Space-time linkage-based digital twin motion trajectory rendering method and system

Abstract

The application discloses a kind of based on spatiotemporal linkage's digital twin motion trajectory rendering method and system, it is related to digital twin technical field, the method includes: based on multi-scene adaptive positioning strategy, determine the physical positioning data of target object in current position scene, current position scene is any one in ordinary scene, indoor complex scene, indoor-outdoor link scene and sheltered scene;Mapping relationship between physical coordinate system and twin model coordinate system is obtained, based on mapping relationship, physical positioning data is converted into twin positioning data;Based on incremental update rendering strategy, determine the change trajectory point corresponding to twin positioning data;Based on change trajectory point, the motion trajectory of target object is rendered in the twin model of building. Through the above mode, reduce the deviation and lag between twin model point and physical entity position, improve trajectory positioning accuracy, and can be applied to different scenes, ensure positioning accuracy in different scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital twinning, in particular to a digital twinning motion trajectory rendering method and system based on space-time linkage. BACKGROUND

[0002] Existing digital twinning is mostly realized based on static building information modeling (BIM), lacks space-time reference linked with the physical world in real time, and UWB (Ultra Wide Band) positioning data is only stored as independent data and not deeply bound with the three-dimensional coordinate system of the twinning model, resulting in that the physical position of the device / personnel cannot be accurately mapped with the point in the twinning model, and it is difficult to be applied to complex scenes.

[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0004] The main purpose of the present application is to provide a digital twinning motion trajectory rendering method and system based on space-time linkage, aiming to solve the technical problems that the physical position of the target object cannot be accurately mapped with the point in the twinning model in the prior art, and it is difficult to be applied to complex scenes.

[0005] To achieve the above purpose, the present application provides a digital twinning motion trajectory rendering method based on space-time linkage, the method comprising:

[0006] Obtaining the current position scene of the target object in the building, determining the physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, the current position scene being any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene, and a shielding scene;

[0007] Obtaining the mapping relationship between the physical coordinate system and the twinning model coordinate system, converting the physical positioning data into twinning positioning data based on the mapping relationship;

[0008] Determining the change trajectory point corresponding to the twinning positioning data based on an incremental update rendering strategy;

[0009] Rendering the motion trajectory of the target object in the twinning model of the building based on the change trajectory point, the rendering parameters of the motion trajectory being determined based on the user's visual angle distance.

[0010] In an embodiment, the step of determining the physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy comprises:

[0011] When the current location scene is an indoor complex scene, current positioning data of an ordinary ultra-wideband anchor point and current positioning data of an anti-interference ultra-wideband anchor point in the current location scene are respectively acquired, wherein the anti-interference ultra-wideband anchor point obtains corresponding current positioning data by filtering metal reflection signals in initial positioning data through a signal phase difference identification algorithm, and the anti-interference ultra-wideband anchor point adjusts parameters used for filtering based on signal noise intensity of the initial positioning data;

[0012] Based on signal intensity of the ordinary ultra-wideband anchor point and the anti-interference ultra-wideband anchor point, an ordinary positioning weight and an anti-interference positioning weight are determined.

[0013] Based on the current positioning data of the ordinary ultra-wideband anchor point, the ordinary positioning weight, the current positioning data of the anti-interference ultra-wideband anchor point, and the anti-interference positioning weight, physical positioning data of the target object in the current location scene is determined.

[0014] In an embodiment, based on a multi-scene adaptive positioning strategy, the step of determining the physical positioning data of the target object in the current location scene comprises:

[0015] When the current location scene is an indoor-outdoor connection scene, a label signal intensity detected by a connection ultra-wideband anchor point in the current location scene is acquired.

[0016] When the label signal intensity is less than a preset intensity threshold, based on distances between each location point and a connection line in the current location scene, a distance ratio of each location point in the current location scene is determined.

[0017] Based on the distance ratio of each location point in the current location scene, an ultra-wideband positioning weight and a Beidou positioning weight of each location point in the current location scene are calculated.

[0018] Ultra-wideband positioning data and Beidou positioning data of the target object in the current location scene are acquired.

[0019] Based on the ultra-wideband positioning data, the ultra-wideband positioning weight, the Beidou positioning data, and the Beidou positioning weight, physical positioning data of the target object in the current location scene is determined.

[0020] In an embodiment, based on a multi-scene adaptive positioning strategy, the step of determining the physical positioning data of the target object in the current location scene comprises:

[0021] When the current location scene is a shielding scene, shielding front positioning data and shielding front signal data within a preset time length are acquired.

[0022] determine an initial position before the occlusion, a moving speed, a moving direction change rate and a moving acceleration of the target object based on the pre-occlusion positioning data, and determine a signal attenuation rate based on the pre-occlusion signal data;

[0023] obtain historical trajectory data corresponding to the initial position before the occlusion, and determine a moving regularity feature based on the historical trajectory data;

[0024] generate a fusion trajectory feature based on the moving speed, the moving direction change rate, the moving acceleration, a distance between the initial position before the occlusion and a surrounding occlusion, the signal attenuation rate and the moving regularity feature;

[0025] input the fusion trajectory feature into a trajectory prediction model to obtain a predicted positioning coordinate of the target object;

[0026] determine physical positioning data of the target object in the current location scene based on the predicted positioning coordinate.

[0027] In an embodiment, before the step of determining the physical positioning data of the target object in the current location scene based on the predicted positioning coordinate, the method further comprises:

[0028] obtain an occlusion time of the target object, and determine an object type of the target object when the occlusion time is greater than a prediction time threshold;

[0029] when the object type is a person, calculate a horizontal direction vector based on a pre-occlusion effective trajectory point;

[0030] use the moving speed and the initial position before the occlusion as a current speed and a current coordinate respectively, and compare the current speed with a preset speed threshold;

[0031] when the current speed is greater than the preset speed threshold, calculate a deceleration prediction coordinate based on the current coordinate, the current speed, the horizontal direction vector and a first preset period, add the deceleration prediction coordinate into the predicted positioning coordinate, update the current coordinate based on the deceleration prediction coordinate, update the current speed based on a preset deceleration rate, and return to the step of comparing the current speed with the preset speed threshold;

[0032] when the current speed is less than or equal to the preset speed threshold, calculate a constant speed prediction coordinate based on the current coordinate, the preset speed threshold, the horizontal direction vector and a second preset period, and add the constant speed prediction coordinate into the predicted positioning coordinate.

[0033] In an embodiment, the step of obtaining the occlusion time of the target object, and determining the object type of the target object when the occlusion time is greater than a predicted duration threshold, further comprises:

[0034] When the object type is an AGV, determining a pre-occlusion path node and a path extension direction from a preset path;

[0035] Determining a fixed speed based on the moving speed and a preset ratio;

[0036] Determining a current path coordinate based on the pre-occlusion path node;

[0037] Based on the current path coordinate, the path direction vector corresponding to the path extension direction, the fixed speed, and a third preset period, calculating a predicted path coordinate, and adding the predicted path coordinate into the predicted positioning coordinate.

[0038] In an embodiment, the step of determining the changed trajectory point corresponding to the twin positioning data based on the incremental update rendering strategy comprises:

[0039] Based on the twin positioning data, calculating a three-dimensional coordinate difference value corresponding to a current trajectory point;

[0040] When the three-dimensional coordinate difference value is greater than a preset value, determining that there is an effective change in the trajectory, taking the current trajectory point and a neighboring trajectory point of the current trajectory point as changed trajectory points, and performing the step of rendering the motion trajectory of the target object in the twin model of the building based on the changed trajectory points;

[0041] When the three-dimensional coordinate difference value is less than or equal to a preset value, determining that there is no effective change in the trajectory, and returning to perform the step of obtaining a current location scene of a target object in a building, and determining physical positioning data of the target object in the current location scene based on a multi-scene adaptive positioning strategy.

[0042] In an embodiment, the step of rendering the motion trajectory of the target object in the twin model of the building based on the changed trajectory points further comprises:

[0043] Obtaining a user perspective position, and calculating a user perspective distance corresponding to the trajectory point position based on the user perspective position and the trajectory point position;

[0044] Determining a perspective distance range matched by the trajectory point position based on the user perspective distance corresponding to the trajectory point position;

[0045] Determining a rendering parameter of the trajectory point position based on the perspective distance range matched by the trajectory point position, the rendering parameter at least including a rendering accuracy level, a trajectory point size, and a trajectory line width.

