Perception model building methods, devices, equipment, media and program products

Abstract

This application provides a method, apparatus, device, medium, and program product for establishing a perception model, relating to the field of communication technology, and is used to improve the accuracy of establishing perception models in 6G networks. The specific technical solution is as follows: receiving spatial perception data from at least two perception node devices within a physical area; determining at least two first spatial perception data sets matching the first communication scenario from the spatial perception data based on the first communication scenario corresponding to the physical area; wherein each first spatial perception data set is spatial perception data collected in the coordinate system used by the corresponding perception node device; converting the at least two first spatial perception data sets into at least two second spatial perception data sets in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario; and establishing a perception model of the physical area based on the at least two second spatial perception data sets. This application is applied to scenarios involving establishing perception models of physical areas.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a method, apparatus, device, medium and program product for establishing a perception model. Background Technology

[0002] As a new generation of mobile communication technology, 6th generation (6G) communication technology is evolving towards intelligence, sustainability, and ubiquitous connectivity. The 6G system is essentially a complex system integrating cross-domain collaboration, artificial intelligence (AI) enhancement, wireless sensing, and multi-source data; its performance is highly dependent on its ability to build a perception model of the physical world.

[0003] Currently, when establishing a perception model for a region in the physical world, it is mainly based on spatial perception data collected by a single perception node device within that region. Specifically, spatial perception data for that region can be collected by a single perception node device, and environmental features of that region can be extracted from the spatial perception data in the local coordinate system of that perception node device. Based on these environmental features, a corresponding perception model for that region can then be established.

[0004] However, in the aforementioned methods for establishing perception models, the spatial perception data collected by a single perception node device often fails to accurately capture key characteristics such as nonlinear distortion and dynamic channel changes, making it difficult to comprehensively and accurately characterize complex dynamic scenes. This results in poor accuracy of perception models established in 6G networks. Summary of the Invention

[0005] This application provides a method, apparatus, device, medium, and program product for establishing a perception model, which can improve the accuracy of establishing a perception model in a 6G network.

[0006] In a first aspect, embodiments of this application provide a method for establishing a perception model, the method comprising: receiving spatial perception data from at least two perception node devices within a physical area; determining at least two first spatial perception data matching the first communication scenario from the spatial perception data based on a first communication scenario corresponding to the physical area; wherein each first spatial perception data is spatial perception data collected in the coordinate system used by the corresponding perception node device; converting the at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario; and establishing a perception model of the physical area based on the at least two second spatial perception data.

[0007] The technical solution provided in this application offers at least the following benefits: In a 6G network, for a given communication scenario corresponding to a physical area, spatial sensing data collected by multiple sensing node devices in different coordinate systems can be converted into spatial sensing data in the same coordinate system. Then, based on the converted spatial sensing data, a sensing model of the physical area can be established. Therefore, when establishing a sensing model in a 6G network, key characteristics such as nonlinear distortion and dynamic channel changes can be accurately captured using coordinate-aligned multi-source spatial sensing data, enabling a comprehensive and accurate depiction of complex dynamic scenarios. This improves the accuracy of establishing sensing models in a 6G network.

[0008] One possible implementation is that the aforementioned at least two first spatial perception data include: first target spatial perception data collected in a first coordinate system and second target spatial perception data collected in a second coordinate system; the conversion of the at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario includes: determining the center position of the aforementioned physical region as a unified coordinate origin according to the modeling accuracy corresponding to the first communication scenario; performing offset processing on the first target spatial perception data according to the unified coordinate origin and the coordinate origin of the first coordinate system to obtain third target spatial perception data; performing offset processing on the second target spatial perception data according to the unified coordinate origin and the coordinate origin of the second coordinate system to obtain fourth target spatial perception data; converting the fourth target spatial perception data into fifth target spatial perception data in the first coordinate system according to the top diagonal coordinate values ​​in the third target spatial perception data and the top diagonal coordinate values ​​in the fourth target spatial perception data; and determining the third target spatial perception data and the fifth target spatial perception data as the aforementioned at least two second spatial perception data.

[0009] Another possible implementation, which establishes a physical region perception model based on at least two second spatial perception data, includes: determining a physical region range corresponding to each of the at least two second spatial perception data, thereby obtaining at least two physical region ranges; and performing spatial overlay processing and azimuth correction processing on the at least two second spatial perception data in descending order of the size of the at least two physical region ranges, thereby obtaining the perception model.

[0010] Another possible implementation is that, before determining at least two first spatial sensing data matching the first communication scenario from the spatial sensing data based on the first communication scenario corresponding to the physical area, the above-mentioned perception model establishment method further includes: acquiring communication service information within the physical area, spatial feature information of the physical area, and spatiotemporal behavioral feature information of the sensing object within the physical area; and determining the first communication scenario based on the communication service information, the spatial feature information, and the spatiotemporal behavioral feature information.

[0011] In another possible implementation, before converting at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario, the above perception model establishment method further includes: determining a first modeling accuracy associated with the first communication scenario from the at least one modeling accuracy according to the correlation between at least one communication scenario and at least one modeling accuracy; wherein, the at least one communication scenario includes the first communication scenario; and determining the first modeling accuracy as the modeling accuracy corresponding to the first communication scenario.

[0012] Secondly, embodiments of this application provide a perception model building apparatus, comprising: a receiving module, a determining module, a conversion module, and a building module; the receiving module is configured to receive spatial perception data from at least two perception node devices within a physical area; the determining module is configured to determine at least two first spatial perception data matching the first communication scenario from the spatial perception data based on the first communication scenario corresponding to the physical area; wherein each first spatial perception data is spatial perception data collected in the coordinate system used by the corresponding perception node device; the conversion module is configured to convert the at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario; and the building module is configured to build a perception model of the physical area based on the at least two second spatial perception data.

[0013] One possible implementation is that the aforementioned at least two first spatial perception data include: first target spatial perception data collected in a first coordinate system and second target spatial perception data collected in a second coordinate system; the aforementioned conversion module is specifically used to determine the center position of the aforementioned physical region as a unified coordinate origin according to the modeling accuracy corresponding to the first communication scenario; and to perform offset processing on the first target spatial perception data according to the unified coordinate origin and the coordinate origin of the first coordinate system to obtain third target spatial perception data; and to perform offset processing on the second target spatial perception data according to the unified coordinate origin and the coordinate origin of the second coordinate system to obtain fourth target spatial perception data; and to convert the fourth target spatial perception data into fifth target spatial perception data in the first coordinate system according to the top diagonal coordinate values ​​in the third target spatial perception data and the top diagonal coordinate values ​​in the fourth target spatial perception data; and to determine the third target spatial perception data and the fifth target spatial perception data as the aforementioned at least two second spatial perception data.

[0014] Another possible implementation is that the aforementioned establishment module is specifically used to determine a physical region range corresponding to each of the at least two second spatial sensing data, thereby obtaining at least two physical region ranges; and to perform spatial overlay processing and azimuth correction processing on the at least two second spatial sensing data in descending order of the size of the at least two physical region ranges, thereby obtaining the aforementioned sensing model.

[0015] In another possible implementation, the aforementioned perception model establishment device further includes an acquisition module; the acquisition module is used to acquire communication service information within the aforementioned physical area, spatial feature information of the physical area, and spatiotemporal behavioral feature information of the perceived object within the physical area before the aforementioned determination module determines at least two first spatial perception data matching the first communication scenario from the spatial perception data based on the first communication scenario corresponding to the physical area; the aforementioned determination module is further used to determine the first communication scenario based on the communication service information, the spatial feature information, and the spatiotemporal behavioral feature information.

