A regionally modular measurement method of design intent

Abstract

This invention relates to the field of intelligent measurement technology and provides a modular measurement method for areas with design intent. The method includes a user terminal and a measurement terminal, the measurement terminal being equipped with a VR module. The method obtains measurement instructions containing user intent through the user terminal and determines spatial indicators. Based on the spatial indicators, it deploys measurement requirements to achieve the design needs and determines the allowable deviation range of the measurement requirements. When the measurement terminal receives a measurement requirement, it performs measurement on each modular spatial area, generates a VR rendered comparison image, and determines whether the measurement result of each measurement requirement is within the allowable deviation range. If a measurement result is outside the allowable deviation range, or if different modular spatial areas overlap in measurement areas, it generates an overlap area identifier within the target design scene. If a measurement result is outside the allowable deviation range, but different modular spatial areas do not overlap in measurement areas, it outputs requirement anomaly information.

Description

Technical Field

[0001] This invention relates to the field of intelligent measurement technology, and in particular to a modular measurement method for a specific area. Background Technology

[0002] With the increasing complexity and precision in fields such as architectural design, industrial manufacturing, and smart cockpits, verifying the consistency between design intent and physical space has become a crucial step in improving product quality. Traditional measurement methods often rely on manually breaking down design requirements and statically deploying measurement processes.

[0003] Therefore, existing interior design is mainly based on the analysis of designers. Although ordinary users can use VR modeling software to input architectural drawings and automatically adapt to different design styles, it can only provide a general decoration style plan. In the actual decoration design process, there are still measurement deviations.

[0004] During the interior design process, designers primarily rely on manual measurements. More advanced designs may use infrared or camera measurements. However, these measurements only provide approximate results and cannot be tailored to the user's needs. For example, in the design of an open kitchen, the countertop height and cabinet parallelism are mainly based on the measurement results to design the corresponding functional requirements. However, because it is a non-standard scenario, the countertop and cabinet measurements are separated, and the kitchen countertop and cabinets are designed separately. When finally assembling them, there may be slight overlap areas between the two, which can only be adjusted manually by the construction workers, which is time-consuming and labor-intensive. Summary of the Invention

[0005] This application proposes a modular measurement method for design intent regions, which improves the rate of design intent transformation and enhances the adaptability to dynamic environmental changes during the measurement process through modular measurement and design requirement transformation. Combined with VR interactive functions, it enables quantitative detection of topological conflicts in multi-module intersection areas.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] In a first aspect, this application proposes a modular measurement method for a region, including a user terminal and a measurement terminal, wherein the measurement terminal is equipped with a VR module, and the method includes:

[0008] The measurement instructions from the user for the target design scenario are obtained through the user terminal to determine the spatial indicators; wherein, the measurement instructions are the design measurement requirements of N modular spatial areas corresponding to N design requirements determined after the user inputs the design intent of the terminal device.

[0009] Based on spatial indicators, deploy each modular spatial area to meet multiple measurement requirements corresponding to the design needs, and determine the allowable deviation range for each measurement requirement;

[0010] When the measurement terminal receives a measurement request, it performs a measurement on each modular space area, generates a VR rendering comparison image, and determines whether the measurement result of each measurement request is within the allowable deviation range.

[0011] Among them, when the measurement results are outside the allowable deviation range and different modular spatial areas overlap the measurement area, an overlap area identifier is generated in the target design scenario;

[0012] When a measurement result is outside the allowable deviation range and there is no overlapping measurement area between different modular spatial areas, an abnormal demand information is output.

[0013] In conjunction with the first aspect, the determination of spatial indicators includes:

[0014] By using the semantic parsing model of design intent in voice chain, we can identify the design intent text in the user terminal and extract the design functional requirements.

[0015] Based on the design functional requirements, determine the design constraints and the key spatial attributes under the design constraints;

[0016] Based on key spatial attributes, match the corresponding set of physical measurement parameters for the functional design from the preset knowledge base;

[0017] Based on the set of physical measurement parameters, determine the measurement requirements list for each modular spatial region, as well as the spatial indicators corresponding to each design functional requirement in the measurement requirements list.