[0046] In an embodiment, the method further comprises:

[0047] selecting a static reference object as a reference point in a digital twin model, and evaluating a health degree of the reference point based on a real-time coordinate intensity of the reference point;

[0048] when the health degree of the reference point meets an effective condition, determining that the reference point is an effective reference point, and determining a coordinate compensation value based on a real-time coordinate of the effective reference point and an initial calibration coordinate;

[0049] when the health degree of the reference point does not meet the effective condition, determining that the reference point is an ineffective reference point, and determining a coordinate compensation value based on a real-time coordinate of a backup reference point and an initial calibration coordinate;

[0050] optimizing a mapping relationship between a physical coordinate system and a twin model coordinate system based on the coordinate compensation value.

[0051] In addition, to achieve the above object, the present application also proposes a digital twin motion trajectory rendering system based on space-time linkage, which comprises:

[0052] a positioning module, configured to obtain a current position scene of a target object in a building, and determine physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, the current position scene being any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene, and a shielding scene;

[0053] a conversion module, configured to obtain a mapping relationship between a physical coordinate system and a twin model coordinate system, and convert the physical positioning data into twin positioning data based on the mapping relationship;

[0054] a rendering module, configured to determine a change trajectory point corresponding to the twin positioning data based on an incremental update rendering strategy;

[0055] The rendering module is further configured to render a motion trajectory of the target object in the twin model of the building based on the change trajectory point, and a rendering parameter of the motion trajectory is determined based on a user perspective distance.

[0056] In addition, to achieve the above object, the present application also proposes a digital twin motion trajectory rendering device based on space-time linkage, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the digital twin motion trajectory rendering method based on space-time linkage as described above.

[0057] In addition, in order to achieve the above-mentioned purpose, the application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program realizes the steps of the method for rendering a motion trajectory of a digital twin based on space-time linkage when executed by a processor.

[0058] In addition, in order to achieve the above-mentioned purpose, the application further provides a computer program product, which comprises a computer program, and the computer program realizes the steps of the method for rendering a motion trajectory of a digital twin based on space-time linkage when executed by a processor.

[0059] The application provides a method for rendering a motion trajectory of a digital twin based on space-time linkage, which comprises the following steps: acquiring a current position scene of a target object in a building; determining physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, wherein the current position scene is any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene and a shielding scene; acquiring a mapping relationship between a physical coordinate system and a twin model coordinate system; converting the physical positioning data into twin positioning data based on the mapping relationship; determining a change trajectory point corresponding to the twin positioning data based on an incremental update rendering strategy; and rendering a motion trajectory of the target object in a twin model of the building based on the change trajectory point, wherein a rendering parameter of the motion trajectory is determined based on a user perspective distance. BRIEF DESCRIPTION OF DRAWINGS

[0060] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0062] Figure 1 Flowchart of the method for rendering a motion trajectory of a digital twin based on space-time linkage according to Embodiment 1 of the present application;

[0063] Figure 2A trajectory prediction model schematic diagram of the digital twin motion trajectory rendering method based on space-time linkage provided by Embodiment One of the present application;

[0064] Figure 3 A flowchart schematic diagram of Embodiment Two of the digital twin motion trajectory rendering method based on space-time linkage of the present application;

[0065] Figure 4 A module structure schematic diagram of the digital twin motion trajectory rendering system based on space-time linkage of the present application;

[0066] Figure 5 A device structure schematic diagram of the hardware running environment involved in the digital twin motion trajectory rendering method based on space-time linkage of the present application.

[0067] The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0068] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and do not limit the present application.

[0069] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the drawings and specific embodiments of the specification.

[0070] The main solution of the present application embodiment is: obtaining a current position scene of a target object in a building, determining physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, the current position scene being any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene and a shielding scene; obtaining a mapping relationship between a physical coordinate system and a twin model coordinate system, converting the physical positioning data into twin positioning data based on the mapping relationship; determining a change trajectory point corresponding to the twin positioning data based on an incremental update rendering strategy; rendering a motion trajectory of the target object in the twin model of the building based on the change trajectory point, a rendering parameter of the motion trajectory being determined based on a user perspective distance.

[0071] The present application provides a solution that can adaptively position according to different scenes, find the accurate physical position of the target object, accurately map the physical position to the corresponding point of the twin model through coordinate conversion and coordinate calibration, and reduce the lag caused by mapping through real-time rendering, improve the trajectory positioning accuracy, which can be applied to different scenes, ensure the positioning accuracy in different scenes, and solve the technical problems that the physical position of the target object and the point of the twin model cannot be accurately mapped, and it is difficult to be applied to complex scenes.

[0072] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, or an electronic device capable of realizing the above functions, a digital twin motion trajectory rendering device based on space-time linkage, etc. The embodiment does not make specific limitations. The following takes the digital twin motion trajectory rendering device based on space-time linkage as an example to illustrate the embodiment and the following embodiments.

[0073] The embodiment of the application provides a digital twin motion trajectory rendering method based on space-time linkage. Figure 1 , Figure 1 The embodiment of the application provides a digital twin motion trajectory rendering method based on space-time linkage.

[0074] In the embodiment, the digital twin motion trajectory rendering method based on space-time linkage comprises steps S10-S40:

[0075] Step S10, obtaining a current position scene of a target object in a building, determining physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, the current position scene being any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene and a shielding scene;

[0076] It should be noted that the building of the embodiment is a digital twin covered building, such as an industrial plant, a high-speed rail station, etc. Ultra-wideband (UWB) anchor points are deployed in the building according to the pre-set density requirements, for example, indoor areas are set at an interval of 5m x 5m, with an installation height of 2.5m (avoiding metal pipes and strong electrical equipment), and outdoor areas are set at an interval of 10m x 10m, which can be installed on the top of a street lamp / monitoring pole (height 5m, ensuring unobstructed view), and the embodiment does not make specific limitations.

[0077] It can be understood that the target object is an object that needs to be tracked and rendered at present, such as a person, an AGV (Automated Guided Vehicle), equipment, etc., and the embodiment does not make specific limitations. The target object usually carries a UWB tag, such as setting a UWB tag in a person's ID card or attaching a UWB tag to equipment. The positioning information of the target object can be obtained by receiving the signal (usually emitted at intervals) emitted by the UWB tag through the UWB anchor point, so as to obtain the positioning coordinates of the target object in the physical coordinate system (UWB coordinate system), i.e. the physical positioning data.

[0078] Additionally, it should be noted that the current location scenario refers to the scenario in which the target object is located. The current location scenario typically falls into one of the following categories: ordinary scenario, complex indoor scenario, indoor-outdoor transition scenario, or occlusion scenario. A complex indoor scenario is a scenario with a relatively complex indoor environment, such as a scene with dense metal elements or multiple reflections, for example, an equipment workshop. An indoor-outdoor transition scenario is a transitional area between indoors and outdoors, such as a park entrance or parking garage passage. An occlusion scenario is a scenario where the signal emitted by the UWB tag is blocked, such as equipment obstruction or dense crowds. An ordinary scenario is a more conventional scenario, i.e., any scenario other than a complex indoor scenario, an indoor-outdoor transition scenario, or an occlusion scenario.

[0079] Understandably, different scenarios require different judgment methods. For example, when the UWB tag enters a pre-defined complex indoor area, the current location scenario is considered a complex indoor scenario; when the UWB tag enters a pre-defined indoor-outdoor transition area (usually consisting of half indoor and half outdoor areas, e.g., 5m x 5m indoors and outdoors), the current location scenario is considered an indoor-outdoor transition scenario; if no signal from the UWB tag can be detected within a pre-defined time period (e.g., 2 seconds), the current location scenario is considered an occlusion scenario. Different scenarios employ different positioning methods, i.e., a multi-scenario adaptive positioning strategy.

[0080] In one feasible implementation, if the current location scene is a normal scene, step S10 may include: when the current location scene is a normal scene, obtaining the positioning data of the ultra-wideband anchor point in the current location scene, and using the positioning data of the ultra-wideband anchor point as the physical positioning data of the target object in the current location scene.

