Multi-node control interface construction method and device, computer equipment and medium

Abstract

The invention relates to a multi-node control interface construction method and device, computer equipment and a medium, and the method comprises the steps: obtaining an environment space map generated by a specific equipment node through a current equipment node in a smart home network, and building a spatial position relation between the current equipment node and the specific equipment node in the map; calculating the spatial position of each equipment node in the map by referring to the spatial position relation based on the received signal strength measured autonomously and mutually among a plurality of equipment nodes in the network; for each equipment node except the current equipment node in the network, identifying an equipment type and a controllable function item of the equipment node according to an equipment identifier carried in the received signal strength of the equipment node and a historically generated network flow characteristic of the equipment node; and rendering control entry icons of the corresponding equipment nodes at corresponding spatial positions of the map, and associating operation controls corresponding to the equipment types and the controllable function items of the corresponding equipment nodes to generate a centralized control interface. According to the invention, visual management and cooperative control of equipment can be realized.

Description

Technical Field

[0001] This application relates to the field of the Internet of Things, and in particular to a method and apparatus for constructing a multi-node control interface, computer equipment and media. Background Technology

[0002] With the popularization of IoT technology, the number and variety of devices in smart home systems are increasing daily. Users typically manage these devices through mobile applications or smart control screens. However, most existing device management interfaces use a simple list format, displaying all smart devices in the home in a flat, text- or icon-based manner. This interaction method has significant limitations.

[0003] From a technical perspective, list-based interfaces only present the logical connections between devices, completely detaching them from their physical location within the home environment. Users cannot intuitively correlate device controls on the interface with their actual locations in the space (such as a ceiling light in the living room or an air conditioner in the bedroom). When a user needs to operate a device in a specific location, they often have to search through a lengthy list, resulting in low efficiency and a poor user experience. Furthermore, when a new device joins the network, it is simply added to the end of the list, and the user still needs to manually rename it to indicate its location, a cumbersome process.

[0004] A deeper technical problem lies in the fact that list-based interfaces cannot reflect the spatial relationships between devices, thus failing to support location-based collaborative control. For example, a user might want to implement a "homecoming mode," the logic of which is to "turn on the entryway light, close all curtains, and turn on the living room air conditioner." With current technology, the user must either find these three devices in the list and operate them one by one, or rely on pre-set complex scene configurations. The system itself cannot understand spatial concepts like "entryway" and "living room," nor can it automatically group devices located in the same area or with functional relationships. The fundamental reason is that traditional control methods only establish a control channel between devices and the cloud, failing to build a cognitive model that maps devices to their physical spaces.

[0005] Therefore, there is an urgent need in this field for a new type of control interface that can organically combine smart devices with their actual location in the home environment, in order to solve the technical problems of inconvenience in operation, lack of spatial awareness, and difficulty in achieving location-based intelligent collaborative control caused by the above-mentioned list-style interface. Summary of the Invention

[0006] The primary objective of this application is to solve at least one of the above-mentioned problems by providing a method and apparatus for constructing a multi-node control interface, as well as a computer device and medium.

[0007] To achieve the various objectives of this application, the following technical solution is adopted: A method for constructing a multi-node control interface, provided to meet one of the purposes of this application, includes the following steps: The current device node in the smart home network obtains an environmental spatial map generated by a specific device node, and establishes a spatial positional relationship between the current device node and the specific device node in the environmental spatial map. Based on the received signal strength autonomously measured between multiple device nodes in the smart home network, the spatial position of each device node in the environmental spatial map is calculated with reference to the spatial position relationship. For each device node in the smart home network other than the current device node, its device type and controllable functions are identified based on the device identifier carried in its received signal strength and its historical network traffic characteristics. The corresponding control entry icon of the corresponding device node is rendered at the corresponding spatial location on the environmental spatial map. The control entry icon is associated with the operation control corresponding to the device type and controllable function item of the corresponding device node to generate a centralized control interface.

[0008] A multi-node control interface construction apparatus is proposed to meet one of the purposes of this application, comprising: The map anchoring module is configured to obtain an environmental spatial map generated by a specific device node from the current device node in the smart home network, and establish a spatial positional relationship between the current device node and the specific device node in the environmental spatial map. The node calculation module is configured to calculate the spatial position of each device node in the environmental spatial map based on the received signal strength autonomously measured between multiple device nodes in the smart home network and with reference to the spatial position relationship. The function configuration module is configured to identify the device type and controllable function items of each device node in the smart home network, except for the current device node, based on the device identifier carried in the received signal strength and the characteristics of its historical network traffic. The interface construction module is configured to render the control entry icon of the corresponding device node at the corresponding spatial location on the environmental spatial map, associate the control entry icon with the operation controls corresponding to the device type and controllable function items of the corresponding device node, and generate a centralized control interface.

[0009] In another aspect, a computer device provided for one of the purposes of this application includes a processor and a memory, wherein the processor invokes and runs a computer program in the memory to perform the steps of the multi-node control interface construction method.

[0010] On another aspect, a computer-readable storage medium is provided to suit another purpose of this application, which stores, in the form of computer-readable instructions, a computer program implemented according to the multi-node control interface construction method, which, when called by a computer, executes the steps included in the corresponding method.

[0011] Compared to traditional technologies, this application completely transforms the traditional list-based interaction method by constructing a centralized control interface integrated with an environmental spatial map. Users can directly operate devices through a visual interface that intuitively reflects the home layout, greatly improving operational efficiency and intuitiveness. The centralized control interface generated by this application inherently possesses spatial awareness capabilities, supporting users to achieve batch collaborative control of devices by selecting areas, significantly lowering the setup threshold for smart scenarios. Furthermore, new devices can be automatically located and their assigned areas recommended when joining the network, eliminating the need for manual naming and achieving plug-and-play functionality, comprehensively enhancing the user experience. Attached Figure Description

[0012] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a typical embodiment of the multi-node control interface construction method of this application; Figure 2 A rendering of the centralized control interface constructed for this application, presented as a three-dimensional spatial model; Figure 3 This is a schematic block diagram of the multi-node control interface construction device of this application; Figure 4 This is a schematic diagram of the structure of a computer device used in this application. Detailed Implementation

[0013] To enable those skilled in the art to better understand and implement this application, the inventive concept of this application will be described in detail below in conjunction with typical application scenarios and network architectures. It should be understood that the embodiments described herein are merely examples and are not intended to limit the scope of protection of this application.

[0014] The multi-node control interface construction method protected in this application can be implemented as a computer application, integrated into a smart home management system, and deployed on a computer device with computing capabilities. This computer device, acting as the logical control hub in the smart home network, is responsible for coordinating communication among various device nodes in the network, collecting network status data, executing the computational processes of this application, and ultimately generating and presenting an intuitive centralized control interface to the user. One or more of the computational processes of this application can also be transferred to a cloud server for implementation, with the terminal device handling the relevant user interactions.

[0015] In terms of application scenarios, the direct users of this application are legitimate users of smart home networks. By operating a smart home management system that integrates the technical solution of this application, users can trigger the system to build and display a control view that is deeply integrated with the physical environment of the home. This view completely changes the traditional flat display method of device lists, accurately mapping each smart device in the home to its actual physical location, such as the living room, bedroom, kitchen, etc., making user control of devices more intuitive and efficient than ever before.

[0016] The computer device implementing the solution of this application can physically be a dedicated smart control screen in a smart home network. It is typically fixedly installed in a central location such as the home entrance or living room, possessing powerful local computing capabilities and stable network connectivity, enabling continuous communication and collaboration with various devices within the network. Alternatively, the computer device can be a user-owned mobile terminal, such as a smartphone or tablet. As long as the terminal device has the corresponding smart home management system application installed and possesses the ability to wirelessly communicate and interact with other smart devices in the home, such as routers, smart appliances, and sensors, it can serve as the operating platform for this application, allowing users to manage and control their smart home environment anytime, anywhere.

[0017] The execution of the method in this application relies on a smart home network architecture. This network typically centers around a home wireless router or gateway, forming a local area network. Various smart device nodes, including smart home appliances, lighting devices, security sensors, and entertainment terminals, access this network via wireless communication protocols such as Wi-Fi, Bluetooth, and ZigBee. The current device node in this application refers to a computer device (e.g., a central control screen or mobile phone) running the computer program implemented according to the method of this application. As a coordinator, it can initiate mutual measurements between devices, collect data, and perform centralized calculations. The specific device node in this application refers to a mobile sensing smart device, such as a robotic vacuum cleaner, that possesses environmental perception and mapping capabilities. The specific device node is the key data source for generating the initial environmental spatial map. The entire solution of this application, based on this network and hardware, achieves intelligent and spatial transformation of the control interface through innovative software algorithms.

[0018] Based on the understanding of the above application scenarios and network architecture, the subsequent embodiments will be developed around the above hardware environment and concepts. The following will continue to elaborate on the description of various embodiments of this application.

[0019] Please see Figure 1 In some embodiments, the multi-node control interface construction method of this application can be implemented as an application program running on a computer device. The method includes: Step S3100: Obtain the environmental spatial map generated by the specific device node from the current device node in the smart home network, and establish the spatial position relationship between the current device node and the specific device node in the environmental spatial map; When constructing the centralized control interface required for this application, the current device node carrying the computer application of this application first needs to obtain an environmental spatial map. Since the current device node, the specific device node, and the other device nodes are all connected to the same smart home network, and the environmental spatial map has been generated in advance by the specific device node in the smart home network, the current device node and the specific device node can obtain the environmental spatial map through authorized sharing.