[0018] In conjunction with the first aspect, the allowable deviation range is the deviation range that can be dynamically adjusted for each functional requirement within the modular space area in the target design scenario; wherein, the deviation range is determined by predicting the influence coefficient of environmental parameters on the measurement results through a regression model trained on historical measurement data, and the environmental parameters are temperature, humidity and light intensity within the target design scenario.

[0019] In conjunction with the first aspect, the cross-coverage area identifier is a display identifier indicating that different modular spatial areas with different design requirements overlap within the target design scenario;

[0020] Among them, the modular space region is associated with the directed acyclic graph deployed within the target design scenario. The nodes of the directed acyclic graph represent the regions of design requirements, and the deviation interval represents the physical overlap relationship of different modular space regions through historical edges.

[0021] Identify and display the location of the overlapping region corresponding to the label in the directed acyclic graph:

[0022] If a child node is an intersection of multiple parent nodes, it is marked as a topological conflict zone and the conflict intensity value is calculated.

[0023] If it is an isolated node, trigger an exception message.

[0024] In conjunction with the first aspect, the marking of the topological conflict zone includes:

[0025] Calculate the error propagation coefficient of the conflict zone to adjacent modules;

[0026] If the propagation coefficient exceeds the threshold, a virtual isolation node is inserted into the DAG to block the error propagation path, and the measurement requirements of the area associated with the isolation node are redeployed.

[0027] In conjunction with the first aspect, when the cross-coverage area identifier is generated, upon receiving the second instruction, a shared virtual space is constructed, and gesture annotations are performed at the boundaries of the modular space areas; wherein, the second instruction is a shared virtual space construction instruction for no less than two users, the shared virtual space is a VR space of the target design area, and gesture annotations are configured at the boundaries of different modular space areas of the shared virtual space;

[0028] When there is a conflict in gesture annotation, the overlapping area is automatically calculated, and the conflict focus with the overlapping area as the geometric center is determined. The overlapping image of the measurement data is then projected at the conflict focus.

[0029] Based on the overlapping images, determine the modification strategy for the design requirements.

[0030] In conjunction with the first aspect, the measurement performed on each modular spatial region includes:

[0031] Based on the geometric location of the modular spatial region and the priority of measurement requirements, a path planning algorithm is invoked to generate the optimal measurement sequence.

[0032] The system monitors the movement trajectory of the measurement terminal in real time. If the deviation from the planned path exceeds the threshold, the system dynamically replans and skips areas that have already met the standards.

[0033] In conjunction with the first aspect, determining whether the measurement result is within the allowable deviation range includes:

[0034] When overlapping coverage areas exist, raw point cloud data is encrypted and obtained from multiple associated measurement terminals;

[0035] Data fusion is performed on the local terminal using a federated learning model, and joint verification results are output.

[0036] The cross-over area flag is triggered only when the joint verification result exceeds the tolerance.

[0037] In conjunction with the first aspect, the output demand anomaly information includes:

[0038] Load the demand anomaly information into the measurement terminal and activate the AR overlay function. Perform the following operations on the output demand anomaly information in the real space view:

[0039] Use pulsed red light to render the boundary of the out-of-tolerance region;

[0040] A 3D heatmap of abnormal parameters is displayed floating in the non-overlapping coverage area;

[0041] It receives user gestures to adjust the virtual measurement baseline and updates the deviation range in real time.

[0042] In conjunction with the first aspect, the output demand anomaly information also includes:

[0043] When outputting abnormal demand information, determine the VR image of the abnormal area to generate the synchronous measurement path trajectory of the VR image;

[0044] Responding to the user's virtual control trajectory on the VR image, the system calculates the dynamic deviation between the user's operation measurement trajectory and the synchronous measurement path trajectory, and identifies the key deviation sources based on the dynamic deviation.

[0045] The beneficial effects of this application are as follows:

[0046] This application automatically extracts design functional requirements through a semantic parsing model and, combined with modular region partitioning, transforms unstructured intents into structured measurement tasks, reducing errors from manual breakdown and improving the efficiency of parallel measurement. The modular measurement method allows for simultaneous determination of whether measurement results meet design requirements and whether design conflicts exist, enabling real-time design interaction based on measurement.

[0047] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0048] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0049] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0050] In the attached diagram:

[0051] Figure 1 This is a flowchart illustrating a modular measurement method for a specific region, as described in an embodiment of the present invention.