[0081] Understandably, in ordinary scenarios, the positioning coordinates determined by the UWB anchor point are the physical positioning data of the target object in ordinary scenarios.

[0082] In another feasible implementation, if the current location scene is a complex indoor scene, step S10 may include steps A11 to A13:

[0083] Step A11: When the current location scene is a complex indoor scene, obtain the current positioning data of the ordinary ultra-wideband anchor point and the current positioning data of the anti-interference ultra-wideband anchor point in the current location scene respectively;

[0084] It should be noted that in addition to a plurality of conventional UWB anchors (ordinary ultra-wideband anchors), the indoor complex scene corresponding to the indoor complex area is usually also provided with at least one anti-interference ultra-wideband anchor, for example: 3 conventional UWB anchors (DW1000) + 1 anti-interference UWB anchor form a positioning network. In this embodiment, the anti-interference ultra-wideband anchor is provided with a built-in ceramic antenna and a signal filtering module, the anti-interference ultra-wideband anchor filters the metal reflection signal in the initial positioning data through a signal phase difference recognition algorithm to obtain corresponding current positioning data, and the anti-interference ultra-wideband anchor adjusts the parameters used for filtering based on the signal noise intensity of the initial positioning data.

[0085] It can be understood that the anti-interference ultra-wideband anchor can analyze the signal noise intensity in real time (such as noise >-70dBm is determined as high interference), automatically adjust the filtering parameters (enhance the filtering strength when the interference is high, and reduce the filtering delay when the interference is low), filter out the metal reflection signal in the preliminary positioning data through the signal phase difference recognition algorithm according to the adjusted filtering parameters, and only keep the direct signal, so that the phase difference fluctuation is less than 5°.

[0086] Step A12, determining the ordinary positioning weight and the anti-interference positioning weight based on the signal intensity of the ordinary ultra-wideband anchor and the anti-interference ultra-wideband anchor;

[0087] It can be understood that the weight is allocated according to the signal intensity received by the anchor, for example: the anchor with a signal intensity >-70dBm has a weight of 0.4, and the rest has a weight of 0.2. The positioning weight of the ordinary ultra-wideband anchor is the ordinary positioning weight, the positioning weight of the anti-interference ultra-wideband anchor is the anti-interference positioning weight, and the ordinary positioning weight + the anti-interference positioning weight = 1.

[0088] Step A13, determining the physical positioning data of the target object in the current location scene based on the current positioning data of the ordinary ultra-wideband anchor, the ordinary positioning weight, the current positioning data of the anti-interference ultra-wideband anchor, and the anti-interference positioning weight.

[0089] It should be noted that the current positioning data is the positioning coordinate of the target object currently determined by the ordinary ultra-wideband anchor / anti-interference ultra-wideband anchor.

[0090] It can be understood that the current positioning data of the ordinary ultra-wideband anchor and the current positioning data of the anti-interference ultra-wideband anchor are weighted according to the determined ordinary positioning weight and anti-interference positioning weight, and the result calculated is the physical positioning data of the target object in the indoor complex scene.

[0091] It should be understood that if the signal of a certain anchor suddenly weakens (such as being temporarily blocked), the weight thereof is automatically reduced (the lowest is 0.1), so as to avoid affecting the overall accuracy.

[0092] In another possible implementation, if the current location scene is an indoor-outdoor connection scene, step S10 can include steps B11-B15:

[0093] Step B11, when the current location scene is an indoor-outdoor connection scene, acquiring a tag signal strength detected by a connection ultra-wideband anchor point in the current location scene;

[0094] It should be noted that the connection ultra-wideband anchor point is a conventional UWB anchor point arranged in an indoor-outdoor connection area corresponding to the indoor-outdoor connection scene. The tag signal strength is the strength of a signal of a UWB tag detected by the connection ultra-wideband anchor point.

[0095] Step B12, when the tag signal strength is less than a preset strength threshold, determining a distance ratio of each location point in the current location scene based on distances between the location points and a connection line in the current location scene;

[0096] It should be noted that, considering that the use of the Beidou system for positioning is more accurate outdoors, in the indoor-outdoor connection scene, the positioning result of the Beidou system and the positioning result of the UWB are combined to obtain the final physical positioning data.

[0097] It can be understood that the anchor point detects the tag signal strength in real time, and if the tag signal strength is less than -85 dBm, the positioning weight is dynamically adjusted by a smooth transition algorithm. The connection line is a demarcation line between the indoor and the outdoor, the distances between the location points in the current location scene and the connection line are calculated, the distance corresponding to the indoor location point adopts a positive value, and the distance corresponding to the outdoor location point adopts a negative value. The distance ratio includes a distance ratio of the indoor location point and a distance ratio of the outdoor location point. The distance ratio of the indoor location point is a ratio of the distance between the indoor location point and the connection line to the distance between the connection line and an indoor side boundary of the indoor connection area. The distance ratio of the outdoor location point is a ratio of the distance between the outdoor location point and the connection line to the distance between the connection line and an indoor side boundary of the outdoor connection area.

[0098] Step B13, calculating ultra-wideband positioning weights and Beidou positioning weights of each location point in the current location scene based on the distance ratios of the location points in the current location scene;

[0099] It should be noted that the ultra-wideband positioning weight is a positioning weight corresponding to the UWB positioning result, the Beidou positioning weight is a positioning weight corresponding to the Beidou system positioning result, and the ultra-wideband positioning weight + the Beidou positioning weight = 1.

[0100] It can be understood that, as the distance ratio decreases, the ultra-wideband positioning weight decreases, and the Beidou positioning weight increases. Illustratively, on the indoor side (UWB signal is strong), the distance ratio of the corresponding position point is larger, at this time the ultra-wideband positioning weight can be 100%, and the Beidou positioning weight can be 0; in the middle of the transition zone (UWB and Beidou signals are balanced), the distance ratio of the corresponding position point is at an intermediate value, the ultra-wideband positioning weight can be 50%, and the Beidou positioning weight can be 50%; on the outdoor side (Beidou signal is strong), the distance ratio of the corresponding position point is smaller, the ultra-wideband positioning weight can be 0, and the Beidou positioning weight can be 100%.

[0101] It should be understood that the deviation of the two positioning data can be compared in real time, and if the deviation is > 20 cm, the weight ratio is automatically fine-tuned (5% adjustment each time), to ensure smooth switching of the weight, and finally output a positioning result with a deviation < 20 cm.

[0102] Step B14, obtaining ultra-wideband positioning data and Beidou positioning data of the target object in the current position scene;

[0103] It should be noted that the ultra-wideband positioning data is the positioning result (positioning coordinates) of UWB, and the Beidou positioning data is the positioning result (positioning coordinates) of the Beidou system.

[0104] Step B15, determining physical positioning data of the target object in the current position scene based on the ultra-wideband positioning data, the ultra-wideband positioning weight, the Beidou positioning data, and the Beidou positioning weight.

[0105] It can be understood that, according to the ultra-wideband positioning weight and the Beidou positioning weight corresponding to the current position of the target object, the ultra-wideband positioning data and the Beidou positioning data are weighted respectively, and the result calculated is the physical positioning data of the target object in the indoor-outdoor transition scene.

[0106] In another possible implementation, if the current position scene is a shielding scene, step S10 can include steps C11-C16:

[0107] Step C11, when the current position scene is a shielding scene, obtaining shielding-pre positioning data and shielding-pre signal data within a preset time period;

[0108] It should be noted that the preset time period is a set time period for extracting shielding-pre related data, for example, 3s, 5s, which is not specifically limited in this embodiment. The shielding-pre positioning data is the positioning coordinates before shielding, and the shielding-pre signal data usually refers to the signal strength of the UWB tag obtained by the anchor point before shielding.

[0109] Step C12, determining the initial position before the occlusion, the moving speed, the moving direction change rate and the moving acceleration of the target object based on the pre-occlusion positioning data, and determining the signal attenuation rate based on the pre-occlusion signal data;

[0110] It can be understood that the last appearing position coordinate before the occlusion (i.e. the initial position before the occlusion) is determined according to the coordinates of the multiple points before the occlusion, and the moving speed, the moving direction change rate (e.g. turning 5° every 0.5s) and the moving acceleration of the target object are calculated. According to the pre-occlusion signal data, the signal attenuation rate is calculated, for example: from -72dBm to -93dBm, the signal attenuation rate is 0.7).

