Building three-dimensional model creation method and device based on personnel positioning trajectory, electronic equipment and medium

Abstract

The present application relates to the technical field of computer, and particularly relates to a building three-dimensional model creation method and device based on personnel positioning track, electronic equipment and medium. A specific embodiment of the method comprises: acquiring a pre-acquired construction personnel positioning space-time task information set; performing building outer contour associated task track filtering processing on the construction personnel positioning space-time task information set; performing grouping processing on the target construction personnel positioning space-time task information set; performing floor elevation range filtering processing on each target construction personnel positioning space-time task information group; performing cross-layer anti-deducting outdoor track elimination processing on the filtered construction personnel positioning space-time task information group; and creating a building three-dimensional model based on each generated target positioning space-time task information cluster set. The embodiment reduces the gap between the appearance of the constructed building three-dimensional model and the actual building.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically to a method, apparatus, electronic device, and medium for creating 3D building models based on personnel positioning trajectories. Background Technology

[0002] With the rapid development of informatization and digital management in the construction industry, Building Information Modeling (BIM) technology is playing an increasingly important role in project management, cost control, and construction simulation. Creating 3D building models based on personnel location trajectories is one such technology. Currently, the common method for constructing 3D building models is to identify the building outlines in CAD drawings and generate the 3D model through extrusion.

[0003] However, when using the above method to construct a 3D building model, the following technical problems often arise:

[0004] Identifying the building outline in CAD drawings and generating a 3D model by extrusion is crucial. However, since drawings only reflect design expectations rather than actual construction results and are difficult to accurately represent complex building structures such as irregular curved surfaces and bay windows, the generated models are often regular box-like models (when a building has complex curves, slopes, decorations, and other irregular elements, simple box-like meshes cannot accurately capture these features), making it difficult to truly reflect the actual external outline of the building. This results in a significant difference between the appearance of the constructed 3D building model and the actual building.

[0005] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not form prior art known to those skilled in the art. Summary of the Invention

[0006] The disclosure portion of this invention is intended to provide a brief overview of the concepts, which will be described in detail in the subsequent detailed description portion. This disclosure portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0007] The present invention discloses some embodiments that propose a method, apparatus, electronic device and computer-readable medium for creating 3D building models based on personnel positioning trajectories to solve the technical problems mentioned in the background section above.

[0008] In a first aspect, some embodiments of the present invention disclose a method for creating a 3D building model based on personnel positioning trajectories. The method includes: acquiring a pre-collected set of spatiotemporal task information for construction personnel positioning; performing building outline-related task trajectory filtering on the aforementioned set of spatiotemporal task information for construction personnel positioning to obtain a target set of spatiotemporal task information for construction personnel positioning; grouping the aforementioned target set of spatiotemporal task information for construction personnel positioning to obtain various target sets of spatiotemporal task information for construction personnel positioning, wherein each target set of spatiotemporal task information for construction personnel positioning has a corresponding construction personnel identifier; and assigning each target set of spatiotemporal task information to a corresponding construction personnel identifier. The location spatiotemporal task information group is filtered by floor elevation range to obtain each filtered construction personnel location spatiotemporal task information group. For each of the above filtered construction personnel location spatiotemporal task information groups, cross-floor reverse deduction of outdoor trajectory is performed to generate target location spatiotemporal task information clusters, which include non-first-floor location spatiotemporal task information clusters and first-floor indoor location spatiotemporal task information clusters. Based on the generated target location spatiotemporal task information clusters, a 3D building model is created.

[0009] Secondly, some embodiments of the present invention disclose a building 3D model creation device based on personnel positioning trajectories. The device includes: an acquisition unit configured to acquire a pre-collected set of spatiotemporal task information of construction personnel positioning; a first filtering processing unit configured to perform building outline-related task trajectory filtering processing on the aforementioned set of spatiotemporal task information of construction personnel positioning to obtain a target set of spatiotemporal task information of construction personnel positioning; a grouping processing unit configured to perform grouping processing on the aforementioned set of target set of spatiotemporal task information of construction personnel to obtain various target set of spatiotemporal task information of construction personnel positioning, wherein each target set of spatiotemporal task information of construction personnel positioning has a corresponding construction personnel identifier; and a second filtering processing unit configured to... The floor elevation range is filtered for each of the above-mentioned target construction personnel positioning spatiotemporal task information groups to obtain each filtered construction personnel positioning spatiotemporal task information group. The elimination processing unit is configured to perform cross-floor reverse-deduction outdoor trajectory elimination processing on each of the above-mentioned filtered construction personnel positioning spatiotemporal task information groups to generate target positioning spatiotemporal task information clusters, wherein the target positioning spatiotemporal task information clusters include non-first-floor positioning spatiotemporal task information clusters and first-floor indoor positioning spatiotemporal task information clusters. The creation unit is configured to create a three-dimensional building model based on the generated target positioning spatiotemporal task information clusters.

[0010] Thirdly, some embodiments of the present invention disclose an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] Fourthly, some embodiments of the present invention disclose a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0012] The above-disclosed embodiments of the present invention have the following beneficial effects: The method for creating 3D building models based on personnel positioning trajectories, as disclosed in some embodiments of the present invention, reduces the discrepancy between the appearance of the constructed 3D building model and the actual building. Specifically, the reason for the large discrepancy between the appearance of the constructed 3D building model and the actual building is that: Identifying the building outline in the CAD drawings and generating a 3D model by extrusion is problematic because the drawings only reflect the design expectations rather than the actual construction results, and are difficult to accurately express complex building structures such as irregular curved surfaces and irregular bay windows. This results in a model that is often a regular box-like model (when the building has complex curves, slopes, decorations, and other irregular elements, a simple box-like mesh cannot accurately capture these features), making it difficult to truly reflect the actual outer contour of the building, leading to a large discrepancy between the appearance of the constructed 3D building model and the actual building. Based on this, the method for creating 3D building models based on personnel positioning trajectories, as disclosed in some embodiments of the present invention, firstly acquires a pre-collected set of spatiotemporal task information on the positioning of construction personnel. This allows for the acquisition of a set of information representing the trajectory of each construction worker while working in the building (e.g., on a curtain wall), with each piece of information including a construction type identifier, timestamp, 3D coordinate data, construction worker identifier, and floor number. Next, the aforementioned set of spatiotemporal task information for construction personnel is filtered for its association with the building's outer contour, resulting in a set of target spatiotemporal task information for construction personnel. This allows for the removal of task trajectories unrelated to the building's outer contour, such as material transport and site cleaning, while retaining trajectories potentially touching the building's boundaries, such as curtain wall installation and rebar tying. The target set of spatiotemporal task information is then grouped to obtain individual target set of spatiotemporal task information, each with a corresponding construction personnel identifier. Next, each target set of spatiotemporal task information is filtered for its floor elevation range, resulting in filtered sets of spatiotemporal task information for construction personnel. Based on the floor elevation information, points outside the elevation range irrelevant to the task on that floor are removed from the worker's trajectory, ensuring that the trajectory data for each floor matches the actual floor position vertically. Next, for each of the above-mentioned filtering construction personnel positioning spatiotemporal task information groups, cross-layer reverse deduction of outdoor trajectory elimination is performed on each filtering construction personnel positioning spatiotemporal task information group to generate target positioning spatiotemporal task information clusters. The target positioning spatiotemporal task information clusters include non-first-floor positioning spatiotemporal task information clusters and first-floor indoor positioning spatiotemporal task information clusters.Therefore, the outdoor activity trajectory of the same worker when working outside the first floor can be used as a template to reverse-engineer and eliminate noise points located in the outdoor leveling area in the first-floor work trajectory, thus obtaining a cluster of spatiotemporal task information for target positioning. Then, based on the generated clusters of spatiotemporal task information for target positioning, a 3D building model is created. This results in a 3D building model with an outline composed of clusters of actual work trajectory points of construction workers. Because the building outline is constructed using the spatiotemporal task information set corresponding to the trajectory left by workers working at the building boundary during actual construction, it reflects the actual activity range of workers in tasks such as curtain wall installation and exterior wall work. Its outer edge naturally conforms to the actual physical boundary of the building, avoiding the model distortion problem caused by the inability of drawings to accurately represent irregular structures when relying on drawing modeling. This allows the generated 3D building model to realistically present irregular contour features such as curves and slopes, thereby reducing the difference between the appearance of the constructed 3D building model and the actual building. Attached Figure Description