[0020] An environmental spatial map is constructed by specific device nodes, which are mobile sensing intelligent devices, such as robotic vacuum cleaners. These nodes typically work in conjunction with their base stations and are equipped with high-performance radar and camera components. Through their own hardware and software capabilities, they perform map discovery as they move within the indoor space, ultimately generating the corresponding environmental spatial map. Therefore, an environmental spatial map is essentially a structured digital description of the physical layout of a smart home environment. The map can be obtained through methods including, but not limited to, the following: initiating a map data request to the specific device node and receiving its response data packet via a device discovery and communication protocol within a local area network; or accessing a copy of the map data uploaded by the specific device node to a cloud server and downloading it locally via the network.

[0021] The data structure of the environmental spatial map includes, but is not limited to, the following parsable elements: boundary coordinate data representing fixed obstacles such as walls, doors, windows, tables, and chairs in the home environment, and reference coordinate points identifying the spatial location of a specific device node when generating the map. In the case of a robotic vacuum cleaner, these reference coordinate points can be the coordinates of its base station. After obtaining the map, the current device node needs to parse the map data and load it into memory for subsequent steps.

[0022] Subsequently, the current device node needs to establish its spatial relationship with other specific device nodes within the environmental spatial map. Specifically, this involves accurately mapping the current device node's location in the real physical environment onto the digital twin model of the environmental spatial map. This mapping requires a pre-defined mapping strategy.

[0023] The implementation of the mapping strategy includes, but is not limited to, the following specific embodiments: If the current device node has its own positioning capability (such as a built-in UWB module or visual SLAM component), it can determine its absolute coordinates in physical space through its own sensor data, and directly calculate its coordinate point in the map based on the map's coordinate system and scale. Another implementation is that if the current device node is a fixed-installation device (such as a smart central control screen), its installation location can be manually marked by the user on the environmental space map during the deployment phase through interactive methods. For example, the user can click on the wall or plane location displayed on the map to complete the location marking. The manually marked coordinates are then recorded as the known spatial location of the current device node in the environmental space map.

[0024] After establishing the spatial relationship between the current device node and the specific device node in the environmental spatial map, the absolute coordinate reference is successfully laid for the spatial positioning of all subsequent device nodes. At this point, the coordinate information of the two reference points with known, fixed coordinates in the environmental spatial map—that is, the spatial positions of the current device node and the specific device node—will serve as constraints referenced in subsequent solution algorithms.

[0025] Step S3200: Based on the received signal strength autonomously measured between multiple device nodes in the smart home network, calculate the spatial position of each device node in the environmental spatial map with reference to the spatial position relationship; After successfully establishing the spatial relationship between the current device node and a specific device node in the environmental spatial map, two spatial reference points with known absolute coordinates are obtained. Using these two reference points, combined with the measured data in the network, the precise spatial location of the remaining device nodes in the smart home network in the environmental spatial map can be calculated.

[0026] To achieve this, the received signal strength measured autonomously between device nodes in a smart home network can be utilized. Specifically, the current device node can send instructions to coordinate other device nodes in the network to periodically perform pairwise wireless signal strength measurements with other device nodes, for example, through Wi-Fi Fine Timing Measurement (FTM) protocol or Bluetooth Signal Strength Indicator (RSSI) measurement, obtaining a large number of received signal strength measurements between devices. This data constitutes the raw observations reflecting the relative distance relationships between devices.

[0027] Spatial calculations are performed based on these observations. In different embodiments, various methods can be used, including triangulation, polygonal positioning, and more advanced graph optimization models. Triangulation and polygonal positioning methods belong to the category of geometric positioning. Their principle is based on the coordinates of known reference points. By measuring the distances or angles from the target point to multiple known points, the coordinates of the target point are directly calculated using geometric relationships. These methods are relatively simple to implement, but their positioning accuracy heavily depends on the accuracy of the wireless signal propagation model. In complex indoor environments, due to the influence of multipath effects, obstacle obstruction, and other factors, there are large errors in the model between signal strength and distance, resulting in limited positioning accuracy, often with deviations at the meter level or even larger.

[0028] To overcome the aforementioned limitations, in the preferred embodiment of this application, a graph optimization-based model is used to perform spatial calculations, resulting in more robust and accurate results. Through the graph optimization model, each device node is considered a vertex of spatial coordinates to be solved. An edge is established for each pair of device nodes with signal strength measurements, and the relative distance estimate obtained from the received signal strength conversion is used as the observation constraint for the distance of that edge. The calculation process is transformed into a large-scale optimization problem: using a reference point with known coordinates (the current device node and a specific device node) as a fixed constraint, and aiming to minimize the overall error between the observed distances of all edges and the Euclidean distance calculated from the vertex coordinates, an iterative optimization algorithm is used to solve for the optimal coordinates of all unknown vertices.

[0029] The advantage of the graph optimization model lies in its ability to integrate a large amount of even redundant observation data, effectively offset the random errors of a single measurement through global optimization, and exhibit good fault tolerance for inconsistent observation data. This significantly improves the overall positioning accuracy and stability in complex indoor environments, and can achieve sub-meter level positioning results in actual measurements, which is superior to traditional geometric positioning methods.

[0030] At this point, each device node in the smart home network has been assigned a coordinate with a clear physical meaning in the environmental spatial map, determining its spatial location in the environmental spatial map, and successfully making a precise digital mapping between the logical device node network and the physical spatial structure of the home.

[0031] Step S3300: For each device node in the smart home network other than the current device node, identify its device type and controllable function items based on the device identifier carried in its received signal strength and its historical network traffic characteristics. After successfully calculating the spatial location of each device node in the environmental spatial map, we can continue to assign the necessary functional semantics to each device node in the map, that is, identify its device type and controllable functional items, and transform the abstract coordinate points into interactive entry points with clear operational meanings.

[0032] Specifically, for each device node in the smart home network other than the current device node, a comprehensive judgment is made based on the device identifier carried in its wireless signal data and the network traffic characteristics generated during its historical operation. The device identifier, such as the device's MAC address or a manufacturer-specific unique identifier, is the primary basis for device identification. A pre-built device information database can be queried to match the device identifier with information such as the device manufacturer and basic model number recorded in the database, thereby obtaining a preliminary identification result of the device's basic type. For example, a specific MAC address prefix may correspond to a smart lighting device of a certain brand.

[0033] However, preliminary identification based solely on device identifiers may be insufficient to accurately determine the specific model or all functions of a device. Therefore, in further embodiments, the historical network traffic characteristics of the device can be analyzed for refinement and verification. Network traffic characteristics reflect the device's behavioral patterns in a real-world usage environment, serving as a behavioral fingerprint indicating the device node. These characteristics include, but are not limited to, the throughput of its data streams, the periodicity of transmission, the structural characteristics of data packets, and the target server or service domain name it communicates with. For example, if a device continuously generates stable uplink video stream data and communicates with a specific cloud storage server, it can be inferred with high confidence that it is a smart camera; conversely, if a device only generates sporadic small data packets when interacting with the user, it is more likely to be a smart switch or sensor.

[0034] By combining the hardware identity provided by device identifiers with the behavioral fingerprints revealed by network traffic characteristics, a precise profile of the device type can be achieved. Based on this, all controllable functions supported by the device node can be mapped from a predefined device capability library according to the finally determined specific device type. For example, a device identified as a "color smart light bulb" might have a set of controllable functions including on / off, brightness adjustment, color temperature adjustment, and color changing. It should be noted that the mapping relationship data between each specific device type and its controllable functions in the capability library can be collected and determined in advance.

[0035] At this point, each device node in the environmental spatial map not only has precise spatial coordinates, but is also given a clear identity, namely device type and capabilities, i.e., controllable functional items.

[0036] Step S3400: Render the control entry icon of the corresponding device node at the corresponding spatial location on the environmental space map, associate the control entry icon with the operation controls corresponding to the device type and controllable function items of the corresponding device node, and generate a centralized control interface.

[0037] After successfully assigning precise spatial coordinates to each device node in the environmental spatial map and identifying its device type and controllable functions, the centralized control interface can be generated accordingly. Specifically, the control entry icon of the corresponding device node can be rendered at the corresponding spatial location on the environmental spatial map, and the control entry icon can be associated with the operation controls corresponding to the device type and controllable functions of the corresponding device node.

[0038] To achieve interface rendering, the specific pixel position of each device node in the map visualization layer is first determined based on the calculated spatial coordinates. Then, according to the identified device type, a matching vector icon is retrieved from a pre-set icon resource library. For example, for a device node identified as a "smart ceiling light," a light fixture-style icon is retrieved; for a device node identified as a "smart air conditioner," an air conditioner-style icon is retrieved. The retrieval process includes, but is not limited to, the following specific implementation methods: querying and matching through a mapping table between device type and icon resource file name; or requesting the corresponding exclusive icon resource from the cloud server based on the device model.

[0039] The rendering engine draws the icons on the corresponding coordinates of the environment space map canvas, thereby generating the user's control entry icons. To optimize the visual experience, the rendering process can include dynamic effects, such as a fade-in animation for the icons of newly connected device nodes, or a pulsed flashing effect for the icons of device nodes in an abnormal state.