[0052] Figure 2 This is an architecture diagram of a regional modular measurement method execution system according to an embodiment of the present invention;

[0053] Figure 3 This is a diagram illustrating the process of obtaining spatial indicators in an embodiment of the present invention. Detailed Implementation

[0054] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0055] Example 1: See Figure 1 and Figure 2 This paper proposes a modular measurement method for design intent, comprising a user terminal 1 and a measurement terminal. The measurement terminal is equipped with a VR module. Both user terminal 1 and the measurement terminal employ a distributed architecture to improve measurement flexibility. User terminal 1 can be an interactive device such as a mobile phone or computer, and the user can be either a designer or a client seeking design services. User terminal 1 receives and decomposes the user's design requirements into instructions. The measurement terminal 2, equipped with a VR module, enables the user to collect data and generate visualizations. The VR module transforms abstract measurement data into intuitive 3D visualizations, enhancing user autonomy and interaction.

[0056] The measurement instructions from the user for the target design scenario are obtained through user terminal 1 to determine the spatial indicators; wherein, the measurement instructions are the design measurement requirements of N modular spatial areas corresponding to N design requirements determined after the user inputs the design intent of the terminal device.

[0057] User terminal 1 utilizes natural language processing technology to perform structured analysis on the user's spoken text or directly inputted requirement text, determining the design intent. This intent is then broken down into modular spatial areas such as storage cabinets, sinks, and islands using a pre-defined rule base. For each spatial area's functional requirements, corresponding measurement needs are determined; for example, the island height must match the user's height to avoid bending over (enabling parallel measurement and adjusting measurement efficiency). Measurement needs can be mapped to quantifiable spatial indicators marked by dimensions, location, and tolerances, thereby reducing human intervention errors. Modular partitioning allows for parallel execution of measurement tasks in complex scenarios.

[0058] Based on spatial indicators, deploy each modular spatial area to meet multiple measurement requirements corresponding to the design needs, and determine the allowable deviation range for each measurement requirement;

[0059] The spatial indicators determine the measurement requirements and methods allocated to each modular area. The measurement terminal 2 can be a lidar, a measuring tape, or a vision sensor, but all of them need to be able to perform specific measurements. However, the measurements are likely to have deviations. Based on historical data and environmental parameters of the target scene (temperature, humidity), a dynamically adjustable allowable deviation range can be determined to improve the measurement accuracy in extreme environments.

[0060] When measurement terminal 2 receives a measurement request, it performs a measurement on each modular space area, generates a VR rendering comparison image, and determines whether the measurement result of each measurement request is within the allowable deviation range.

[0061] Measurement terminal 2 collects 3D point cloud data through multi-sensor fusion, compares it with the CAD data of the design model, and determines the deviation. During this process, the VR module will compare and render the results to output an image superimposed with the design value and the measured value, and use the built-in algorithm to determine whether the deviation is within the range.

[0062] Among them, when the measurement results are outside the allowable deviation range and different modular spatial areas overlap the measurement area, an overlap area identifier is generated in the target design scenario;

[0063] When there are overlapping measurement areas, spatial topology algorithms (such as ray method) are used to detect the geometric overlap of different modular areas. For the out-of-tolerance results of the overlapping area, the results are visualized through color borders and error value labels. Different measurement items are prioritized in the visualization, thereby identifying problems such as vertical deviation of the boundary area causing out-of-tolerance issues at the splicing seams of adjacent modules, and focusing on key overlapping areas.

[0064] When a measurement result is outside the allowable deviation range and there is no overlapping measurement area between different modular spatial areas, an abnormal demand information is output.

[0065] If the cross-coverage area does not exist, but there is still a deviation, that is, the out-of-tolerance area is an isolated module, it will be judged as a result of a conflict between the design requirements of a single module and the actual measurement results, such as the design size deviation. Then, a structured anomaly report will be pushed through user terminal 1 to determine the deviation value, sensor ID, and environmental parameters of the out-of-tolerance.

[0066] Example 2: See Figure 2 and Figure 3 User terminal 1 is used to determine spatial indicators, including:

[0067] Using the semantic parsing model of design intent in voice chain, the design intent text in user terminal 1 is identified and the design functional requirements are extracted.

