this application provides a signal positioning device, which can be a server or a chip or system-on-a-chip within a server. This signal positioning device can implement the functions performed by the server in the first aspect or any possible implementation of the first aspect, and these functions can be implemented in hardware. In one possible implementation, the signal positioning device includes a processor and a communication interface. The processor and communication interface are used to support the signal positioning device in executing the methods in the first aspect or any possible implementation of the first aspect. In yet another possible implementation, the signal positioning device may further include a memory for storing necessary computer execution instructions and data. When the signal positioning device is running, the processor executes the computer execution instructions stored in the memory to cause the signal positioning device to perform the methods as described in the first aspect or any possible implementation of the first aspect.

[0052] Fourthly, this application provides a signal testing system, which includes a first terminal and the signal positioning device provided in the second or third aspect above.

[0053] The first terminal is used to provide the signal positioning device with first signal data of the site and multiple images; the first signal data includes multiple network signal values ​​and the sampling time corresponding to each network signal value; different images correspond to different areas in the site;

[0054] A signal positioning device is used to perform the first aspect or any possible implementation of the first aspect based on first signal data and multiple images.

[0055] Fifthly, this application provides a computer program product that, when an instruction is executed by a signal positioning device, causes the signal positioning device to perform the method described in the first aspect or any optional implementation thereof.

[0056] Sixthly, this application provides a computer-readable storage medium including computer program instructions. When the computer program instructions are executed by a signal positioning device, the signal positioning device executes the instructions in the computer program stored in the computer-readable storage medium to perform the method in the first aspect or any optional implementation thereof.

[0057] The technical effects of any of the optional implementations of aspects two through six can be found in the first aspect or the technical effects of any of the optional implementations of aspect one. Further details are omitted here. Based on the implementations provided in the above aspects, this application can be further combined to provide more implementations. Attached Figure Description

[0058] Figure 1This is a schematic diagram of a signal positioning method;

[0059] Figure 2 This is a schematic diagram of the signal testing system provided in this application;

[0060] Figure 3 A schematic diagram illustrating the creation process of the three-dimensional spatial model of the target site provided in this application;

[0061] Figure 4 A flowchart illustrating the sequence panoramic pose calculation provided in this application;

[0062] Figure 5 A schematic diagram of rotation provided in this application;

[0063] Figure 6 A schematic diagram showing the association between the first and second panoramic images provided for this application and three-dimensional points in space;

[0064] Figure 7 A rendering diagram of the NeRF model provided in this application;

[0065] Figure 8 Flowchart of the signal positioning method provided in this application Figure 1 ;

[0066] Figure 9A A schematic diagram of the target three-dimensional spatial model provided for this application;

[0067] Figure 9B A schematic diagram of the user interface provided in this application;

[0068] Figure 10 Flowchart of the signal positioning method provided in this application Figure 2 ;

[0069] Figure 11 A schematic diagram illustrating the network signal value location process provided in this application;

[0070] Figure 12 This is a schematic diagram of the tag rendering process provided in this application;

[0071] Figure 13 A schematic diagram illustrating the label size variation provided in this application;

[0072] Figure 14 A schematic diagram of the field of view cone range provided in this application;

[0073] Figure 15 This application provides a schematic diagram illustrating the switching of viewing angles.

[0074] Figure 16 Schematic diagram of the signal positioning device provided in this application Figure 1 ;

[0075] Figure 17 Schematic diagram of the signal positioning device provided in this application Figure 2 . Detailed Implementation

[0076] During signal measurement, testers set up the theoretical movement trajectory and planned test points along the trajectory based on the site map. They then manually recorded the signal values ​​at these planned test points using a terminal. During the test, the number of signals received by the terminal per unit time was the same, but the testers' walking speed varied per unit time, resulting in different signal sampling numbers between adjacent planned test points. Figure 1 As shown in Figure (a), excessively fast walking speed leads to sparse measurement points, resulting in a smaller number of collected signal values ​​and thus reducing the reliability of the test results. Furthermore, there is a problem of missed planned test points. Additionally, the testing process requires personnel to compare the locations of planned test points with drawings, which can lead to inaccurate location positioning, causing a mismatch between signal values ​​and locations, further reducing the accuracy of the test results. Figure 1 As shown in Figure (b), the location is inaccurate and does not match the theoretical trajectory.

[0077] Additionally, during signal measurement, testers can also automatically mark test points using laser equipment. Testers use lidar to create a map of the site and use it for positioning during the test, displaying the walking path. However, due to the limitations of the laser equipment's positioning accuracy, there is an error between the actual movement trajectory and the displayed trajectory, such as... Figure 1 As shown in Figure (c), this reduces the accuracy of the test results.

[0078] In addition, as mentioned above Figure 1 As shown in Figures (a), (b), and (c), the test results of the signal measurement in the above two methods are displayed by marking the location of the test point on the site plan, which is a single display method.

[0079] Therefore, to improve the accuracy and visualization of test results in scenarios with weak satellite signals, this application provides a signal positioning method. Compared to signal testing methods that rely on satellite signal positioning, this application utilizes image data and a feature library to align the region corresponding to the image data with the location points of the target scene. Based on the image data and first signal data, it determines the signal value corresponding to the location point, enabling a comparison between the signal value and the location point. Since this application does not use satellite signals, even in situations with weak satellite signals, it can still ensure the degree of matching between the signal value and the location point, thereby improving the accuracy of the signal test results. Furthermore, this application renders labels for the signal values ​​of the location points in a three-dimensional spatial model, providing a visual representation of the signal test results. The image data includes multiple images.

[0080] Specifically, the server stores a 3D spatial model of the target site and a feature library of the target site. This feature library includes multiple location points within the target site and the visual features of each location point. During signal testing of the target scene on the server, the server acquires first signal data of the target site and image data of different areas within the target site. For the first image among multiple images, the server, based on the feature library, the first signal data, and the visual features of the first image, obtains the first signal value of the first location point in the 3D spatial model. Based on the first location point and its corresponding signal value, the server renders a first label in the 3D spatial model to display the signal value of the first location point within the 3D spatial model.

[0081] The signal positioning method provided in this application can be used not only to measure wireless network signals, but also to measure local area network signals or indoor network signals. It can also be used to measure network signals of future communication technologies. Furthermore, the embodiments of this application do not limit the specific type of the target site. For example, the target site can be an outdoor site, such as a street, residential area, or garden. Alternatively, the target site can be a large venue, such as a stadium, airport, or shopping mall. Yet another example is that the target site can also be a small indoor site, such as an office space or residence. In addition, the technical solutions involved in this application can be applied not only to current signal testing systems, signal testing terminals, signal testing equipment, or signal testing servers, but also to future signal testing technologies or equipment, or signal testing systems that include servers or testing terminals.

[0082] The terminology used in the implementation section of this application is only for explaining specific embodiments of this application and is not intended to limit this application. A brief introduction to some concepts that may be involved in this application is given below.

[0083] 3D reconstruction: Establishing a mathematical model of a 3D object that is suitable for computer identification and processing.

[0084] NeRF (Neural Radiance Fields) model training: A technique for reconstructing a 3D model of a site. This technique utilizes multiple images of the site, along with the corresponding camera poses, as training data to train a neural radiance field model, resulting in an implicit 3D model of the site. This implicit 3D model is then rendered to generate the final 3D model of the site.

[0085] Camera pose refers to the position and orientation of the camera in the real environment when an image is captured. One image corresponds to one camera pose.

[0086] Camera pose can also be called viewpoint, pose, or other names. Attitude can also be called angle or direction.

[0087] Camera pose can be obtained by using sequential panoramic pose calculation techniques on images.

[0088] Sequence panoramic pose estimation: This involves estimating the relative pose of the camera by analyzing panoramic images of the site. The panoramic images can be 360° views of the site. Sequence panoramic pose estimation can also be called panoramic pose estimation or pose estimation.

[0089] Cloud computing environment: An entity that provides cloud services to users using basic resources under the cloud computing model. The cloud environment includes cloud data centers and cloud service platforms.

[0090] Cloud data centers encompass a vast amount of basic resources (including computing clusters, storage resources, and network resources) owned by cloud service providers. In this article, cloud data centers may also be referred to as cloud platforms, cloud management platforms, cloud computing platforms, etc.

[0091] A host refers to a physical server deployed in a cloud data center. The physical resources of a host include the physical central processing unit (CPU) and memory devices. Each host runs virtualization software, which virtualizes some physical resources into virtual resources for use by instances. For example, the virtualization software virtualizes the CPU into a virtual CPU (vCPU). The host also has resources such as memory channels, cache channels, caches, network input / output (I / O) bandwidth, and storage I / O bandwidth that are shared by the instances running on the host.

[0092] Instance: A compute node running on a host machine. Common instances include virtual machines (VMs) or containers. Each instance consumes some or all of the host machine's virtual resources. Typically, instances deployed on compute nodes can be used for data transfer, data computation, etc.

[0093] The technical solution provided in this application is described below with reference to the accompanying drawings.

[0094] See Figure 2 , Figure 2 This is a schematic diagram of a signal testing system provided in this application. The signal testing system 100 shown includes a work terminal 30, a client 20, and a cloud server 10. This signal testing system 100 can be used to measure wireless signals in a field, or to measure other types of network signals. In some alternative embodiments, this signal testing system 100 may also be called a testing system, a work system, or other names, etc., and this application embodiment does not limit this.

[0095] The client 20 and the operation terminal 30 are described below by example.

[0096] The work terminal 30 can refer to the physical carrier tool used by testers to conduct signal tests, and is used to provide signal data and image data of the target site to the cloud service platform 120 and the cloud platform 110. In some optional embodiments, the work terminal 30 may also be called a first terminal, a test terminal, or other names, etc., and this application embodiment does not limit this.

[0097] In one alternative scenario, it may include a mobile terminal and a panoramic camera. The mobile terminal is used to acquire signal data of the target site, and the panoramic camera is used to acquire image data of the target site, such as image data of a local area or panoramic video data.