[0040] While rendering the control entry icons, or afterward, each icon needs to be associated with its corresponding operation control. Specifically, the set of controllable functions of the previously identified device nodes can be transformed into user-interactive interface elements. Associated operations include, but are not limited to, the following examples: binding an event listener to the icon; when the user clicks or hovers over the icon, triggering a pop-up floating menu or window; dynamically generating and arranging operation controls that correspond one-to-one with the controllable functions within the menu or window.

[0041] The specific form of the control depends on the nature of the function. For example, for the "switch" function, the corresponding control can be rendered as a toggle switch; for the "brightness adjustment" function, the corresponding control can be rendered as a slider; and for the "mode selection" function, the corresponding control can be rendered as a drop-down selector. The definition data of these controls comes from a preset device capability library, which defines the control type, parameter range, and control instruction template for each controllable function of each device type.

[0042] Ultimately, all the rendered control icons and their associated controls together constitute the centralized control interface of this application. This centralized control interface can also be further converted into a three-dimensional spatial model to present a more immersive interactive effect, see reference [reference needed]. Figure 2 As shown in the rendered image, the interface presents users with an interactive smart device control layer overlaid on a map of the home space. Within this interface, users can intuitively locate and operate devices based on their physical positions. For example, clicking the air conditioner icon in the living room area adjusts the temperature, or clicking the light icon in the bedroom area changes the brightness, thus achieving truly intuitive, efficient, and deeply integrated device control within the space.

[0043] As can be seen from the above embodiments, this application, based on the environmental spatial map generated by specific device nodes in a smart home network, can determine the identity and controllable functions of each device node by performing intelligent technical identification on the device nodes in the network, thereby constructing a centralized control interface. This has multiple positive technical effects, including but not limited to: First, this application fundamentally transforms the interaction method of smart home systems by constructing a centralized control interface integrated with an environmental spatial map. It completely changes the traditional flat, list-style interface that is detached from physical space, allowing users to manage and control devices in a visual environment that intuitively reflects the physical layout of the home. Users no longer need to painstakingly search through lengthy device lists; instead, they can directly find the icon of the target device in the corresponding room location and operate it, greatly improving the intuitiveness and efficiency of operation.

[0044] Secondly, because the control interface is built directly onto the environmental spatial map, it naturally possesses spatial awareness, making location-based intelligent collaborative control possible. For example, users can easily select all lights, air conditioners, and audio-visual devices in the living room area at once by simply selecting the area, and then perform batch operations on them, such as turning them off or setting scene modes. This interaction method greatly lowers the technical barrier to setting up complex smart scenes and improves the automation level of smart homes.

[0045] Furthermore, the centralized control interface constructed in this application can guide new devices to join the network. When a new device connects to the network, it can combine its location information with a spatial map, automatically render a control entry icon near its discovered physical location, and intelligently recommend the room or functional area to which it belongs. This eliminates the tedious steps of manually naming and classifying devices, achieving true plug-and-play functionality and significantly improving the user experience.

[0046] As can be seen, this application has successfully solved a series of technical problems existing in traditional list-style interfaces, such as inconvenience of operation, lack of spatial sense, and difficulty in collaborative control, by deeply integrating device control with physical space. This provides an effective technical foundation for achieving truly intuitive, efficient, and intelligent home device control.

[0047] Based on any embodiment of the method in this application, the spatial position of each device node in the environmental spatial map is calculated based on the received signal strength autonomously measured between multiple device nodes in the smart home network, with reference to the spatial positional relationship, including: Step S3210: Control the multiple device nodes to perform wireless signal strength measurements between each other, and obtain the received signal strength from itself to the other device nodes as determined by each device node. Before starting spatial location calculation, the basic observation data used for the location calculation must first be acquired, namely the received signal strength measurements between device nodes. The current device node acts as the coordinator, initiating and controlling a distributed signal strength measurement activity to organize all device nodes in the smart home network to collect raw wireless signal strength data reflecting the relative distance relationships between devices.

[0048] In practice, the current device node broadcasts a sequence of measurement commands to other device nodes in the smart home network through its communication module. This command sequence contains measurement parameter configuration information, such as the specified measurement period, duration, and the wireless communication frequency band and channel used. The transmission of measurement commands can rely on existing network management protocols or custom application layer protocols to ensure that commands are reliably sent to each device node.

[0049] Upon receiving a measurement command, the device nodes in the network sequentially act as both signal transmitters and receivers, performing wireless signal strength measurements between each pair of device nodes, according to the command requirements. Measurement implementation methods include, but are not limited to, the following specific embodiments: In a Wi-Fi network environment, the Fine Timing Measurement (FTM) mechanism in the IEEE 802.11 protocol suite can be used to interactively complete the round-trip time (RTT) measurement between a pair of devices, thereby deriving the equivalent value of the Received Signal Strength Indication (RSSI); in a Bluetooth network environment, the Bluetooth Low Energy (BLE) broadcast and scanning mechanism can be directly utilized, with the receiving device directly reading the RSSI value from the broadcast frame. To ensure the comprehensiveness of the measurement data, multiple rounds of measurement can be performed to ensure that the vast majority of device pairs in the network can obtain valid wireless signal strength data.

[0050] Throughout the measurement process, each device node independently records its measurement results. The records include at least: the device identifier of the signal transmitter (such as MAC address), the device identifier of the signal receiver, and the received signal strength value obtained in this measurement. After the measurement is completed, each device node summarizes and reports its recorded data to the current device node via wireless transmission.

[0051] The current device node receives and integrates all reported data, ultimately forming a complete inter-device signal strength matrix. This matrix constitutes the most basic and direct observation input required for subsequent distance estimation and location calculation algorithms, providing a solid data foundation for the entire spatial positioning process.

[0052] Step S3220: Based on the predetermined path loss model, convert the received signal strength into an estimated relative distance between device nodes; After acquiring the received signal strength data measured pairwise between device nodes, these raw observations reflecting signal strength need to be converted into distance information with clear physical meaning. This conversion can be achieved using a path loss model, which models the attenuation of wireless signals propagating in space. This model describes the quantitative relationship between signal strength attenuation and propagation distance, and is crucial for estimating spatial distance from signal measurements.

[0053] The specific form of the path loss model can be selected and parameterized according to the channel characteristics of the actual application scenario. Optional models include free-space propagation models, logarithmic distance path loss models, and more complex models that consider wall attenuation. Taking the logarithmic distance path loss model as an example, its mathematical expression of path loss formula can be expressed as: in Indicates distance Path loss at the location, Indicates the reference distance Path loss at the location, This is the path loss index. This is a random variable following a zero-mean Gaussian distribution, used to characterize shadow fading. In practical applications, the received signal strength... With path loss The relationship is , The transmitted signal strength.

[0054] Based on the selected path loss model, the measured received signal strength values ​​are substituted into the inverse solution of the model to calculate the estimated relative distance between the corresponding device nodes. In practice, key parameters in the model can utilize pre-calibrated values, such as the path loss index. and reference distance Path loss value at These parameters can be obtained through field calibration in a typical home environment, or set according to the parameter values ​​recommended by the International Telecommunication Union (ITU) for indoor environments. The conversion process includes, but is not limited to, the following specific implementation: For each pair of device nodes with signal strength measurements, the measured RSSI value is substituted into the path loss formula to solve for the distance. The estimated value; if the FTM mechanism is used to obtain more accurate time of flight (ToF) information, the distance can be calculated directly from the product of the speed of light and the time of flight. In this case, the path loss model is mainly used to assist in verification or correction.

[0055] It should be noted that due to factors such as multipath effects and obstacle obstruction in indoor environments, the distance estimated by a single deterministic model will contain errors. Therefore, the relative distance estimate output in this step should be understood as a statistical estimate, usually expressed as "estimated distance d ± error range ε". This relative distance estimate matrix constitutes the core input constraint for subsequent geometric positioning or graph optimization algorithms to solve for the absolute spatial position of device nodes.

[0056] Thus, by applying the path loss model, the wireless signal strength data measured at the physical layer was successfully converted into the relative distance relationship data between device nodes required for network layer positioning calculation, laying a solid foundation for the final spatial location calculation.

[0057] Step S3230: Using the known spatial positions of the current device node and the specific device node in the environmental spatial map as fixed references, and constrained by the estimated relative distance between all device nodes, calculate the spatial positions of all other device nodes in the environmental spatial map except for the current device node.

[0058] After obtaining the relative distance estimation matrix between device nodes, these relative distance relationships are further converted into the absolute coordinates of the device nodes in the environmental spatial map. Since the spatial positions of the current device node and a specific device node in the environmental spatial map are known, constituting a priori conditions, these two points with known coordinates form an absolute fixed reference frame, providing anchor points for the spatial positioning of the entire network.

[0059] The solution process can be mathematically modeled as a large-scale geometric constraint satisfaction problem. The goal is to assign a set of coordinates to each device node at an unknown location in two-dimensional or three-dimensional space, such that the Euclidean distance between nodes calculated from these coordinates matches the relative distance estimate obtained through the path loss model as closely as possible, while strictly fixing the coordinates of known reference points. This problem can be expressed as finding a set of coordinates that minimizes the sum of the squared errors between the estimated distances and the Euclidean distances between all node pairs.