[0013] The above and other features, advantages, and aspects of the various embodiments disclosed herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0014] Figure 1 This is a flowchart of some embodiments of the method for creating a three-dimensional building model based on personnel positioning trajectory disclosed in this invention;

[0015] Figure 2 This is a schematic diagram of some embodiments of the building 3D model creation device based on personnel positioning trajectory disclosed in the present invention;

[0016] Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present invention. Detailed Implementation

[0017] The embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the present invention are shown in the drawings, it should be understood that the embodiments disclosed herein can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0018] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0020] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0021] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0022] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] Figure 1 A flowchart 100 is shown illustrating some embodiments of a method for creating a 3D building model based on personnel positioning trajectories disclosed in this invention. This method for creating a 3D building model based on personnel positioning trajectories includes the following steps:

[0024] Step 101: Obtain the pre-collected spatiotemporal task information set of construction personnel.

[0025] In some embodiments, the executing entity (e.g., a computing device) of the method for creating a 3D building model based on personnel positioning trajectories can obtain a pre-collected set of spatiotemporal task information on the positioning of construction personnel. In practice, the aforementioned self-executing entity can obtain the pre-collected set of spatiotemporal task information on the positioning of construction personnel from a preset BIM system or preset building files.

[0026] In some optional implementations of certain embodiments, the aforementioned spatiotemporal task information set for construction personnel positioning is collected through the following steps:

[0027] The first step involves receiving, within a preset time period, the location spatiotemporal task information of construction workers transmitted by each of the preset positioning terminals at preset time intervals. These preset positioning terminals are worn by construction workers within a preset building. The location spatiotemporal task information includes a construction type identifier, a timestamp, three-dimensional coordinate data, a construction worker identifier, and a floor number. The preset positioning terminals can be wearable IoT devices (e.g., smart helmets, smart bracelets, etc.) pre-worn by the construction workers and capable of automatically collecting and transmitting location spatiotemporal task information at preset time intervals. The construction type identifier can be an identifier indicating the type of construction work performed by the construction worker (e.g., curtain wall). The three-dimensional coordinate data can be three-dimensional coordinates. The construction worker identifier can be the worker's identifier (e.g., 001). The floor number can be the floor number where the construction worker is located during construction work (e.g., the 2nd floor).

[0028] The second step is to determine the received spatiotemporal task information of each construction worker as the construction worker positioning spatiotemporal task information set.

[0029] Step 102: Perform building outline-related task trajectory filtering on the spatiotemporal task information set of construction personnel positioning to obtain the target construction personnel positioning spatiotemporal task information set.

[0030] In some embodiments, the aforementioned execution entity may perform building outline-related task trajectory filtering on the aforementioned construction personnel location spatiotemporal task information set to obtain the target construction personnel location spatiotemporal task information set.

[0031] In some optional implementations of certain embodiments, the aforementioned execution entity may perform building outline-related task trajectory filtering on the aforementioned construction worker positioning spatiotemporal task information set through the following steps to obtain the target construction worker positioning spatiotemporal task information set:

[0032] The first step is to perform the following steps for filtering the building outline-related task trajectories for each construction worker's location spatiotemporal task information in the construction worker location spatiotemporal task information set:

[0033] The first sub-step is to determine the construction type identifier included in the spatiotemporal task information for the positioning of construction personnel.

[0034] The second sub-step, in response to determining that the aforementioned construction type identifier is not in the preset building outline construction type identifier table, involves deleting the aforementioned construction personnel positioning spatiotemporal task information from the aforementioned construction personnel positioning spatiotemporal task information set, thereby updating the construction personnel positioning spatiotemporal task information set. The aforementioned preset building outline construction type identifier table can be a preset list of building outline construction type identifiers (e.g., curtain wall installation, rebar tying, etc.) corresponding to various task trajectories related to the building outline.

[0035] The second step is to determine the updated spatiotemporal task information set for the construction personnel as the target spatiotemporal task information set for the construction personnel.

[0036] Step 103: Group the spatiotemporal task information set of the target construction personnel to obtain each target construction personnel spatiotemporal task information group.

[0037] In some embodiments, the aforementioned execution entity may group the aforementioned target construction personnel location spatiotemporal task information set to obtain various target construction personnel location spatiotemporal task information groups, wherein each target construction personnel location spatiotemporal task information group has a corresponding construction personnel identifier.

[0038] In some optional implementations of certain embodiments, the aforementioned executing entity may group the aforementioned target construction personnel location spatiotemporal task information set through the following steps to obtain each target construction personnel location spatiotemporal task information group:

[0039] The first step is to deduplicate the identifiers of each construction worker in the spatiotemporal task information set for locating the target construction workers, and to determine the deduplicated set of construction worker identifiers. In practice, a hash deduplication algorithm can be used to deduplicate the identifiers of each construction worker in the spatiotemporal task information set for locating the target construction workers.

[0040] The second step is to identify each deduplicated construction worker identifier in the deduplicated construction worker identifier set, and to identify at least one target construction worker positioning spatiotemporal task information in the target construction worker positioning spatiotemporal task information set that contains the aforementioned deduplicated construction worker identifier as a target construction worker positioning spatiotemporal task information group with the aforementioned deduplicated construction worker identifier.

[0041] Step 104: Filter the spatiotemporal task information groups of each target construction worker location by floor elevation range to obtain each filtered spatiotemporal task information group of the construction worker location.

[0042] In some embodiments, the aforementioned executing entity may perform floor elevation range filtering on the aforementioned target construction personnel positioning spatiotemporal task information groups to obtain various filtered construction personnel positioning spatiotemporal task information groups. Each of the aforementioned filtered construction personnel positioning spatiotemporal task information groups corresponds to a specific target construction personnel positioning spatiotemporal task information group within the aforementioned target construction personnel positioning spatiotemporal task information groups.