[0098] The mobile terminal can also be referred to as a terminal device, mobile phone terminal, or handheld terminal. This mobile terminal can be a mobile phone, tablet computer, laptop computer, wireless terminal in industrial control, or any other terminal device capable of measuring network signals. The embodiments of this application do not limit the specific technology or device form used in the mobile terminal.

[0099] In an alternative scenario, the mobile terminal is equipped with an application for measuring network signals, such as a network signal measurement application. This network signal measurement application can obtain test tasks for the target site from the cloud service platform 120 or the cloud platform 110 online or offline, and execute the test tasks to collect signal data from the target site.

[0100] In the first alternative scenario, the mobile terminal and the panoramic camera can be integrated; for example, the panoramic camera can be integrated into the mobile terminal. In this way, the mobile terminal can simultaneously acquire signal data and image data of the target site.

[0101] In the second alternative scenario, the mobile terminal and the panoramic camera are configured separately. For example, the mobile terminal communicates with the panoramic camera, the panoramic camera returns image data to the mobile terminal, and the mobile terminal uploads the image data and signal data to the cloud server 10. Alternatively, the mobile terminal returns signal data to the cloud server 10, and the panoramic camera returns image data to the cloud server 10. In this way, the mobile terminal and the panoramic camera can operate independently.

[0102] The following provides an example of client 20.

[0103] In a first optional implementation, the client 20 can be a computer running an application. This computer can be a physical machine or a virtual machine. For example, if the computer running the application is a physical computing device, it can be a host or a terminal. The terminal can also be called a terminal device, user equipment (UE), mobile station (MS), mobile terminal (MT), etc. Terminals can be mobile phones, tablets, laptops, desktop computers, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in autonomous driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc. The embodiments of this application do not limit the specific technology or device form used by the client 20.

[0104] In the second alternative implementation, client 20 can be an application, such as a signal testing result display application or a site network planning application. Alternatively, client 20 can be a web client. Client 20 runs on a terminal device. The terminal device includes, but is not limited to, mobile terminals, tablets, personal computers, or laptops.

[0105] The two implementation methods described above are merely different ways of implementing client 20. In practical applications, client 20 can also have other implementation methods. For example, client 20 can be a software module running on any one or more hosts in computing cluster 112. Another example is that client 20 can also be the aforementioned mobile terminal. Yet another example is that client 20 can also be an application for measuring network signals deployed in the aforementioned mobile terminal. This application does not limit this.

[0106] In one alternative implementation, the cloud server 10 is used to provide signal testing services, creation services for the three-dimensional model of the site, management services, and test result services. The cloud server 10 may also be called a server, a cloud-based operating system, the cloud, or other names, and this application does not limit it to any particular name.

[0107] In an optional case, such as Figure 2 As shown, the cloud server 10 may include a cloud service platform 120 and a cloud platform 110. The cloud platform 110 deploys a signal positioning device 111, a NeRF model, etc.

[0108] In one alternative example, the signal positioning device 111 can be deployed independently within an instance of the cloud platform 110.

[0109] In some embodiments, the signal positioning device 111 may also be deployed in a distributed manner across multiple instances of the cloud platform 110.

[0110] Similarly, the NeRF model can be deployed independently on a single instance of the cloud platform 110, or distributed across multiple instances of the cloud platform 110.

[0111] like Figure 2As shown, the signal positioning device 111 is abstracted by the cloud service provider on the cloud service platform 120 into a signal testing service or signal positioning service and provided to the user. After the user purchases the signal positioning service on the cloud service platform 120 through the work terminal 30 and client 20, the cloud environment uses the signal positioning device 111 deployed on the cloud platform 110 to provide the signal positioning service to the user. When using the signal positioning service, the user can upload signal data and image data of the target site to the cloud environment through the application program interface (API) or graphical user interface (GUI) in the work terminal 30. The signal positioning device 111 in the cloud environment calls the NeRF model to create a three-dimensional model of the target site, receives the signal data and image data of the target site, performs data processing to obtain signal test results, and renders the signal test results in the three-dimensional model to obtain business results. The signal positioning device 111 returns the signal test results or business results during the data processing process to the user through the API or GUI.

[0112] Alternatively, users can upload the identification information of the target site they wish to view to the cloud environment via the API or GUI in client 20. The signal positioning device 111 in the cloud environment returns the service results of the target scene to client 20 via the API or GUI. The service results are used to provide the network signal values ​​of different test points (or location points) in the target scene.

[0113] In addition, in some other embodiments, the function of the signal positioning device 111 may be performed by the cloud platform 110 or other components of the cloud platform 110, and this application does not limit its implementation.

[0114] The system architecture and application scenarios described in this application are intended to more clearly illustrate the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0115] During signal testing, the aforementioned signal positioning device 111 can provide visualized signal test results to the client 20 based on the signal data and image data collected by the operating terminal 30. Furthermore, the signal positioning method provided in this application can be implemented during the process of generating the signal test results. Regarding the process of generating the signal test results, the following describes... Figures 3 to 15 An example is provided.

[0116] In one alternative implementation, to visualize the signal test results, the signal location device 111 creates a three-dimensional model of the target site. During the signal test, the signal location device 111 renders the signal test results on the three-dimensional spatial model and outputs the target three-dimensional spatial model. This target three-dimensional spatial model displays the network signal values. Thus, the signal test results can be intuitively displayed in the three-dimensional spatial model.

[0117] The following, combined with Figures 3 to 7 An exemplary description is provided of how the signal positioning device 111 creates a three-dimensional spatial model.

[0118] In one alternative implementation, the signal positioning device 111 can perform NeRF model training based on panoramic video data of the target site to obtain a three-dimensional spatial model of the target site.

[0119] like Figure 3 As shown, Figure 3 This is a schematic diagram of the creation process of the three-dimensional spatial model of the target site provided in this application. The creation process of the three-dimensional spatial model of the target site includes steps S310 to S330.

[0120] S310, the signal positioning device 111 acquires panoramic video data of the target site.

[0121] In the first optional implementation, the signal positioning device 111 sends a video acquisition task to the operation terminal 30 and receives panoramic video data of the target site uploaded by the operation terminal 30.

[0122] For example, the work terminal 30 responds to the video acquisition task, starts the panoramic camera, and captures the target site from different angles to obtain panoramic video data of the target site.

[0123] For example, the work terminal 30 captures video data of the target site from different perspectives, and uses this video data as panoramic video data of the target site. Alternatively, the work terminal 30 captures video data of the target site from different perspectives. The work terminal 30 then samples this video data to obtain panoramic video data of the target site. This sampling can be performed by the work terminal 30 using video processing software.

[0124] In the first alternative method, the signal positioning device 111 actively sends a video acquisition task to the operation terminal 30.

[0125] For example, if the cloud server 10 does not store a three-dimensional spatial model of the target site, the signal testing terminal sends a video acquisition task to the operation terminal 30.

[0126] For example, if the signal positioning device 111 detects a change in the target site, the signal testing terminal sends a video acquisition task to the operation terminal 30. Here, "a change in the target site" could mean the target site has been rebuilt or renovated.

[0127] In the second alternative approach, the signal positioning device 111 may respond to the first request by issuing a video acquisition task to the work terminal 30.

[0128] The first request is used to instruct the signal positioning device 111 to create a three-dimensional model of the target site. This first request may be sent by an external device (operation terminal 30 or client 20, or other devices).

[0129] The two optional methods mentioned above are merely different triggering methods for the signal positioning device 111 to issue video acquisition tasks. In other embodiments, the signal positioning device 111 may issue video acquisition tasks by other triggering methods, which are not limited in this application.

[0130] In a second alternative implementation, the signal positioning device 111 can also acquire panoramic video data of the target site sent by other devices. Exemplarily, other devices may include, but are not limited to, mobile phones, cameras, tablets, webcams, etc. This application embodiment does not limit the source device of the panoramic video data, nor does it limit the number of source devices.

[0131] The two optional implementation methods described above are merely different ways in which the signal positioning device 111 acquires panoramic video data. In practical applications, the signal positioning device 111 can also use other implementation methods to acquire panoramic video data. For example, the signal positioning device 111 can read panoramic video data from the storage of a cloud server. This application embodiment does not limit this.

[0132] S320, the signal positioning device 111 obtains three-dimensional map data of the target site based on the panoramic video data.

[0133] In one alternative implementation, 3D map data is used to provide the 3D shape and aggregate positional relationships of the target site. For example, the 3D map data includes the coordinates of each of the multiple locations of the target site in real space, as well as the camera pose of the panoramic image corresponding to each location.

[0134] In an alternative approach, the three-dimensional map data may also be referred to as a 3D sparse map or SLAM map data, as described in this application.

[0135] In one alternative implementation, the signal positioning device 111 can acquire camera poses of different panoramic images and create 3D map data by sequential panoramic pose calculation.

[0136] For example, such as Figure 4 As shown, Figure 4 The flowchart of the sequence panoramic pose calculation provided in this application is shown, and the sequence panoramic pose calculation process includes stages ① to ⑤.

[0137] Stage ①, Feature Extraction.

[0138] The signal positioning device 111 extracts feature points from each frame of the panoramic image in the panoramic video data. Feature points refer to pixels in the panoramic image that possess scale invariance. For example, feature points can be points in the panoramic image where the grayscale value changes drastically or points with significant curvature at the image edges. For instance, feature points can be corner points, edges, etc., that reflect the essential characteristics of the panoramic image. In some alternative methods, feature points can also be called test points, location points, three-dimensional points, or salient feature points.

[0139] In some possible cases, the signal positioning device 111 can use the scale-invariant feature transform (SIFT) algorithm or the speeded-up robust features (SURF) algorithm to extract feature points in each frame of the panoramic image. Other algorithms can also be used to extract feature points in each frame of the panoramic image, such as the oriented fast and rotated brief (ORB) algorithm, etc., which are not limited in this application embodiment.