[0060] In practice, various numerical optimization algorithms can be used to solve this problem. A basic implementation is a multilateral positioning method based on the least squares approach. This method uses the estimated distances from each unknown node to multiple known reference points as constraints, and estimates its coordinates by solving an overdetermined system of equations. However, in real-world environments with measurement noise and model errors, this method may not be stable enough.

[0061] A superior and more robust implementation employs a graph optimization model. In this model, each device node is considered a vertex in the graph, and an edge is created for each pair of device nodes with an estimated relative distance, using this estimated distance as an observation constraint on the edge length. Subsequently, the vertex coordinates corresponding to the current device node and specific device nodes are fixed to their known absolute coordinates in the environmental spatial map. The solution process is transformed into a nonlinear least-squares optimization problem, the objective function of which is to minimize the overall error between the observed distances of all edges and the Euclidean distances calculated from the vertex coordinates. This optimization problem can be solved using iterative optimization algorithms such as the Levenberg-Marquardt algorithm or the Gauss-Newton algorithm, which effectively handle noise and converge to a globally or locally optimal coordinate configuration.

[0062] After the calculation is completed, each device node in the smart home network whose previous location was unknown is assigned an absolute coordinate in the environmental spatial map coordinate system. At this point, the logical device network is completely and accurately mapped onto the physical spatial structure of the home, successfully establishing a one-to-one correspondence between the digital space and the physical environment.

[0063] The above embodiments, in the spatial location calculation stage, construct a complete technical chain from relative distance observation to absolute benchmark anchoring and then to optimization algorithm solution, achieving significant technical effects compared to traditional single geometric positioning methods. Specifically, this embodiment innovatively abstracts the device node network into a graph model and introduces graph optimization theory, transforming the spatial positioning problem into a global optimization problem with the goal of minimizing overall observation error. This effectively integrates redundant observation data from multiple device nodes and utilizes the inherent error smoothing characteristics of the optimization algorithm to significantly suppress single measurement errors and outlier interference caused by complex indoor environments, thereby greatly improving overall positioning accuracy and robustness. Crucially, incorporating known absolute spatial positions as strong constraints into the optimization process ensures that the coordinates of all device nodes ultimately calculated have consistent absolute meaning corresponding to the actual physical space, rather than isolated relative relationships. This provides an indispensable and highly reliable spatial data foundation for subsequently generating a control interface that accurately overlays the real environment, fundamentally solving the core technical problems of traditional list-style interfaces, such as unintuitive operation and difficulties in collaborative control due to the lack of accurate spatial mapping.

[0064] Based on any embodiment of the method in this application, after calculating the spatial positions of all device nodes other than the current device node in the environmental spatial map, the method includes: Step S3240: Determine the signal propagation path of each pair of device nodes in the environmental spatial map based on the spatial location of each device node obtained by calculation, wherein the path loss model is initially set as the path loss index for each device node when calculating the spatial location. Since the path loss model parameters used in the initial calculation, such as the path loss exponent, are usually a globally uniform preset value, the initial setting before the first calculation fails to fully consider the specific occlusion conditions on the signal propagation path between specific device node pairs in a complex indoor environment, thus introducing model errors. To address this, the structural information of the environmental spatial map in this application can be used as prior knowledge to make personalized corrections to the model.

[0065] Specifically, based on the calculated spatial coordinates of each device node, a virtual signal propagation path is determined on the environmental spatial map between each pair of device nodes where signal measurement is present. This path is a straight line segment connecting the coordinates of two points. Based on this straight line segment, the spatial relationship between it and elements representing spatial structures on the map (such as the boundary outlines of walls, doors, windows, and large furniture) can be determined.

[0066] Step S3250: Based on the spatial structure information of the environmental spatial map, determine the occlusion type of each pair of device nodes on their signal propagation path, and update the path loss index of the path loss model for each pair of device nodes according to the occlusion type. Based on the spatial relationship information provided by the connecting straight lines between each pair of device nodes, the type of obstruction on the signal propagation path of each pair of device nodes can be determined. The determination of obstruction type includes, but is not limited to, the following specific embodiments: if the propagation path passes through a load-bearing wall or metal partition, it is determined as "high-loss obstruction"; if the propagation path only passes through a regular gypsum board partition, it is determined as "medium-loss obstruction"; if the propagation path is within sight or only passes through a wooden door, it is determined as "low-loss obstruction" or "no significant obstruction". Each obstruction type corresponds to an empirically or experimentally calibrated path loss index correction. For example, for the "high-loss obstruction" type, the corresponding path loss index increment Δn is retrieved from the pre-stored correction value table, and the initial global path loss index n is updated to a personalized value n_pair = n + Δn for that device pair. Thus, each straight line segment actually obtains a corresponding personalized updated path loss index.

[0067] Step S3260: Using the updated path loss index, the received signal strength is converted back into a relative distance estimate, and the calculation step is performed again to obtain a more accurate spatial location of the device node.

[0068] After updating the personalized path loss index for all device pairs, the stored original received signal strength data is used with the updated personalized model parameters to re-perform distance estimation, i.e., step S3220 is re-executed. This generates a set of relative distance estimates that better reflect actual propagation conditions. Using this more accurate distance constraint, the spatial solution algorithm (step S3230) is executed again to obtain a more precise spatial location of the device nodes. This iterative optimization process effectively compensates for model errors caused by environmental occlusion, significantly improving the final positioning accuracy in complex indoor scenarios.

[0069] The above embodiments achieve significant technical advantages by introducing structural information from the environmental spatial map to dynamically and personally correct the path loss model: First, it breaks through the limitations of traditional positioning methods that use a globally unified path loss model. By accurately identifying the specific types of obstructions such as load-bearing walls and partitions on the signal propagation path between each pair of device nodes, and dynamically assigning differentiated path loss indices to each pair of device nodes based on this, it accurately compensates for the non-uniform signal attenuation caused by complex indoor environments at the algorithm level. This iterative optimization mechanism based on the prior map structure elevates the one-time coarse-grained positioning to a feedback loop that can continuously approach the real position. Finally, by recalculating, it obtains high-precision spatial location data at the meter or sub-meter level, far exceeding the initial result, providing crucial technical support for building a truly seamless and precise control interface that is superimposed on the physical space.

[0070] Based on any embodiment of the method in this application, using the known spatial positions of the current device node and the specific device node in the environmental spatial map as a fixed reference, and constrained by the estimated relative distances between all device nodes, the spatial positions of all other device nodes besides the current device node in the environmental spatial map are calculated, including: Step S3231: Treat each device node as a vertex to be optimized in the graph optimization model, establish an edge for each pair of device nodes with relative distance estimates, and use the relative distance estimates as the observation constraint for the distance of the edge. This embodiment uses a graph optimization model to solve for the spatial coordinates of device nodes, transforming the problem of locating device nodes in physical space into a computable model. To this end, the entire smart home network can be abstracted as a graph structure, where each device node is considered a vertex in the graph, and the vertex attributes are the two-dimensional or three-dimensional coordinates of the device in the environmental spatial map.

[0071] For each pair of device nodes in the network with estimated relative distances, an undirected edge is created between the corresponding two vertices in the graph. This edge carries crucial observation information: the estimated relative distance between the pair of device nodes, obtained through measurement and path loss model transformation, serves as a strong constraint on the ideal length of the edge. For example, if the estimated relative distance between device A and device B is d_AB, then an edge is created between vertex A and vertex B in the graph model, and d_AB is set as the observation constraint, i.e., the observed distance value, for this edge. All such edges and their observed values ​​together constitute the constraint network of the graph model.

[0072] The objective of solving this graph optimization model is thus clearly defined as: finding an optimal set of vertex coordinates, i.e., the spatial locations of all device nodes, such that the overall difference between the Euclidean distance of each edge in the graph calculated from these coordinates and its corresponding observation distance constraint is minimized. This objective can be expressed as a nonlinear least squares optimization problem, whose objective function is to minimize the sum of squares of the differences between the observation distance and the Euclidean distance of all edges.

[0073] Step S3232: Fix the coordinates of the vertices corresponding to the current device node and the specific device node to their known spatial positions in the environmental space map; To achieve the solution, the known spatial information needs to be transformed into fixed constraints for the model. Specifically, the coordinates of the vertices corresponding to the current device node and specific device nodes are directly fixed to their known absolute coordinates in the environmental spatial map. These two known points serve as reference anchors, providing an absolute coordinate reference framework for the entire optimization problem, ensuring that the final solution has real spatial meaning, and not just relative topological relationships.

[0074] Step S3233: With the objective of minimizing the overall error between the relative distance estimates in all observation constraints and the Euclidean distance calculated from the vertex coordinates, solve the graph optimization model to obtain the optimal spatial position of the remaining device nodes.

[0075] Finally, with the objective of minimizing the overall error between the relative distance estimates in all observation constraints and the Euclidean distance calculated from the vertex coordinates, a numerical optimization algorithm is used to solve this graph optimization model. The solution process includes, but is not limited to, the following specific implementation: using nonlinear least squares optimizers such as the Levenberg-Marquardt algorithm or the Gauss-Newton method for iterative solution, the final output is the coordinates of each vertex that minimize the overall error, that is, the optimal spatial position estimates of all other device nodes in the environmental spatial map except for the current device node and specific device nodes. The corresponding device nodes can then be marked on the environmental map according to the coordinates of these optimal spatial positions.