[0043] In some optional implementations of certain embodiments, the aforementioned executing entity may perform floor elevation range filtering on the aforementioned target construction personnel location spatiotemporal task information groups through the following steps to obtain each filtered construction personnel location spatiotemporal task information group:

[0044] The first step is to perform the following floor elevation range filtering steps for each target construction worker positioning spatiotemporal task information group within each target construction worker positioning spatiotemporal task information group:

[0045] Sub-step one: Determine the floor number included in the above-mentioned target construction personnel location spatiotemporal task information as the floor number to be queried.

[0046] Sub-step two: Query the floor elevation range corresponding to the aforementioned floor number. In practice, the executing entity can query a preset mapping table to find the preset floor elevation range corresponding to the aforementioned floor number as the floor elevation range. The aforementioned preset mapping table can be a preset table that records the correspondence between floor numbers and preset floor elevation ranges. For example, the preset floor elevation range corresponding to floor 2 is 5.880m-10.380m.

[0047] Sub-step three: In response to determining that the height value in the three-dimensional coordinates included in the above-mentioned target construction personnel positioning spatiotemporal task information is not within the above-mentioned floor elevation range, the above-mentioned target construction personnel positioning spatiotemporal task information is deleted from the above-mentioned target construction personnel positioning spatiotemporal task information group in order to update the target construction personnel positioning spatiotemporal task information group.

[0048] The second step is to identify each updated target construction personnel location spatiotemporal task information group as a filter construction personnel location spatiotemporal task information group.

[0049] Step 105: For each of the filtering construction personnel positioning spatiotemporal task information groups, perform cross-layer reverse deduction of outdoor trajectory removal processing on each filtering construction personnel positioning spatiotemporal task information group to generate target positioning spatiotemporal task information clusters.

[0050] In some embodiments, the aforementioned execution entity may perform cross-layer reverse deduction of outdoor trajectory elimination processing on each of the aforementioned filtering construction personnel positioning spatiotemporal task information groups to generate a target positioning spatiotemporal task information cluster, wherein the target positioning spatiotemporal task information cluster includes non-first-floor positioning spatiotemporal task information clusters and first-floor indoor positioning spatiotemporal task information clusters.

[0051] In addressing the aforementioned technical problems in the application scenario—automatically generating 3D building models based on personnel positioning trajectories during the construction phase—the following technical issues often arise: the first-floor trajectory is a linear overlap of indoor and outdoor positioning spatiotemporal task information, completely overlapping (with the same frequency) along the Z-axis. Traditional filtering algorithms struggle to distinguish between indoor and outdoor points, resulting in the first-floor trajectory containing a large amount of outdoor site leveling activity data unrelated to the building boundaries (such as material transfer and site cleaning at elevations). This leads to the generated first-floor outline including outdoor areas, causing a significant discrepancy between the 3D building model and the actual building appearance. To address the following requirements for this application scenario: the automated construction of the 3D building model needs the ability to separate indoor and outdoor trajectories to ensure that the first-floor outline accurately reflects the actual physical boundaries of the building. Faced with these technical problems, we have decided to adopt the following solution:

[0052] In some optional implementations of certain embodiments, the aforementioned execution entity may perform cross-layer reverse deduction of outdoor trajectory elimination processing on each filtered construction worker positioning spatiotemporal task information group through the following steps to generate a target positioning spatiotemporal task information cluster:

[0053] The first step is to identify at least one set of construction worker positioning spatiotemporal task information from the aforementioned set of filtered construction worker positioning spatiotemporal task information that meets the first preset condition as the first-floor positioning spatiotemporal task information cluster. The first preset condition can be that the floor number is 1.

[0054] The second step is to identify at least one target construction worker positioning spatiotemporal task information cluster that does not meet the preset conditions in the target construction worker positioning spatiotemporal task information cluster corresponding to the above-mentioned target construction worker positioning spatiotemporal task information cluster.

[0055] The third step is to determine the three-dimensional coordinates included in the non-first-layer positioning spatiotemporal task information cluster as the three-dimensional coordinates of each target. Each of the above target three-dimensional coordinates includes a horizontal coordinate value, a vertical coordinate value, and a height value. The above target three-dimensional coordinates correspond to one of the non-first-layer positioning spatiotemporal task information in the above non-first-layer positioning spatiotemporal task information cluster.

[0056] The fourth step is to determine at least one target 3D coordinate that meets the preset screening criteria as the 3D coordinates for each outdoor activity. The preset screening criteria can be that the height value of the target 3D coordinates is within a preset range. For example, the preset range could be "0m to 5m".

[0057] The fifth step is to determine each of the three-dimensional coordinates included in the above-mentioned first-layer positioning spatiotemporal task information cluster as a first-layer three-dimensional coordinate, and each of the above-mentioned first-layer three-dimensional coordinates corresponds to a first-layer positioning spatiotemporal task information in the above-mentioned first-layer positioning spatiotemporal task information cluster.

[0058] The sixth step is to determine the three-dimensional coordinates of each of the above outdoor activities as the three-dimensional coordinates of each of the first clusters to be clustered.

[0059] Step 7: Determine the three-dimensional coordinates of each first layer as the three-dimensional coordinates of each second cluster to be clustered.

[0060] Step 8: Perform clustering processing on the aforementioned first and second 3D coordinates to be clustered, resulting in cluster groups of 3D coordinates. In practice, the DBSCAN clustering algorithm can be used to perform clustering processing on the aforementioned first and second 3D coordinates to be clustered, resulting in cluster groups of 3D coordinates.

[0061] Step 9: Determine at least one outdoor three-dimensional coordinate cluster group that contains the first three-dimensional coordinate to be clustered as at least one outdoor three-dimensional coordinate group.

[0062] Step 10: Determine the first three-dimensional coordinates of each of the above-mentioned first-layer three-dimensional coordinates as the first three-dimensional coordinate set.

[0063] Step 11: Determine the individual outdoor three-dimensional coordinates included in at least one outdoor three-dimensional coordinate set as the second three-dimensional coordinate set.

[0064] Step 12: Determine the intersection of the first three-dimensional coordinate set and the second three-dimensional coordinate set as the three-dimensional coordinate intersection to be removed.

[0065] Step 13: For each three-dimensional coordinate to be removed in the intersection of the three-dimensional coordinates to be removed, remove the first-layer positioning spatiotemporal task information containing the three-dimensional coordinates to be removed from the first-layer positioning spatiotemporal task information cluster, so as to update the first-layer positioning spatiotemporal task information cluster.

[0066] Step 14: The updated first-floor positioning spatiotemporal mission information cluster is identified as the first-floor indoor positioning spatiotemporal mission information cluster.

[0067] Step 15: Determine the non-first-floor positioning spatiotemporal task information cluster and the first-floor indoor positioning spatiotemporal task information cluster as the target positioning spatiotemporal task information cluster set.