[0140] In one alternative implementation, the signal positioning device 111 can preprocess the panoramic video data to obtain preprocessed panoramic video data. The signal positioning device 111 then performs feature extraction on the preprocessed panoramic video data to obtain feature points in each frame of the panoramic image.

[0141] Preprocessing can include one or more of the following methods: noise reduction, lens distortion correction, image enhancement, etc.

[0142] Phase 2, Feature Matching.

[0143] The signal positioning device 111 matches feature points in a first panoramic image and a second panoramic image in the panoramic video data to obtain matching feature point pairs between the first panoramic image and the second panoramic image. The feature point pairs may include identical feature points in both the first panoramic image and the second panoramic image. "Matching feature points in the first panoramic image and the second panoramic image" can mean matching identical feature points in both images, i.e., identifying identical feature points in both images.

[0144] The first image and the second image can be adjacent frames in the panoramic video data. Alternatively, the first image and the second image can be images with overlapping content in the panoramic video data.

[0145] In one alternative approach, the signal positioning device 111 may employ a random sample consensus (RANSAC) algorithm to match feature points in the first panoramic image and the second panoramic image. Alternatively, the signal positioning device 111 may also use a least squares algorithm to match feature points in the first panoramic image and the second panoramic image. Furthermore, the signal positioning device 111 may also use a quadtree or a binary tree to match feature points in the first panoramic image and the second panoramic image. This application embodiment does not limit the scope of the application.

[0146] Phase 3, camera pose estimation.

[0147] The signal positioning device 111 calculates the relative transformation matrix between the first panoramic image and the second panoramic image based on the matched feature point pairs between them. Based on the relative transformation matrix, the relative pose between the first panoramic image and the second panoramic image is obtained, and the position information of each feature point is calculated according to the relative pose. Then, using the position information of the feature points and their corresponding feature points in the image, the camera pose corresponding to the first panoramic image is calculated.

[0148] The relative transformation matrix can be a transformation matrix between the coordinate values ​​of feature points in the first panoramic image and the coordinate values ​​of feature points in the second panoramic image. This relative transformation matrix is ​​used to provide the rotation matrix R and translation information T required to transform feature points in the first panoramic image to feature points in the second panoramic image.

[0149] The rotation matrix R indicates the angle required to rotate from the coordinate system of the first panoramic image to the coordinate system of the second panoramic image. This angle includes roll, pitch, and yaw angles.

[0150] like Figure 5 As shown, Figure 5 This is a schematic diagram of rotation provided in this application. For feature point P in the first panoramic image, the signal positioning device 111 maps feature point P in the first panoramic image to feature point P3 in the third coordinate system in the order of rotation around the Z-axis → around the Y-axis → around the X-axis.

[0151] like Figure 5As shown, in stage ①, the yaw angle is obtained by rotating the coordinate system of the first panoramic image around the Z-axis to obtain the first coordinate system, the first rotation sub-matrix between the coordinate system of the first panoramic image and the first coordinate system, and the coordinates of feature point P in the first coordinate system. In stage ②, the pitch angle is obtained by rotating the first coordinate system around the Y-axis to obtain the second coordinate system, the second rotation sub-matrix between the first and second coordinate systems, and the coordinates of feature point P1 in the first coordinate system in the second coordinate system. In stage ③, the roll angle is obtained by rotating the second coordinate system around the X-axis to obtain the third coordinate system, the third rotation sub-matrix between the third and second coordinate systems, and the coordinates of feature point P2 in the second coordinate system in the third coordinate system. Figure 5 The coordinates of feature point P3 in the third coordinate system. Among them, feature points P1, P2 and P3 are the projection points of feature P in the first coordinate system, the second coordinate system and the third coordinate system, respectively.

[0152] The signal positioning device 111 obtains a rotation matrix using the first rotation sub-matrix, the second rotation sub-matrix, and the third rotation sub-matrix.

[0153] In one alternative implementation, "the location information of each feature point" can refer to the coordinates of the feature point in three-dimensional space. This three-dimensional point is a spatial point of the target site in real three-dimensional space.

[0154] For example, Figure 6 This is a schematic diagram illustrating the association between the first and second panoramic images and three-dimensional points in space, provided for embodiments of this application. For example... Figure 6 As shown, feature point p in image 1 matches feature point p' in image 2. Both feature points correspond to a 3D point (or position point) p0 in the real 3D space. Finally, using the 3D point and its corresponding feature point in image 1, the camera pose corresponding to image 1 is calculated.

[0155] In some possible implementations, collection mapping (COLMAP) tools can be used to estimate the camera pose for each panoramic image using the structure from motion (SFM) algorithm.

[0156] Phase 4, map construction.

[0157] The signal positioning device 111 creates a 3D map based on the camera pose and the position information of all feature points. It then aligns all the panoramic images into a single coordinate system based on the camera poses of all frames, forming a panoramic image sequence. This panoramic image sequence is used to provide a 3D scene of the target site.

[0158] based on Figure 4In the provided embodiment, the signal positioning device 111 uses sequential panoramic pose calculation to obtain three-dimensional map data, ensuring that the three-dimensional map data can provide the pose of the panoramic image, thereby ensuring the degree of matching between the three-dimensional map data and the real environment of the target site, and thus ensuring the reliability of the subsequently generated three-dimensional model.

[0159] S330, the signal positioning device 111 inputs the three-dimensional map data into the NeRF model, trains the NeRF model to obtain the trained NeRF model, and uses the trained NeRF model to generate a rendering map to obtain a three-dimensional spatial model.

[0160] The NeRF model can map the coordinates of a location point and its viewing direction to the color and spatial density of that location point. For example... Figure 7 As shown, R1 and R2 are two rays with different directions. Each ray corresponds to the viewing angle of the camera at a certain coordinate position. Image 1 shows the target observed through the viewing direction of R1 (i.e., Figure 7 Image 1 is the image observed when viewing the target through the viewing direction of R2 (the black cube in the image). Image 2 is the image observed when viewing the target through the viewing direction of R2. From Figure 7 As can be seen, a ray can pass through multiple spatial points in the target scene, that is, a ray includes multiple position points. The color and volume density of all position points on the ray together constitute the pixel color observed in the observation direction of the ray.

[0161] The coordinates of the pixel points in the panoramic image corresponding to the location points in the target site can be determined by the panoramic image and the camera pose corresponding to the panoramic image.

[0162] The viewing direction can be determined by the camera pose when the panoramic image is captured. The pixel value of the pixel in the observed image can be obtained by integrating the color and density of one or more spatial points in the target scene in a viewing direction.

[0163] In one optional implementation, the training process of the NeRF model by the signal localization device 111 includes: The signal localization device 111 obtains the coordinates and corresponding viewing directions of the position points on different rays in the target scene based on the panoramic image of each position point in the 3D map data and the corresponding camera position. The signal localization device 111 constructs a model training vector corresponding to each position point based on the coordinates and corresponding viewing directions of the position points on each ray. During model training, the signal localization device 111 inputs this model training vector into the NeRF model to obtain the color and volume density of each position point. Based on the color and volume density of all position points on a ray, the observed pixel color under the viewing direction of that ray is estimated. Based on the estimated pixel color and the ground truth value of the pixel color represented by the obtained image under that viewing direction, the output loss of the current neural radiation field model is calculated. The parameters of the NeRF model are adjusted based on the output loss until the NeRF model converges, resulting in the trained NeRF model.

[0164] based on Figure 3 In the provided embodiment, the signal positioning device 111 is trained using a NeRF model to create a 3D model of the target site, reconstructing and rendering the environmental reality of the target site. This improves rendering quality while ensuring the realism of the 3D spatial model, thereby ensuring that the final signal test results are more intuitive.

[0165] In one optional implementation, to facilitate spatial positioning of signal values, after acquiring 3D map data of the target site, the signal positioning device 111 can extract features from the panoramic image of each location point to obtain the visual features of each location point. The signal positioning device 111 associates and stores multiple location points in the target site with the visual features of each location point to obtain a feature library. Subsequently, the signal positioning device 111 retrieves the feature library using the visual features of the acquired images to perform spatial positioning of the signal value. Thus, even in situations with weak satellite signals, the signal positioning device 111 can still ensure the degree of matching between the signal value and the location point, thereby improving the accuracy of the signal test results.

[0166] Among them, visual features may include, but are not limited to: image features such as corner points, edges, textures, and structures of the image, and camera parameters such as exposure parameters, intrinsic parameters, and extrinsic parameters of the camera.

[0167] In one optional implementation, the signal positioning device 111 can slice each panoramic image to obtain sliced ​​images. The signal positioning device 111 then performs feature extraction on the sliced ​​images to obtain the visual features of the location points corresponding to the panoramic image. In this way, the signal positioning device 111 reduces the amount of data extracted each time by slicing, thereby improving the efficiency of feature extraction.

[0168] Among them, slicing, also known as panoramic slicing or image segmentation, is used to divide a panoramic image into multiple image blocks or image regions. An image block or image region can be called a sliced ​​image.

[0169] In one alternative example, the signal positioning device 111 can slice the panoramic image for each panoramic image in several ways, for example:

[0170] In the first implementation, the signal positioning device 111 uses a grid to divide the panoramic image into multiple rectangular areas.

[0171] In the second implementation, the signal positioning device 111 divides the panoramic image into multiple image regions based on the image content (such as edge detection, color distribution, etc.), and the image content is different in different image regions.

[0172] In the third implementation method, the signal positioning device 111 divides the panoramic image into multiple rectangular areas according to the latitude and longitude of the panoramic image.

[0173] The above three implementation methods are merely different ways in which the signal positioning device 111 slices the panoramic image. In other embodiments, the signal positioning device 111 may also use other implementation methods to slice the panoramic image, and this application embodiment does not limit this.