[0076] The above embodiments transform the spatial positioning problem into a global optimization problem by introducing a graph optimization model, achieving a breakthrough technical advantage in improving positioning accuracy: This model can simultaneously integrate the relative distance observation constraints between all device nodes in the network, effectively offsetting the random and gross errors of a single measurement by minimizing the overall error optimization objective; In particular, incorporating device nodes with known spatial locations as fixed vertices into the optimization framework provides an absolute coordinate reference for the solution, fundamentally avoiding the error accumulation problem in traditional recursive positioning methods; Finally, the spatial positions of the device nodes obtained by the nonlinear least squares algorithm not only satisfy the local distance constraints but also achieve the globally optimal spatial coordinate configuration, thus enabling sub-meter level high-precision positioning even in complex indoor environments, laying a solid technical foundation for building a truly accurate spatial control interface.

[0077] Based on any embodiment of the method in this application, for each device node in the smart home network other than the current device node, its device type and controllable function items are identified according to the device identifier carried in its received signal strength and its historical network traffic characteristics, including: Step S3310: Based on the device identifier carried in the received signal strength, query the preset device information database to obtain the manufacturer and basic type information of the corresponding device node, and form a preliminary identification result; In the initial stage of the device identification process, the device identifier, a key piece of information, enables rapid preliminary classification of device nodes. The device identifier refers to hardware-coded information embedded in the device's wireless signal data packets that uniquely or quasi-uniquely identifies the device's origin. Typical examples include, but are not limited to, MAC addresses (Media Access Control addresses), device serial numbers, or manufacturer-specific unique identifiers. These identifiers are usually embedded in the network interface hardware during device manufacturing and are automatically included in the frame header or specific information element fields of the data packets when the device conducts wireless communication.

[0078] To extract device identifiers, the collected raw wireless signal data is parsed. The specific implementation process includes: the system listens for and captures wireless data frames used in communication between device nodes, and extracts the values ​​of the source address field or vendor information element field from the frame structure. For example, in a Wi-Fi network, the source MAC address can be extracted from the header of a management frame or data frame; in a Bluetooth network, the device address can be extracted from broadcast messages or scan response messages.

[0079] After obtaining the device identifier, a pre-built device information database is queried to retrieve the corresponding device information. This device information database is a database that stores the mapping relationship between device identifiers and device attributes. Its construction methods include, but are not limited to, the following embodiments: integrating a publicly available OUI (Organization Unique Identifier) ​​database, which is maintained by IEEE and maps the first 24 bits of the MAC address to the device manufacturer; and extending this database with a custom database storing device model and functional descriptions, which can be continuously updated through publicly available data from device manufacturers or historical user feedback data. The query process involves matching the extracted device identifier with the records in the database. For example, if the first 24 bits of the extracted MAC address are "AA:BB:CC", and querying the OUI database reveals that this address segment belongs to "a certain intelligent technology company", then the device manufacturer is initially identified as that manufacturer.

[0080] Based on the query results, preliminary identification results are generated. These results include at least the device manufacturer information and basic type classification information. Basic type classification is a coarse-grained classification based on manufacturer and product series, such as identifying the device as "a smart lighting device from a certain manufacturer" or "an environmental sensor from a certain brand." This preliminary identification result provides important background context for subsequent fine-grained identification based on network traffic characteristics, effectively narrowing the search scope for precise identification and improving overall identification efficiency.

[0081] Step S3320: Analyze the network traffic data generated by the device node during its historical operation to determine the corresponding network traffic characteristics, including traffic size, periodicity, data packet characteristics, and target service of communication. After obtaining preliminary identification results based on device identifiers, we further extract deeper behavioral features by analyzing the historical network traffic data of device nodes to compensate for the shortcomings of simple hardware device identifier identification and provide key behavioral evidence for the accurate determination of subsequent device types.

[0082] Network traffic characteristics refer to the quantifiable and distinguishable patterned characteristics of network communication data generated by devices during their historical operation. These characteristics are closely related to the functional nature of device nodes.

[0083] In practice, relevant communication records of target device nodes are extracted from the historical traffic logs of the smart home network. The analysis process includes the extraction and quantification of multi-dimensional features of the traffic data. Network traffic features include, but are not limited to: traffic volume characteristics, i.e., the data throughput of device nodes per unit time, for example, smart cameras generate continuous large volumes of uplink data, while sensors typically only generate intermittent small data packets; periodic characteristics, analyzing the regularity of device node communication behavior, for example, smart curtain motors send status updates at specific times, while the communication of smart light bulbs is more random; data packet characteristics, including data packet length distribution, protocol type, and load characteristics, for example, video streaming devices typically use the UDP protocol and have larger packet lengths, while control devices mostly use the TCP protocol and have smaller packet lengths; and target service characteristics of the communication, resolving the server IP or domain name to which the device is connected, for example, the communication mode of connecting to a well-known cloud service platform or a specific vendor's private cloud is highly identifiable.

[0084] Various techniques can be employed to extract these features. For example, deep packet inspection (DPI) technology can be used to analyze the protocol headers and payloads of network packets; traffic statistics methods can be used to calculate metrics such as the number of bytes, packets, and connection frequency within a specific time window; and time-series analysis methods can be used to identify periodic patterns and peak characteristics of communication behavior. All extracted features are quantified into feature vectors, forming a digital profile of the device's network behavior.

[0085] Step S3330: Refine the basic type information in the preliminary identification result based on the network traffic characteristics to obtain a more specific device type for the corresponding device node; After feature processing through the above process, the final output is a set of structured and computable network traffic feature data. These features, combined with the preliminary identification results, can be used to finely identify the device type of device nodes.

[0086] In practice, the initial identification results (such as "a smart lighting device from a certain manufacturer") are cross-validated and logically inferred with the extracted network traffic characteristics (such as traffic patterns, communication targets, etc.). The basic principle is that specific types of devices exhibit unique and stable communication behavior patterns on the network. By matching the observed actual behavior with predefined device behavior templates, fine-grained classification can be achieved.

[0087] The refinement process includes, but is not limited to, the following specific embodiments: If the initial identification result is "a certain brand of environmental sensor", but its network traffic characteristics show continuous high-definition video streaming behavior, and its communication target is a cloud video storage server, then its basic type can be refined to "smart camera"; conversely, if a device is initially identified as a "network media device", but its traffic characteristics are low frequency, small data packets and have strict periodicity, and it communicates with an environmental data platform, then it can be refined to "environmental sensor".

[0088] To achieve this matching, a device behavior knowledge base can be constructed. This base stores typical network traffic feature templates corresponding to various specific device types. The refinement process involves calculating the similarity between the feature vector extracted from the target device and the templates in the base, and selecting the device type corresponding to the template with the highest similarity as the final determination result. The matching algorithm can adopt rule-based conditional judgment, such as "if the device communicates with a specific cloud domain name and the average uplink traffic is greater than the threshold T, then it is determined to be a camera"; or it can adopt a machine learning-based classification model, inputting the feature vector into a pre-trained classifier (such as a support vector machine or decision tree) to directly output the specific device type label.

[0089] Thus, the identification of device nodes has been refined from vague broad categories such as "smart home appliances" to specific models or functional categories such as "a certain brand of smart socket Zigbee version" or "a smart color light that supports color adjustment," completing the identification process from coarse-grained to specific device types.

[0090] Step S3340: Determine the set of controllable function items for the corresponding device node according to the device type.

[0091] Based on the final determined device type, such as "Brand X Smart Colored Light Pro," further queries are performed in the device capability library to retrieve the corresponding records. The device capability library can be constructed in ways including, but not limited to, the following embodiments: integrating the function set defined in the official application programming interface (API) documentation released by the device manufacturer; summarizing the function list by analyzing the communication protocols of the official device application; or a publicly available device capability database maintained by a user community through crowdsourcing. Each record in the device capability library clearly specifies all control commands and corresponding parameter ranges that the device type can respond to, where each control command corresponds to a controllable function item.

[0092] The query results will show a set of controllable functions generated by the device node. This set is a complete enumeration of all operable functions of the device. Each function is clearly defined by its corresponding control commands and parameter ranges, specifying its control semantics, parameter type, and value range. For example, for a device node identified as a "smart colored light," its set of controllable functions might include: on / off status control (parameter: on / off), brightness adjustment (parameter: integer value from 0-100%), color temperature adjustment (parameter: integer value from 2700K-6500K), and color control (parameter: RGB triplet or HSV color space value). For a device node identified as a "smart air conditioner," its set might include: power switch, mode switching (cooling / heating / fan / dehumidification), target temperature setting (parameter: 16℃-30℃), and fan speed adjustment (parameter: low / medium / high / auto), among other functions.

[0093] The determination of the set of controllable functional items provides each device node with a clear and structured description of its operational capabilities. This set serves as the direct data source for generating specific operational controls (such as buttons, sliders, and selectors) in the next interface rendering stage, ensuring that every control presented in the user interface accurately corresponds to the actual control functions supported by the device, thus achieving a closed loop from device identification to function visualization.