[0068] The above technical solution, combined with step 106 and related content, serves as an inventive point of this invention, addressing the technical problem of "significant discrepancy between the 3D building model and the actual building appearance." Factors leading to this discrepancy often include: the first-floor trajectory is a linear superposition of indoor and outdoor positioning spatiotemporal task information, completely overlapping (with the same frequency) along the Z-axis. Traditional filtering algorithms struggle to distinguish between indoor and outdoor points, resulting in the first-floor trajectory corresponding to the filtered construction worker positioning spatiotemporal task information group containing a large amount of outdoor site leveling activity data unrelated to the building boundary (such as material transfer and site cleaning at elevations). This causes the generated first-floor building outline to include outdoor areas, resulting in a significant discrepancy between the 3D building model and the actual building appearance. Solving these factors can reduce the discrepancy between the 3D building model and the actual building appearance. To achieve this, firstly, at least one set of filtered construction worker positioning spatiotemporal task information whose floor number meets the first preset condition is identified as the first-floor positioning spatiotemporal task information cluster. At least one target construction worker positioning time-space task information group from the aforementioned target construction worker positioning time-space task information groups whose floor numbers do not meet the preset conditions in the target construction worker positioning time-space task information group corresponding to the aforementioned filtered construction worker positioning time-space task information group is identified as a non-first-floor positioning time-space task information cluster. Therefore, the filtered construction worker positioning time-space task information group can be divided into a first-floor positioning time-space task information cluster and a non-first-floor positioning time-space task information cluster. Next, each three-dimensional coordinate included in the non-first-floor positioning time-space task information cluster is identified as a target three-dimensional coordinate, wherein each of the aforementioned target three-dimensional coordinates includes a horizontal coordinate value, a vertical coordinate value, and a height value, and the aforementioned target three-dimensional coordinates correspond to one non-first-floor positioning time-space task information in the aforementioned non-first-floor positioning time-space task information cluster. The aforementioned target three-dimensional coordinates are then selected based on preset filtering conditions.

[0069] At least one target 3D coordinate is determined as the 3D coordinate of each outdoor activity. Since the same worker works on the first floor today, the second floor tomorrow, and the third floor the day after, his activity trajectory in the public area (outdoor area) on the first floor should be similar to that of the non-first floor. Therefore, the indoor and outdoor elevations (height values) of the non-first floor (second floor and above) that are the same as those of the first floor are determined as the 3D coordinates of the outdoor activities of the first floor, thus obtaining the 3D coordinates of each outdoor activity, i.e., the clean outdoor samples. Then, the 3D coordinates included in the above-mentioned first-floor positioning spatiotemporal task information cluster are determined as the 3D coordinates of each first-floor location, and each of the above-mentioned first-floor 3D coordinates corresponds to one of the first-floor positioning spatiotemporal task information in the above-mentioned first-floor positioning spatiotemporal task information cluster. Next, the above-mentioned outdoor activity 3D coordinates are determined as the 3D coordinates to be clustered in the first stage. Then, the above-mentioned first-floor 3D coordinates are determined as the 3D coordinates to be clustered in the second stage. Then, the above-mentioned first-floor 3D coordinates to be clustered and the above-mentioned second-floor 3D coordinates to be clustered are clustered to obtain the 3D coordinate cluster groups. Therefore, the known clean outdoor samples (i.e., the 3D coordinates of each outdoor activity) and the 3D coordinates to be processed can be clustered in the same spatial coordinate system. Using spatial proximity, points in the first layer that are spatially close to the outdoor samples are automatically grouped into the same cluster, resulting in various 3D coordinate cluster groups. Next, at least one 3D coordinate cluster group containing the first 3D coordinate to be clustered is determined as at least one outdoor 3D coordinate group. Then, the aforementioned first-layer 3D coordinates are determined as the first 3D coordinate set. Afterward, the outdoor 3D coordinates included in the at least one outdoor 3D coordinate group are determined as the second 3D coordinate set. Then, the intersection of the first and second 3D coordinate sets is determined as the intersection of the 3D coordinates to be removed. Thus, the intersection of the 3D coordinates to be removed, which belongs to both the first layer and the same spatial region as the 3D coordinates of each outdoor activity, can be determined. Then, for each 3D coordinate to be removed in the intersection, the first-layer positioning spatiotemporal task information cluster containing the aforementioned 3D coordinate to be removed is removed to update the first-layer positioning spatiotemporal task information cluster. Therefore, the spatial-temporal task information for the first-floor outdoor positioning can be removed. Next, the updated first-floor spatial-temporal task information cluster is determined as the first-floor indoor spatial-temporal task information cluster. Thus, outdoor site leveling activity data unrelated to the building boundaries can be removed, i.e., after removing the first-floor outdoor positioning spatial-temporal task information, the first-floor indoor positioning spatial-temporal task information cluster representing the first-floor indoor trajectory is obtained. Next, the non-first-floor positioning spatial-temporal task information cluster and the first-floor indoor positioning spatial-temporal task information cluster are determined as the target positioning spatial-temporal task information cluster set. Then, based on the generated target positioning spatial-temporal task information cluster sets from step 106, a 3D building model is created.Therefore, a 3D building model can be constructed based on the clusters of spatiotemporal task information of each target after removing outdoor site leveling activity data unrelated to the building boundary, i.e., removing the location spatiotemporal task information of the first floor outdoor area. This reduces the impact of the location spatiotemporal task information of construction personnel in outdoor site leveling activity areas unrelated to the building boundary (such as material transfer and site cleaning outside the first floor at the same elevation) on the outline of the first floor in the building model, and reduces the gap between the 3D building model and the actual building appearance.

[0070] Step 106: Based on the generated spatiotemporal task information clusters for each target location, create a 3D building model.

[0071] In some embodiments, the executing entity creates a 3D building model based on the generated spatiotemporal task information clusters for each target location. This 3D building model can be a 3D model representing the outline of a pre-defined building.

[0072] In addressing the technical problems mentioned above, the following technical issues arise when developing a 3D model of a building with various construction tasks, such as curtain wall installation, interior masonry, and material transportation: Due to the diverse construction tasks (e.g., curtain wall installation, interior decoration, electromechanical installation), these tasks have varying degrees of relevance to the building's outline (curtain wall installation points are close to the building's outer boundary, while interior decoration points are located inside). Traditional algorithms treat all trajectory points as geometrically equal, failing to distinguish between highly relevant and low-relevance points. This results in the generated building outline being "skewed" by numerous low-relevance interior work points, leading to a significant discrepancy between the 3D model and the actual building appearance. The following characteristics are required for this application scenario: The ability to assign different outline-related weights to each trajectory point based on the construction task type, and to ensure that high-weight (strongly relevant) points play a dominant role in outline generation during geometric reconstruction, while low-weight (weakly relevant) points serve only as auxiliary references, ensuring that the generated model boundary accurately matches the actual physical outer edge of the building. To address these technical problems, we have decided to adopt the following solution:

[0073] In some optional implementations of certain embodiments, the aforementioned execution entity can create a 3D building model based on the generated spatiotemporal task information clusters for each target location through the following steps:

[0074] The first step is to determine the first-floor indoor positioning spatiotemporal task information clusters, which are included in the above-mentioned target positioning spatiotemporal task information clusters, as the first-floor indoor positioning spatiotemporal task information clusters.

[0075] The second step is to determine and filter the various indoor positioning spatiotemporal task information groups included in the above-mentioned first-floor indoor positioning spatiotemporal task information cluster.

[0076] The third step is to identify the non-first-layer positioning spatiotemporal task information clusters included in each target positioning spatiotemporal task information cluster as non-first-layer positioning spatiotemporal task information clusters.

[0077] The fourth step is to determine the various positioning spatiotemporal task information included in the above-mentioned non-first-layer positioning spatiotemporal task information cluster as the positioning spatiotemporal task information set to be divided.