[0016] In another possible implementation, the determining module is further configured to, before the conversion module converts at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario, determine a first modeling accuracy associated with the first communication scenario from the at least one modeling accuracy according to the association relationship between the at least one communication scenario and the at least one modeling accuracy; wherein the at least one communication scenario includes the first communication scenario; and determine the first modeling accuracy as the modeling accuracy corresponding to the first communication scenario.

[0017] Thirdly, this application provides an electronic device comprising: a processor and a memory; the memory stores a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the method of the first aspect described above.

[0018] Fourthly, this application provides a readable storage medium on which a program or instructions are stored, which, when executed by a computer, implement the method of the first aspect described above.

[0019] Fifthly, this application provides a computer program product stored in a storage medium, which, when executed by a computer, implements the method described in the first aspect.

[0020] In a sixth aspect, embodiments of this application provide a chip including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method described in the first aspect.

[0021] The beneficial effects of the second to sixth aspects mentioned above are described in the corresponding description of the first aspect and will not be repeated here. Attached Figure Description

[0022] Figure 1 A schematic diagram of the network architecture for an application of a perception model building method provided in this application embodiment;

[0023] Figure 2 A flowchart illustrating a method for establishing a perception model provided in an embodiment of this application;

[0024] Figure 3 A flowchart illustrating another method for establishing a perception model provided in an embodiment of this application;

[0025] Figure 4 A flowchart illustrating another method for establishing a perception model provided in this application embodiment;

[0026] Figure 5 A flowchart illustrating another method for establishing a perception model provided in an embodiment of this application;

[0027] Figure 6 A flowchart illustrating another method for establishing a perception model provided in an embodiment of this application;

[0028] Figure 7 A flowchart illustrating the implementation process of a perception model establishment method provided in this application embodiment;

[0029] Figure 8 This is a schematic diagram illustrating a method for determining a unified coordinate origin in a perception model establishment method provided in an embodiment of this application;

[0030] Figure 9 This is a schematic diagram of the structure of a perception model building device provided in an embodiment of this application;

[0031] Figure 10 A schematic diagram of another perception model building device provided in this application embodiment;

[0032] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0033] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0034] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0035] The terms "at least one," "at least one of," etc., used in the specification and claims of this application refer to any one, any two, or a combination of two or more of the included items. For example, at least one of a, b, and c can mean: "a," "b," "c," "a and b," "a and c," "b and c," and "a, b, and c," where a, b, and c can be single or multiple. Similarly, "at least two" refers to two or more items, and its meaning is similar to that of "at least one."

[0036] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0037] The following explains some concepts and terms involved in the perception model establishment method, apparatus, device, medium and program products provided in the embodiments of this application.

[0038] I. Communication Sensing: This usually refers to Integrated Sensing and Communication (ISAC), also known as "Sensing Integration". It is one of the core technology directions in the 6G and 5G-Advanced stages. The core idea is to enable a single set of hardware and a single spectrum to simultaneously realize the two major functions of "wireless communication" and "wireless sensing", breaking the traditional situation of independent design and resource isolation between the two.

[0039] II. Spatial Sensing Data: In the context of ISAC and ubiquitous sensing, spatial sensing data refers to structured data containing information about the location, shape, motion, and attributes of a target or environment in a spatial dimension. It is the direct result or intermediate product output by sensing node devices (such as integrated sensing base stations, radar sensors, etc.) after processing radio echoes, optical signals, or other physical field signals. Spatial sensing data typically contains information from the following key layers:

[0040] Geometric and positional information: target range, azimuth, elevation, and the resulting three-dimensional coordinates (X, Y, Z) or geographic coordinates (latitude, longitude, and altitude).

[0041] Motion status information: radial velocity (Velocity / Doppler), acceleration, motion trajectory, etc.;

[0042] Attributes and features: the target's scattering cross-section, size, shape profile (point cloud data), micro-Doppler features (used to identify pedestrians, vehicle types, etc.), and even material and pose derived through high-order algorithms;

[0043] Environmental semantic information: a structured description of the static environment, such as indoor maps, obstacle distribution, channel environment characteristics (multipath parameters), etc.

[0044] The present application provides a method, apparatus, device, medium, and program product for establishing a perception model, which can be applied to scenarios where a perception model of a physical area is established.

[0045] 6G is the next generation of mobile communication technology, evolving towards "intelligent, sustainable, and ubiquitous connectivity." Key technologies such as Asia Pacific Hertz Communication, AI-native architecture, and ISAC are becoming core supports. Sensing is a potential characteristic technology of 6G networks, and high-precision sensing is crucial for building future immersive communication and digital twin applications. However, the complexity of 6G systems (such as high-frequency propagation characteristics, multi-technology integration, and cross-domain collaboration) far exceeds that of 5G systems. Conventional modeling methods can no longer accurately capture key characteristics such as nonlinear distortion and dynamic channel changes. The foundation for this lies in accurately modeling dynamic intervention methods specific to 6G mobile scenarios.

[0046] Furthermore, 6G digital twins are not simply "virtual modeling," but rather a complex system involving cross-domain collaboration, artificial intelligence enhancement, hardware closed-loop, wireless sensing, and multi-source data. Among these, high-fidelity dynamic modeling is the foundation and prerequisite for the entire 6G network digital twin and simulation.

[0047] In mobile network sensing, multi-mode, multi-source data from multiple stations has not yet been introduced on a large scale; currently, the focus is mainly on single-station sensing and environment reconstruction. Specifically, spatial sensing data of a region can be collected by a single sensing node device within that region, and environmental features of the region can be extracted from this spatial sensing data in the local coordinate system of that sensing node device. Based on these environmental features, a corresponding sensing model for that region can be established.

[0048] Currently, communication sensing and fusion involving multiple stations in 6G are still in their early stages. In a multi-station joint sensing environment, the issues and methods for integrated sensing, localization, and environmental reproduction have not yet been considered. Achieving accurate location matching based on this multimodal data is the primary challenge in modeling. This requires more precise dynamic and real-time modeling, matching, and alignment of multiple data sources. Real-time dynamic environment modeling needs to address multiple issues, including accuracy, a unified coordinate system and origin, multiple coordinate systems, alignment of directions, and algorithms to improve positional accuracy. Ultimately, this ensures accurate and scientific prediction and network service provision in a dynamic 6G sensing environment.

[0049] Therefore, to address the aforementioned technical problems, this application provides a method, apparatus, device, medium, and program product for establishing a perception model. The perception model establishment method provided in this application can be applied to 6G full-domain intelligent network environments, particularly in scenarios requiring high-precision, high-real-time environmental perception and network self-optimization. By introducing multi-base station (or multi-node) joint perception and fusing multimodal data such as radar, vision, and wireless signals, it solves the spatial and temporal alignment problem of heterogeneous data sources, constructing a dynamic and accurate digital twin world. This scenario covers everything from microscopic indoor human-computer interaction to macroscopic wide-area traffic management. The core is to utilize 6G's ISAC capabilities, enabling the network not only to transmit data but also to accurately "understand" the physical world like a sensory organ, and dynamically adjust network resources accordingly to support immersive communication and various vertical industry applications.

[0050] For example, specific application scenarios are as follows:

[0051] 1. Immersive Extended Reality and Holographic Communication: In the metaverse or holographic conferences of the future, users will need extremely low latency and high-precision spatial positioning to ensure the perfect overlay of virtual objects with the real environment.

[0052] 2. Low-altitude economy and drone swarm control: For low-altitude scenarios such as drone delivery and urban air traffic, it is necessary to achieve all-weather, high-precision monitoring and obstacle avoidance of a large number of drones in complex urban canyon environments.