[0094] The above embodiments have achieved a fundamental technological breakthrough in intelligent device node identification by integrating hardware identity authentication of device identifiers with behavioral fingerprint analysis of network traffic characteristics. This completely changes the limitations of traditional solutions that rely solely on a single MAC address or manufacturer information for coarse-grained classification. By deeply analyzing the historical communication patterns of devices (such as traffic cycles, data packet characteristics, and service connection features), a precise profile of the device's functional essence is achieved. This dual verification mechanism, which combines hardware identity and behavioral characteristics, can not only effectively identify privacy-protected devices with randomized MAC addresses, but also refine the device type from the broad category of "smart home appliances" to the specific category of "a smart ambient light from a certain brand that supports HSV color adjustment." This allows for the dynamic generation of a highly accurate set of controllable functional items for each device node, providing core technical support for building a truly plug-and-play, functionally adaptive intelligent centralized control interface.

[0095] Based on any embodiment of the method in this application, after generating the centralized control interface, the method includes: Step S4100: Collect multi-dimensional operational data of the smart home network from the current device node, including the wireless signal strength of each device node, network performance indicators between the device node and the gateway and other device nodes, and its historical network traffic characteristics. The current device node can proactively initiate the collection of various real-time and historical data generated during the operation of the smart home network that can reflect the health status of the network. These data are then categorized according to different dimensions to form multi-dimensional operational data.

[0096] In one embodiment, the collected multi-dimensional operational data covers several key aspects: physical layer connection quality, network layer transmission performance, and application layer traffic patterns. Specifically, this includes wireless signal strength data of each device node, such as by periodically sending probe requests to each device and recording the Received Signal Strength Indicator (RSSI) value of its response signal, or by directly obtaining the link quality indicators actively reported by the device to the access point (AP); network performance indicators between the device and the gateway and other device nodes, such as measuring the round-trip delay (RTT) and packet loss rate between the device and the gateway through ICMP ping, or measuring the throughput and jitter of communication between devices through tools such as iPerf; and historical network traffic characteristics of each device node, which are extracted from long-term operational logs, including but not limited to traffic volume (such as daily average uplink and downlink data volume), periodic patterns (such as the period of time for smart cameras to upload video streams), packet characteristics (such as protocol type, average packet length, and flag distribution), and network traffic characteristics of the target service of communication (such as the IP address or domain name connected to a specific cloud service).

[0097] Data acquisition can be implemented in several ways, including but not limited to the following specific examples: obtaining interface traffic statistics and error counts from network devices (such as routers and switches) via Simple Network Management Protocol (SNMP) polling; mirroring and analyzing raw traffic within the local area network to extract Deep Packet Inspection (DPI) features using a packet capture agent installed on the current device node; or directly calling the network status application programming interface (API) provided by the device operating system to read real-time connectivity metrics. All collected data is timestamped and stored in a structured manner, forming a complete snapshot of the network's operational status, providing accurate and rich input features for subsequent fault diagnosis models.

[0098] Step S4200: Input the multi-dimensional operation data into the pre-trained fault diagnosis model, and the fault diagnosis model outputs the fault type and its confidence level for the device node, the link between device nodes or the global state of the network. After successfully collecting and structuring multi-dimensional operational data, a pre-trained fault diagnosis model can be used to intelligently analyze this data, enabling accurate diagnosis and fault location of the network's health status. This fault diagnosis model employs a supervised learning-trained machine learning model, capable of extracting feature patterns from complex multi-dimensional data and outputting specific fault diagnosis conclusions and their confidence assessments.

[0099] The fault diagnosis model is built upon training with historical fault data. Specifically, the training data comes from labeled datasets accumulated during the long-term operation of the smart home network. This dataset contains multi-dimensional operational data samples under various known fault states and their corresponding real fault labels. Model structure choices include, but are not limited to, the following embodiments: using ensemble learning models based on gradient boosting decision trees (such as XGBoost or LightGBM) to process structured feature data; or using deep neural networks (such as multilayer perceptrons, MLP) to learn complex nonlinear feature relationships; for data with temporal characteristics, temporal convolutional networks (TCN) or long short-term memory networks (LSTM) can also be used to capture temporal dependencies.

[0100] Before inputting the collected real-time multi-dimensional runtime data into the pre-trained model, necessary feature preprocessing and vectorization are required to ensure it meets the model's input requirements. Preprocessing includes, but is not limited to: standardizing and scaling continuous numerical features, one-hot encoding categorical features, and sliding window segmentation and feature extraction for temporal features. Finally, all features are combined into a fixed-dimensional feature vector, which serves as the model's input.

[0101] The model inference process involves calculating the input feature vector, and the final output layer generates a prediction of the potential fault type. This output typically includes two key components: a possible fault type classification and a confidence score for that classification. The fault type classification system is predefined before training, covering typical faults at three levels: device nodes, inter-device links, and the network as a whole. Examples include, but are not limited to, specific fault types such as "device node hardware failure," "wireless signal interference," "channel congestion," "IP address conflict," and "gateway overload." The confidence score is a probability value between 0 and 1, reflecting the model's confidence in the fault diagnosis result; for example, the confidence score for the "wireless signal interference" fault type is 0.92.

[0102] The application of the model includes, but is not limited to, the following specific embodiments: inputting real-time feature vectors into the model at once for offline diagnosis; or building an online inference service to continuously receive real-time data streams and periodically output diagnostic results to achieve near real-time network health monitoring.

[0103] Through the above process, the fault diagnosis model intelligently transforms multi-dimensional operational data from raw data into semantic diagnostic results, providing clear basis and location information for accurately rendering fault effects in the visualization interface.

[0104] Step S4300: Based on the fault type and its corresponding device node or link location, render the corresponding fault effect image on the environmental space map of the centralized control interface, wherein the image effect of the fault effect image is controlled by the confidence level corresponding to the fault type.

[0105] After obtaining the fault type and its confidence level output by the fault diagnosis model, these abstract diagnostic conclusions can be transformed into visual feedback that users can intuitively perceive on the centralized control interface, thereby realizing the visual location and status perception of the fault. Based on the fault type specified in the diagnostic results and its associated specific device node or link location information, this process dynamically renders a matching fault effect image at the corresponding spatial location on the environmental spatial map.

[0106] The design and rendering strategy of fault effect images are closely tied to the fault type. A fault effect resource library can be pre-configured, storing graphical representation templates corresponding to various fault types. The rendering process includes, but is not limited to, the following specific examples: For a diagnosed "wireless signal interference" fault, if its associated location is a wireless access point (AP), a dynamic, semi-transparent icon with interference ripple diffusion effect is overlaid and rendered at the coordinates of the AP in the environmental spatial map; for a diagnosed "device node hardware fault," a flashing red exclamation mark icon is rendered at the coordinates of the corresponding device node; for a diagnosed "network bandwidth congestion" fault, if it is associated with a certain link (such as the path from the device to the gateway), a highlighted color band is rendered on the visual connection line of that link, and the width or color saturation of the color band can be positively correlated with the degree of congestion.

[0107] The visual intensity of the fault effect image can be directly controlled by the diagnostic confidence level. Confidence level, as a quantitative indicator, is used to control the salience and warning level of the rendering effect. Control methods include, but are not limited to, the following specific examples: when the confidence level is high (e.g., greater than 0.8), a more prominent visual effect is used, such as a higher flashing frequency, a more saturated warning color (e.g., dark red), or a larger icon size; when the confidence level is moderate (e.g., between 0.5 and 0.8), a relatively mild visual effect is used, such as a constantly lit yellow icon; when the confidence level is low (e.g., below 0.5), the fault effect may not be rendered, or only a semi-transparent gray icon may be used for a slight prompt to avoid unnecessary interference to the user. This confidence-based dynamic rendering mechanism ensures the accuracy of interface feedback and the rationality of the user experience.

[0108] Ultimately, all rendered fault effect images are overlaid on the environmental space map along with the original device control entry icons, forming a complete intelligent operation and maintenance view that integrates device control and status monitoring functions. Through this interface, users can clearly grasp the health status of the entire smart home network, accurately locate fault points, and quickly take corresponding maintenance measures based on visual prompts.

[0109] The closed-loop technical framework provided in the above embodiments has achieved significant technical advantages in intelligent diagnosis and interaction of network device node faults. It completely overturns the traditional fault diagnosis mode that relies on command-line tools or decentralized log analysis. By integrating multi-dimensional operational data such as physical layer signal strength, network layer performance indicators, and application layer traffic characteristics, it provides panoramic data support for fault diagnosis. The pre-trained machine learning diagnostic model realizes intelligent mapping from massive data to accurate fault types and confidence levels, and has the fundamental ability to explain complex network anomalies. In particular, it innovatively binds abstract diagnostic results with concrete spatial locations. Through dynamic visualization effects controlled by confidence levels, it achieves accurate fault location and status perception on the environmental spatial map. Finally, it constructs a new paradigm of intelligent operation and maintenance interaction that integrates real-time monitoring, intelligent diagnosis, intuitive presentation, and precise intervention, greatly reducing the technical threshold for users to understand and handle network faults.

[0110] Based on any embodiment of the method in this application, after generating the centralized control interface, the method includes: Step S6100: Convert the environmental space map into a virtual three-dimensional space model with a transparent wall effect, and adjust the altitude of the operation entry icon in the three-dimensional space model according to the device type of each device node. After generating a centralized control interface, the user's spatial interaction experience can be further enhanced. The two-dimensional environmental space map can be converted into a more immersive and intuitive virtual three-dimensional space model to upgrade the visual presentation. In particular, appropriate height coordinates can be assigned to the device nodes in three-dimensional space according to their physical characteristics, so that the virtual scene closely matches the real home environment.