[0174] In one alternative implementation, the signal positioning device 111 refers to the above. Figures 3 to 7 A three-dimensional model and feature library of the target site are created. When the signal positioning device 111 receives the signal data and image data of the target site, it provides the client 20 with visualized signal test results based on the image data, signal data, three-dimensional model of the target site, and feature library.

[0175] The following is combined Figures 8 to 15 An exemplary description is provided of how the signal positioning device 111 performs signal testing and provides visualized signal test results.

[0176] Please see Figure 8 , Figure 8 This is a flowchart illustrating the signal positioning method provided in this application, which includes steps S810 to S830.

[0177] S810, the signal positioning device 111 acquires the first signal data and multiple images of the target site.

[0178] The first signal data includes multiple signal values ​​and the sampling time corresponding to each signal value.

[0179] Multiple images may contain different images that correspond to different regions or test points within the target site. Alternatively, at least two images may contain images that correspond to different regions.

[0180] In one alternative implementation, the signal positioning device 111 can read the first signal data of the stored target site as well as multiple image data.

[0181] For example, the signal positioning device 111 can read the first signal data of the target site and multiple image data from the memory of the cloud server 10.

[0182] In another alternative implementation, the signal positioning device 111 can receive first signal data of the target site and multiple image data uploaded by the work terminal 30.

[0183] For example, in response to a signal acquisition command, the work terminal 30 performs a signal acquisition operation. The work terminal 30 moves within the target scene. During the movement, the work terminal 30 acquires signal values ​​according to a preset sampling period and obtains first signal data and multiple image data of the target site based on video or images during the movement. The work terminal 30 then sends the first signal data and multiple image data to the signal positioning device 111.

[0184] The movement of the work terminal 30 in the target scene can be achieved by a tester holding the work terminal 30 and moving it within the target area, or by the work terminal 30 being mounted on a mobile tool, which moves within the target scene to move the work terminal 30. The mobile tool can include, but is not limited to, robots, intelligent vehicles, drones, or other tools. This application embodiment does not impose any limitations on this.

[0185] In the first alternative approach, the signal acquisition command may be issued by the signal positioning device 111.

[0186] For example, client 20 sends a signal test request to signal positioning device 111, and signal positioning device 111 responds to the signal test request by issuing a signal acquisition command to operating terminal 30.

[0187] For example, if the client 20 sends a request to the signal positioning device 111 to view the signal test results, and the signal positioning device 111 fails to read the first signal data and multiple image data of the target site, the signal positioning device 111 issues a signal acquisition command to the operation terminal 30.

[0188] For example, the signal positioning device 111 performs the above-mentioned... Figure 3 In the provided embodiment, after creating a three-dimensional spatial model, a signal acquisition command is sent to the operation terminal 30.

[0189] In the second alternative approach, signal acquisition commands can also be input by the tester via an interface.

[0190] For example, the work terminal 30 provides a test interface, through which the tester inputs signal acquisition commands. In an alternative approach, the test interface may also be referred to as the first interface, signal acquisition interface, signal test interface, etc. Similarly, the first operation may be called the test initiation operation.

[0191] The two optional methods described above are merely different triggering methods for the signal acquisition command. In other embodiments, the signal acquisition command may have other triggering methods, such as the client 20 sending a signal acquisition command to the operating terminal 30. This application embodiment does not limit this.

[0192] S820, for the first image among multiple images, the signal positioning device 111 compares the visual features of the first image with the feature library, and determines the first network signal value of the first position point in the three-dimensional spatial model based on the first signal data.

[0193] The first location point is used to indicate the location information of the area captured by the first image in the three-dimensional spatial model.

[0194] In one optional implementation, the signal positioning device 111 may extract the visual features of the first image by referring to the visual feature extraction method in S330 above. This embodiment of the application will not elaborate on this.

[0195] In one optional implementation, the signal positioning device 111 can locate a first position point in the three-dimensional model by comparing the visual features of the first image with a feature library. For example, the signal positioning device 111 can refer to the following... Figure 11 The provided embodiment locates the position information of the area captured by the first image in a three-dimensional spatial model. The embodiments of this application will not be described in detail here.

[0196] In one optional implementation, the signal positioning device 111 can determine the first network signal value of the first location point in the three-dimensional spatial model by obtaining the network signal value matching the sampling time and the acquisition time based on the acquisition time of the first image and the signal values ​​corresponding to different sampling times in the first signal data. Figure 8 As shown, the first network signal value S at the first location point is obtained. Exemplarily, the signal positioning device 111 can refer to the following... Figure 11 The provided embodiment determines a first network signal value at a first location point. The embodiments described in this application will not be elaborated upon here.

[0197] S830, the signal positioning device 111 renders the first label of the first position point in the three-dimensional space model.

[0198] The first label is used to indicate the first network signal value corresponding to the first location point.

[0199] The embodiments of this application do not limit the specific shape of the first label. For example, the first label can be rectangular. Another example is that the first label can be balloon-shaped. Yet another example is that the first label can also be bubble-shaped.

[0200] In one optional implementation, the signal positioning device 111 forms the content of the first tag based on the first network signal value corresponding to the first location point. The signal positioning device 111 determines the display position of the first tag in the 3D model based on the coordinates of the first location point. Based on the content of the first tag and its display position in the 3D spatial model, the signal positioning device 111 renders the first tag in the 3D spatial model. After rendering of multiple location points in the 3D spatial model (such as all location points, or location points corresponding to multiple images) is complete, the signal positioning device 111 outputs the target 3D spatial model.

[0201] The target 3D spatial model is a 3D model in which multiple location points in the 3D spatial model are labeled. For example... Figure 9A As shown, in Figure 9A This is a schematic diagram of the target three-dimensional spatial model provided in this application. The target site's three-dimensional spatial model includes location point 1, location point 2, and location point 3. Location point 1 is labeled with label 1, location point 2 with label 2, and location point 3 with label 3. Label 1 displays the network signal values ​​PCI X1 and RARP Y1 for location point 1. Label 2 displays the network signal values ​​PCI X2 and RARP Y2 for location point 2. Label 3 displays the network signal values ​​PCI X3 and RARP Y3 for location point 3.

[0202] In an alternative approach, to more intuitively display the network signal value of each location point, the signal positioning device 111 can divide the network signal values ​​of multiple location points into one or more network signal value ranges, and render the labels with network signal values ​​in different network signal value ranges in different colors.

[0203] For example, the signal positioning device 111 can compare the network signal values ​​of multiple location points with a network signal value threshold, and render the labels with network signal values ​​greater than or equal to the network signal value threshold as a first color. Labels with network signal values ​​less than the network signal value threshold are rendered as a second color. The specific colors of the first and second colors are not limited in this embodiment. The network signal value threshold can be set by the user, by the tester, or by the signal positioning device 111 itself; this embodiment does not limit its implementation.

[0204] In another approach, the signal positioning device 111 determines the signal state of each location point based on the network signal values ​​of multiple locations. The signal positioning device 111 then renders the labels of location points with different signal states with different colors.

[0205] This application does not limit the specific type of signal state in its embodiments. For example, signal state may include: good network quality, network quality needs optimization, network interference, etc. Or, for example, signal state may include: good network quality, poor network quality, etc.

[0206] In one alternative implementation, after the signal positioning device 111 forms a three-dimensional spatial model of the target, it sends the target three-dimensional spatial model to the client 20. The client 20 then displays the target three-dimensional spatial model in its user interface.

[0207] In another optional implementation, after the signal positioning device 111 forms the target three-dimensional spatial model, it associates and stores the target three-dimensional spatial model with the site identifier of the target site. Upon receiving the second request sent by the client 20, the signal positioning device 111 returns the target three-dimensional spatial model of the first site requested in the second request to the client 20. The second request carries a site identifier, which indicates the site requested by the client 20. The second request is used to request the acquisition of the target three-dimensional spatial model of the first site corresponding to the site identifier.

[0208] In the first alternative approach, if the cloud platform 110 stores a target three-dimensional spatial model that matches the site identifier, the signal positioning device 111 returns the target three-dimensional spatial model of the first site to the client 20.

[0209] In the second alternative approach, if the cloud platform 110 does not store a target three-dimensional spatial model that matches the site identifier, the signal positioning device 111 executes the above-described S810 to S830 to obtain the target three-dimensional spatial model of the first site, and the signal positioning device 111 returns the target three-dimensional spatial model of the first site to the client 20.

[0210] For example, such as Figure 9B As shown. Figure 9B Figure (a) shows a user interface 200 with a "Result Display" control. Client 20 detects a user action, such as a click, on the "Result Display" control, and in response, sends a second request to signal positioning device 111 and receives the signal test results returned by signal positioning device 111. Client 20 displays the result as shown in Figure (a). Figure 9B The user interface 300 is shown in Figure (b). The user interface 300 includes a preview box, operation controls, and an exit control.

[0211] The preview box is used to display the target's 3D spatial model. For example... Figure 9B As shown in Figure (b), label 1 is displayed in the target's three-dimensional spatial model. This target's three-dimensional spatial model is based on the above-mentioned signal measuring device. Figure 3 , Figure 8 The provided examples simulate virtual scenes.

[0212] The manipulation controls can be used to change the user's viewing angle. The client 20 can detect the sliding operation on the manipulation controls in different directions. In response to the operation, the client 20 can update the displayed content in the preview box according to the sliding operation.

[0213] For example, when client 20 detects a left swipe operation on the control 403, client 20 adds a view of the left-side 3D model (not shown) to the left of the preview frame, and removes the view of the partially shown target 3D spatial model from the right, giving the user a roaming effect as if the viewing angle is moving to the left. Figure 9B As shown in Figure (c), the target 3D spatial model in the user interface 400 is displayed with labels 1, 2 and 3.

[0214] An exit control can be used to trigger client 20 to stop displaying the target 3D spatial model. For example, when client 20 detects a user action on the exit control, in response to that action, client 20 can display something like... Figure 9B The user interface 200 is shown in Figure (a).