[0053] 3. Intelligent driving and vehicle-road cooperation: Level 4 / Level 5 autonomous vehicles not only need to know where they are, but also need to know the surrounding environment (including the intentions of pedestrians, non-motorized vehicles and other vehicles).

[0054] 4. Industrial Digital Twins and Flexible Manufacturing: In Industry 4.0 / 5.0 factories, Automated Guided Vehicles (AGVs), robotic arms, and human workers work collaboratively in the same space, requiring extremely high positioning accuracy and collision avoidance mechanisms.

[0055] 5. Public safety and emergency response in smart cities: Non-contact monitoring of population density, movement patterns and vital signs is required at disaster sites such as fires and earthquakes, or during large gatherings.

[0056] 6. High-precision indoor positioning and asset tracking: In large warehouses, museums or hospital operating rooms, it is necessary to locate specific items (such as medical consumables and valuable equipment) in real time with sub-meter or even centimeter accuracy.

[0057] It should be noted that the scenarios listed above are merely illustrative of the applicable scenarios for the perception model establishment method provided in this application embodiment. In actual implementation, the perception model establishment method provided in this application embodiment can also be applied to any scenario that requires the establishment of a perception model of the physical world, and this application embodiment does not impose any limitations.

[0058] The perception model establishment method provided in this application allows for the conversion of spatial perception data collected by multiple sensing node devices in different coordinate systems into spatial perception data in the same coordinate system for a given communication scenario within a physical area in a 6G network. Based on this converted spatial perception data, a perception model for the physical area is then established. This enables the accurate capture of key characteristics such as nonlinear distortion and dynamic channel changes using coordinate-aligned multi-source spatial perception data when establishing a perception model in a 6G network, thus comprehensively and accurately depicting complex dynamic scenarios. This improves the accuracy of perception model establishment in 6G networks.

[0059] It should be noted that the perception model establishment method provided in the application embodiments is not only applicable to the establishment of perception models in 6G networks, but also applicable to the establishment of perception models in future 7th Generation (7G) networks and other next-generation networks. This application embodiment does not limit the application.

[0060] The following description, in conjunction with the accompanying drawings, details the perception model establishment method, apparatus, device, medium, and program products provided in the embodiments of this application.

[0061] Figure 1 This illustration shows a network architecture for an application of a perception model building method provided in an embodiment of this application. For example... Figure 1 As shown, the network architecture includes a perception model establishment device 101 and a terminal device 102. The perception model establishment device 101 and the terminal device 102 are interconnected.

[0062] In some embodiments, the perception model building device 101 may be a server, a computer, or a processor or processing unit within a server or computer. The server may be a single server or a server cluster consisting of multiple servers. It should be noted that the embodiments of this application do not limit the specific device form of the perception model building device 101. Figure 1 The perception model building device 101 is shown as a single server as an example.

[0063] In some embodiments, the terminal device may be a mobile phone, tablet computer, laptop computer, handheld computer, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, personal computer (PC), ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., and the embodiments of this application do not specifically limit it. Figure 1 The example shown is a mobile phone, with terminal device 102 as an example.

[0064] In some embodiments, the perception model building device 101 can receive spatial perception data from at least two perception node devices within a physical area; and based on a first communication scenario corresponding to the physical area, determine at least two first spatial perception data matching the first communication scenario from the spatial perception data; wherein each first spatial perception data is spatial perception data collected in the coordinate system used by the corresponding perception node device; and based on the modeling accuracy corresponding to the first communication scenario, convert the at least two first spatial perception data into at least two second spatial perception data in the same coordinate system; and based on the at least two second spatial perception data, build a perception model of the physical area. Then, the perception model building device 101 can send the perception model to the terminal device 102, so that the terminal device 102 can construct key applications for future immersive communication and digital twins based on high-precision perception.

[0065] It should be noted that the network architecture described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As network architectures evolve, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0066] See Figure 2This is a flowchart illustrating a method for establishing a perception model provided in an embodiment of this application. Figure 2 As shown, the perception model establishment method provided in this application embodiment can be implemented by the above-mentioned perception model establishment device, specifically including the following steps 201 to 204.

[0067] Step 201: The perception model establishment device receives spatial perception data from at least two perception node devices within the physical area.

[0068] In some embodiments, the aforementioned physical region refers to a region in the real world.

[0069] In some embodiments, the physical area can be any physical area such as an urban area, residential community, industrial park, factory workshop or scenic area.

[0070] In some embodiments, the aforementioned sensing node device may include, but is not limited to, at least one of a sensing base station and a sensing terminal.

[0071] For example, the aforementioned at least two sensing node devices can both be sensing base stations; or the aforementioned at least two sensing node devices can both be sensing terminals; or the aforementioned at least two sensing node devices can include at least one sensing base station and at least one sensing terminal.

[0072] In some embodiments, each of the at least two sensing node devices described above can collect spatial sensing data and send the collected spatial sensing data to the sensing model building device.

[0073] In some embodiments, the aforementioned spatial sensing data is structured data containing information on the location, shape, motion, and attributes of a target or environment in a spatial dimension. Spatial sensing data is the direct result or intermediate product output by a sensing node device after processing radio echoes, optical signals, or other physical field signals.

[0074] In some embodiments, the aforementioned spatial perception data may include, but is not limited to, at least one of the following: synesthetic data, point cloud data, oblique photogrammetry data, vector modeling data, three-dimensional geographic information system (3D GIS) data, etc.

[0075] It should be noted that point cloud data refers to a set of discrete points in three-dimensional space acquired through sensing devices such as LiDAR and depth cameras. It includes the three-dimensional coordinates (X, Y, Z) of each point, as well as possible information such as color and intensity. It is direct spatial geometric sensing data, commonly used for the 3D reconstruction of terrain, buildings, and objects. Oblique photogrammetry data refers to image data acquired through multi-angle (oblique and vertical) photogrammetry techniques. After processing, it can generate 3D models (such as realistic 3D models) and digital surface models. It belongs to vision-based spatial sensing data and can reflect the texture and 3D structure of ground features. Vector modeling data refers to 3D models (such as building vector models and road vector models) built based on vector data (points, lines, and surfaces). It is usually a structured abstraction of real-world features or scenes, containing spatial location and attribute information. It belongs to manually modeled or semi-automatically generated spatial sensing data. 3D GIS is a platform or system for managing, storing, analyzing, and processing 3D spatial data. Its data sources can include point clouds, oblique photogrammetry models, and vector models. It is itself a spatial data organization and application framework, but its core is the processing of 3D spatial sensing data.

[0076] In some embodiments, different types of spatial sensing data may correspond to different coordinate systems.

[0077] For example, synesthetic data corresponds to the Universal Transverse Mercator (UTM) projection coordinate system, while 3D GIS data corresponds to the Geographic Coordinate System (GCS).

[0078] It should be noted that the UTM projected coordinate system is a plane rectangular coordinate system based on the transverse Mercator projection. It divides the Earth's surface into 6° longitude zones (60 zones in total), projecting the ellipsoid onto a plane within each zone, and representing positions using east (X) and north (Y) distances in meters. It has advantages such as minimal deformation within zones and ease of planar geometric calculations of distance / area, and is commonly used in regional / city surveying, engineering planning, and local spatial analysis. However, it is discontinuous between zones. GCS, such as the World Geodetic System 1984 (WGS84), is a spherical / ellipsoidal coordinate system that represents positions in angular units (longitude and latitude). Based on a specific ellipsoid (such as the WGS84 ellipsoid) and a geodetic datum, it is globally continuous. It is suitable for global positioning (such as the Global Positioning System), cross-regional geographic data stitching, and 3D GIS global frameworks. However, the ground distance corresponding to the same longitude and latitude difference varies with latitude, making direct planar geometric calculations inconvenient.