[0078] The fifth step is to group at least one set of positioning spatiotemporal task information with the same floor number in the set of positioning spatiotemporal task information to be divided, thereby obtaining at least one set of positioning spatiotemporal task information groups.

[0079] The sixth step is to determine at least one set of positioning spatiotemporal task information groups to be divided as at least one set of filtering positioning spatiotemporal task information groups.

[0080] Step 7: For each selected location spatiotemporal task information group within the determined selection location spatiotemporal task information groups, perform the following construction process:

[0081] The first sub-step involves determining each of the three-dimensional coordinates included in the above-mentioned selected and positioned spatiotemporal task information group as a three-dimensional coordinate set.

[0082] The second sub-step involves generating a tetrahedral mesh corresponding to the aforementioned 3D coordinate set, where the coordinates of the vertices of each tetrahedron in the tetrahedral mesh are 3D coordinates from the aforementioned 3D coordinate set. In practice, the 3D coordinate set can be partitioned into tetrahedrals using the Delaunay algorithm to obtain the tetrahedral mesh corresponding to the aforementioned 3D coordinate set.

[0083] The third sub-step involves performing the following steps for each tetrahedron in the aforementioned tetrahedral mesh:

[0084] Sub-step one: Determine the coordinates of each vertex of the tetrahedron mentioned above;

[0085] Sub-step two: For each vertex coordinate in the vertex coordinate system, perform the following steps:

[0086] Step 1: Determine the construction type identifier included in the selected positioning spatiotemporal task information where the vertex coordinates are located in the selected positioning spatiotemporal task information group as the target construction type identifier.

[0087] Step two: Based on the target construction type identifier mentioned above, determine the contour-related weights corresponding to the vertex coordinates. In practice, this can be done by querying the contour-related weights corresponding to the target construction type identifier from a pre-built mapping table of construction type identifiers and contour-related weights. For example, the mapping relationship in the above mapping table can be: "Construction type identifier: Concrete pouring corresponds to contour-related weight: 0.8; Construction type identifier: Decoration and finishing corresponds to contour-related weight: 0.4".

[0088] Sub-step three involves generating target contour-related weights corresponding to the aforementioned tetrahedron based on the determined contour-related weights. In practice, the average of the contour-related weights can be used as the target contour-related weight.

[0089] Sub-step four: Determine the radius of the circumcircle of the aforementioned tetrahedron as the target radius.

[0090] Sub-step five involves generating the weighted circumsphere radius based on the aforementioned target radius and target contour-related weights. In practice, the ratio of the target radius to the target contour-related weights can be used to determine the weighted circumsphere radius.

[0091] Sub-step six: In response to determining that the weighted circumscribed sphere radius is less than or equal to a preset radius value, the edges of the aforementioned tetrahedrons in the tetrahedral mesh are removed to update the tetrahedral mesh.

[0092] The fourth sub-step involves defining the updated tetrahedral mesh as the 3D sub-model of the building.

[0093] The eighth step is to stitch together the determined 3D sub-models of the building to obtain the 3D building model. In practice, geometric computing libraries such as CGAL and OpenVDB can be used to perform a union operation on the various 3D sub-models of the building, i.e., the various tetrahedral meshes, and the merged tetrahedral mesh is determined as the 3D building model.

[0094] The above-described technical solution and related content, as an inventive point of the disclosed embodiments of this invention, solve the technical problem of "the generated building outline being 'skewed' by a large number of low-relevance indoor work points, resulting in a significant difference between the 3D building model and the actual building appearance." The factors that cause the generated building outline to be "skewed" by a large number of low-relevance indoor work points, resulting in a significant difference between the 3D building model and the actual building appearance, are often as follows: Due to the existence of various construction tasks during the building construction process (such as curtain wall installation, interior decoration, electromechanical installation, etc.), these tasks have different relevance to the building outline (curtain wall installation points are close to the outer boundary of the building, while interior decoration points are located inside the building). Traditional algorithms treat all trajectory points as geometrically equal objects, failing to distinguish between highly relevant and low-relevance points, leading to the generated building outline being "skewed" by a large number of low-relevance indoor work points, resulting in a significant difference between the 3D building model and the actual building appearance. Solving these factors can reduce the effect of the generated building outline being "skewed" by a large number of low-relevance indoor work points, thus reducing the difference between the generated building outline and the actual building appearance. To achieve this effect, firstly, the spatial-temporal positioning information clusters of each first-floor indoor location included in the aforementioned target positioning spatial-temporal task information clusters are defined as first-floor indoor positioning spatial-temporal task information clusters. The spatial-temporal positioning information of each first-floor indoor location included in the aforementioned first-floor indoor positioning spatial-temporal task information clusters are then defined as filtered positioning spatial-temporal task information groups. The spatial-temporal positioning information clusters of each target positioning spatial-temporal task information clusters that are not first-floor locations are defined as non-first-floor positioning spatial-temporal task information clusters. The spatial-temporal positioning information of each non-first-floor location included in the aforementioned non-first-floor positioning spatial-temporal task information clusters are defined as positioning spatial-temporal task information sets to be divided. At least one set of positioning spatial-temporal task information with the same floor number in the set of positioning spatial-temporal task information to be divided is grouped together, resulting in at least one set of positioning spatial-temporal task information sets to be divided. The at least one set of positioning spatial-temporal task information sets to be divided is then defined as at least one filtered positioning spatial-temporal task information group. Thus, the filtered positioning spatial-temporal task information group corresponding to each floor in the actual building can be determined, so as to generate a 3D sub-model of each floor. Next, for each of the identified spatiotemporal task information groups, the following construction process is performed: First, the three-dimensional coordinates included in the identified spatiotemporal task information group are determined as a three-dimensional coordinate set. Second, a tetrahedral mesh corresponding to the three-dimensional coordinate set is generated, wherein the coordinates of the vertices of each tetrahedron in the tetrahedral mesh are three-dimensional coordinates from the three-dimensional coordinate set. Thus, a tetrahedral mesh based on Delaunay triangulation can be constructed within each floor. Third, for each tetrahedron in the tetrahedral mesh, the following steps are performed: First, the coordinates of each vertex of the tetrahedron are determined.The second step involves performing the following steps for each vertex coordinate: First, determine the construction type identifier included in the filtered positioning spatiotemporal task information of the vertex coordinates within the filtered positioning spatiotemporal task information group as the target construction type identifier. Second, based on the target construction type identifier, determine the contour-related weights corresponding to the vertex coordinates. This allows assigning each trajectory point a contour-related weight matching its construction task type (e.g., points for highly relevant tasks such as curtain wall installation receive high weights, while points for low-relevance tasks such as interior masonry receive low weights). Third, based on the determined contour-related weights, generate the target contour-related weights corresponding to the tetrahedron. Fourth, determine the circumcircle radius of the tetrahedron as the target radius. Fifth, based on the target radius and the target contour-related weights, generate the weighted circumsphere radius. Sixth, in response to determining that the weighted circumsphere radius is less than or equal to a preset radius value, remove the edges of the tetrahedron in the tetrahedral mesh to update the tetrahedral mesh. Therefore, vertex weights can be incorporated into the geometric judgment. For tetrahedrons with high average vertex weights (representing regions dominated by highly relevant points), the weighted circumsphere radius will be enlarged. For tetrahedrons with low average vertex weights (representing regions dominated by low-relevance points), the weighted circumsphere radius will be compressed. This filters out tetrahedrons with insufficient weighted circumsphere radii, reducing the "straightening" of low-relevance points and preventing discrepancies between the 3D building model and the actual building appearance. The updated tetrahedral mesh is then used as the 3D building sub-model. This results in 3D building sub-models for each floor, dominated by high-weight points and filtered by low-weight points. These sub-models are then stitched together to obtain the final 3D building model. Finally, a complete 3D building model is obtained by stitching together the floor sub-models. By replacing the traditional circumcircle radius with a weighted circumsphere radius as the basis for retaining tetrahedral edges, points with high weight (strong correlation with the building outline) play a dominant role in outline generation, while points with low weight (weak correlation) are filtered out. This solves the problem of the traditional algorithm treating all points equally, which causes the outline to be "skewed" by low-correlation points, resulting in a discrepancy with the actual building appearance.