[0068] The design intent semantic parsing model is a model trained using natural language processing technology. It is used to identify unstructured design intent text input by users, determine the corresponding design entities, and analyze the relationship between the design entities and the specific design space, as well as the functional requirements and design constraints. It can be input via text or voice, or it can be a verbal scenario of a visual designer, construction worker, or decoration customer.

[0069] Based on the design functional requirements, determine the design constraints and the key spatial attributes under the design constraints;

[0070] Design functional requirements, derived by the rule engine and combined with design constraints, determine the quantifiable spatial characteristics of the design entity, forming an attribute set. This transforms abstract functional requirements into measurable constraint boundaries, laying the foundation for subsequent parameter matching. The association rules between constraints and spatial attributes can be dynamically updated.

[0071] Based on key spatial attributes, match the corresponding set of physical measurement parameters for the functional design from the preset knowledge base;

[0072] By leveraging key spatial attributes within a pre-defined knowledge base, a mapping relationship between functional design and measurement parameters can be established. A knowledge graph is constructed using a graph database, supporting inter-attribute association queries. Through cosine similarity or rule matching, a parameter set containing measurement items, accuracy levels, and measurement tools is output, making measurements more accurate.

[0073] Based on the set of physical measurement parameters, determine the measurement requirements list for each modular spatial region, as well as the spatial indicators corresponding to each design functional requirement in the measurement requirements list.

[0074] The measurement list is a list of measurement results and a list of measurement requirements obtained by splitting the physical measurement parameter set into modular regions and assigning independent measurement items to each region. Spatial index quantification is to assign specific values ​​and tolerances to each measurement item, generate a structured spatial index table, realize the modular distribution of measurement tasks, and bind spatial indexes to design functional requirements one by one, which facilitates the tracking of the degree of achievement of design intent.

[0075] Example 3: See Figure 2 User terminal 1 is used to set the allowable deviation range, which is the deviation range that can be dynamically adjusted for each functional requirement within the modular space area in the target design scenario. The deviation range is determined by the influence coefficient of environmental parameters on the measurement results predicted by a regression model trained from historical measurement data. The environmental parameters are the temperature, humidity and light intensity in the target design scenario.

[0076] The allowable deviation range differs from the traditional fixed deviation range. The deviation range of this application binds functional requirements, modular areas and environmental parameters to form a dynamic deviation range that is dynamically adjusted in three dimensions. If the environmental parameters exceed the preset threshold or the priority of functional requirements changes, the deviation range is automatically recalculated to fit the specific environment.

[0077] During the deployment of measurement requirements, the measurement terminal 2, equipped with a built-in temperature and humidity sensor and a light meter, collects environmental parameters in real time. Based on historical measurement data from similar scenarios (generally using sample data from the past three years for training), a multi-source linear regression model is trained. During training, the dependent variable (measurement error) is determined, and the independent variables (temperature, humidity, and light intensity) are identified, outputting the influence coefficient of the error.

[0078] In terms of design specifications, the basic allowable deviation for the current functional requirements is first determined. Then, environmental factors are incorporated into the model to calculate the influence coefficients and determine the dynamically expanded deviation range. Under abnormal environments such as high temperature and high humidity, the basic allowable deviation is increased. Conversely, when environmental factors meet or exceed the expected standards, the basic allowable deviation is reduced, thereby improving measurement accuracy and adapting to various different scenarios.

[0079] Example 4: See Figure 2 The cross-coverage area marker used by measurement terminal 2 is a display marker indicating that different modular spatial areas with different design requirements overlap in the target design scenario;

[0080] The calculation of overlapping areas is achieved by using a spatial set algorithm to calculate the spatial intersection of different modular areas. Then, the overlapping areas are given visual markers with color overlay and text labels, which are superimposed on the VR rendered image to make the boundaries of different areas clear. The measurement results can show whether the design is reasonable.

[0081] Among them, the modular space region is associated with the directed acyclic graph deployed within the target design scenario. The nodes of the directed acyclic graph represent the regions of design requirements, and the deviation interval represents the physical overlap relationship of different modular space regions through historical edges.