[0079] Step 202: The perception model establishment device determines at least two first spatial perception data that match the first communication scenario from the spatial perception data, based on the first communication scenario corresponding to the physical area.

[0080] Among them, each of the above at least two first spatial perception data is spatial perception data collected in the coordinate system used by the corresponding perception node device.

[0081] In some embodiments, the perception model building device may first define multiple communication scenarios, and then determine a first communication scenario from the multiple communication scenarios based on network communication services and technical requirements within the physical area.

[0082] The specific method for determining the first communication scenario using the perception model building device will be described in detail in the following embodiments, and will not be repeated here to avoid repetition.

[0083] In some embodiments, the above-mentioned multiple communication scenarios may include micro-scenes, deep scenes, and wide scenes.

[0084] For example, taking the above-mentioned communication scenarios as examples in a 6G network, the specific definitions of these communication scenarios are shown in Table 1 below:

[0085] Table 1

[0086]

[0087] As can be seen, the communication scenarios defined in Table 1 above include micro-scenarios, deep-scenarios, and wide-scenarios. The perception model building device can determine the micro-scenario, deep-scenario, or wide-scenario as the first communication scenario based on the network communication services and technical requirements within the aforementioned physical area.

[0088] In some embodiments, different communication scenarios are applicable to or matched with different types of spatial sensing data. After receiving spatial sensing data from at least two sensing node devices, the sensing model building device can first determine a first communication scenario, and then determine at least two first spatial sensing data that match the first communication scenario from the spatial sensing data.

[0089] For example, if the first communication scenario is the aforementioned micro-scenario, then the aforementioned at least two first spatial perception data may include synesthetic data, point cloud data, vector modeling data, and 3D GIS data; if the first communication scenario is the aforementioned deep scenario, then the aforementioned at least two first spatial perception data may include synesthetic data, point cloud data, oblique photogrammetry data, vector modeling data, and 3D GIS data; if the first communication scenario is the aforementioned wide scenario, then the aforementioned at least two first spatial perception data may include oblique photogrammetry data and 3D GIS data.

[0090] It should be noted that the above example is only one possible example and is not limited in actual implementation.

[0091] For example, assuming that the above-mentioned at least two first spatial sensing data include spatial sensing data A and spatial sensing data B, then spatial sensing data A can be spatial sensing data collected in the UTM projection coordinate system used by sensing node device a, and spatial sensing data B can be spatial sensing data collected in the WGS84 system used by sensing node device b.

[0092] In some embodiments, the coordinate systems used by any two of the at least two sensing node devices may be the same or different; that is, any two of the at least two first spatial sensing data may correspond to the same or different coordinate systems.

[0093] In some embodiments, the above-mentioned at least two first spatial sensing data can be multi-source sensing data. For different source environment scenarios, the different source data in the multi-source sensing data are mostly in the following ways:

[0094] Typically, to determine the extent of a twin region for network simulation, the top diagonal coordinates are removed, such as: (x o1u ,y o1u ,x o2u ,y o2u (; Longitude zone), where the format is the projected coordinates after WGS conversion, in meters, and the corresponding WGS84 latitude and longitude range is (x o1w ,y o1w ,x o2w ,y o2w The precision must be at least 6 decimal places. The initial positions of different source data are shown in Table 2 below.

[0095] Table 2

[0096]

[0097] The longitude zone is the UTM zone data for the location, such as 49N for a typical area. X and Y are the coordinates in WGS84 latitude and longitude or UTM projected coordinate system (in meters). If it is WGS84 latitude and longitude, the longitude zone is not specified. Z is the height above the ground at the location (x, y), in meters.

[0098] It can be seen that different coordinate systems bring significant problems to the unified fusion of data. For example, 6G sensing calculations often use the sector locations of 6G base stations as base points, and joint sensing or positioning based on different base stations will lead to complex issues. It should be noted that the data points in Table 2 above do not yet establish a relationship with the 6G coverage area. Also note that data from different data sources, such as point cloud data or sensing data, are mostly in file format, and their location information may not be the same.

[0099] In addition, each type of source data contains multiple individual data points, the location information of which is shown in Table 3 below:

[0100] Table 3

[0101]

[0102] Table 3 above shows the typical data formats for this type of dataset, namely surfaces, lines, and points. Environmental data such as 6G sensing that exist in different categories of data usually belong to one of these categories.

[0103] Step 203: The perception model building device converts at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario.

[0104] In some embodiments, the modeling accuracy can be at the millimeter, meter, 20-meter, or 50-meter level, etc.

[0105] In some embodiments, the perception model building device may first define the modeling precision corresponding to different communication scenarios, and then determine the modeling precision corresponding to the first communication scenario from the defined modeling precision based on the first communication scenario.

[0106] The specific method for determining the modeling accuracy of the first communication scenario using the perception model building device will be described in detail in the following embodiments. To avoid repetition, it will not be repeated here.

[0107] In some embodiments, the aforementioned same coordinate system may be the coordinate system corresponding to any one of the at least two first spatial sensing data, or any coordinate system other than the coordinate system corresponding to the at least two first spatial sensing data; the specific coordinate system may be determined according to actual usage requirements, and this application embodiment does not limit it.

[0108] For example, the same coordinate system mentioned above could be a UTM projected coordinate system or WGS84, etc.

[0109] In some embodiments, the aforementioned at least two first spatial perception data include: first target spatial perception data acquired in a first coordinate system and second target spatial perception data acquired in a second coordinate system. For example, in combination with... Figure 2 ,like Figure 3As shown, step 203 above can be implemented through steps 203a to 203d.

[0110] Step 203a: The perception model building device determines the center position of the physical area as the unified coordinate origin according to the modeling accuracy corresponding to the first communication scenario.

[0111] In some embodiments, to ensure the uniform overlay of different source data, the unified coordinate origin is the center of the physical region, and the altitude of the region center is used as the center of the altitude origin.

[0112] Step 203b: The perception model establishment device performs offset processing on the first target space perception data according to the unified coordinate origin and the coordinate origin of the first coordinate system to obtain the third target space perception data; and performs offset processing on the second target space perception data according to the unified coordinate origin and the coordinate origin of the second coordinate system to obtain the fourth target space perception data.

[0113] In some embodiments, the first coordinate system is different from the second coordinate system.

[0114] In some embodiments, the perception model building device can perform offset processing on the first target space perception data according to the offset value between the unified coordinate origin and the coordinate origin of the first coordinate system to obtain the third target space perception data; and perform offset processing on the second target space perception data according to the offset value between the unified coordinate origin and the coordinate origin of the second coordinate system to obtain the fourth target space perception data.

[0115] In some embodiments, steps 203a and 203b described above can address the outward expansion of the scene and ensure the unified loading of relevant spatial perception data. Furthermore, for auxiliary coordinate origin positioning, the orientation is set to 0 degrees directly above, increasing clockwise to reach 360 degrees. Based on this requirement and the data preparation status, unified orientation data can be organized as shown in Table 4 below:

[0116] Table 4

[0117]

[0118] Step 203c: The perception model establishment device converts the fourth target space perception data into the fifth target space perception data in the first coordinate system based on the top diagonal coordinate values ​​in the third target space perception data and the top diagonal coordinate values ​​in the fourth target space perception data.

[0119] In some embodiments, the perception model building device may first select a first coordinate system from a first coordinate system and a second coordinate system based on a first communication scenario, and then convert the target space perception data in the second coordinate system into target space perception data in the first coordinate system.

[0120] In some embodiments, the accuracy of spatial perception data in the first coordinate system is maximized in the first communication scenario.