[0215] based on Figure 8 In the provided embodiment, the signal positioning device 111 uses image data and a feature library to align the region corresponding to the image data with the location points of the target scene. Based on the image data and first signal data, it determines the network signal value corresponding to the location point, thus achieving a comparison between the network signal value and the location point. Since this application does not use satellite signals, even in situations where satellite signals are weak, the matching degree between the network signal value and the location point can still be ensured, thereby improving the accuracy of the signal test results. Furthermore, the signal positioning device 111 renders labels for the network signal values ​​of the location points in a three-dimensional spatial model, enabling a visual display of the signal test results.

[0216] The above Figures 3 to 9B The signal positioning method provided in this application is described using the signal positioning device 111 as the executing entity. In some optional implementations, the signal positioning method provided in this application embodiment can also be executed by other computing devices. For example, the computing device may include, but is not limited to: a server, a cloud server, a cloud platform 110, a computing node or computing device with rendering function, or other nodes or clusters that can execute the signal positioning method provided in this application embodiment.

[0217] In addition, the signal positioning method provided in this application can be used not only to display network signal values ​​measured in real scenarios, but also to display network signal values ​​simulated in virtual scenarios.

[0218] Here, "real-world scene" can refer to panoramic images of a location captured in a real-world environment, as described above. Figure 3 The provided embodiments create a three-dimensional spatial model. A "virtual scene" can be a three-dimensional point cloud model created using a two-dimensional plan view or a three-dimensional model of the site. This three-dimensional point cloud model can also be called three-dimensional point cloud data, point cloud data, etc. "Simulated network signal values" can refer to the network signal values ​​of locations within the site in a virtual scene simulated by software, models, tools, or programs. "Measured network signal values" can refer to the network signal values ​​of locations within the site collected in a real environment using the aforementioned workstation and signal testing APP.

[0219] The following combination Figure 10 This paper provides an exemplary description of a signal localization method in a virtual scene.

[0220] Please see Figure 10 , Figure 10 Flowchart of the signal positioning method provided in this application Figure 2 The signal localization method includes steps S101 to S104.

[0221] S101, the signal positioning device 111 acquires point cloud data of the site and second signal data.

[0222] The second signal data includes the analog network signal value at each of the multiple location points in the site. In some alternative embodiments, the second signal data may also be referred to as analog signal data, virtual signal data, or other names, and this application embodiment does not limit this.

[0223] In the first optional implementation, the point cloud data can be sent by an external device. This external device can be the aforementioned client 20, or other cloud platforms 110, other servers, or computing devices. This application embodiment does not limit the specific type of the source device for the point cloud data.

[0224] In the second alternative implementation, the point cloud data can also be generated by the signal positioning device 111.

[0225] For example, the signal positioning device 111 acquires a three-dimensional model of the site. The signal positioning device 111 converts the three-dimensional model of the site into point cloud data. For instance, the signal positioning device 111 uses a deep learning model to convert the three-dimensional model of the site into point cloud data, wherein the deep learning model may include, but is not limited to, models based on graph neural networks, machine learning, or large language models. Alternatively, the signal positioning device 111 invokes a modeling tool to convert the three-dimensional model of the site into point cloud data.

[0226] The two optional implementation methods mentioned above are only different ways for the signal positioning device 111 to acquire the point cloud data of the site. In other embodiments, the signal positioning device 111 may also use other implementation methods to acquire the point cloud data of the site. This application embodiment does not limit this.

[0227] In one alternative implementation, similar to the point cloud data described above, the second signal data can be sent by an external device or generated by the signal positioning device 111.

[0228] The following example illustrates how the signal positioning device 111 acquires the second signal data.

[0229] In a first optional embodiment, the signal positioning device 111 acquires the parameters of the simulated signal source in the site, and predicts the simulated network signal value of each of the multiple location points in the site based on the parameters of the simulated signal source through a network signal value transmission model.

[0230] The parameters of the analog signal source include, but are not limited to, the signal strength, location information, altitude, pitch angle, and viewing angle. The analog signal source can refer to a three-dimensional point, representing the origin of the network signal. The network signal propagates in a straight line from the analog signal source, stopping at the intersection point where the line intersects an object. The analog signal source can be an antenna, base station, router, or other network device.

[0231] This application does not limit the specific type of network signal value transmission model. For example, the network signal value transmission model can be a free space transmission model, an empirical model, a ray tracing model, a stochastic geometric model, or a Monte Carlo model. Furthermore, the network signal value transmission model can also be a prediction model based on a neural network.

[0232] In a second alternative implementation, the signal positioning device 111 acquires the parameters of the analog signal source in the field, calls the simulation tool based on the parameters of the analog signal source, and obtains the analog network signal value of each location point among multiple location points in the field.

[0233] In some alternative approaches, the simulation tool may also be referred to as a software tool or a simulation tool. This application does not limit the specific type of simulation tool.

[0234] The two optional implementation methods described above are merely different ways for the signal positioning device 111 to generate the second signal data. In other embodiments, the signal positioning device 111 may also use other optional methods to generate the second signal data, which are not limited in this application.

[0235] S102, for the first point cloud coordinates in the point cloud data, the signal positioning device 111 determines the analog network signal value corresponding to the first point cloud coordinates based on the second signal data.

[0236] In one optional implementation, the signal positioning device 111 can align each location point in the second signal data with each point cloud coordinate in the point cloud data to obtain the point cloud coordinates matching each location point, thus establishing a mapping relationship between location points and point cloud coordinates. For a first point cloud coordinate in the point cloud data, the signal positioning device 111, based on the mapping relationship between location points and point cloud coordinates, obtains the target location point corresponding to the first point cloud coordinate, and uses the analog network signal value of that target location point in the second signal data as the analog network signal value corresponding to the first point cloud coordinate. For example... Figure 10 As shown, the simulated network signal value corresponding to the cloud coordinates of the first point is K.

[0237] The mapping relationship between the location point and the point cloud coordinates can be a transformation matrix between the coordinates of the location point and the coordinates of the point cloud.

[0238] In one alternative implementation, the signal positioning device 111 may employ one or more point cloud registration methods, such as feature matching, iterative closest point (ICP) algorithm, and global registration, to align each location point in the second signal data with each point cloud coordinate in the point cloud data. Alternatively, the signal positioning device 111 may utilize a neural network-based model to align each location point in the second signal data with each point cloud coordinate in the point cloud data.

[0239] S103, the signal positioning device 111 renders the second label of the first point cloud coordinates in the point cloud data.

[0240] The second label is used to indicate the simulated network signal value corresponding to the first point cloud coordinates.

[0241] In an alternative implementation, the signal positioning device 111 may render a second label of the first point cloud coordinates in the point cloud data using the above-described S830. Further details of the embodiments in this application will not be elaborated upon here.

[0242] S104, after multiple point cloud coordinates in the point cloud data have been rendered, the signal positioning device 111 outputs the target point cloud data of the site.

[0243] The target point cloud data refers to a point cloud where multiple point cloud coordinates are displayed with labels.

[0244] In an alternative implementation, the signal positioning device 111 may refer to the above-described... Figure 5 The target point cloud data of the output site is not described in detail in this embodiment.

[0245] based on Figure 10 The provided embodiment, during the site network planning phase, forms a three-dimensional model of the site network planning by simulating network signal values ​​at multiple locations within the site, visually demonstrating the site's network signal performance. This improves user interaction.

[0246] Regarding the above Figure 8 The implementation of S820 in [the context of the text] will be discussed below. Figure 11 An example is provided.

[0247] Please see Figure 11 , Figure 11 The diagram illustrates the network signal value location process provided in this application, which includes steps S821 to S824.

[0248] S821, the signal positioning device 111 acquires the visual features of the first image.

[0249] In an alternative implementation, the signal positioning device 111 may refer to the above-described... Figure 4 In stage ④ of the process, visual features of the first image are extracted, which will not be described in detail in this embodiment.

[0250] S822, Based on the feature library and the visual features of the first image, determine the first position point corresponding to the first image.

[0251] In one alternative implementation, the signal positioning device 111 can determine the first location point corresponding to the first image by searching a feature library based on the visual features of the first image. Thus, the signal positioning device 111 achieves location positioning using a three-dimensional spatial model and local images of the site, resulting in a simple positioning method. Furthermore, the use of visual feature comparison can improve positioning accuracy.

[0252] For example, the signal positioning device 111 queries a feature library based on the visual features of the first image to obtain a first visual feature in the feature library that matches the visual features of the first image. The signal positioning device 111 then determines the location point corresponding to the first visual feature as the first location point.

[0253] In a first optional embodiment, the signal positioning device 111 can acquire the similarity between the visual features of the first image and the visual features of different locations in the feature library. The visual feature with the highest similarity is determined as the first visual feature.

[0254] The similarity can be calculated by measuring the distance between the visual features of the first image and the visual features of different points in the feature library (e.g., Euclidean distance or Mahalanobis distance). Alternatively, the similarity can be obtained by measuring the structural similarity between the visual features of the first image and the visual features of different points in the feature library.

[0255] In a second alternative implementation, the signal positioning device 111 predicts the probability values ​​of visual features at different locations in the feature library as visual features of the first image, and determines the visual feature with the highest probability value as the first visual feature.

[0256] In one example, the signal positioning device 111 can predict probability values ​​using a machine learning-based prediction model. This machine learning-based prediction model can be a logistic regression-based model, an SVM-based model, or a random forest-based model; the specific type of machine learning-based prediction model is not limited in this embodiment.

[0257] In another example, the signal localization device 111 can predict probability values ​​based on a neural network prediction model. This neural network prediction model can be a convolutional neural network (CNN), a recurrent neural network (RNN), a fully connected network, or a large language model, etc. This application does not limit the specific type of neural network prediction model.