[0095] The above embodiments of the present invention have the following beneficial effects: the method for creating a 3D building model based on personnel positioning trajectories according to some embodiments of the present invention reduces the gap between the appearance of the constructed 3D building model and the actual building. Specifically, the reason for the large gap between the appearance of the constructed 3D building model and the actual building is that: the building outline in the CAD drawing is identified, and a 3D model is generated by extrusion. Since the drawing only reflects the design expectation rather than the actual construction result, and it is difficult to accurately express complex building structures such as irregular curved surfaces and irregular bay windows, the generated model is often a regular box-shaped model (when the building has complex curves, slopes, decorations and other irregular elements, a simple box-shaped mesh is difficult to accurately capture these features), which is difficult to truly reflect the actual outer contour of the building, resulting in a large gap between the appearance of the constructed 3D building model and the actual building. Based on this, the method for creating a 3D building model based on personnel positioning trajectories disclosed in some embodiments of the present invention first obtains a pre-collected set of spatiotemporal task information of construction personnel positioning. Thus, it is possible to obtain a set of information representing the trajectory of each construction worker when working in the building (such as the curtain wall), and each piece of information includes a construction type identifier, timestamp, 3D coordinate data and construction worker identifier and floor number. Next, the aforementioned set of spatiotemporal task information for construction personnel is filtered for its association with the building's outer contour, resulting in a set of target spatiotemporal task information for construction personnel. This allows for the removal of task trajectories unrelated to the building's outer contour, such as material transport and site cleaning, while retaining trajectories potentially touching the building's boundaries, such as curtain wall installation and rebar tying. The target set of spatiotemporal task information is then grouped to obtain individual target set of spatiotemporal task information, each with a corresponding construction personnel identifier. Next, each target set of spatiotemporal task information is filtered for its floor elevation range, resulting in filtered sets of spatiotemporal task information for construction personnel. Based on the floor elevation information, points outside the elevation range irrelevant to the task on that floor are removed from the worker's trajectory, ensuring that the trajectory data for each floor matches the actual floor position vertically. Next, for each of the aforementioned filtering construction worker positioning spatiotemporal task information groups, a cross-layer reverse-deduction outdoor trajectory elimination process is performed on each filtering construction worker positioning spatiotemporal task information group to generate a target positioning spatiotemporal task information cluster. This target positioning spatiotemporal task information cluster includes non-first-floor positioning spatiotemporal task information clusters and first-floor indoor positioning spatiotemporal task information clusters. Therefore, the outdoor activity trajectory of the same worker operating outside the first floor can be used as a template to reverse-engineer and eliminate noise points located in the outdoor leveling area within their first-floor work trajectory, thus obtaining the target positioning spatiotemporal task information cluster.Subsequently, a 3D building model is created based on the generated clusters of spatiotemporal task information for each target location. This results in a 3D building model with an outline composed of clusters of actual worker trajectory points. Because the building outline is constructed using the spatiotemporal task information corresponding to the trajectories left by workers during actual construction work at the building boundaries, it reflects the actual activity range of workers in tasks such as curtain wall installation and exterior wall work. Its outer edges naturally conform to the actual physical boundaries of the building, avoiding the model distortion problems caused by the inability of drawings to accurately represent irregular structures when relying on blueprints for modeling. This allows the generated 3D building model to realistically present irregular contour features such as curves and slopes, thereby reducing the discrepancy between the appearance of the constructed 3D building model and the actual building.

[0096] Further reference Figure 2 As an implementation of the methods shown in the figures, this invention provides some embodiments of a building 3D model creation device based on personnel positioning trajectories. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0097] like Figure 2 As shown, a building 3D model creation device 200 based on personnel positioning trajectories in some embodiments includes: an acquisition unit 201, a first filtering processing unit 202, a grouping processing unit 203, a second filtering processing unit 204, a rejection processing unit 205, and a creation unit 206. The acquisition unit 201 is configured to acquire a pre-collected set of spatiotemporal task information of construction personnel positioning; the first filtering processing unit 202 is configured to perform building outline-related task trajectory filtering processing on the aforementioned set of spatiotemporal task information of construction personnel positioning to obtain a target set of spatiotemporal task information of construction personnel positioning; the grouping processing unit 203 is configured to perform grouping processing on the aforementioned set of target set of spatiotemporal task information of construction personnel positioning to obtain various target set of spatiotemporal task information of construction personnel positioning, wherein each target set of spatiotemporal task information of construction personnel positioning has a corresponding construction personnel identifier; the second filtering processing unit 204 is configured to process the aforementioned set of target set of spatiotemporal task information of construction personnel positioning... The information group is filtered by floor elevation range to obtain each filtered construction personnel positioning spatiotemporal task information group; the elimination processing unit 205 is configured to perform cross-floor reverse deduction of outdoor trajectory elimination processing on each of the above filtered construction personnel positioning spatiotemporal task information groups to generate a target positioning spatiotemporal task information cluster, wherein the target positioning spatiotemporal task information cluster includes non-first floor positioning spatiotemporal task information cluster and first floor indoor positioning spatiotemporal task information cluster; the creation unit 206 is configured to create a three-dimensional building model based on the generated target positioning spatiotemporal task information clusters.

[0098] It is understandable that the units described in the device 200 are related to the reference. Figure 1 The steps in the method described above correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 200 and the units contained therein, and will not be repeated here.

[0099] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present invention. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed in this invention.

[0100] like Figure 3 As shown, the electronic device 300 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0101] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0102] In particular, according to some embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 309, or installed from a storage device 308, or installed from a ROM 302. When the computer program is executed by the processing device 301, it performs the functions defined in the methods of some embodiments disclosed in this invention.