[0111] Step C13, obtaining the historical trajectory data corresponding to the initial position before the occlusion, and determining the moving law feature based on the historical trajectory data;

[0112] It can be understood that the historical trajectory data is extracted according to the initial position before the occlusion, and the corresponding moving law feature is determined, for example: people often move along the positive direction of the X axis.

[0113] Step C14, generating the fusion trajectory feature based on the moving speed, the moving direction change rate, the moving acceleration, the distance between the initial position before the occlusion and the surrounding occlusion, the signal attenuation rate and the moving law feature;

[0114] It should be noted that in this embodiment, the moving speed, the moving direction change rate and the moving acceleration are used as the motion feature, the moving law feature and the distance between the initial position before the occlusion and the surrounding occlusion are used as the environmental feature, and the signal attenuation rate is used as the label feature. In addition to the motion feature, the environmental feature and the label feature, other features, i.e. special features, can also be set, which are not limited in this embodiment. The motion feature, the environmental feature, the label feature and the special feature all have corresponding weights, i.e. the motion weight, the environmental weight, the label weight and the special weight. Among them, the distance between the initial position before the occlusion and the surrounding occlusion is quantified as a numerical value, for example: the distance of metal occlusion object <1m is recorded as 1, 1~3m is recorded as 0.5, and >3m is recorded as 0. The type of occlusion object can also be added, which is not limited in this embodiment.

[0115] It can be understood that the fusion trajectory feature is obtained by fusing the motion feature, the environmental feature, the label feature and the special feature, and the calculation relationship is: fusion trajectory feature = motion feature x motion weight + environmental feature x environmental weight + label feature x label weight + special feature x special weight.

[0116] Step C15, inputting the fusion trajectory feature into the trajectory prediction model to obtain the predicted positioning coordinate of the target object.

[0117] It should be noted that in the typical occlusion scene covering the target object (such as shelf occlusion, device blocking, and crowded area), complete trajectory data of 5s before occlusion + 3s during occlusion + 2s after recovery is collected, and at least 1000 valid samples (including normal occlusion, signal interference, and other sub-scenes) are collected for each scene. Abnormal data is removed, for example, signal strength mutation (fluctuation > 20dBm within 1s), coordinate jump (single sampling deviation > 30cm), and acceleration > 0.2m / s² when the tag is stationary. Missing data is supplemented, for example, linear interpolation is used to fill the missing coordinates of a single sampling period. The corresponding motion features, environmental features, tag features, and special feature fusion are extracted as input features for training. All input features are normalized (mapped to [0, 1]) to avoid dimension difference affecting model weights.

[0118] In addition, it should be noted that, referring to Figure 2 , the trajectory prediction model is based on an LSTM model, including an input layer, a hidden layer, and an output layer. The hidden layer includes two LSTM layers, the first layer has 64 neurons, and the second layer has 32 neurons. The activation function of the activation layer uses ReLU to avoid gradient disappearance. The output layer includes a fully connected layer, which can output predicted positioning coordinates (X, Y, Z). Training parameter configuration: the optimizer uses Adam optimizer with a learning rate of 0.001 (decaying to 0.0001 in the later training period); the loss function uses MSE (mean square error) to minimize the coordinate deviation; the number of iterations is set to 50 rounds, and the early stopping mechanism is used (stopping if the validation set loss does not decrease for 5 consecutive rounds); scene migration training: first train the initial model with general scene data, then fine-tune (transfer learning) with the data of the target building to reduce data collection.

[0119] Step C16, based on the predicted positioning coordinates, determining physical positioning data of the target object in the current location scene.

[0120] It can be understood that inputting the fused trajectory features into the trajectory prediction model can obtain the predicted positioning coordinates of the target object (with a timestamp), which can be used as the physical positioning data of the target object in the occlusion scene. The prediction time of the trajectory prediction model can be configured according to the type of the target object. Generally, the prediction time of personnel type / AGV type is 3s, and the prediction time of device type is 2s. The output is 30 predicted points of coordinates (3s x 10Hz) or 20 predicted points of coordinates (2s x 10Hz).

[0121] It should be understood that when the tag signal is recovered, the predicted positioning coordinates are compared with the actual UWB coordinates, if the deviation is > 5cm, linear interpolation method is used to correct point by point, and trajectory continuity check is added at the same time. After correction, check whether the trajectory is smoothly connected with the front and rear segments (deviation < 3cm), if not, re-optimize the interpolation parameters to ensure that the trajectory is not broken. In addition, if the predicted point overlaps with the obstacle (distance < 0.3m), automatically adjust the coordinates to the nearest safe position (such as offset 0.3m along the edge of the obstacle), to avoid wall penetration, collision and other predictions that do not conform to the physical logic.

[0122] Further, in a possible implementation, before step C16, further comprising: obtaining an occlusion time of the target object, determining an object type of the target object when the occlusion time is greater than a prediction duration threshold; when the object type is a person, calculating a horizontal direction vector based on the effective trajectory point before occlusion; taking the moving speed and the initial position before occlusion as the current speed and the current coordinates respectively, and comparing the current speed with a preset speed threshold; when the current speed is greater than the preset speed threshold, calculating a deceleration prediction coordinate based on the current coordinates, the current speed, the horizontal direction vector and a first preset period, adding the deceleration prediction coordinate into the predicted positioning coordinates, updating the current coordinates based on the deceleration prediction coordinate, and updating the current speed based on a preset deceleration rate, and returning to execute the step of comparing the current speed with the preset speed threshold; when the current speed is less than or equal to the preset speed threshold, calculating a constant speed prediction coordinate based on the current coordinates, the preset speed threshold, the horizontal direction vector and a second preset period, and adding the constant speed prediction coordinate into the predicted positioning coordinates.

[0123] It should be noted that the occlusion time is the duration that the target object has been in the occlusion scene, the prediction duration threshold is the set maximum duration of prediction, the object type is the type of the target object, different object types can set different prediction duration thresholds, for example: 3s for personnel type / AGV type, 2s for device type. If the occlusion time is greater than the prediction duration threshold, stop the model inference and start the placeholder coordinate generation. The generated placeholder coordinates are marked as virtual placeholder coordinates (transparency 30%) in the twin engine, which are clearly distinguished from the real coordinates (solid color) and the model prediction coordinates (semi-transparent 50%), to avoid visual confusion.

[0124] It can be understood that if the object type is a personnel type, the trajectory is continued to extend along the motion direction before the occlusion, and the speed is reduced at a fixed deceleration rate until the minimum constant speed standard is reached, which conforms to the natural motion characteristics of the personnel throughout the journey.

[0125] Specifically, the preset deceleration rate is set to 0.1m / s 2The preset speed threshold (minimum uniform speed threshold) is 0.2 m / s (the speed is not reduced after reducing to the value), the first preset period is 100 ms (1 placeholder point is generated every 100 ms), and the second preset period is 1 s (1 placeholder point is generated every 1 s). According to the direction of the line connecting the last two effective trajectory points (P1 and P2) before the occlusion, a horizontal direction vector (the Z-axis coordinate remains unchanged before the occlusion) is calculated, the average speed in the last 1 s before the occlusion is taken as the current speed (V0), the deceleration prediction coordinates are calculated every 100 ms, the deceleration prediction coordinates = current coordinates + current speed x horizontal direction vector x first preset period, the current speed is updated, the new current speed = original current speed - 0.01 m / s, when the speed reduces to 0.2 m / s, the deceleration is stopped, and the subsequent placeholder points are calculated at an interval of 1 s at a uniform speed, that is, the uniform speed prediction coordinates = current coordinates + preset speed threshold x horizontal direction vector x second preset period. Finally, all generated deceleration prediction coordinates and uniform speed prediction coordinates are added to the prediction positioning coordinates.

[0126] In a feasible implementation, when the object type is AGV, a path node before the occlusion and a path extension direction are determined from a preset path; a fixed speed is determined based on the moving speed and a preset ratio; a current path coordinate is determined based on the path node before the occlusion; and a prediction path coordinate is calculated based on the current path coordinate, a path direction vector corresponding to the path extension direction, the fixed speed, and a third preset period, and the prediction path coordinate is added to the prediction positioning coordinates.