[0082] Directed acyclic graphs (DAGs) use modular regions as nodes and physically overlapping relationships as directed edges to construct an acyclic topology, preventing logical conflicts arising from circular dependencies. Furthermore, adjacency matrices can record overlapping attribute data such as overlapping area, boundary length, and relative position between nodes. This transforms complex spatial relationships into structured graph data, thereby enabling conflict path tracing.

[0083] Identify and display the location of the overlapping region corresponding to the label in the directed acyclic graph:

[0084] If a child node is an intersection of multiple parent nodes, it is marked as a topological conflict zone and the conflict intensity value is calculated.

[0085] If it is an isolated node, trigger an exception message.

[0086] Finally, a graph traversal algorithm is used to determine the number of parent nodes for overlapping areas (e.g., node C is pointed to by both node A and node B, i.e., a child node with multiple parent nodes). Based on the functional priority of the parent nodes, the percentage of overlapping area, and the type of design requirement conflict, a weighted formula is used to calculate the conflict intensity value. The measurement results show the design contradictions that occur at the intersection of areas, preventing local errors in a single area. In the DAG, if an overlapping area node has no parent node (no preceding associated area) and no subsequent child nodes (no dependent area), it is determined to be an isolated node. Isolated nodes are areas between equipment rooms that were missed in the design or areas that are not associated with any functional area. A structured report is automatically pushed, which includes the isolated node's ID, spatial coordinates, and suggested processing solutions to prevent missed measurements in the solution.

[0087] In the implementation of the above scheme, a mapping between spatial regions and topology is constructed by using the modular spatial regions of DGA nodes and the physical overlap relationship represented by the edges of the directed acyclic graph. By identifying the intersecting child nodes of multiple parent nodes in the DGA, the topological conflict areas of multiple overlapping regions are determined. That is, there are multiple functional requirements in the modular spatial region that may overlap. This enables the output of corresponding abnormal information and can accurately determine which two design functional blocks have overlapping or far-away locations, thus making it less likely to encounter problems in judging whether there are design conflicts.

[0088] Example 5: See Figure 2 Measurement terminal 2 is used to mark topological conflict areas, and after marking the topological conflict areas, it is also used for:

[0089] Calculate the error propagation coefficient of the conflict zone to adjacent modules; the error propagation coefficient can quantify data such as the size deviation and unique offset of the conflict zone, determine the degree of diffusion of the modular area to adjacent modules, and then determine the conflict image result by calculating the logic, i.e. DAG topology relationship, combined with the physical connection strength, material heat lines and functional correlation between modules.

[0090] If the propagation coefficient exceeds a threshold, a virtual isolation node is inserted into the DAG to block the error propagation path, and the measurement requirements of the area associated with the isolation node are redeployed. A preset propagation coefficient threshold is used during the threshold determination process. Exceeding the threshold indicates that the error may cause the functionality of adjacent modules to fail. For example, structural deviations in the conflict zone may propagate to the load-bearing module, posing a safety risk. Therefore, a virtual node is inserted between the conflict zone node and adjacent module nodes in the DAG to disconnect the original error propagation edge while retaining necessary physical connection information. During redeployment, measurement tasks are reassigned to the area associated with the isolation node, the measurement frequency is increased for the conflict zone, and isolation boundary error detection items are added to adjacent modules. The existence of a conflict zone is determined through measurement.

[0091] Example 6: See Figure 2 Measurement terminal 2, upon receiving a second instruction during the generation of cross-coverage area identifiers, constructs a shared virtual space and performs gesture annotations at the boundaries of modular space areas. The second instruction is a shared virtual space construction instruction for at least two users. The shared virtual space is a VR space representing the target design area, and gesture annotations are configured at the boundaries of different modular space areas within the shared virtual space. The second instruction is triggered by receiving a collaboration instruction through a multi-user terminal 1 (such as a VR headset or tablet), verifying user permissions, and then starting the shared virtual space engine to achieve multi-user synchronization. The BIM model of the target design scene is then imported into the virtual space, and user hand movements are captured using a gesture recognition algorithm. Annotation data is synchronized in real-time to all user terminals 1, enabling cross-terminal collaboration. Multiple users verify user identities via blockchain or a centralized server to ensure that only authorized users can initiate / join the shared space. Modular area boundaries are displayed as semi-transparent grid lines in the VR space, and gesture annotations are overlaid with colored lines and user ID watermarks to avoid confusion.