[0103] It should be noted that the computer-readable medium described in some embodiments of this invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination of both. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0104] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0105] Computer-readable media may be contained within an electronic device or may exist independently of the electronic device. A computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: perform building outline-related task trajectory filtering on the aforementioned set of spatiotemporal task information for construction personnel positioning to obtain a target set of spatiotemporal task information for construction personnel positioning; group the aforementioned set of target set of spatiotemporal task information for construction personnel positioning to obtain various target set of spatiotemporal task information for construction personnel positioning, wherein each target set of spatiotemporal task information for construction personnel positioning has a corresponding construction personnel identifier; perform floor elevation range filtering on each target set of spatiotemporal task information for construction personnel positioning to obtain various filtered sets of spatiotemporal task information for construction personnel positioning; for each filtered set of spatiotemporal task information for construction personnel positioning, to perform cross-floor reverse-deduction outdoor trajectory removal processing on each filtered set of spatiotemporal task information for construction personnel positioning to generate a cluster of target spatiotemporal task information for positioning, wherein the cluster of target spatiotemporal task information for positioning includes a cluster of non-first-floor positioning spatiotemporal task information and a cluster of first-floor indoor positioning spatiotemporal task information; and create a three-dimensional model of the building based on the generated clusters of target spatiotemporal task information for positioning.

[0106] Computer program code for performing operations of some embodiments of the present invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0108] The units described in some embodiments of this invention can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including an acquisition unit, a first filtering unit, a grouping unit, a second filtering unit, a rejection unit, and a creation unit. The names of these units do not necessarily limit the specific unit; for example, the acquisition unit can also be described as "a unit that acquires a pre-collected set of spatiotemporal task information on the location of construction personnel."

[0109] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0110] The above description is merely a selection of preferred embodiments of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention as described in the disclosed embodiments is not limited to technical solutions formed by specific combinations of technical features, but should also cover other technical solutions formed by arbitrary combinations of technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting features with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A method for creating a 3D building model based on personnel positioning trajectory, characterized by: Acquire a pre-collected set of spatiotemporal task information on the location of construction personnel, wherein the set of spatiotemporal task information on the location of construction personnel is collected through the following steps, characterized by: Within a preset time period, the system receives spatiotemporal task information of each construction worker sent by each preset positioning terminal. Each preset positioning terminal sends the spatiotemporal task information of the construction worker at a preset time interval. The preset positioning terminal is worn by the construction worker in the preset building. The spatiotemporal task information of the construction worker includes construction type identifier, timestamp, three-dimensional coordinate data, construction worker identifier, and floor number. The received spatiotemporal task information of each construction worker is determined as the spatiotemporal task information set of construction workers. The spatiotemporal task information set of the construction personnel is subjected to building outline-related task trajectory filtering processing to obtain the spatiotemporal task information set of the target construction personnel. The target construction personnel location spatiotemporal task information set is grouped to obtain each target construction personnel location spatiotemporal task information group, wherein each target construction personnel location spatiotemporal task information group has a corresponding construction personnel identifier. The spatiotemporal task information groups for the location of each target construction worker are filtered by floor elevation range to obtain each filtered spatiotemporal task information group for the location of the construction worker. For each of the filtering construction personnel positioning spatiotemporal task information groups, a cross-layer reverse-dial outdoor trajectory elimination process is performed on each filtering construction personnel positioning spatiotemporal task information group to generate a target positioning spatiotemporal task information cluster. The target positioning spatiotemporal task information cluster includes non-first-floor positioning spatiotemporal task information clusters and first-floor indoor positioning spatiotemporal task information clusters. The process of performing cross-layer reverse-dial outdoor trajectory elimination on each filtering construction personnel positioning spatiotemporal task information group to generate the target positioning spatiotemporal task information cluster is characterized by: At least one of the filtered construction personnel positioning spatiotemporal task information whose floor number meets the first preset condition is identified as the first floor positioning spatiotemporal task information cluster. At least one target construction worker positioning time and space task information in each target construction worker positioning time and space task information group whose floor number in the target construction worker positioning time and space task information group corresponding to the filtered construction worker positioning time and space task information group does not meet the preset conditions is identified as a non-first floor positioning time and space task information cluster. Each three-dimensional coordinate included in the non-first-layer positioning spatiotemporal task information cluster is determined as a target three-dimensional coordinate. Each target three-dimensional coordinate includes a horizontal coordinate value, a vertical coordinate value, and a height value. The target three-dimensional coordinate corresponds to a non-first-layer positioning spatiotemporal task information in the non-first-layer positioning spatiotemporal task information cluster. At least one target three-dimensional coordinate that satisfies the preset screening conditions is determined as the three-dimensional coordinate of each outdoor activity. Each three-dimensional coordinate included in the first-layer positioning spatiotemporal task information cluster is determined as a first-layer three-dimensional coordinate; The three-dimensional coordinates of each outdoor activity are determined as the three-dimensional coordinates of each first cluster to be clustered. The three-dimensional coordinates of each first layer are determined as the three-dimensional coordinates of each second cluster to be clustered. Clustering processing is performed on each of the first three-dimensional coordinates to be clustered and each of the second three-dimensional coordinates to be clustered to obtain each cluster of three-dimensional coordinates; Each cluster of three-dimensional coordinates contains at least one cluster of three-dimensional coordinates to be clustered as at least one outdoor three-dimensional coordinate group. Each of the first-layer three-dimensional coordinates is defined as the first three-dimensional coordinate set; Each outdoor three-dimensional coordinate included in at least one outdoor three-dimensional coordinate set is defined as a second three-dimensional coordinate set; The intersection of the first three-dimensional coordinate set and the second three-dimensional coordinate set is determined as the three-dimensional coordinate intersection to be removed; For each three-dimensional coordinate to be removed in the intersection of the three-dimensional coordinates to be removed, the first-layer positioning spatiotemporal task information containing the three-dimensional coordinate to be removed in the first-layer positioning spatiotemporal task information cluster is removed in order to update the first-layer positioning spatiotemporal task information cluster. The updated first-layer positioning spatiotemporal mission information cluster is identified as the first-layer indoor positioning spatiotemporal mission information cluster. The non-first-level positioning spatiotemporal task information cluster and the first-level indoor positioning spatiotemporal task information cluster are identified as the target positioning spatiotemporal task information cluster set; Based on the generated spatiotemporal task information clusters for each target location, a 3D building model is created.

2. The method according to claim 1, wherein, Each non-first-floor positioning spatiotemporal task information in the non-first-floor positioning spatiotemporal task information cluster includes a task type identifier, timestamp, three-dimensional coordinate data, construction personnel identifier, and floor number. The method for creating a three-dimensional building model based on the generated target positioning spatiotemporal task information clusters is characterized by: For each target positioning spatiotemporal task information cluster in the various target positioning spatiotemporal task information cluster sets, perform the following steps: The floor numbers included in the non-first-floor positioning spatiotemporal task information cluster of the target positioning spatiotemporal task information cluster are determined as the floor number set; The floor numbers in the floor number set are deduplicated to obtain a deduplicated floor number set; For each deduplicated floor number in the deduplicated floor number set, at least one non-first-floor positioning spatiotemporal task information containing the deduplicated floor number in the non-first-floor positioning spatiotemporal task information cluster is determined as the positioning spatiotemporal task information cluster corresponding to the deduplicated floor number. The determined positioning spatiotemporal task information clusters and the first-floor indoor positioning spatiotemporal task information clusters included in the target positioning spatiotemporal task information cluster set are determined as the reference positioning spatiotemporal task information cluster set. Based on the determined spatiotemporal mission information clusters of each reference positioning, a 3D model of the building is created.