[0127] It should be noted that, if the object type is AGV, a trajectory is generated at a fixed uniform speed along the extension direction of the path segment before the occlusion based on the preset path of the AGV, to ensure that the AGV path constraint is met.

[0128] It can be understood that the preset path of the AGV is obtained, the path node N1 corresponding to the last effective position before the occlusion and the next path node N2 are found, the subsequent path extension direction (N1 to N2) is determined, the fixed speed (V = V0 x 0.8) is calculated at 80% (preset ratio) of the average speed in the last 1 s before the occlusion, the third preset period is 100 ms (1 placeholder point is generated every 100 ms), the prediction path coordinate is calculated every 100 ms along the path extension direction, the prediction path coordinate = current path coordinate + fixed speed x path direction vector x third preset period. If the calculated prediction path coordinate has extended to the next path node N2, and there is no subsequent path node, the extension is stopped, and the N2 coordinate is maintained until the signal is restored, if the prediction path coordinate has not extended to the next path node N2, the current path coordinate is updated according to the prediction path coordinate, and the next new prediction path coordinate is continuously generated. Finally, all generated prediction path coordinates are added to the prediction positioning coordinates.

[0129] In a feasible implementation, when the object type is a device, the last valid track point P0 (X0, Y0, Z0) before occlusion and the motion direction are recorded, the average speed V0 in the last 1s before occlusion is obtained, the deceleration rate is a speed reduction of V0 / 10 per 100 ms, one placeholder point is generated per 100 ms, the current speed = V0-(V0 / 10) x n (n = 1-10, corresponding to 10 sampling points), P0 is used as the initial current coordinate, the predicted coordinate = current coordinate + current speed x direction vector of motion direction x 0.1s, the current coordinate is updated according to the predicted coordinate, the predicted coordinate in the next deceleration process is continuously calculated, and linear deceleration is performed to static state within 1s, and then a fixed coordinate is maintained, that is, all subsequent placeholder points maintain the coordinate of the 10th deceleration point and do not change, thereby avoiding device drift without basis. Wherein, every time a placeholder point is generated in the deceleration stage, it is checked whether it exceeds the mechanical limiting range of the device, and if it exceeds, the deceleration is immediately stopped and the static state is entered in advance.

[0130] In step S20, a mapping relationship between the physical coordinate system and the twin model coordinate system is obtained, and the physical positioning data is converted into twin positioning data based on the mapping relationship.

[0131] It should be noted that the BIM model of the building is imported into the digital twin engine (such as Unity / UnrealEngine) synchronously, the twin model coordinate system (X axis is the horizontal direction major axis, Y axis is the horizontal direction minor axis, and Z axis is the vertical direction longitudinal axis) is established with the fixed reference objects (such as corners and columns) in the building as the origin, and the twin coordinates of all reference objects are labeled.

[0132] It can be understood that the physical coordinates (X1, Y1, Z1) of each UWB anchor point are measured on site using a high-precision laser total station (precision ±2mm), and recorded to the anchor point configuration table. The virtual position corresponding to each anchor point is located in the twin engine, the twin coordinates (X2, Y2, Z2) thereof are read, the coordinate conversion matrix is calculated by the least square method, the mapping relationship between the physical coordinate system and the twin model coordinate system is generated (error range <5mm), and the mapping relationship can be used to directly convert the positioning data of the UWB anchor point into the corresponding twin coordinates in the twin model, i.e., the twin positioning data, without the need for secondary processing.

[0133] In step S30, the changed track point corresponding to the twin positioning data is determined based on an incremental update rendering strategy.

[0134] It should be noted that the incremental update rendering strategy is adopted in this embodiment, and only the track segment with a coordinate difference greater than 5mm is updated.

[0135] Step S40, based on the change trajectory point, render the motion trajectory of the target object in the twin model of the building, and the rendering parameters of the motion trajectory are determined based on the user perspective distance.

[0136] It can be understood that different target objects are marked with different visual marks, such as equipment (red, flashing frequency 1Hz), personnel (blue, static portrait mark), AGV (green, display direction arrow), and state association dyeing is added, such as when the equipment temperature is greater than 80℃, the trajectory becomes orange, and when the fault occurs, it becomes red (flashing frequency 2Hz), which intuitively displays the state anomaly. If the real-time monitoring rendering delay is greater than 100ms, then the non-critical scene precision is automatically reduced (such as simplifying the details of the distant model), to ensure that the delay is stable and less than 100ms, so that the physical motion and the twin trajectory are "zero lag".

[0137] In a possible implementation, before step S40, the user perspective position can be obtained, the user perspective distance corresponding to the trajectory point position is calculated based on the user perspective position and the trajectory point position in the motion trajectory, the perspective distance range matched with the trajectory point position is determined based on the user perspective distance corresponding to the trajectory point position, and the rendering parameters of the trajectory point position are determined based on the perspective distance range matched with the trajectory point position. The rendering parameters at least include rendering precision level, trajectory point size and trajectory line width.

[0138] It should be noted that the embodiment can adjust the rendering parameters according to the user perspective distance, and the rendering parameters at least include rendering precision level, trajectory point size and trajectory line width.

[0139] It can be understood that the three-dimensional distance between the user perspective and each trajectory point is calculated as the user perspective distance in real time, and the data related to the user perspective can be obtained by the camera. Different rendering parameters are set according to the user perspective distance, the rendering details are reduced in the distant area (smaller points and thinner lines), the millimeter-level precision is maintained in the near focus area, and the visual effect and the power consumption are balanced. Exemplarily, the perspective focus area (distance < 10m) is set to have the rendering parameters of trajectory point size 2mm, line width 1mm and high precision mode, to ensure millimeter-level visual precision and clearly identify the trajectory details, the perspective mid-distance area (10m~50m) is set to have the rendering parameters of trajectory point size 1.5mm, line width 0.8mm and standard precision mode, to balance the precision and the load without affecting the overall observation, and the perspective distant area (distance > 50m) is set to have the rendering parameters of trajectory point size 1mm, line width 0.5mm and simplified precision mode, to greatly reduce the rendering vertex number and reduce the engine load. If different paragraphs of the same trajectory are in different precision levels (such as one end of the trajectory is within 10m and the other end is outside 50m), then the paragraphs are adjusted respectively to ensure a smooth transition.

[0140] Further, a static reference object is selected as a reference point in the digital twin model, the health degree of the reference point is evaluated based on the real-time coordinate intensity of the reference point, when the health degree of the reference point meets the effective condition, the reference point is determined as an effective reference point, and the coordinate compensation value is determined based on the real-time coordinate and the initial calibration coordinate of the effective reference point; when the health degree of the reference point does not meet the effective condition, the reference point is determined as an invalid reference point, and the coordinate compensation value is determined based on the real-time coordinate and the initial calibration coordinate of the standby reference point; and the mapping relationship between the physical coordinate system and the twin model coordinate system is optimized based on the coordinate compensation value.

[0141] It should be noted that more than three static reference objects (such as walls and fixed equipment) in the twin model are selected as reference points, and the UWB real-time coordinates of the reference points are collected once every 30 seconds. The effective condition for evaluating the health degree of the reference point is set: if the signal intensity of a certain reference point is collected for 5 times continuously and is less than -85dBm, the health degree is unqualified, and the reference point is determined as an invalid reference point; otherwise, the health degree is qualified, and the reference point is determined as an effective reference point. If the reference point is an effective reference point, the Kalman filtering algorithm is used to compare the deviation between the real-time UWB coordinate and the initial calibration coordinate, if the deviation is greater than 2mm, the compensation value (maximum compensation ±2mm per hour) is automatically generated, and the mapping relationship between the physical coordinate system and the twin model coordinate system is updated synchronously; if the reference point is an invalid reference point, the standby reference point is automatically switched to, the compensation value is automatically generated according to the real-time coordinate and the initial calibration coordinate of the standby reference point, and the mapping relationship between the physical coordinate system and the twin model coordinate system is updated synchronously.