[0258] The two optional implementation methods described above are merely alternative ways for the signal positioning device 111 to determine the first visual feature in the feature library that matches the visual features of the first image. In other embodiments, the signal positioning device 111 may also use other alternative methods to determine the first visual feature. For example, the signal positioning device 111 may calculate the absolute value of the difference between the visual features of the first image and the visual features at different locations in the feature library, and take the visual feature with the smallest absolute value of the difference as the first visual feature. Another example is that the signal positioning device 111 uses the visual features of the first image as cluster centers to cluster the visual features at different locations in the feature library to obtain the first visual feature that matches the visual features of the first image. Yet another example is that the signal positioning device 111 may also determine the first visual feature in the feature library that matches the visual features of the first image through maximum likelihood estimation. This application does not limit these methods.

[0259] S823, the signal positioning device 111 obtains the target network signal value whose sampling time matches the acquisition time of the first image based on the sampling time corresponding to each network signal value in the first signal data and the acquisition time of the first image.

[0260] In one alternative approach, "matching the sampling time with the acquisition time of the first image" can mean that the sampling time and the acquisition time of the first image are the same. Alternatively, "matching the sampling time with the acquisition time of the first image" can also mean that the time difference between the sampling time and the sampling time of the first image is less than a time difference threshold. This application does not limit the specific numerical range of the time difference threshold in its embodiments.

[0261] In one alternative implementation, the signal positioning device 111 can query the first signal data based on the acquisition time of the first image to obtain a first sampling time that matches the acquisition time of the first image. The signal positioning device 111 then obtains the target network signal value based on the network signal value corresponding to the first sampling time.

[0262] In a first optional implementation, the first sampling time is the same as the acquisition time of the first image. The signal positioning device 111 uses the network signal value corresponding to the first sampling time as the target network signal value.

[0263] In a second optional implementation, the time difference between the first sampling time and the acquisition time of the first image is less than a time difference threshold. When there is only one first sampling time, the signal positioning device 111 uses the network signal value corresponding to the first sampling time as the target network signal value. When there are multiple first sampling times, the signal positioning device 111 can use the average, maximum, or minimum value of the network signal values ​​corresponding to the multiple first sampling times as the target network signal value. Alternatively, when there are multiple first sampling times, the signal positioning device 111 interpolates based on the network signal values ​​corresponding to the first sampling times to obtain the target network signal value.

[0264] The two optional implementation methods described above are merely different ways in which the signal positioning device 111 obtains the target network signal value that matches the acquisition time of the first image. In other embodiments, the signal positioning device 111 may also use other implementation methods to obtain the target network signal value that matches the acquisition time of the first image, and this application embodiment does not limit this.

[0265] The execution order of S821 to S823 described above is not limited in this embodiment. For example:

[0266] In the first optional implementation, the signal positioning device 111 executes in the order of S821→S822→S823.

[0267] In the second alternative implementation, the signal positioning device 111 executes in the order of S823→S821→S822.

[0268] In the third optional implementation, the signal positioning device 111 executes the above S822 to S823 in parallel. After the signal positioning device 111 determines the first position point corresponding to the first image and obtains the target network signal value that matches the acquisition time of the first image, the signal positioning device 111 executes the following S824.

[0269] The above three optional implementation methods are merely different execution orders of S821 to S823 by the signal positioning device 111. In other embodiments, the signal positioning device 111 may also execute S821 to S823 in other orders. This application embodiment does not limit this.

[0270] S824, the signal positioning device 111 uses the target network signal value as the first network signal value corresponding to the first location point.

[0271] In some alternative implementations, during the acquisition of images and first signal data, the work terminal 30 associates the images acquired at the same time with the first network signal value, and then sends the image associated with the first network signal value to the signal positioning device 111. After acquiring multiple images, the signal positioning device 111 determines the first location point corresponding to the first image and the target network signal value of the first location point. That is, when each of the multiple images acquired by the signal positioning device 111 is associated with a corresponding first network signal value, the signal positioning device 111 executes S821→S822→S824 to obtain the target network signal value of the first location point.

[0272] based on Figure 11 In the provided embodiment, the signal positioning device 111 uses a three-dimensional spatial model and local images of the site to achieve location positioning, and locates the network signal value by correlating the image with the network signal value. This improves positioning accuracy and ensures location positioning even when satellite signals are weak.

[0273] The following combination Figures 12 to 15 An exemplary description is provided of how the signal positioning device 111 renders location point labels in a three-dimensional spatial model.

[0274] For example, taking the signal positioning device 111 rendering a label for a location point as an example, such as Figure 12 As shown, Figure 12 This is a schematic diagram of the label rendering process provided in an embodiment of this application. The label rendering process shown includes steps S831 to S834.

[0275] S831, the signal positioning device 111 determines the coordinate data of the first tag based on the coordinates of the first position point and the shape of the first tag.

[0276] In one optional implementation, the coordinate data of the first label includes the coordinate values ​​of the first label's vertices in the rendering camera coordinate system. For example... Figure 12 As shown, the coordinate data of the first label includes the coordinate values ​​of vertices a0, a1, a2, a3 and a4 in the first label.

[0277] In one alternative implementation, the rendering camera coordinate system can be related to the viewing angle of the 3D spatial model. For example, the signal positioning device 111 uses the viewing angle to determine the position of the rendering camera and establishes the rendering camera coordinate system with the position of the rendering camera as the origin. Alternatively, the signal positioning device 111 can rotate the initial rendering camera coordinate system using the viewing angle to obtain the final rendering camera coordinate system.

[0278] The viewing angle can be preset by the signal positioning device 111. Alternatively, the viewing angle can be input by the user to the signal positioning device 111 through the client 20, for example, by the user through the aforementioned Figure 9B The operation controls in Figure (b) input the viewing angle to the signal positioning device 111.

[0279] The initial rendering camera coordinate system can be the rendering camera coordinate system preset by the signal positioning device 111, or the rendering camera coordinate system used by the signal positioning device 111 when rendering the target three-dimensional space model last time.

[0280] In one alternative approach, as described above Figure 9B As shown in Figures (a) and (b), when the user switches viewing angles, the signal positioning device 111 can update the rendering camera coordinate system according to the new viewing angle, and re-render based on the updated rendering camera coordinate system to form a new target 3D spatial model. This allows the target 3D spatial model to switch according to the user's viewing angle.

[0281] In one alternative implementation, the vertices of the first label can be corner points or edge points of the first label. For example, taking a rectangle as the first label... Figure 12 As shown, the vertices in the first label include a0, a1, a2, a3, and a4.

[0282] In one alternative implementation, the shape of the first tag may be preset by the signal positioning device 111 or customized by the user.

[0283] Taking the shape of a user-defined first label as an example, the user inputs the shape parameters of the label through the user interface provided by the client 20, and the client 20 sends the user-input shape parameters to the signal positioning device 111. The signal positioning device 111 determines the shape of the first label according to the label's shape parameters. The shape parameters are used to indicate the shape of the label; for example, the shape parameters can be the label's shape identifier, or the label parameters can be the label's length, width, or radius.

[0284] The following is an exemplary description of how the signal positioning device 111 determines the coordinate data of the first tag.

[0285] In one alternative implementation, the signal positioning device 111 can use the coordinates of the first position point as the coordinates of the key point of the first label, determine the distance between the vertex of the first label and the key point of the first label according to the shape of the first label, and obtain the coordinate value of the vertex of the first label based on the distance and the coordinates of the key point.

[0286] The key point of the first label can be the center point of the first label (e.g., the geometric center point or the centroid point), or the key point of the first label can be the midpoint of the edge of the first label.

[0287] For example, with Figure 12 Taking the provided first label as an example, the keypoint of the first label is vertex a0, and the coordinates of the keypoint of the first label are the same as the coordinates of the first position point. The coordinates of vertices a1, a2, a3, and a4 are related to the coordinates of vertex a0 and the size of the first label. For example, if the coordinates of vertex a0 are (0,0,0), and the length and width of the first label are L, then the coordinates of vertex a1 are (-L / 2,0,0), the coordinates of vertex a2 are (-L / 2,H,0), the coordinates of vertex a3 are (L / 2,0,0), and the coordinates of vertex a4 are (L / 2,H,0).

[0288] In another alternative implementation, the signal positioning device 111 can determine the initial coordinate values ​​of the vertices in the first label based on the coordinates of the first position point and the shape of the first label. The signal positioning device 111 determines the transformation matrix between the coordinate system of the 3D spatial model and the rendering camera coordinate system based on the viewing angle. Based on the transformation matrix between the coordinate system of the 3D spatial model and the rendering camera coordinate system, and the initial coordinate values ​​of the vertices in the first label, the signal positioning device 111 transforms the vertices in the first label into the rendering camera coordinate system, thus obtaining the coordinate values ​​of the vertices of the first label.

[0289] The two optional implementation methods described above are merely different ways in which the signal positioning device 111 determines the coordinate data of the first label. In other embodiments, the signal positioning device 111 may also use other implementation methods to determine the coordinate data of the first label. For example, the signal positioning device 111 may determine the initial coordinate values ​​of the vertices in the first label based on the coordinates of the first position point and the shape of the first label, and transform the initial coordinate values ​​of the vertices in the first label to the rendering camera coordinate system based on the camera pose of the first image to obtain the coordinate values ​​of the vertices of the first label. This application does not limit this aspect.

[0290] S832 determines the distance between the first label and the rendering camera based on the coordinate data of the first label.

[0291] The distance is used to indicate the depth value of the first label in the target 3D spatial model. In some alternative ways, the distance between the first label and the rendering camera can also be referred to as the depth value of the first label, or the depth of field of the first label.

[0292] In one alternative implementation, the signal positioning device 111 can obtain the coordinate value of the center point of the first label based on the coordinate data of the first label, obtain the distance between the center point of the first label and the origin of the rendering coordinate system based on the coordinate value of the center point of the first label, and determine the distance between the first label and the rendering camera.

[0293] In another alternative implementation, the signal positioning device 111 may also obtain the distance between the key point of the first label and the origin of the rendering coordinate system based on the coordinate values ​​of the key point of the first label in the rendering coordinate system, and determine the distance between the first label and the rendering camera.