[0092] When a conflict exists in gesture annotations, the system automatically calculates the overlapping area and determines the conflict focus with the overlapping area as the geometric center. It then projects an image of the overlapping measurement data onto the conflict focus. Through a spatial coordinate comparison algorithm, it identifies the degree of overlap of the boundaries of annotations by different users, calculates the geometric center of the overlapping area, and generates the coordinates of the conflict focus. Subsequently, it overlays the measurement data such as the corresponding dimensions, materials, and load-bearing parameters of each user annotation onto the conflict focus in an image format (e.g., the left side shows the architect's annotation of "3m wide doorway", and the right side shows the structural engineer's annotation of "2.5m wide load-bearing column") to achieve automatic conflict detection.

[0093] Based on the overlapping imagery, a strategy for modifying design requirements is determined. Based on data differences within the overlapping imagery, a rule engine identifies the type of conflict, and a solution is recommended using a domain knowledge base. The spatial effects of the modifications are then simulated.

[0094] Example 7: See Figure 2Measurement terminal 2 is used to perform measurements on each modular space region, including:

[0095] Based on the geometric location and measurement requirement priority of modular spatial regions, a path planning algorithm is invoked to generate the optimal measurement sequence. Geometric location involves abstracting the modular region into spatial coordinate points, and optimizing the search efficiency of neighboring regions using KD-trees or R-trees. Measurement requirement priority is achieved by converting measurement requirement priorities into weight values ​​using the analytic hierarchy process (AHP). The optimal measurement sequence uses the shortest total travel distance as the objective function, combined with prioritizing access to high-priority regions. A weighted TSP algorithm is invoked to output the measurement order, reducing invalid measurements. Traditional measurement methods primarily involve one-time planning and optimization of local designs to prevent overlap, necessitating design redundancy to avoid design errors. This application, however, employs real-time trajectory monitoring and global sequence replanning. During the measurement process, redundant regions are reduced and marked as unnecessary. Combined with sequence generation based on geometric location and priority, cross-regional travel distances are reduced, and already qualified regions are skipped to avoid repeated paths, saving measurement time by at least half.

[0096] The movement trajectory of measurement terminal 2 is monitored in real time. If the deviation from the planned path exceeds a threshold, dynamic replanning is performed, and areas that have already met the criteria are skipped. The measurement of the terminal's movement trajectory is achieved by real-time data collection from indoor and outdoor areas using the built-in equipment of measurement terminal 2 to determine the location data and compare it with the planned path using Euclidean distance. When the deviation between the real-time location and the planned path exceeds the threshold, dynamic path adjustment is triggered, and a fast replanning algorithm is invoked to generate a new path. At the same time, areas that have already been measured are automatically skipped through area status markers (met the criteria / not met the criteria). Furthermore, real-time obstacle perception is introduced during replanning to ensure the feasibility of the new path.

[0097] Example 8: See Figure 2 Measurement terminal 2 is used to determine whether the measurement result is within the allowable deviation range, specifically including:

[0098] When overlapping coverage areas exist, raw point cloud data is encrypted and acquired from multiple associated measurement terminals 2. When the overlapping coverage area is triggered, the overlapping area is identified through the spatial topology relationship identification module to determine the DAG node association information and automatically activate the multi-terminal collaborative measurement mode. The measurement data, namely point cloud data such as three-dimensional coordinates, reflection intensity, and acquisition timestamp, is transmitted using an end-to-end encryption protocol to prevent data tampering or leakage. According to the spatial range of the overlapping coverage area, the preset terminal association list is called.

[0099] Data fusion is performed locally on the terminal using a federated learning model, and joint verification results are output. Each measurement terminal 2 trains a sub-model locally, uploading only the model parameters to the central node. The central node aggregates the parameters and then issues updates, preventing the original data from leaving the network. The point cloud data from multiple terminals is aligned using the ICP algorithm, and the weight coefficients output by the federated learning model are combined to calculate the mean and deviation range of the fused 3D coordinates, determining the fused coordinates and the joint standard deviation. The cross-coverage area indicator is triggered only when the joint verification result exceeds the tolerance. The joint verification result is compared with the allowable deviation range. If the fused coordinate deviation > threshold or the joint standard deviation > threshold, it is determined to be out of tolerance. When out of tolerance, the cross-coverage area display indicator is automatically activated; otherwise, it is not triggered.