[0121] For example, from the perspective of 6G network planning and twin applications, the selection rules for the first coordinate system are as follows:

[0122] A. If the first communication scenario is the aforementioned micro-scenario, then in order to improve the accuracy of 6G network planning and application, the Cartesian coordinate system will be used as the main coordinate format.

[0123] B. If the first communication scenario is the aforementioned deep or wide scenario, then WGS84+projected coordinates UTM and WGS84 will be the primary methods. WGS84 is the conventional latitude and longitude method, and its accuracy will be somewhat reduced during calculation. UTM, based on WGS data projection coordinates, ensures a certain level of accuracy within a certain range. The conversion between UTM and WGS84 to a general method will not be elaborated here.

[0124] For example, taking the first coordinate system as the UTM rectangular coordinate system and the second coordinate system as WGS84, the perception model building device can transform the data in Tables 2 and 3 above. The specific process is as follows:

[0125] To achieve data unification and overlay from different data sources, ultimately forming a real-time, dynamic 6G environment, the basic coordinate origin O(x0, y0, z0) of the aforementioned physical region is first determined, as follows:

[0126] ; .

[0127] Simultaneously calculate the optimized fast algorithm for WGS84 to UTM conversion within the above physical region:

[0128] Let the points to be converted be (xw, yw) in WGS84 format and (xu, yu) in UTM format, then:

[0129] ; .

[0130] Using the above conversion method, WGS84 latitude and longitude formats in different files can be quickly converted to a unified UTM rectangular coordinate system, achieving a more accurate conversion to UTM format.

[0131] Secondly, using the origin as the reference coordinate system, organize and calculate the position data in Table 2 above. If it is WGS84 latitude and longitude data, calculate it quickly using the method described above. This ensures that the position data in Table 2 are all UTM coordinate data. Let its UTM position data be O1(x t0 y t0， z t0 The converted data is (x t1 y t1， z t1 The calculation is as follows:

[0132] ; ; .

[0133] For the individual data in Table 3 above, its position relative to O1 is (x n0 y n0， z n0 Then the unified location data is:

[0134] ; ; .

[0135] Thus, by calculating all the data in Tables 2 and 3 according to the above algorithm, we can obtain the unified position data of the superimposed data in the entire three-dimensional space of the above physical region.

[0136] It is understandable that, through the above method, the perception model building device can convert the spatial perception data of the fourth target into the spatial perception data of the fifth target in the first coordinate system.

[0137] Step 203d: The perception model establishment device determines the third target space perception data and the fifth target space perception data as at least two second space perception data.

[0138] In some embodiments, the third target space perception data and the fifth target space perception data are target space perception data in the same coordinate system.

[0139] Thus, the perception model building device can first use the center position of the aforementioned physical region as a unified coordinate origin to perform offset processing on the first target spatial perception data and the second target spatial perception data to align the coordinate system origins of the different target spatial perception data. Then, using their respective top-diagonal coordinate values, coordinate transformation is performed on the offset second target spatial perception data, thereby converting at least two sets of second spatial perception data into spatial perception data in the first coordinate system. This avoids errors in coordinate transformation, improves the accuracy of coordinate transformation, and thus improves the precision of the established perception model.

[0140] Step 204: The perception model establishment device establishes a perception model of the physical region based on at least two second spatial perception data.

[0141] In some embodiments, combined with Figure 2 ,like Figure 4 As shown, step 204 above can be implemented through steps 204a and 204b.

[0142] Step 204a: The perception model establishment device determines a physical region range corresponding to each second spatial perception data based on at least two second spatial perception data, thereby obtaining at least two physical region ranges.

[0143] In some embodiments, each of the above-mentioned at least two physical region ranges is one of the physical region ranges.

[0144] In some embodiments, any two of the above-mentioned at least two physical region ranges may or may not overlap.

[0145] Step 204b: The sensing model building device performs spatial overlay processing and azimuth angle correction processing on at least two second spatial sensing data in descending order of the size of at least two physical regions to obtain a sensing model.

[0146] In some embodiments, the sizes of the at least two physical region ranges are ordered from largest to smallest, i.e., in descending order of size.

[0147] In some embodiments, the perception model building apparatus may first perform spatial superposition processing on at least two second spatial perception data, and then perform azimuth correction processing to obtain the above-mentioned perception model.

[0148] For example, the perception model building device can superimpose the above-mentioned at least two second spatial perception data in descending order of their corresponding physical region ranges, paying attention to the superposition and adjustment at the Z-height. Secondly, the different source data are uniformly adjusted according to their azimuth angles to ensure that the position, azimuth, and attitude are consistent with the actual communication scenario.

[0149] Thus, the perception model building device can perform spatial overlay processing and azimuth angle correction processing on the above-mentioned at least two second spatial perception data in descending order of the size of the above-mentioned at least two physical region ranges to obtain the above-mentioned perception model. In this way, when building the perception model, spatial perception data corresponding to multiple physical region ranges can be overlaid, and the accuracy of building the perception model can be effectively improved by azimuth angle correction.

[0150] The perception model establishment method provided in this application, within a 6G network, for a given communication scenario corresponding to a physical area, can convert spatial perception data collected by multiple perception node devices in different coordinate systems into spatial perception data in the same coordinate system. Then, based on the converted spatial perception data, a perception model for that physical area is established. Therefore, when establishing a perception model in a 6G network, key characteristics such as nonlinear distortion and dynamic channel changes can be accurately captured using coordinate-aligned multi-source spatial perception data, comprehensively and accurately depicting complex dynamic scenarios. This improves the accuracy of establishing perception models in 6G networks.

[0151] In some embodiments, combined with Figure 2 ,like Figure 5 As shown, before step 202 and after step 201, the perception model establishment method provided in this application embodiment may further include the following steps 205 and 206.

[0152] It should be noted that, Figure 5 The example shown is that steps 205 and 206 are executed before step 202 and after step 201. In actual implementation, steps 205 and 206 can also be executed before step 201 or simultaneously with step 201. This application does not limit the implementation.

[0153] Step 205: The perception model building device acquires communication service information, spatial feature information of the physical area, and spatiotemporal behavioral feature information of the perceived objects within the physical area.

[0154] In some embodiments, the aforementioned communication service information may include the types of services provided within the aforementioned physical area, the volume of services carried, and specific service configuration information. This mainly includes, but is not limited to, at least one of the following: basic voice and traditional services, data and internet access services, multimedia and video services, mobile and wireless communication services, value-added and intelligent network services, regional traffic volume statistics, and service configuration and subscription information.

[0155] In some embodiments, the aforementioned spatial feature information is used to define the geographical location, geometric shape, spatial relationships, and environmental attributes of the aforementioned physical area. Specifically, this includes, but is not limited to, at least one of the following: geographical location and coordinate information, geometric shape and coverage, spatial relationships and topological information, site and environmental features, and scale and accuracy information.

[0156] In some embodiments, the sensing objects may include, but are not limited to, at least one of the following: the person being monitored, the terminal, the vehicle, the device, the sensor node, or the mobile site.

[0157] In some embodiments, the spatiotemporal behavioral feature information of the perceived object described above is used to describe a set of features that indicate when the perceived object is in what spatial location, what behavior it has performed / what state change has occurred. This generally includes, but is not limited to, at least one of the following: temporal features, spatial features, behavioral / state features, spatiotemporal joint features, and statistical and abstract features.

[0158] Step 206: The perception model establishment device determines the first communication scenario based on communication service information, spatial feature information, and spatiotemporal behavioral feature information.