[0294] The two optional implementation methods described above are simply different ways in which the signal positioning device 111 determines the distance between the first tag and the rendering camera. In other embodiments, the signal positioning device 111 may also use other implementation methods to determine the distance between the first tag and the rendering camera. This application does not limit this aspect.

[0295] S833, the signal positioning device 111 determines the position information of the first label in the three-dimensional space model according to the distance between the first label and the rendering camera.

[0296] The position information of the first label in the three-dimensional space model may include the size of the first label in the three-dimensional space model and the coordinates of each vertex of the first label in the three-dimensional space model.

[0297] In one optional implementation, the signal positioning device 111 projects the coordinates of each vertex of the first label onto the image plane of the 3D spatial model based on the distance between the first label and the rendering camera and the camera parameters of the rendering camera, thereby obtaining the size and position of the first label on the image plane of the 3D spatial model. The size and position of the first label on the image plane of the 3D spatial model are used as the position information of the first label in the 3D spatial model.

[0298] The camera parameters include the focal length and pixel resolution of the rendering camera.

[0299] The image plane can also be called the imaging plane, screen, or other names, and this application does not limit this. The image plane of the three-dimensional spatial model is used to indicate the surface on which the three-dimensional spatial model is projected onto the two-dimensional image.

[0300] The size of the first label on the image plane of the 3D spatial model can include the length and width of the first label, or the radius of the first label. In one optional example, the farther the first label is from the rendering camera, the smaller its projection on the image plane. Figure 13 As shown, the size of the first label gradually decreases as the distance between the first label and the rendering camera increases.

[0301] S834, the signal positioning device 111 renders the first label at the first position point in the three-dimensional space model according to the position information.

[0302] In one alternative implementation, the signal positioning device 111 invokes the vertex renderer to render the first label at the first position point in the three-dimensional space model based on the position information.

[0303] The vertex renderer can also be called a vertex shader.

[0304] In addition, the signal positioning device 111 can also call the vertex renderer to render the first label at the first position point in the three-dimensional space model based on the position information, color, and transparency of the first label.

[0305] Furthermore, the signal positioning device 111 can also render the first label at its first position point in the 3D spatial model using a vertex renderer based on the first label's position information, color, transparency, texture, and normals. The normals are used to indicate the lighting information of the first label, and the texture is used to indicate the surface texture of the first label in the 3D spatial model.

[0306] based on Figure 12 In the provided embodiment, the signal positioning device 111 uses the coordinates of a first location point and the distance between the first location point and the rendering camera to determine the size and position of a first label at the first location point. The signal positioning device 111 then renders the signal in a three-dimensional spatial model based on the size and position of the first label and the first network signal value at the first location point. Thus, users can observe the distribution of network signal values ​​at different locations in the field without having to physically visit the site, improving the visualization of signal test results.

[0307] In one alternative implementation, the signal positioning device 111 can obtain the network signal value corresponding to a location point on the three-dimensional spatial model, and then refer to the above... Figure 12 The provided embodiment renders the label for that location point.

[0308] In another alternative implementation, the signal positioning device 111 may also, after acquiring the network signal values ​​corresponding to multiple location points (e.g., all location points, or multiple image-corresponding location points) on the three-dimensional spatial model, refer to the above-mentioned... Figure 12 The provided embodiment renders the label for each of the multiple location points.

[0309] In a first alternative example, the signal positioning device 111 performs the above-described S831 to S834 to render the label for each location point for each location point.

[0310] In a second alternative example, the signal positioning device 111 samples one or more sampling location points from a plurality of location points. For each sampling location point, the above-described S831 to S834 steps are performed to render a label for each sampling location point. This application embodiment does not limit the number of sampling location points.

[0311] In a third alternative example, the signal positioning device 111 performs S831 to S832 to obtain the distance between the label of each of the multiple location points and the rendering camera. The signal positioning device 111 then renders the label of each location point sequentially according to the order of distance from largest to smallest or smallest to largest, as described in S833 to S834.

[0312] The above three examples are just different implementations of the signal positioning device 111 rendering labels for multiple location points. In another optional implementation, the signal positioning device 111 may also use other implementations to render labels for multiple location points. This application embodiment does not limit this.

[0313] In one optional implementation, after the signal positioning device 111 executes the above steps S831 to S833 to obtain the position information of the label of each of the multiple position points, it performs batch rendering of the labels of the multiple position points based on the position information of the labels of each of the multiple position points. In this way, the signal positioning device 111 calls the vertex renderer once to render the labels of multiple position points, thereby reducing the number of times the vertex renderer is called and thus increasing the consumption of computing resources by the signal positioning device 111.

[0314] In two other optional implementations, the signal positioning device 111 executes S831 to S832 to obtain the distance between the label of each of the multiple location points and the rendering camera. The signal positioning device 111 filters the multiple location points based on the distance between the label of each location point and the rendering camera to obtain one or more second location points. The signal positioning device 111 executes S833 to S834 based on the distance between the label of the second location point and the rendering camera to render the label of the second location point.

[0315] In one alternative approach, the second location point can be one of multiple location points where the distance between the label and the rendering camera is less than the depth value of the 3D spatial model. In this way, the signal positioning device 111 can filter displayable labels based on the depth value of the 3D spatial model, avoiding the problem of poor visual effect of the target 3D spatial model caused by displaying a large number of labels, thus improving the visual effect and visualization of the target 3D spatial model.

[0316] The depth value of the 3D spatial model, also known as the background depth value, indicates the depth of the farthest point in the 3D spatial model when viewed from the perspective of the viewer. This depth value is used to determine the frustum of the 3D spatial model from the viewer's perspective.

[0317] The visual cone extent can refer to the visual field range formed by the visual cone. For example... Figure 14 As shown, Figure 14 This is a schematic diagram of the visual cone range provided in an embodiment of this application. The visual cone is a three-dimensional geometric shape. This visual cone is used to simulate the human eye's visual field, conforming to the principle of near objects appearing larger than distant ones. The visual cone range can be... Figure 14 The region between the first plane and the clipping plane in the center-view cone, and the second plane. The distance from the rendering camera to the second plane represents the depth value of the 3D spatial model.

[0318] Taking the first label at the first location point as an example, if the distance between the first label and the rendering camera is greater than the depth value of the 3D spatial model, the first label is occluded, and the signal positioning device 111 does not render the first label. If the distance between the first label and the rendering camera is less than the depth value of the 3D spatial model, the first label is within the view frustum of the viewing angle, and the signal positioning device 111 executes S833 to S834 to render the first label. Alternatively, if the distance between the first label and the rendering camera is equal to the depth value of the 3D spatial model, the signal positioning device 111 may execute S833 to S834 to render the first label, or the signal positioning device 111 may choose not to render the first label.

[0319] In one alternative approach, when the viewing angle changes, the depth value of the three-dimensional spatial model changes accordingly, and the signal positioning device 111 re-executes the above-described S831 to S834 based on the new depth value of the three-dimensional spatial model and the new viewing angle to form a new target three-dimensional spatial model.

[0320] like Figure 15 As shown, in the case of viewing angle 1, such as Figure 15 As shown in Figure (a), the target 3D spatial model displayed in the user interface 500 contains labels 1, 2, and 3. When the viewing perspective is switched from viewing perspective 1 to viewing perspective 2, labels 2 and 3 are obscured, as shown in Figure (a). Figure 15 As shown in Figure (b), the target 3D spatial model displayed by the user interface 600 has labels 1 and 4.

[0321] To achieve the functions of the above embodiments, the signal positioning device 111 includes hardware structures and / or software modules corresponding to each function. Those skilled in the art should readily recognize that, based on the units and method steps described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0322] The above Figures 3 to 15 This application provides a detailed description of the signal testing system, signal positioning method, and signal positioning device 111. In some optional implementations, the signal positioning device 111 can be implemented by software modules or by hardware structures.

[0323] For example, taking the signal positioning device 111 implemented through a software module as an example, such as Figure 16 As shown, Figure 16 Schematic diagram of the signal positioning device 111 provided in this application Figure 1 The signal positioning device 111 shown includes a communication module 151, a processing module 152, and a storage module 153.

[0324] The storage module 153 is used to store executable program code and data (such as feature library, three-dimensional spatial model, first signal data, etc.) of the signal positioning device 111 during the signal positioning process.

[0325] Communication module 151 is used to acquire first signal data and multiple images of the site; the first signal data includes multiple network signal values ​​and the sampling time corresponding to each network signal value; different images correspond to different areas in the site. For example, communication module 151 performs the above... Figure 8 The S810 in it.

[0326] Processing module 152 is configured to, for a first image among multiple images, compare the visual features of the first image with a feature library, and determine the first network signal value of a first location point in a three-dimensional spatial model based on the first signal data. It also renders a first label at the first location point in the three-dimensional spatial model. For example, processing module 152 performs the above... Figure 8 S820 to S830.

[0327] Wherein, the first location point is used to indicate the location information of the area captured by the first image in the three-dimensional spatial model; the first label is used to indicate the first network signal value corresponding to the first location point.

[0328] The communication module 151, processing module 152, and storage module 153 can be implemented in software or in hardware. For example, the implementation of processing module 152 will be described below. Similarly, the implementation of communication module 151 and storage module 153 can refer to the implementation of processing module 152.

[0329] As an example of a software functional unit, processing module 152 may include code running on a computing instance. The computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Further, the computing instance may be one or more. For example, processing module 152 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed in the same region or in different regions. Further, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including one or more geographically proximate data centers. Typically, a region may include multiple AZs.

[0330] Similarly, multiple hosts / virtual machines / containers used to run this code can be distributed within the same Virtual Private Cloud (VPC) or across multiple VPCs. Typically, a VPC is set up within a region. Communication between two VPCs within the same region, as well as between VPCs in different regions, requires a communication gateway to be set up within each VPC to enable interconnection between VPCs.