[0100] Example 9: See Figure 2 Measurement terminal 2 is used to output demand anomaly information, including:

[0101] Load the abnormal demand information into the measurement terminal 2 and start the AR overlay function. Perform the following operations on the output abnormal demand information in the real space view: load the abnormal information such as out-of-tolerance coordinates, deviation values, and area IDs from the backend database (such as PostgreSQL) into the measurement terminal 2 and convert it into a spatial anchoring data format supported by the AR engine; the AR overlay function can achieve synchronous positioning and map building through SLAM, enabling the technology to build a real space three-dimensional mesh in real time and bind the virtual abnormal information with physical space coordinates, for example: anchoring the boundary of the out-of-tolerance area to the actual wall / equipment surface.

[0102] The boundary of the out-of-tolerance area is rendered using pulsed red light. This is based on edge detection of point cloud data to extract the outline of the out-of-tolerance area, generate polygon boundary coordinates, and realize the red light pulse effect through AR shader to highlight visual warning.

[0103] The three-dimensional heatmap of abnormal parameters is displayed floating in non-overlapping areas. It filters overlapping areas through spatial topology and activates the display only in non-overlapping areas. The abnormal parameters are mapped to color gradients, and a three-dimensional chart is generated through volume rendering technology. The display is then anchored to the corresponding area in space.

[0104] The system receives user gestures to adjust the virtual measurement baseline and updates the deviation range in real time. User gestures are captured via the terminal camera / sensors and classified into translation, rotation, and zoom commands using a CNN model. Based on the adjusted virtual baseline, the system recalculates the deviation values ​​for each measurement point and updates the deviation values ​​displayed in the AR view in real time.

[0105] Example 10: See Figure 2 Measurement terminal 2 is used to output demand anomaly information, and specifically includes:

[0106] When outputting abnormal information, the VR image of the abnormal area is determined to generate a synchronous measurement path trajectory for the VR image. The VR image of the abnormal area is based on the point cloud data collected by measurement terminal 2. A three-dimensional mesh model of the abnormal area is generated by the Poisson surface reconstruction algorithm, and the texture information of the device surface material and color is superimposed to construct an immersive VR image. The design reference path of the abnormal area is extracted and mapped to the VR coordinate system to generate a synchronous measurement path trajectory with a timestamp, ensuring the correlation between virtual operation and physical space.

[0107] Responding to the user's virtual control trajectory on the VR image, the system calculates the dynamic deviation between the user's operation measurement trajectory and the synchronous measurement path trajectory, and identifies key deviation sources based on the dynamic deviation. Specifically, the system uses the VR controller's six-DOF sensor to collect the user's operation trajectory in real time, generating spatiotemporal sequence data including position and orientation. A dynamic time warping algorithm is used to align the user trajectory with the synchronous path trajectory, calculating the Euclidean distance deviation and attitude angle deviation at each timestamp, and outputting deviation curves such as horizontal axis time and vertical axis deviation values. Time-domain and frequency-domain analyses are performed on the dynamic deviation curves to extract feature vectors. Then, a pre-trained deviation source classification model is used to match the feature vectors with a known deviation source database, outputting confidence ranking results.

[0108] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A modular measurement method for a designed region, characterized in that, The method includes a user terminal and a measurement terminal, the measurement terminal being equipped with a VR module, and includes: The measurement instructions from the user for the target design scenario are obtained through the user terminal to determine the spatial indicators; wherein, the measurement instructions are the design measurement requirements of N modular spatial areas corresponding to N design requirements determined after the user inputs the design intent of the terminal device. Based on spatial indicators, deploy each modular spatial area to meet multiple measurement requirements corresponding to the design needs, and determine the allowable deviation range for each measurement requirement; When the measurement terminal receives a measurement request, it performs a measurement on each modular space area, generates a VR rendering comparison image, and determines whether the measurement result of each measurement request is within the allowable deviation range. Among them, when the measurement results are outside the allowable deviation range and different modular spatial areas overlap the measurement area, an overlap area identifier is generated in the target design scenario; When the measurement result is outside the allowable deviation range and there is no overlapping measurement area between different modular spatial areas, output demand anomaly information; The cross-over area identifier is a display identifier indicating that different modular spatial areas with different design requirements overlap within the target design scenario; Among them, the modular space region is associated with the directed acyclic graph deployed within the target design scenario. The nodes of the directed acyclic graph represent the regions of design requirements, and the deviation interval represents the physical overlap relationship of different modular space regions through historical edges. Identify and display the location of the overlapping region corresponding to the label in the directed acyclic graph: If a child node is an intersection of multiple parent nodes, it is marked as a topological conflict zone and the conflict intensity value is calculated. If it is an isolated node, trigger an exception message.