[0111] The environmental spatial map contains the boundary coordinates of fixed structures such as walls, doors, and windows within the home environment. Using computer graphics technology, this two-dimensional contour information is stretched into a three-dimensional wall model with thickness. A specific material shader is applied to set the three-dimensional wall model to a transparent wall effect; this shader can achieve the light transmission effect by adjusting the material's alpha channel value.

[0112] After completing the basic 3D scene construction, the altitude of the operation entry icon in the 3D spatial model can be adjusted according to the device type of each device node. The altitude setting follows the typical installation height of the device in the real world, and the mapping strategy includes, but is not limited to, the following specific embodiments: For ceiling-mounted devices such as ceiling lights and air conditioner indoor units, the altitude of their icons is set to a height close to the room ceiling; for wall-mounted devices such as smart TVs and wall switches, their icon height is set to the eye level range of an average person standing; for floor-mounted devices such as robot vacuum cleaners and smart sockets, their icon height is set to a height close to the ground plane. This height mapping relationship can be obtained by looking up a preset device type-height lookup table. For example, the table defines a height value of 3.0 meters for the "ceiling light" type, 1.2 meters for the "TV" type, and 0.1 meters for the "robot vacuum cleaner" type.

[0113] After the above transformations and adjustments, a virtual 3D space model is finally generated that faithfully reflects the physical structure of the home, conforms to the actual installation height of equipment, and features transparent walls. This model provides users with a highly intuitive and freely explorable interactive environment that can be used for subsequent 3D interactions.

[0114] Step S6200: Display the virtual three-dimensional space model to the user, wherein each device node is placed in the corresponding position in the model according to its calculated spatial position and estimated altitude; When displaying a virtual 3D space model to users, a graphics rendering engine converts the 3D model data into a user-visual interactive interface. Display methods include, but are not limited to, the following specific embodiments: Rendering the entire home's 3D scene using perspective projection in a full-screen window of a smart control screen or mobile terminal application; users can freely change their viewing angle using touch gestures (such as swiping, zooming, and rotating) to achieve virtual roaming; or rendering a local 3D scene of a room from a fixed third-person perspective; users can switch between different rooms by clicking on the floor plan. During the rendering process, the operation entry icons of each device node are precisely placed in their corresponding positions in 3D space based on their calculated 2D spatial coordinates and estimated altitude. For example, the ceiling light icon floats below the ceiling, the TV icon is affixed to the center of the wall, and the robot vacuum cleaner icon is placed on the floor surface, forming a visual layout highly consistent with the real home environment.

[0115] Step S6300: In response to the user's touch selection operation on the control entry icon of any device node in the three-dimensional space model, expand the corresponding floating function window, which displays the controllable function items corresponding to the device node. When a user selects the control entry icon of any device node in three-dimensional space via touch operation, the system responds instantly to this touch selection operation. The response method includes, but is not limited to, the following specific embodiments: when the three-dimensional collision detection result of the touch point and an icon shows an intersection, the icon is determined to be selected; subsequently, a floating function window is generated near the current touch position. This window can be presented as a non-transparent or semi-transparent panel, and its content dynamically loads and displays all controllable functions corresponding to the device node. The presentation forms of controllable functions include, but are not limited to: organizing functions into an array of buttons with icons, such as presenting "on / off," "brightness adjustment," "color temperature adjustment," and "color change" function buttons for a "smart color light"; or organizing functions into a finely detailed control panel with sliders and values, such as presenting "temperature setting slider," "fan speed selector," and "mode switching switch" controls for an "air conditioner."

[0116] Step S6400: Respond to the user's touch event on any controllable function item in the floating function window, generate the corresponding device control command, and send the control command to the corresponding device node.

[0117] When a user touches any controllable function item in the floating function window, the corresponding touch event is responded to, thus enabling actual control of the corresponding device node. An example of the response process is as follows: If the user clicks the "Switch" button, a corresponding device control command is generated. This command follows the communication protocol disclosed by the device manufacturer, such as encapsulating it in JSON format as {"device_id":"light_001", "command":"turn_on"}.

[0118] If the user drags the "brightness adjustment" slider, a control command containing brightness parameter values ​​will be generated in real time, such as {"device_id":"light_001", "command":"set_brightness", "value":80}.

[0119] After the control command is generated, it is sent to the corresponding target device node through the communication module of the smart home network connected to the device node. The target device node receives and parses the command and executes the corresponding operation, thereby achieving the user's ultimate goal of remotely controlling physical devices through a three-dimensional spatial interface.

[0120] The above embodiments achieve further technical advantages in smart home control and interaction by constructing an immersive three-dimensional interactive environment. Replacing the traditional list-style or planar two-dimensional interactive mode, it innovatively maps the device control interface with the physical space of the home in three dimensions. Through the transparent wall effect and the elevation adjustment of device icons based on the actual installation height, users can obtain an intuitive visual perception that almost perfectly matches the real space. Users can freely roam in the three-dimensional model and directly select device icons in the space. It responds in real time through precise collision detection and dynamically generates floating function windows to present context-related controllable function items. Finally, touch operation is seamlessly converted into precise device control commands, realizing a natural interactive experience of what you see is what you get and what you point to is controllable. This greatly reduces the user's cognitive load and improves the accuracy and immersion of control.

[0121] Please see Figure 3 This invention provides a multi-node control interface construction device to meet one of the purposes of this application. It is a functional embodiment of the multi-node control interface construction method of this application. The device includes a map anchoring module 3100, a node calculation module 3200, a function configuration module 3300, and an interface construction module 3400. The map anchoring module 3100 is configured to obtain an environmental spatial map generated by a specific device node from the current device node in the smart home network, and establish a spatial positional relationship between the current device node and the specific device node in the environmental spatial map. The node calculation module 3200 is configured to perform autonomous interaction between multiple device nodes in the smart home network. The measured received signal strength is used to calculate the spatial position of each device node in the environmental spatial map based on the spatial position relationship. The function configuration module 3300 is configured to identify the device type and controllable function items of each device node in the smart home network other than the current device node, based on the device identifier carried in the received signal strength and its historical network traffic characteristics. The interface construction module 3400 is configured to render the control entry icon of the corresponding device node at the corresponding spatial position in the environmental spatial map, associate the control entry icon with the operation controls corresponding to the device type and controllable function items of the corresponding device node, and generate a centralized control interface.

[0122] Based on any embodiment of the device in this application, the node calculation module 3200 includes: an autonomous measurement module, configured to control the plurality of device nodes to perform wireless signal strength measurements between each other, and obtain the received signal strength from itself to the other device nodes as determined by each device node; a distance estimation module, configured to convert the received signal strength into relative distance estimates between device nodes according to a predetermined path loss model; and a location determination module, configured to use the known spatial locations of the current device node and the specific device node in the environmental spatial map as a fixed reference, and constrained by the relative distance estimates between all device nodes, to calculate the spatial locations of the remaining device nodes other than the current device node in the environmental spatial map.

[0123] Based on any embodiment of the device in this application, following the location determination module, the device further includes: a path determination module, configured to determine the signal propagation path of each pair of device nodes in the environmental spatial map based on the calculated spatial location of each device node, wherein the path loss model initially sets a path loss index for each device node when calculating the spatial location; a loss update module, configured to determine the occlusion type of each pair of device nodes on its signal propagation path based on the spatial structure information of the environmental spatial map, and update the path loss index of the path loss model for each pair of device nodes according to the occlusion type; and an iterative optimization module, configured to use the updated path loss index to reconvert the received signal strength into a relative distance estimate and perform the calculation steps again to obtain a more accurate spatial location of the device nodes.

[0124] Based on any embodiment of the device in this application, the position determination module includes: a node graph construction module, configured to treat each device node as a vertex to be optimized in a graph optimization model, establish an edge for each pair of device nodes with relative distance estimates, and use the relative distance estimates as observation constraints for the distance of the edge; a known anchoring module, configured to fix the coordinates of the vertices corresponding to the current device node and the specific device node to their known spatial positions in the environmental spatial map; and an observation optimization module, configured to solve the graph optimization model with the objective of minimizing the overall error between the relative distance estimates in all observation constraints and the Euclidean distance calculated from the vertex coordinates, to obtain the optimal spatial positions of the remaining device nodes.

[0125] Based on any embodiment of the device in this application, the functional configuration module 3300 includes: a preliminary identification module, configured to query a preset device information database based on the device identifier carried in the received signal strength to obtain the manufacturer and basic type information of the corresponding device node, forming a preliminary identification result; a traffic analysis module, configured to analyze the network traffic data generated by the device node during historical operation to determine the corresponding network traffic characteristics, the network traffic characteristics including traffic size, periodicity, data packet characteristics, and target service of communication; a type refinement module, configured to refine the basic type information in the preliminary identification result according to the network traffic characteristics to obtain a more specific device type of the corresponding device node; and a function determination module, configured to determine the set of controllable function items of the corresponding device node according to the device type.