[0159] In some embodiments, the perception model building device may determine a matching first communication scenario from a plurality of defined communication scenarios based on the aforementioned communication service information, spatial feature information, and spatiotemporal behavioral feature information, and in conjunction with Table 1 above.

[0160] Thus, the perception model building device can determine the first communication scenario based on the aforementioned communication service information, spatial feature information, and spatiotemporal behavioral feature information. It can then combine the feature information of the aforementioned physical area in multiple dimensions to determine the communication scenario corresponding to that physical area, thereby improving the accuracy of determining the communication scenario.

[0161] In some embodiments, combined with Figure 2 ,like Figure 6 As shown, before step 203 and after step 202, the perception model establishment method provided in this application embodiment may further include the following steps 207 and 208.

[0162] It should be noted that, Figure 6 The example shown is only illustrative, with steps 207 and 208 performed before step 203 and after step 202. In actual implementation, steps 207 and 208 can also be performed before step 202 and after step 201, or simultaneously with step 202; they can also be performed before step 201, or simultaneously with step 201, etc. The embodiments of this application are not limited.

[0163] Step 207: The perception model building device determines the first modeling accuracy associated with the first communication scenario from the at least one modeling accuracy based on the correlation between at least one communication scenario and at least one modeling accuracy.

[0164] Among them, at least one of the above communication scenarios includes the first communication scenario.

[0165] In some embodiments, the perception model building apparatus may predefine the correlation between at least one communication scenario and at least one modeling accuracy.

[0166] For example, the perception model building device can determine the modeling accuracy of the communication scenarios identified in Table 1 above, combined with the requirements of network planning simulation twins in different 6G environmental scenarios. The correlation between communication scenarios and modeling accuracy is shown in Table 5 below:

[0167] Table 5

[0168]

[0169] For the aforementioned wide-area scenarios, considering 6G coverage in mountainous and rural areas, a range of 50 meters is considered for low-level coverage, while other scenarios require a range of 20 meters or more.

[0170] In some embodiments, after determining the first communication scenario, the perception model building device can determine the first modeling accuracy associated with the first communication scenario based on the above-mentioned correlation.

[0171] For example, as shown in Table 5 above, if the first communication scenario is a micro-scenario, the first modeling accuracy is at the millimeter level; if the first communication scenario is a deep scenario, the first modeling accuracy is at the meter level; if the first communication scenario is a wide scenario, the first modeling accuracy is at the 20-meter / 50-meter level.

[0172] Step 208: The perception model building device determines the first modeling accuracy as the modeling accuracy corresponding to the first communication scenario.

[0173] In some embodiments, after determining the first modeling accuracy, the perception model building apparatus may use the first modeling accuracy as the modeling accuracy corresponding to the first communication scenario for subsequent perception model building.

[0174] For example, if the first modeling accuracy determined by the perception model building device is at the millimeter level, the perception model building device can determine the millimeter level as the modeling accuracy corresponding to the first communication scenario; if the first modeling accuracy determined by the perception model building device is at the meter level, the perception model building device can determine the meter level as the modeling accuracy corresponding to the first communication scenario; if the first modeling accuracy determined by the perception model building device is at the 20-meter / 50-meter level, the perception model building device can determine the 20-meter / 50-meter level as the modeling accuracy corresponding to the first communication scenario.

[0175] In this way, the perception model building device can predefine the correlation between communication scenarios and modeling accuracy. Then, after determining the first communication scenario, it can directly determine the modeling accuracy corresponding to the first communication scenario based on the correlation, thereby simplifying the process of determining the modeling accuracy of the communication scenario and enabling the modeling accuracy of the first communication scenario to be determined quickly, thus improving the efficiency of building the perception model.

[0176] The following describes the perception model establishment method of this application through specific embodiments.

[0177] like Figure 7 As shown, the perception model establishment method of this application embodiment can model multi-mode and multi-source data, forming a unified wireless scenario in a 6G real-time dynamic environment, forming the foundation and prerequisite for 6G network digital twin simulation, and providing a core method for future 6G real-time dynamic factor planning, construction, operation and optimization based on perception data. The specific process includes the following S1 to S6:

[0178] S1. Prepare 6G communication scenarios and 3D modeling data.

[0179] Based on the 6G communication scenarios and their 6G network communication services and technical requirements, key scenarios were identified, and three types of 6G communication scenarios were determined, as shown in Table 1 above.

[0180] 6G introduces various data sources (i.e., the aforementioned spatial perception data) such as sensing (6G's own sensing technology for modeling and attitude tracking), point clouds, oblique photography, vector modeling, and 3D GIS. This type of data possesses its own location positioning system. For different source environments and scenarios, different source data are typically presented in the following ways:

[0181] Typically, to determine the extent of a twin region for network simulation, the top diagonal coordinates are removed, such as: (x o1u ,y o1u ,x o2u ,y o2u (; Longitude zone), where the format is the projected coordinates after WGS conversion, in meters, and the corresponding WGS84 latitude and longitude range is (x o1w ,y o1w ,x o2w ,y o2w It requires that its precision retain at least 6 decimal places.

[0182] The initial locations of different source data are shown in Table 2 above. The longitude zone represents the UTM zone data for the location of the longitude, such as 49N for a typical area. X and Y are coordinates (in meters) in WGS84 latitude and longitude or the UTM projected coordinate system. If it is WGS84 latitude and longitude, the longitude zone is not specified.

[0183] Z represents the height above the ground at location (x, y), in meters. This presents a significant challenge to the unified fusion of data, and is one of the problems this application aims to address. For example, 6G sensing calculations often use the locations of 6G base station sectors as base points, and joint sensing or positioning based on different base stations will lead to complex issues. It should be noted that the data points in Table 2 above do not yet establish a relationship with the 6G coverage area. Note that data from different data sources, such as point clouds or 6G sensing data, are mostly in file format, and their location information may not be identical.

[0184] Each source data category will contain multiple individual data points, the location information of which is shown in Table 3 above. Table 3 shows the typical data formats for this type of dataset, namely, surfaces, lines, and points. Environmental data such as 6G sensing data present in different categories of data usually belong to one of these categories.

[0185] S2: Determine the modeling accuracy based on the communication scenario.

[0186] Based on the categories identified in the first step, and considering the requirements for network planning simulation twins in different 6G environmental scenarios, the modeling accuracy of the basic scenario (i.e., the first communication scenario) is determined, and its accuracy requirements are shown in Table 5 above. For the wide-area scenario, considering 6G coverage in mountainous and rural areas, a low-level accuracy of 50m is considered, while for other scenarios, accuracy above 20m is required.

[0187] S3: Determine a unified coordinate origin based on accuracy.

[0188] To ensure consistent overlay of data from different sources, a unified coordinate origin is established at the center of the region (i.e., the center of the aforementioned physical region), with the elevation of that region center serving as the center of the elevation origin. For example... Figure 8 As shown, this mode can handle the expansion of the scene to the periphery and ensure that the relevant data is loaded uniformly.

[0189] In addition, for auxiliary coordinate origin positioning, the azimuth is set at 0 degrees directly above, and the angle increases clockwise to reach 360 degrees. Based on this requirement and the data preparation, standardized azimuth data is compiled, as shown in Table 4 above.

[0190] S4: Determine the coordinate format (i.e., the first coordinate system) and height mode.

[0191] From the perspective of 6G network planning and twin applications, there are three scenarios:

[0192] For micro-scenarios, to improve the accuracy of 6G network planning and application, a Cartesian coordinate system is used as the primary coordinate format. Verification shows that this method achieves optimal accuracy at the precision determined in step 2.