3. The method according to claim 1, wherein, The spatiotemporal task information for locating construction workers includes construction type identifier, timestamp, three-dimensional coordinate data, construction worker identifier, and floor number. The method involves filtering the construction worker location spatiotemporal task information set using a building outline-related task trajectory to obtain the target construction worker location spatiotemporal task information set. Its characteristic is: For each construction worker's location spatiotemporal task information in the construction worker location spatiotemporal task information set, perform the following building outline-related task trajectory filtering steps: Determine the construction type identifier, including the spatiotemporal task information for the location of construction personnel; In response to determining that the construction type identifier is not in the preset building outline construction type identifier table, the construction personnel positioning spatiotemporal task information is deleted from the construction personnel positioning spatiotemporal task information set to update the construction personnel positioning spatiotemporal task information set; The updated spatiotemporal task information set for the location of construction personnel is determined as the target spatiotemporal task information set for the location of construction personnel.

4. The method according to claim 1, wherein, The spatiotemporal task information for locating construction personnel includes construction type identifier, timestamp, three-dimensional coordinate data, construction personnel identifier, and floor number. The information is characterized by grouping the target construction personnel location spatiotemporal task information set to obtain various target construction personnel location spatiotemporal task information groups. The process involves deduplicating the identifiers of each construction worker in the spatiotemporal task information set for locating the target construction workers, and then determining the deduplicated identifiers as the deduplicated construction worker identifier set. For each deduplicated construction worker identifier in the deduplicated construction worker identifier set, at least one target construction worker positioning spatiotemporal task information in the target construction worker positioning spatiotemporal task information set containing the deduplicated construction worker identifier is determined as a target construction worker positioning spatiotemporal task information group with the deduplicated construction worker identifier.

5. The method according to claim 1, wherein, The spatiotemporal task information for locating construction personnel includes a construction type identifier, a timestamp, three-dimensional coordinate data, and construction personnel identifiers and floor numbers. The three-dimensional coordinate data includes three-dimensional coordinates. The process of filtering each target construction personnel spatiotemporal task information group by floor elevation range to obtain each filtered construction personnel spatiotemporal task information group is characterized by: For each target construction worker location spatiotemporal task information group within each target construction worker location spatiotemporal task information group, perform the following floor elevation range filtering steps for each target construction worker location spatiotemporal task information within each target construction worker location spatiotemporal task information group: The floor number included in the target construction personnel location spatiotemporal task information is determined as the floor number to be queried; Query the floor elevation range corresponding to the floor number; In response to determining that the height value in the three-dimensional coordinates included in the target construction worker's location spatiotemporal task information is not within the floor elevation range, the target construction worker's location spatiotemporal task information is deleted from the target construction worker's location spatiotemporal task information group in order to update the target construction worker's location spatiotemporal task information group; Each updated target construction worker location spatiotemporal task information group is designated as a filter construction worker location spatiotemporal task information group.

6. A device for creating a 3D building model based on personnel positioning trajectory, characterized in that: The acquisition unit is configured to acquire a pre-collected set of spatiotemporal task information for construction workers, wherein the set of spatiotemporal task information for construction workers is acquired through the following steps, characterized by: receiving spatiotemporal task information for each construction worker sent by each preset positioning terminal within a preset time period, wherein each preset positioning terminal sends the spatiotemporal task information for construction workers at preset time intervals, the preset positioning terminals being worn by construction workers in preset buildings, and the spatiotemporal task information for construction workers including construction type identifier, timestamp, three-dimensional coordinate data, construction worker identifier, and floor number; and determining the received spatiotemporal task information for each construction worker as the set of spatiotemporal task information for construction workers. The first filtering processing unit is configured to perform building outline-related task trajectory filtering processing on the spatiotemporal task information set of the construction personnel positioning to obtain the target spatiotemporal task information set of the construction personnel positioning. The grouping processing unit is configured to group the target construction personnel location spatiotemporal task information set to obtain each target construction personnel location spatiotemporal task information group, wherein each target construction personnel location spatiotemporal task information group has a corresponding construction personnel identifier. The second filtering unit is configured to perform floor elevation range filtering on the spatiotemporal task information group of each target construction worker to obtain each filtered spatiotemporal task information group of construction workers. The elimination processing unit is configured to perform cross-floor reverse-dial outdoor trajectory elimination processing on each of the filtering construction worker positioning spatiotemporal task information groups to generate a target positioning spatiotemporal task information cluster. The target positioning spatiotemporal task information cluster includes non-first-floor positioning spatiotemporal task information clusters and first-floor indoor positioning spatiotemporal task information clusters. The cross-floor reverse-dial outdoor trajectory elimination processing is performed on each filtering construction worker positioning spatiotemporal task information group to generate the target positioning spatiotemporal task information cluster. The characteristic of this process is that at least one filtering construction worker in the filtering construction worker positioning spatiotemporal task information group whose floor number meets a first preset condition is excluded. Personnel positioning spatiotemporal task information is determined as the first-floor positioning spatiotemporal task information cluster; at least one target construction worker positioning spatiotemporal task information in each target construction worker positioning spatiotemporal task information group whose floor number does not meet the preset condition in the target construction worker positioning spatiotemporal task information group corresponding to the filtered construction worker positioning spatiotemporal task information group is determined as a non-first-floor positioning spatiotemporal task information cluster; each three-dimensional coordinate included in the non-first-floor positioning spatiotemporal task information cluster is determined as each target three-dimensional coordinate, wherein each target three-dimensional coordinate includes a horizontal coordinate value, a vertical coordinate value, and a height value, and the target three-dimensional coordinate is related to a non-first-floor positioning spatiotemporal task in the non-first-floor positioning spatiotemporal task information cluster. Information correspondence; at least one target 3D coordinate satisfying the preset screening conditions is determined as each outdoor activity 3D coordinate; each 3D coordinate included in the first-layer positioning spatiotemporal task information cluster is determined as each first-layer 3D coordinate; each outdoor activity 3D coordinate is determined as each first-layer 3D coordinate to be clustered; each first-layer 3D coordinate is determined as each second-layer 3D coordinate to be clustered; clustering processing is performed on each first-layer 3D coordinate and each second-layer 3D coordinate to obtain each clustered 3D coordinate cluster group; at least one clustered 3D coordinate cluster group containing the first-layer 3D coordinate to be clustered is determined as at least one outdoor 3D coordinate group; the respective The first set of three-dimensional coordinates is defined as the first three-dimensional coordinate set; the outdoor three-dimensional coordinates included in at least one outdoor three-dimensional coordinate group are defined as the second three-dimensional coordinate set; the intersection of the first three-dimensional coordinate set and the second three-dimensional coordinate set is defined as the intersection of the three-dimensional coordinates to be removed; for each three-dimensional coordinate to be removed in the intersection of the three-dimensional coordinates to be removed, the first-layer positioning spatiotemporal task information containing the three-dimensional coordinate to be removed is removed to update the first-layer positioning spatiotemporal task information cluster; the updated first-layer positioning spatiotemporal task information cluster is defined as the first-layer indoor positioning spatiotemporal task information cluster; the non-first-layer positioning spatiotemporal task information cluster and the first-layer indoor positioning spatiotemporal task information cluster are defined as the target positioning spatiotemporal task information cluster set; The creation unit is configured to create a 3D building model based on the generated clusters of spatiotemporal task information for each target location.

7. An electronic device, characterized in that: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 5.

8. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 5.

Images