[0142] The embodiment provides a digital twin motion trajectory rendering method based on space-time linkage, acquires a current position scene of a target object in a building, determines physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, the current position scene being any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene and a shielding scene, acquires a mapping relationship between a physical coordinate system and a twin model coordinate system, converts the physical positioning data into twin positioning data based on the mapping relationship, determines a change trajectory point corresponding to the twin positioning data based on an incremental update rendering strategy, and renders a motion trajectory of the target object in the twin model of the building based on the change trajectory point, a rendering parameter of the motion trajectory being determined based on a user perspective distance. The embodiment can adaptively position according to different scenes, find an accurate physical position of the target object, accurately map the physical position to a corresponding point in the twin model through coordinate conversion and coordinate calibration, and reduce lag caused by mapping through real-time rendering, thereby improving trajectory positioning accuracy and being applicable to different scenes and ensuring positioning accuracy in different scenes.

[0143] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above embodiment one can refer to the above introduction, and the subsequent will not be described. On this basis, please refer to Figure 3 , step S30 can include steps S301-S302:

[0144] Step S301, based on the twin positioning data, the three-dimensional coordinate difference value corresponding to the current trajectory point is calculated;

[0145] It should be noted that the current trajectory point ( ) is extracted, and the last frame coordinate of the corresponding trajectory ( ) is matched, and the three-dimensional coordinate difference value is calculated according to the following formula:

[0146]

[0147] It can be understood that the calculated value usually retains 2 decimal places, for example: 3.2mm, 6.8mm.

[0148] Step S302, when the three-dimensional coordinate difference value is greater than the preset value, it is determined that the trajectory changes effectively, and the current trajectory point and the adjacent trajectory point of the current trajectory point are taken as the change trajectory point.

[0149] It should be noted that the preset value is usually set to 5mm. The adjacent trajectory point of the current trajectory point is the previous trajectory point and the next trajectory point of the current trajectory point. The change trajectory point is the trajectory point corresponding to the changed trajectory segment.

[0150] It can be understood that if the three-dimensional coordinate difference value Δ is greater than 5mm, it is determined that the trajectory changes effectively, and the trajectory point and the adjacent point before and after are marked as the change trajectory point, and step S40 is executed.

[0151] It should be understood that only the change trajectory point is redrawn, the vector point cloud rendering mode is adopted, the color and transparency consistent with the original trajectory are maintained, and other static models (such as BIM building components) and unchanged trajectories in the scene are not touched.

[0152] In one possible implementation, when the three-dimensional coordinate difference value is less than or equal to the preset value, it is determined that the trajectory does not change effectively, and the step of returning to execute the current position scene of the target object in the building is returned to execute the step of determining the physical positioning data of the target object in the current position scene based on the multi-scene adaptive positioning strategy.

[0153] It can be understood that if the three-dimensional coordinate difference value Δ is less than or equal to 5mm, it is determined that the trajectory does not change effectively, no rendering operation is performed, and the new coordinate is directly cached for difference calculation of the next frame, and the step S10 is returned.

[0154] The embodiment provides a digital twin motion trajectory rendering method based on space-time linkage, calculates a three-dimensional coordinate difference value corresponding to a current trajectory point based on twin positioning data; when the three-dimensional coordinate difference value is greater than a preset value, it is determined that the trajectory is effectively changed, and the current trajectory point and a neighboring trajectory point of the current trajectory point are taken as changed trajectory points. The method can adaptively position according to different scenes, find the accurate physical position of a target object, accurately map the physical position to a corresponding point of a twin model through coordinate conversion and coordinate calibration, and reduce the lag caused by mapping through real-time rendering, thereby improving the trajectory positioning accuracy and being applicable to different scenes and ensuring the positioning accuracy in different scenes.

[0155] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the digital twin motion trajectory rendering method based on space-time linkage of the present application. More forms of simple transformation based on the technical concept are within the protection scope of the present application.

[0156] The present application also provides a digital twin motion trajectory rendering system based on space-time linkage, please refer to Figure 4 The digital twin motion trajectory rendering system based on space-time linkage comprises:

[0157] A positioning module 10 is configured to acquire a current position scene of a target object in a building, determine physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, and the current position scene is any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene and a shielding scene.

[0158] A conversion module 20 is configured to acquire a mapping relationship between a physical coordinate system and a twin model coordinate system, and convert the physical positioning data into twin positioning data based on the mapping relationship.

[0159] A rendering module 30 is configured to determine changed trajectory points corresponding to the twin positioning data based on an incremental update rendering strategy.

[0160] The rendering module 30 is further configured to render a motion trajectory of the target object in the twin model of the building based on the changed trajectory points, and a rendering parameter of the motion trajectory is determined based on a user perspective distance.

[0161] In a feasible implementation, the positioning module 10 is further configured to, when the current position scene is an indoor complex scene, acquire current positioning data of a normal ultra-wideband anchor point and current positioning data of an anti-interference ultra-wideband anchor point in the current position scene, respectively, wherein the anti-interference ultra-wideband anchor point filters a metal reflection signal in initial positioning data through a signal phase difference identification algorithm to obtain corresponding current positioning data, and adjusts a parameter used for filtering based on a signal noise intensity of the initial positioning data.

[0162] determine a normal positioning weight and an anti-interference positioning weight based on the signal strengths of the normal ultra-wideband anchor point and the anti-interference ultra-wideband anchor point;

[0163] determine physical positioning data of the target object in the current location scenario based on the current positioning data of the normal ultra-wideband anchor point, the normal positioning weight, the current positioning data of the anti-interference ultra-wideband anchor point, and the anti-interference positioning weight.

[0164] In a possible implementation, the positioning module 10 is further configured to, when the current location scenario is an indoor-outdoor connection scenario, acquire a tag signal strength detected by a connection ultra-wideband anchor point in the current location scenario;

[0165] when the tag signal strength is less than a preset strength threshold, determine a distance ratio of each location point in the current location scenario based on distances between each location point and a connection line in the current location scenario;

[0166] calculate ultra-wideband positioning weights and Beidou positioning weights of each location point in the current location scenario based on the distance ratios of each location point in the current location scenario;

[0167] acquire ultra-wideband positioning data and Beidou positioning data of the target object in the current location scenario;

[0168] determine physical positioning data of the target object in the current location scenario based on the ultra-wideband positioning data, the ultra-wideband positioning weight, the Beidou positioning data, and the Beidou positioning weight.

[0169] In a possible implementation, the positioning module 10 is further configured to, when the current location scenario is an occlusion scenario, acquire pre-occlusion positioning data and pre-occlusion signal data within a preset time length;

[0170] determine a pre-occlusion initial position, a moving speed, a moving direction change rate, and a moving acceleration of the target object based on the pre-occlusion positioning data, and determine a signal attenuation rate based on the pre-occlusion signal data;

[0171] acquire historical trajectory data corresponding to the pre-occlusion initial position, and determine a moving regularity feature based on the historical trajectory data;

[0172] generate a fused trajectory feature based on the moving speed, the moving direction change rate, the moving acceleration, a distance between the pre-occlusion initial position and a surrounding occlusion object, the signal attenuation rate, and the moving regularity feature;

[0173] input the fusion trajectory feature into a trajectory prediction model to obtain predicted positioning coordinates of the target object;

[0174] based on the predicted positioning coordinates, determine physical positioning data of the target object in the current location scene.

[0175] In a feasible implementation, the positioning module 10 is further configured to obtain an occlusion time of the target object, and when the occlusion time is greater than a prediction time threshold, determine an object type of the target object;

[0176] when the object type is a person, based on a valid trajectory point before occlusion, calculate a horizontal direction vector;

[0177] take the moving speed and the initial position before occlusion as a current speed and a current coordinate respectively, and compare the current speed with a preset speed threshold;

[0178] when the current speed is greater than the preset speed threshold, based on the current coordinate, the current speed, the horizontal direction vector, and a first preset period, calculate a deceleration prediction coordinate, add the deceleration prediction coordinate into the predicted positioning coordinates, update the current coordinate based on the deceleration prediction coordinate, and update the current speed based on a preset deceleration rate, and return to perform the step of comparing the current speed with the preset speed threshold;

[0179] when the current speed is less than or equal to the preset speed threshold, based on the current coordinate, the preset speed threshold, the horizontal direction vector, and a second preset period, calculate a constant speed prediction coordinate, and add the constant speed prediction coordinate into the predicted positioning coordinates.