[0193] For scenarios involving depth and breadth, WGS84+projected coordinates UTM and WGS84 are the primary methods. WGS84 is the conventional latitude and longitude method, but its accuracy will be somewhat reduced during calculation. UTM, based on WGS data, ensures a certain level of accuracy within a certain range. The conversion between UTM and WGS84 into a universal method will not be elaborated here.

[0194] S5: Determine the master template and match different data calculations

[0195] To achieve data unification and overlay from different data sources, ultimately forming a real-time, dynamic 6G environment, the basic coordinate origin O(x0, y0, z0) of the region is first determined, as follows:

[0196] ; .

[0197] An optimized fast algorithm for simultaneously calculating the WGS84 to UTM conversion within the aforementioned physical region:

[0198] Let the points to be converted be (xw, yw) in WGS84 format and (xu, yu) in UTM format, then:

[0199] ; .

[0200] Using the above conversion method, WGS84 latitude and longitude formats in different files can be quickly converted to a unified UTM rectangular coordinate system, achieving a more accurate conversion to UTM format.

[0201] Secondly, using the origin as the reference coordinate system, organize and calculate the position data in Table 2 above. If it is WGS84 latitude and longitude data, calculate it quickly using the method described above. This ensures that the position data in Table 2 are all UTM coordinate data. Let its UTM position data be O1(x t0 y t0， z t0 The converted data is (x t1 y t1， z t1 The calculation is as follows:

[0202] ; ; .

[0203] For the individual data in Table 3 above, its position relative to O1 is (x n0 y n0， z n0 Then the unified location data is:

[0204] ; ; .

[0205] Thus, by calculating all the data in Tables 2 and 3 according to the above algorithm, we can obtain the unified position data of the superimposed data in the entire three-dimensional space of the above physical region.

[0206] S6: Models and stitches data for a unified 6G environment scenario.

[0207] First, based on the data generated by S5, the data from different source units in Table 2 above are superimposed one by one in descending order of range (i.e., the size of at least two physical regions mentioned above), paying attention to the superposition and adjustment at the Z-height. Second, the different source data are uniformly adjusted according to the azimuth angle (i.e., the azimuth angle correction process mentioned above) to ensure that the position, azimuth, and attitude are consistent with the actual 6G communication scenario.

[0208] This solves the problem of comprehensive scenario modeling based on 6G sensing multi-source data, especially for data loading and mapping under 6G multi-site joint sensing, offering a significant advantage. It also supports dynamic loading and computation, and proposes an optimized accuracy algorithm to improve accuracy to the millimeter level in specific scenarios. This type of scenario and comprehensive data overlay is the first of its kind, solving the problems of rapid computation and accuracy in this type of loading. Specifically:

[0209] 1. To address the multi-source data and communication requirements of 6G, a classification method for wireless scenarios is determined, and different levels of precision and modes are adopted for digital twin simulation of different network categories;

[0210] 2. For the calculation algorithm of uniformly superimposing data categories and layer-by-layer superposition of different source data, innovative methods are proposed, focusing on the problems of chaotic, inconsistent, and numerous source data.

[0211] 3. An algorithm for convenient conversion between WGS and UTM within a certain range, which is fast and accurate in a localized area;

[0212] 4. For 3D data overlay, a unified calculation method for Z-height from different data sources is proposed, and an orientation parameter method is introduced.

[0213] It should be noted that the descriptions of each step S1 to S6 in this embodiment can be found in the descriptions in the above embodiments, and will not be repeated here.

[0214] It should be noted that the above-described method embodiments, or the various possible implementations of the method embodiments, can be executed individually, or, provided there is no conflict, they can be combined with each other. The specific implementation can be determined according to actual usage requirements, and this application embodiment does not impose any restrictions on this.

[0215] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0216] This application embodiment can divide the perception model building device into functional modules according to the above method example. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0217] In some embodiments, this application also provides a perception model building apparatus. This perception model building apparatus may include one or more functional modules for implementing the perception model building method of the above method embodiments.

[0218] For example, Figure 9 This is a schematic diagram of a perception model building device provided in an embodiment of this application. Figure 9 As shown, the perception model building device 900 includes: a receiving module 901, a determining module 902, a conversion module 903, and a building module 904.

[0219] The receiving module 901 is used to receive spatial sensing data from at least two sensing node devices within a physical area; the determining module 902 is used to determine at least two first spatial sensing data that match the first communication scenario from the spatial sensing data based on the first communication scenario corresponding to the physical area; wherein each first spatial sensing data is spatial sensing data collected in the coordinate system used by the corresponding sensing node device; the conversion module 903 is used to convert the at least two first spatial sensing data into at least two second spatial sensing data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario; and the establishing module 904 is used to establish a sensing model of the physical area based on the at least two second spatial sensing data.

[0220] The sensing model building device provided in this application, within a 6G network, for a given communication scenario corresponding to a physical area, can convert spatial sensing data collected by multiple sensing node devices in different coordinate systems into spatial sensing data in the same coordinate system. Then, based on the converted spatial sensing data, a sensing model of the physical area is built. Therefore, when building a sensing model in a 6G network, key characteristics such as nonlinear distortion and dynamic channel changes can be accurately captured using coordinate-aligned multi-source spatial sensing data, comprehensively and accurately depicting complex dynamic scenarios. This improves the accuracy of building sensing models in 6G networks.

[0221] One possible implementation is that the aforementioned at least two first spatial perception data include: first target spatial perception data collected in a first coordinate system and second target spatial perception data collected in a second coordinate system; the aforementioned conversion module 903 is specifically used to determine the center position of the aforementioned physical region as a unified coordinate origin according to the modeling accuracy corresponding to the first communication scenario; and to perform offset processing on the first target spatial perception data according to the unified coordinate origin and the coordinate origin of the first coordinate system to obtain third target spatial perception data; and to perform offset processing on the second target spatial perception data according to the unified coordinate origin and the coordinate origin of the second coordinate system to obtain fourth target spatial perception data; and to convert the fourth target spatial perception data into fifth target spatial perception data in the first coordinate system according to the top diagonal coordinate values ​​in the third target spatial perception data and the top diagonal coordinate values ​​in the fourth target spatial perception data; and to determine the third target spatial perception data and the fifth target spatial perception data as the aforementioned at least two second spatial perception data.

[0222] Another possible implementation is that the aforementioned establishment module 904 is specifically used to determine a physical region range corresponding to each of the at least two second spatial sensing data, thereby obtaining at least two physical region ranges; and to perform spatial overlay processing and azimuth correction processing on the at least two second spatial sensing data in descending order of the size of the at least two physical region ranges, thereby obtaining the aforementioned sensing model.

[0223] Another possible implementation method, combined with Figure 9 ,like Figure 10As shown, the aforementioned perception model establishment device 900 further includes an acquisition module 905; the acquisition module 905 is used to acquire communication service information, spatial feature information of the physical area, and spatiotemporal behavior feature information of the perceived object in the physical area before the determination module 902 determines at least two first spatial perception data matching the first communication scenario from the spatial perception data based on the first communication scenario corresponding to the physical area; the determination module 902 is also used to determine the first communication scenario based on the communication service information, the spatial feature information, and the spatiotemporal behavior feature information.

[0224] In another possible implementation, the determining module 902 is further configured to, before the conversion module 903 converts at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario, determine a first modeling accuracy associated with the first communication scenario from the at least one modeling accuracy according to the association relationship between the at least one communication scenario and the at least one modeling accuracy; wherein the at least one communication scenario includes the first communication scenario; and determine the first modeling accuracy as the modeling accuracy corresponding to the first communication scenario.

[0225] It should be noted that the perception model building device can implement all the processes implemented in the above method embodiments and achieve the same beneficial effects. To avoid repetition, it will not be described again here.