[0331] As an example of a hardware functional unit, the processing module 152 may include at least one computing device, such as a server. Alternatively, the processing module 152 may also be a device implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be implemented using a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), generic array logic (GAL), or any combination thereof.

[0332] The processing module 152 includes multiple computing devices that can be distributed within the same region or in different regions. Similarly, the communication module 151 includes multiple computing devices that can be distributed within the same Availability Zone (AZ) or in different AZs. Likewise, the processing module 152 includes multiple computing devices that can be distributed within the same Virtual Private Cloud (VPC) or multiple VPCs. These multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0333] It should be noted that, in other embodiments, the processing module 152 can be used to execute any step in the signal positioning method. The communication module 151 can be used to execute any step in the signal positioning method. The storage module 153 can be used to execute any step in the signal positioning method. The communication module 151, processing module 152, and storage module 153 can all execute any step in the signal positioning method. The steps implemented by the communication module 151, processing module 152, and storage module 153 can be specified as needed. By implementing different steps in the signal positioning method through the communication module 151, processing module 152, and storage module 153, all functions of the signal positioning device 111 are realized.

[0334] For example, taking the signal positioning device 111 implemented through a hardware structure as an example, such as Figure 17 As shown, the signal positioning device 111 includes a bus 162, a processor 164, a memory 166, and a communication interface 168. The processor 164, the memory 166, and the communication interface 168 communicate with each other via the bus 162. The signal positioning device 111 can be a server or a terminal device. It should be understood that this application does not limit the number of processors 164 and memory 166 in the signal positioning device 111. Furthermore, in some optional implementations where the signal positioning device 111 is implemented through a hardware structure, the signal positioning device can also be referred to as a computing device, a computing node, or a server, and this application embodiment does not limit this.

[0335] Bus 162 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 17 The bus 162 may be represented by a single line, but this does not mean that there is only one bus or one type of bus. The bus 162 may include a path for transmitting information between the various components of the signal positioning device 111 (e.g., memory 166, processor 164, communication interface 168).

[0336] Processor 164 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0337] In this application, processor 164 can perform the above-mentioned... Figure 8 The provided signal localization method involves, for example, acquiring first signal data of a site and images of different areas within the site. For the first image among multiple images, the visual features of the first image are compared with a feature library, and based on the first signal data, the first network signal value of a first location point in the 3D spatial model is determined. Finally, a first label is rendered at the first location point in the 3D spatial model.

[0338] Memory 166 may include volatile memory, such as random access memory (RAM). Processor 164 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0339] The memory 166 stores executable program code, and the processor 164 executes the executable program code to implement the functions of the aforementioned communication module 151, processing module 152, and storage module 153, thereby realizing the signal localization method. That is, the memory 166 stores instructions for executing the signal localization method.

[0340] The communication interface 168 uses transceiver modules such as, but not limited to, network interface cards and transceivers to enable communication between the signal positioning device 111 and other devices or communication networks.

[0341] The signal localization method disclosed in the above embodiments can be applied to, or implemented by, processor 164. Processor 164 can be an integrated circuit chip with signal processing capabilities.

[0342] In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 164 or by instructions in the form of software. The processor 164 can be a general-purpose processor, including a CPU, a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete vacuum tubes or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of the hardware decoding processor, or the execution can be completed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 166, and the processor 164 reads the information in memory 166 and completes the steps of the above method in combination with its hardware.

[0343] In one possible implementation, the processor 164 can also be used to execute a signal positioning method. For specific implementation, please refer to the embodiments provided by the above-described signal positioning method. The embodiments of this application will not be repeated here.

[0344] In this embodiment of the application, the chip system may be composed of chips or may include chips and other discrete devices.

[0345] The method steps in this embodiment can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a computing device. Of course, the processor and storage medium can also exist as discrete components in a network device or terminal device.

[0346] This application also provides a computer program product containing instructions. The computer program product may be software or program products containing instructions, capable of running on a computing device or stored on any usable medium. When the computer program product runs on at least one computing device, it causes the at least one computing device to perform the aforementioned hard disk fault identification method.

[0347] For example, when a computer program product is run on at least one computing device, it causes the at least one computing device to perform... Figure 8 The signal localization method shown.

[0348] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. This program can be stored in the computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be a terminal of any of the foregoing embodiments, such as an internal storage unit including a data transmission end and / or a data receiving end, like a hard disk or memory of the terminal. The computer-readable storage medium can also be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal. Further, the computer-readable storage medium can include both the internal storage unit and the external storage device of the terminal. The computer-readable storage medium is used to store the computer program and other programs and data required by the terminal. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0349] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. A computer program product includes one or more computer programs or instructions. When a computer program or instruction is loaded and executed on a computer, the processes or functions of the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, a computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video disc (DVD); or it can be a semiconductor medium, such as a solid-state drive (SSD).

[0350] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A signal localization method, characterized in that, The method is applied to a server, which stores a three-dimensional spatial model of the site and a feature library of the site; the feature library of the site includes multiple location points in the site and the visual features of each location point. The method includes: Acquire first signal data and multiple images of the site; the first signal data includes multiple network signal values ​​and the sampling time corresponding to each network signal value; different images in the multiple images correspond to different areas of the site; For the first image data among the plurality of image data, the visual features of the first image are compared with the feature library, and the first network signal value of the first location point in the three-dimensional spatial model is determined based on the first signal data; the first location point is used to indicate the location information of the area captured by the first image data in the three-dimensional spatial model; A first label is rendered at the first location point in the three-dimensional spatial model, and the first label is used to indicate the first network signal value corresponding to the first location point.

2. The method according to claim 1, characterized in that, Rendering the first label at the first location point in the three-dimensional space model includes: Based on the coordinates of the first location point and the shape of the first label, the coordinate data of the first label is determined; the coordinate data of the first label includes the coordinate values ​​of the vertices of the first label in the rendering camera coordinate system; The distance between the first label and the rendering camera is determined based on the coordinate data of the first label; Based on the distance between the first label and the rendering camera, determine the position information of the first label in the three-dimensional space model; The first label is rendered at the first location point in the three-dimensional space model according to the location information.

3. The method according to claim 1 or 2, characterized in that, Before rendering the first label at the first location point in the three-dimensional space model, the method further includes: Based on the coordinates of the first location point, determine the distance between the first label and the rendering camera; If the distance is less than the depth value of the three-dimensional spatial model, the step of rendering the first label at the first location point in the three-dimensional spatial model is performed.

4. The method according to any one of claims 1 to 3, characterized in that, After rendering the first label at the first location point in the three-dimensional space model, the method further includes: After rendering multiple points in the 3D spatial model, the target 3D spatial model is output; the target 3D spatial model is a 3D model with labels displayed at multiple points in the 3D spatial model.

5. The method according to any one of claims 1 to 4, characterized in that, The step of comparing the visual features of the first image with the feature library and determining the first network signal value of the first location point in the three-dimensional spatial model based on the first signal data includes: Based on the feature library and the visual features of the first image data, determine the first location point corresponding to the first image; Based on the sampling time corresponding to each signal value in the first signal and the acquisition time of the first image, a target network signal value whose sampling time matches the acquisition time of the first image is obtained. The target network signal value is used as the first network signal value corresponding to the first location point.

6. The method according to claim 5, characterized in that, The step of determining the first location point corresponding to the first image based on the feature library and the visual features of the first image data includes: Based on the visual features of the first image, the feature library is queried to obtain the first visual feature in the feature library that matches the visual features of the first image; The location point corresponding to the first visual feature is determined as the first location point.

7. The method according to any one of claims 1 to 6, characterized in that, Before acquiring the first signal data and multiple images of the site, the method further includes: Based on the panoramic video data of the site, the three-dimensional map data of the site and the feature library are obtained; The 3D map data is input into the NeRF model of the neural radiation scene, and the NeRF model is trained to obtain the trained NeRF model. The trained NeRF model is then used to generate a rendering map to obtain the 3D spatial model.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: The point cloud data of the site and the second signal data are acquired; the second signal data includes the analog network signal value of each of the multiple location points in the site. For the first point cloud coordinates in the point cloud data, the analog network signal value corresponding to the first point cloud coordinates is determined based on the second signal data; A second label is rendered in the point cloud data for the first point cloud coordinates; the second label is used to indicate the analog network signal value corresponding to the first point cloud coordinates.

9. A signal positioning device, characterized in that, The device is installed on the server, which stores a three-dimensional spatial model of the site and a feature library of the site; the feature library of the site includes multiple location points in the site and the visual features of each location point. The device includes: The communication module is used to acquire first signal data and multiple images of the site; the first signal data includes multiple network signal values ​​and the sampling time corresponding to each network signal value; different images correspond to different areas in the site; The processing module is configured to, for a first image among the plurality of images, compare the visual features of the first image with the feature library, determine the first network signal value of a first location point in the three-dimensional spatial model based on the first signal data, and render a first label at the first location point in the three-dimensional spatial model; Wherein, the first location point is used to indicate the location information of the area captured by the first image in the three-dimensional spatial model; the first label is used to indicate the first network signal value corresponding to the first location point.

10. A signal positioning device, characterized in that, Including processor and memory; The processor is configured to execute instructions stored in the memory to cause the apparatus to perform the method as described in any one of claims 1 to 8.

11. A signal testing system, characterized in that, The system includes: A first terminal is used to provide the signal testing device with first signal data of the site and multiple images; the first signal data includes multiple network signal values ​​and the sampling time corresponding to each network signal value; different images correspond to different areas in the site; The signal positioning device is used to perform the method of any one of claims 1 to 8 based on the first signal data and the plurality of images.

12. A computer program product containing instructions, characterized in that, When the instruction is executed by the signal testing device, the signal testing device performs the method as described in any one of claims 1 to 8.

13. A computer-readable storage medium, characterized in that, It includes computer program instructions, which, when executed by a signal testing device, perform the method as described in any one of claims 1 to 8.

Images