[0180] In a feasible implementation, the positioning module 10 is further configured to, when the object type is an AGV, determine a path node before occlusion and a path extension direction from a preset path;

[0181] based on the moving speed and a preset ratio, determine a fixed speed;

[0182] based on the path node before occlusion, determine a current path coordinate;

[0183] based on the current path coordinate, a path direction vector corresponding to the path extension direction, the fixed speed, and a third preset period, calculate a predicted path coordinate, and add the predicted path coordinate into the predicted positioning coordinates.

[0184] In a feasible implementation, the rendering module 30 is further configured to, based on the twin positioning data, calculate a three-dimensional coordinate difference value corresponding to a current trajectory point;

[0185] when the three-dimensional coordinate difference is greater than a preset value, determining that the trajectory has an effective change, taking the current trajectory point and a neighboring trajectory point of the current trajectory point as a change trajectory point, and performing a step of rendering a motion trajectory of the target object in the twin model of the building based on the change trajectory point;

[0186] when the three-dimensional coordinate difference is less than or equal to a preset value, determining that the trajectory has no effective change, and returning to perform a step of obtaining a current location scene of a target object in a building, and determining physical positioning data of the target object in the current location scene based on a multi-scene adaptive positioning strategy.

[0187] In an available implementation, the rendering module 30 is further configured to obtain a user perspective position, calculate a user perspective distance corresponding to the trajectory point position based on the user perspective position and the trajectory point position in the motion trajectory, and

[0188] determine a perspective distance range matched with the trajectory point position based on the user perspective distance corresponding to the trajectory point position.

[0189] determine a rendering parameter of the trajectory point position based on the perspective distance range matched with the trajectory point position, the rendering parameter at least including a rendering precision level, a trajectory point size, and a trajectory line width.

[0190] In an available implementation, the conversion module 20 is further configured to select a static reference object as a reference point in the digital twin model, and evaluate a health degree of the reference point based on a real-time coordinate intensity of the reference point.

[0191] when the health degree of the reference point meets an effective condition, determining that the reference point is an effective reference point, and determining a coordinate compensation value based on a real-time coordinate and an initial calibration coordinate of the effective reference point.

[0192] when the health degree of the reference point does not meet the effective condition, determining that the reference point is an ineffective reference point, and determining a coordinate compensation value based on a real-time coordinate and an initial calibration coordinate of a backup reference point.

[0193] optimizing a mapping relationship between a physical coordinate system and a twin model coordinate system based on the coordinate compensation value.

[0194] The space-time linkage-based digital twin motion trajectory rendering system provided in the application adopts the space-time linkage-based digital twin motion trajectory rendering method in the above embodiment, and can solve the technical problem that the physical position of the target object and the point position of the twin model cannot be accurately mapped and are difficult to be applied to complex scenes. Compared with the prior art, the space-time linkage-based digital twin motion trajectory rendering system provided in the application has the same beneficial effects as the space-time linkage-based digital twin motion trajectory rendering method provided in the above embodiment, and other technical features in the space-time linkage-based digital twin motion trajectory rendering system are the same as the features disclosed in the above embodiment method, and will not be described here.

[0195] It should be noted that the user-related data (for example, user geographic location) involved in the application is obtained after obtaining the user's permission or consent; that is, when the application is applied to a specific product or technology, the user's permission needs to be obtained to realize the acquisition and processing of related data, and the processing of related data needs to comply with relevant laws, regulations and regulatory standards in relevant countries and regions.

[0196] For example, when the current geographic location of the user needs to be acquired, a location acquisition prompt can be displayed in the terminal of the user, and after receiving the confirmation operation of the user for the location acquisition prompt, the terminal can acquire the current geographic location of the user.

[0197] The application provides a space-time linkage-based digital twin motion trajectory rendering device, which comprises at least one processor and a memory in communication connection with the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the space-time linkage-based digital twin motion trajectory rendering method in the above embodiment one.

[0198] Reference will be made to Figure 5 which shows a structural schematic diagram of a space-time linkage-based digital twin motion trajectory rendering device suitable for implementing the embodiments of the application. The space-time linkage-based digital twin motion trajectory rendering device in the embodiments of the application can include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 5The illustrated space-time linkage-based digital twin motion trajectory rendering device is merely an example and should not bring any limitation to the function and use range of the embodiments of the present application.

[0199] As Figure 5 shown, the space-time linkage-based digital twin motion trajectory rendering device can include a processing system 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a ROM (Read Only Memory) 1002 or programs loaded from a storage system 1003 into a RAM (Random Access Memory) 1004. In the RAM 1004, various programs and data required for operation of the space-time linkage-based digital twin motion trajectory rendering device are also stored. The processing system 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input system 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output system 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage system 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication system 1009. The communication system 1009 can allow the space-time linkage-based digital twin motion trajectory rendering device to communicate with other devices wirelessly or by wire to exchange data. Although the space-time linkage-based digital twin motion trajectory rendering device with various systems is shown in the figure, it should be understood that all the illustrated systems are not required to be implemented or possessed. More or fewer systems can be alternatively implemented or possessed.

[0200] In particular, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product including a computer program carried on a computer readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through a communication system, or installed from the storage system 1003, or installed from the ROM 1002. When the computer program is executed by the processing system 1001, the above-mentioned functions defined in the methods of the embodiments of the present application are performed.

[0201] The space-time linkage-based digital twin motion trajectory rendering device provided in the application adopts the space-time linkage-based digital twin motion trajectory rendering method in the above embodiment, and can solve the technical problems that the physical position of the target object and the point position of the twin model cannot be accurately mapped, and it is difficult to be applied to complex scenes. Compared with the prior art, the beneficial effects of the space-time linkage-based digital twin motion trajectory rendering device provided in the application are the same as those of the space-time linkage-based digital twin motion trajectory rendering method provided in the above embodiment, and other technical features in the space-time linkage-based digital twin motion trajectory rendering device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0202] It should be understood that parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0203] The above is merely specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0204] The present application provides a computer readable storage medium having computer readable program instructions (i.e. computer programs) stored thereon, the computer readable program instructions being used to execute the space-time linkage-based digital twin motion trajectory rendering method in the above embodiment.

[0205] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electrical connection with one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiment, the 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, system, or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to electrical wires, optical cables, RF (Radio Frequency), and the like, or any suitable combination of the above.

[0206] The computer readable storage medium described above may be contained in a space-time linkage-based digital twin motion trajectory rendering device; or may exist independently and not be assembled into the space-time linkage-based digital twin motion trajectory rendering device.

[0207] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the space-time linkage-based digital twin motion trajectory rendering device, the space-time linkage-based digital twin motion trajectory rendering device: obtains a current position scene of a target object in a building, determines physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, the current position scene being any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene, and an occlusion scene; obtains a mapping relationship between a physical coordinate system and a twin model coordinate system, converts the physical positioning data to twin positioning data based on the mapping relationship; determines a change trajectory point corresponding to the twin positioning data based on an incremental update rendering strategy; and renders a motion trajectory of the target object in a twin model of the building based on the change trajectory point, a rendering parameter of the motion trajectory being determined based on a user perspective distance.

[0208] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0209] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0210] The modules involved in the embodiments of the present application can be implemented in software or hardware. In some cases, the names of the modules do not constitute a limitation on the modules themselves.

[0211] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., computer programs) for executing the above-mentioned space-time linkage-based digital twin motion trajectory rendering method, and can solve the technical problems that the physical position of the target object and the point position of the twin model cannot be accurately mapped, and it is difficult to be applied to complex scenes. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the space-time linkage-based digital twin motion trajectory rendering method provided by the above-mentioned embodiments, and will not be described here.

[0212] The application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method for rendering a digital twin motion trajectory based on spatio-temporal linkage as described above.

[0213] The computer program product provided by the application can solve the technical problems that the physical position of the target object and the point position of the twin model cannot be accurately mapped, and it is difficult to be applied to complex scenes. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the method for rendering a digital twin motion trajectory based on spatio-temporal linkage provided by the above-mentioned embodiments, and are not repeated here.

[0214] The above is only some embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation made by using the content of the specification and drawings, or direct / indirect application in other related technical fields under the technical concept of the application is included in the patent protection scope of the application.