[0226] In the case where the functions of the integrated modules described above are implemented in hardware, this application provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 11 As shown, the electronic device 90 includes: a processor 92, a communication interface 93, and a bus 94. Optionally, the electronic device 90 may also include a memory 91.

[0227] Processor 92 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0228] Communication interface 93 is used to connect with other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0229] The memory 91 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0230] As one possible implementation, the memory 91 can exist independently of the processor 92. The memory 91 can be connected to the processor 92 via a bus 94 and is used to store instructions or program code. When the processor 92 calls and executes the instructions or program code stored in the memory 91, it can implement the perception model establishment method provided in the embodiments of this application.

[0231] In another possible implementation, memory 91 can also be integrated with processor 92.

[0232] Bus 94 can be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 94 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 11 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0233] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0234] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described perception model establishment method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0235] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0236] This application also provides a readable storage medium storing a program or instructions that, when executed by a computer, implement the perception model establishment method provided in the above embodiments. It is understood that all or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware; the readable storage medium can be any of the foregoing embodiments or memory; the readable storage medium can also be an external storage device of the service invocation device, such as a pluggable hard drive, SmartMedia Card (SMC), Secure Digital (SD) card, flash card, etc., equipped on the service invocation device. Further, the readable storage medium can include both internal storage units of the service invocation device and external storage devices. The readable storage medium is used to store the computer program and other programs and data required by the service invocation device. The readable storage medium can also be used to temporarily store data that has been output or will be output.

[0237] This application also provides a computer program product, which is stored in a storage medium and, when executed by a computer, implements the perception model establishment method provided in the above embodiments.

[0238] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0239] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0240] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for establishing a perception model, characterized in that, include: Receive spatial sensing data from at least two sensing node devices within the physical area; Based on the first communication scenario corresponding to the physical region, at least two first spatial perception data that match the first communication scenario are determined from the spatial perception data; wherein, each first spatial perception data is spatial perception data collected in the coordinate system used by the corresponding sensing node device; Based on the modeling accuracy corresponding to the first communication scenario, the at least two first spatial perception data are converted into at least two second spatial perception data in the same coordinate system; Based on the at least two second spatial perception data, a perception model of the physical region is established.

2. The method for establishing a perception model according to claim 1, characterized in that, The at least two first spatial perception data include: first target spatial perception data collected in a first coordinate system and second target spatial perception data collected in a second coordinate system; The step of converting the at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario includes: Based on the modeling precision corresponding to the first communication scenario, the center position of the physical region is determined as the unified coordinate origin; Based on the unified coordinate origin and the coordinate origin of the first coordinate system, offset processing is performed on the first target space perception data to obtain the third target space perception data; and based on the unified coordinate origin and the coordinate origin of the second coordinate system, offset processing is performed on the second target space perception data to obtain the fourth target space perception data. Based on the top-diagonal coordinates of the third target space perception data and the top-diagonal coordinates of the fourth target space perception data, the fourth target space perception data is converted into the fifth target space perception data in the first coordinate system; The third target spatial perception data and the fifth target spatial perception data are identified as the at least two second spatial perception data.

3. The method for establishing a perception model according to claim 1, characterized in that, The step of establishing a perception model for the physical region based on the at least two second spatial perception data includes: Based on the at least two second spatial sensing data, a physical region range corresponding to each second spatial sensing data is determined, resulting in at least two physical region ranges; According to the order of the size of the at least two physical regions from largest to smallest, spatial overlay processing and azimuth correction processing are performed on the at least two second spatial sensing data to obtain the sensing model.

4. The method for establishing a perception model according to any one of claims 1 to 3, characterized in that, Before determining at least two first spatial sensing data points matching the first communication scenario from the spatial sensing data based on the first communication scenario corresponding to the physical region, the sensing model establishment method further includes: Acquire communication service information within the physical area, spatial feature information of the physical area, and spatiotemporal behavioral feature information of sensed objects within the physical area; The first communication scenario is determined based on the communication service information, the spatial feature information, and the spatiotemporal behavior feature information.

5. The method for establishing a perception model according to any one of claims 1 to 3, characterized in that, Before converting the at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario, the perception model establishment method further includes: Based on the association between at least one communication scenario and at least one modeling precision, a first modeling precision associated with the first communication scenario is determined from the at least one modeling precision; wherein, the at least one communication scenario includes the first communication scenario; The first modeling accuracy is determined to be the modeling accuracy corresponding to the first communication scenario.

6. A sensory model building device, characterized in that, include: Receive module, determine module, convert module, and establish module; The receiving module is used to receive spatial sensing data from at least two sensing node devices within the physical area; The determining module is used to determine at least two first spatial sensing data that match the first communication scenario from the spatial sensing data based on the first communication scenario corresponding to the physical area; wherein each first spatial sensing data is spatial sensing data collected in the coordinate system used by the corresponding sensing node device; The conversion module is used to convert the at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario. The establishment module is used to establish a perception model of the physical region based on the at least two second spatial perception data.

7. The perceptual model building apparatus according to claim 6, characterized in that, The at least two first spatial perception data include: first target spatial perception data collected in a first coordinate system and second target spatial perception data collected in a second coordinate system; The conversion module is specifically used to determine the center position of the physical region as a unified coordinate origin according to the modeling accuracy corresponding to the first communication scenario; and to perform offset processing on the first target spatial perception data according to the unified coordinate origin and the coordinate origin of the first coordinate system to obtain third target spatial perception data; and to perform offset processing on the second target spatial perception data according to the unified coordinate origin and the coordinate origin of the second coordinate system to obtain fourth target spatial perception data; and to convert the fourth target spatial perception data into fifth target spatial perception data in the first coordinate system according to the top diagonal coordinate values ​​in the third target spatial perception data and the top diagonal coordinate values ​​in the fourth target spatial perception data; and to determine the third target spatial perception data and the fifth target spatial perception data as the at least two second spatial perception data.

8. The perceptual model building apparatus according to claim 6, characterized in that, The establishment module is specifically used to determine a physical region range corresponding to each of the at least two second spatial sensing data, thereby obtaining at least two physical region ranges; and to perform spatial overlay processing and azimuth correction processing on the at least two second spatial sensing data in descending order of the size of the at least two physical region ranges, thereby obtaining the sensing model.

9. The perceptual model building apparatus according to any one of claims 6 to 8, characterized in that, The perception model building device also includes an acquisition module; The acquisition module is used to acquire communication service information within the physical area, spatial feature information of the physical area, and spatiotemporal behavior feature information of the sensed object within the physical area before the determination module determines at least two first spatial sensing data matching the first communication scenario from the spatial sensing data based on the first communication scenario corresponding to the physical area. The determining module is further configured to determine the first communication scenario based on the communication service information, the spatial feature information, and the spatiotemporal behavior feature information.

10. The perceptual model building apparatus according to any one of claims 6 to 8, characterized in that, The determining module is further configured to, before the conversion module converts the at least two first spatial perception data into at least two second spatial perception data in the same coordinate system based on the modeling accuracy corresponding to the first communication scenario, determine a first modeling accuracy associated with the first communication scenario from the at least one modeling accuracy according to the association relationship between at least one communication scenario and at least one modeling accuracy; wherein the at least one communication scenario includes the first communication scenario; and determine the first modeling accuracy as the modeling accuracy corresponding to the first communication scenario.

11. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the perception model building method as described in any one of claims 1-5.

12. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions, which, when executed by a computer, implement the perception model establishment method as described in any one of claims 1-5.

13. A computer program product, characterized in that, The computer program product is stored in a storage medium, and when executed by a computer, the computer program product implements the perception model building method as described in any one of claims 1-5.

Images