2. The regional modular measurement method according to claim 1, characterized in that, The spatial indicators for determination include: By using the semantic parsing model of design intent in voice chain, we can identify the design intent text in the user terminal and extract the design functional requirements. Based on the design functional requirements, determine the design constraints and the key spatial attributes under the design constraints; Based on key spatial attributes, match the corresponding set of physical measurement parameters for the functional design from the preset knowledge base; Based on the set of physical measurement parameters, determine the measurement requirements list for each modular spatial region, as well as the spatial indicators corresponding to each design functional requirement in the measurement requirements list.

3. The regional modular measurement method according to claim 1, characterized in that, The allowable deviation range is the deviation range that can be dynamically adjusted for each functional requirement within the modular space area in the target design scenario; wherein, the deviation range is determined by the influence coefficient of environmental parameters on the measurement results predicted by a regression model trained on historical measurement data, and the environmental parameters are the temperature, humidity and light intensity in the target design scenario.

4. The regional modular measurement method according to claim 1, characterized in that, The marking of a topological conflict zone includes: Calculate the error propagation coefficient of the conflict zone to adjacent modules; If the propagation coefficient exceeds the threshold, a virtual isolation node is inserted into the DAG to block the error propagation path, and the measurement requirements of the area associated with the isolation node are redeployed.

5. The regional modular measurement method according to claim 1, characterized in that, When the cross-coverage area identifier is generated, upon receiving the second instruction, a shared virtual space is constructed, and gesture annotations are performed at the boundaries of the modular space areas; wherein, the second instruction is a shared virtual space construction instruction for no less than two users, the shared virtual space is the VR space of the target design area, and gesture annotations are configured at the boundaries of different modular space areas of the shared virtual space; When there is a conflict in gesture annotation, the overlapping area is automatically calculated, and the conflict focus with the overlapping area as the geometric center is determined. The overlapping image of the measurement data is then projected at the conflict focus. Based on the overlapping images, determine the modification strategy for the design requirements.

6. The regional modular measurement method according to claim 1, characterized in that, The measurement performed on each modular spatial region includes: Based on the geometric location of the modular spatial region and the priority of measurement requirements, a path planning algorithm is invoked to generate the optimal measurement sequence. The system monitors the movement trajectory of the measurement terminal in real time. If the deviation from the planned path exceeds the threshold, the system dynamically replans and skips areas that have already met the standards.

7. The regional modular measurement method according to claim 1, characterized in that, The determination of whether the measurement result is within the allowable deviation range includes: When overlapping coverage areas exist, raw point cloud data is encrypted and obtained from multiple associated measurement terminals; Data fusion is performed on the local terminal using a federated learning model, and joint verification results are output. The cross-over area flag is triggered only when the joint verification result exceeds the tolerance.

8. The regional modular measurement method according to claim 1, characterized in that, The output demand anomaly information includes: Load the demand anomaly information into the measurement terminal and activate the AR overlay function. Perform the following operations on the output demand anomaly information in the real space view: Use pulsed red light to render the boundary of the out-of-tolerance region; A 3D heatmap of abnormal parameters is displayed floating in the non-overlapping coverage area; It receives user gestures to adjust the virtual measurement baseline and updates the deviation range in real time.

9. The regional modular measurement method according to claim 1, characterized in that, The output demand anomaly information also includes: When outputting abnormal demand information, determine the VR image of the abnormal area to generate the synchronous measurement path trajectory of the VR image; Responding to the user's virtual control trajectory on the VR image, the system calculates the dynamic deviation between the user's operation measurement trajectory and the synchronous measurement path trajectory, and identifies the key deviation sources based on the dynamic deviation.

Images