[0126] Based on any embodiment of the device in this application, following the interface construction module 3400, the device further includes: a data acquisition module, configured to collect multi-dimensional operational data of the smart home network from the current device node, including the wireless signal strength of each device node, network performance indicators between the device node and the gateway and other device nodes, and its historical network traffic characteristics; a fault analysis module, configured to input the multi-dimensional operational data into a pre-trained fault diagnosis model, and output the fault type and its confidence level for the device node, the link between device nodes, or the global state of the network; and a fault rendering module, configured to render a corresponding fault effect image on the environmental space map of the centralized control interface according to the fault type and its corresponding device node or link location, wherein the image effect of the fault effect image is controlled by the confidence level corresponding to the fault type.

[0127] Based on any embodiment of the device in this application, following the interface construction module 3400, the device further includes: a three-dimensional conversion module, configured to convert the environmental space map into a virtual three-dimensional space model with a transparent wall effect, and adjust the altitude of the operation entry icon in the three-dimensional space model according to the device type of each device node; a model display module, configured to display the virtual three-dimensional space model to the user, wherein each device node is placed in the corresponding position in the model according to its calculated spatial position and estimated altitude; an interaction response module, configured to respond to the user's touch selection operation on the operation entry icon of any device node in the three-dimensional space model, expand the corresponding floating function window, and present the controllable function item corresponding to the device node; and an instruction control module, configured to respond to the user's touch event on any controllable function item in the floating function window, generate the corresponding device control instruction, and send the control instruction to the corresponding device node.

[0128] To address the aforementioned technical problems, embodiments of this application also provide a computer device. For example... Figure 4 The diagram shows the internal structure of a computer device. This computer device includes a processor, a computer-readable storage medium, a memory, a network interface, and various communication components connected via a system bus. The computer-readable storage medium stores an operating system, a database, and computer-readable instructions. The database may store control information sequences. When the computer-readable instructions are executed by the processor, they enable the processor to implement a multi-node control interface construction method. The processor of this computer device provides computing and control capabilities, supporting the operation of the entire computer device. The memory of this computer device may store computer-readable instructions. When these computer-readable instructions are executed by the processor, they enable the processor to execute the multi-node control interface construction method of this application. The network interface of this computer device is used for communication with a terminal. Those skilled in the art will understand that… Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0129] In this embodiment, the processor is used to execute... Figure 3 The system defines the specific functions of each module and its sub-modules. The memory stores the program code and various data required to execute these modules or sub-modules. The network interface is used for data transmission between the user terminal and the server. In this embodiment, the memory stores the program code and data required to execute all modules / sub-modules in the multi-node control interface construction device of this application. The server can call the server's program code and data to execute the functions of all sub-modules.

[0130] This application also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the multi-node control interface construction method of any embodiment of this application.

[0131] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0132] Those skilled in the art will understand that the steps, measures, and solutions in the various operations, methods, and processes discussed in this application can be alternated, modified, combined, or deleted. Furthermore, other steps, measures, and solutions in the various operations, methods, and processes discussed in this application can also be alternated, modified, rearranged, decomposed, combined, or deleted. Furthermore, steps, measures, and solutions in the prior art that are similar to those in the open-source operations, methods, and processes of this application can also be alternated, modified, rearranged, decomposed, combined, or deleted.

[0133] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for constructing a multi-node control interface, characterized in that, include: The current device node in the smart home network obtains an environmental spatial map generated by a specific device node, and establishes a spatial positional relationship between the current device node and the specific device node in the environmental spatial map. Based on the received signal strength autonomously measured between multiple device nodes in the smart home network, the spatial position of each device node in the environmental spatial map is calculated with reference to the spatial position relationship. For each device node in the smart home network other than the current device node, its device type and controllable functions are identified based on the device identifier carried in its received signal strength and its historical network traffic characteristics. The control entry icon of the corresponding device node is rendered at the corresponding spatial location on the environmental spatial map. The control entry icon is associated with the operation control corresponding to the device type and controllable function item of the corresponding device node to generate a centralized control interface.

2. The multi-node control interface construction method according to claim 1, characterized in that, Based on the received signal strength autonomously measured between multiple device nodes in the smart home network, and referring to the spatial positional relationships, the spatial position of each device node in the environmental spatial map is calculated, including: Control the multiple device nodes to perform wireless signal strength measurements between each other, and obtain the received signal strength from itself to the other device nodes as determined by each device node. Based on a predetermined path loss model, the received signal strength is converted into an estimated relative distance between device nodes; Using the known spatial positions of the current device node and the specific device node in the environmental spatial map as fixed benchmarks, and constrained by the estimated relative distance between all device nodes, the spatial positions of all other device nodes besides the current device node in the environmental spatial map are calculated.

3. The multi-node control interface construction method according to claim 2, characterized in that, After calculating the spatial positions of all device nodes other than the current device node in the environmental spatial map, the process includes: The signal propagation path of each pair of device nodes in the environmental spatial map is determined based on the spatial location of each device node obtained by the solution. When solving the spatial location, the path loss model is to initially set the path loss index for each device node. Based on the spatial structure information of the environmental spatial map, the occlusion type of each pair of device nodes on its signal propagation path is determined, and the path loss index of the path loss model is updated in a personalized manner for each pair of device nodes according to the occlusion type. Using the updated path loss index, the received signal strength is reconverted into a relative distance estimate, and the solution step is performed again to obtain a more accurate spatial location of the device nodes.

4. The multi-node control interface construction method according to claim 2, characterized in that, Using the known spatial positions of the current device node and the specific device node in the environmental spatial map as fixed references, and constrained by the estimated relative distances between all device nodes, the spatial positions of all other device nodes besides the current device node in the environmental spatial map are calculated, including: Each device node is treated as a vertex to be optimized in the graph optimization model. An edge is established for each pair of device nodes with a relative distance estimate, and the relative distance estimate is used as the observation constraint for the distance of the edge. The coordinates of the vertices corresponding to the current device node and the specific device node are fixed to their known spatial positions in the environmental space map; With the objective of minimizing the overall error between the relative distance estimates in all observation constraints and the Euclidean distance calculated from the vertex coordinates, the graph optimization model is solved to obtain the optimal spatial positions of the remaining device nodes.

5. The method for constructing a multi-node control interface according to claim 1, characterized in that, For each device node in the smart home network other than the current device node, its device type and controllable functions are identified based on the device identifier carried in its received signal strength and its historical network traffic characteristics, including: Based on the device identifier carried in the received signal strength, a pre-set device information database is queried to obtain the manufacturer and basic type information of the corresponding device node, thus forming a preliminary identification result. Analyze the network traffic data generated by the device node during its historical operation to determine the corresponding network traffic characteristics, including traffic volume, periodicity, data packet characteristics, and the target service of communication; Based on the network traffic characteristics, the basic type information in the preliminary identification results is refined to obtain a more specific device type for the corresponding device node; The set of controllable functional items for the corresponding device node is determined based on the device type.

6. The method for constructing a multi-node control interface according to any one of claims 1 to 5, characterized in that, After generating the centralized control interface, it includes: The smart home network collects multi-dimensional operational data from the current device nodes, including the wireless signal strength of each device node, network performance indicators between the device node and the gateway and other device nodes, and its historical network traffic characteristics. The multi-dimensional operational data is input into a pre-trained fault diagnosis model, which outputs the fault type and its confidence level for the device node, the link between device nodes, or the global state of the network. Based on the fault type and its corresponding device node or link location, a corresponding fault effect image is rendered on the environmental space map of the centralized control interface, wherein the image effect of the fault effect image is controlled by the confidence level corresponding to the fault type.

7. The method for constructing a multi-node control interface according to any one of claims 1 to 5, characterized in that, After generating the centralized control interface, it includes: The environmental space map is converted into a virtual three-dimensional space model with a transparent wall effect. The altitude of the operation entry icon in the three-dimensional space model is adjusted according to the device type of each device node. The virtual three-dimensional space model is displayed to the user, in which each device node is placed in the corresponding position in the model according to its calculated spatial position and estimated altitude; In response to the user's touch selection operation on the control entry icon of any device node in the three-dimensional space model, the corresponding floating function window is expanded, which displays the controllable function items corresponding to the device node; In response to a user's touch event on any controllable function item in the floating function window, a corresponding device control command is generated and sent to the corresponding device node.

8. A multi-node control interface construction device, characterized in that, include: The map anchoring module is configured to obtain an environmental spatial map generated by a specific device node from the current device node in the smart home network, and establish a spatial positional relationship between the current device node and the specific device node in the environmental spatial map. The node calculation module is configured to calculate the spatial position of each device node in the environmental spatial map based on the received signal strength autonomously measured between multiple device nodes in the smart home network and with reference to the spatial position relationship. The function configuration module is configured to identify the device type and controllable function items of each device node in the smart home network, except for the current device node, based on the device identifier carried in the received signal strength and the characteristics of its historical network traffic. The interface construction module is configured to render the control entry icon of the corresponding device node at the corresponding spatial location on the environmental spatial map, associate the control entry icon with the operation controls corresponding to the device type and controllable function items of the corresponding device node, and generate a centralized control interface.

9. A computer device comprising a processor and a memory, characterized in that, The processor invokes and runs a computer program in the memory to perform the steps of the multi-node control interface construction method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores, in the form of computer-readable instructions, a computer program implemented according to any one of claims 1 to 7, which, when invoked by a computer, performs the steps included in the corresponding method.

Images