Claims

1. A spatio-temporal linkage-based digital twin motion trajectory rendering method, characterized in that, The method comprises: acquiring a current position scene of a target object in a building, determining physical positioning data of the target object in the current position scene based on a multi-scene adaptive positioning strategy, the current position scene being any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene, and a shielding scene; acquiring a mapping relationship between a physical coordinate system and a twin model coordinate system, and converting the physical positioning data into twin positioning data based on the mapping relationship; determining a change trajectory point corresponding to the twin positioning data based on an incremental update rendering strategy; rendering a motion trajectory of the target object in the twin model of the building based on the change trajectory point, a rendering parameter of the motion trajectory being determined based on a user perspective distance; the step of determining the physical positioning data of the target object in the current position scene based on the multi-scene adaptive positioning strategy comprises: when the current position scene is a shielding scene, acquiring pre-shielding positioning data and pre-shielding signal data within a preset time length; determining a pre-shielding initial position, a moving speed, a moving direction change rate, and a moving acceleration of the target object based on the pre-shielding positioning data, and determining a signal attenuation rate based on the pre-shielding signal data; acquiring historical trajectory data corresponding to the pre-shielding initial position, and determining a moving law feature based on the historical trajectory data; generating a fusion trajectory feature based on the moving speed, the moving direction change rate, the moving acceleration, a distance between the pre-shielding initial position and a surrounding shielding object, the signal attenuation rate, and the moving law feature; inputting the fusion trajectory feature into a trajectory prediction model to obtain a predicted positioning coordinate of the target object; determining the physical positioning data of the target object in the current position scene based on the predicted positioning coordinate.

2. The method of claim 1, wherein, the step of determining the physical positioning data of the target object in the current position scene based on the multi-scene adaptive positioning strategy comprises: when the current position scene is an indoor complex scene, acquiring current positioning data of a normal ultra-wideband anchor point and current positioning data of an anti-interference ultra-wideband anchor point in the current position scene, wherein the anti-interference ultra-wideband anchor point obtains corresponding current positioning data by filtering metal reflection signals in initial positioning data through a signal phase difference recognition algorithm, and adjusts parameters used for filtering based on signal noise intensity of the initial positioning data; determining a normal positioning weight and an anti-interference positioning weight based on signal intensity of the normal ultra-wideband anchor point and the anti-interference ultra-wideband anchor point; determining the physical positioning data of the target object in the current position scene based on the current positioning data of the normal ultra-wideband anchor point, the normal positioning weight, the current positioning data of the anti-interference ultra-wideband anchor point, and the anti-interference positioning weight.

3. The method of claim 1, wherein, the step of determining the physical positioning data of the target object in the current position scene based on the multi-scene adaptive positioning strategy comprises: when the current position scene is an indoor-outdoor connection scene, acquiring label signal intensity detected by a connection ultra-wideband anchor point in the current position scene; When the label signal intensity is less than a preset intensity threshold, distances of each position point in the current position scene from a connection line are determined based on distances of each position point in the current position scene from the connection line, wherein the connection line is a demarcation line between indoor and outdoor; Based on the distance proportions of each position point in the current position scene, ultra-wideband positioning weights and Beidou positioning weights of each position point in the current position scene are calculated; Obtain the ultra-wideband positioning data and the Beidou positioning data of the target object in the current position scene; Based on the ultra-wideband positioning data, the ultra-wideband positioning weight, the Beidou positioning data and the Beidou positioning weight, the physical positioning data of the target object in the current position scene is determined.

4. The method of claim 1, wherein, The step of determining the physical positioning data of the target object in the current position scene based on the predicted positioning coordinates further comprises: Obtain the occlusion time of the target object, and when the occlusion time is greater than a prediction time threshold, determine the object type of the target object; When the object type is a person, a horizontal direction vector is calculated based on the effective trajectory point before occlusion; The moving speed and the initial position before occlusion are taken as the current speed and the current coordinate respectively, and the current speed is compared with a preset speed threshold; When the current speed is greater than the preset speed threshold, a deceleration prediction coordinate is calculated based on the current coordinate, the current speed, the horizontal direction vector and a first preset period, the deceleration prediction coordinate is added to the predicted positioning coordinates, the current coordinate is updated based on the deceleration prediction coordinate, and the current speed is updated based on a preset deceleration rate, and the step of comparing the current speed with the preset speed threshold is returned to execute; When the current speed is less than or equal to the preset speed threshold, a constant speed prediction coordinate is calculated based on the current coordinate, the preset speed threshold, the horizontal direction vector and a second preset period, and the constant speed prediction coordinate is added to the predicted positioning coordinates.

5. The method of claim 4, wherein, After the step of obtaining the occlusion time of the target object, and when the occlusion time is greater than a prediction time threshold, determining the object type of the target object, further comprises: When the object type is AGV, a path node before occlusion and a path extension direction are determined from a preset path; A fixed speed is determined based on the moving speed and a preset proportion; A current path coordinate is determined based on the path node before occlusion; A prediction path coordinate is calculated based on the current path coordinate, a path direction vector corresponding to the path extension direction, the fixed speed and a third preset period, and the prediction path coordinate is added to the predicted positioning coordinates.

6. The method of claim 1, wherein, The step of determining the changed trajectory point corresponding to the twin positioning data based on the incremental update rendering strategy comprises: Based on the twin positioning data, a three-dimensional coordinate difference value corresponding to the current trajectory point is calculated; determining that the trajectory has an effective change when the three-dimensional coordinate difference is greater than a preset value, taking the current trajectory point and a neighboring trajectory point of the current trajectory point as a change trajectory point, and performing a step of rendering a motion trajectory of the target object in the twin model of the building based on the change trajectory point; determining that the trajectory has no effective change when the three-dimensional coordinate difference is less than or equal to the preset value, and returning to perform a step of obtaining a current location scene of a target object in a building, and determining physical positioning data of the target object in the current location scene based on a multi-scene adaptive positioning strategy.

7. The method of claim 1, wherein, The step of rendering the motion trajectory of the target object in the twin model of the building based on the change trajectory point further includes: obtaining a user perspective position, calculating a user perspective distance corresponding to the trajectory point position based on the user perspective position and the trajectory point position in the motion trajectory; determining a perspective distance range matched with the trajectory point position based on the user perspective distance corresponding to the trajectory point position; determining a rendering parameter of the trajectory point position based on the perspective distance range matched with the trajectory point position, the rendering parameter at least including a rendering accuracy level, a trajectory point size, and a trajectory line width.

8. The method of claim 1, wherein, The method further includes: selecting a static reference object as a reference point in the digital twin model, and evaluating a health degree of the reference point based on a real-time coordinate intensity of the reference point, wherein the real-time coordinate intensity of the reference point is a UWB tag signal intensity collected when a UWB real-time coordinate of the reference point is determined; determining that the reference point is a valid reference point when the health degree of the reference point meets an effective condition, and determining a coordinate compensation value based on a real-time coordinate and an initial calibration coordinate of the valid reference point; determining that the reference point is an invalid reference point when the health degree of the reference point does not meet the effective condition, and determining a coordinate compensation value based on a real-time coordinate and an initial calibration coordinate of a backup reference point; optimizing a mapping relationship between a physical coordinate system and a twin model coordinate system based on the coordinate compensation value.

9. A spatio-temporal linkage-based digital twin motion trajectory rendering system, characterized in that, The system includes: a positioning module configured to obtain a current location scene of a target object in a building, and determine physical positioning data of the target object in the current location scene based on a multi-scene adaptive positioning strategy, the current location scene being any one of a normal scene, an indoor complex scene, an indoor-outdoor connection scene, and a shielding scene; a conversion module configured to obtain a mapping relationship between a physical coordinate system and a twin model coordinate system, and convert the physical positioning data into twin positioning data based on the mapping relationship; a rendering module configured to determine a change trajectory point corresponding to the twin positioning data based on an incremental update rendering strategy; the rendering module is further configured to render a motion trajectory of the target object in the twin model of the building based on the change trajectory point, a rendering parameter of the motion trajectory being determined based on a user perspective distance; the positioning module is further configured to obtain shielding front positioning data and shielding front signal data within a preset time period when the current location scene is a shielding scene. determine an initial position before the occlusion, a moving speed, a moving direction change rate, and a moving acceleration of the target object based on the pre-occlusion positioning data, and determine a signal attenuation rate based on the pre-occlusion signal data; obtain historical trajectory data corresponding to the initial position before the occlusion, and determine a moving regularity feature based on the historical trajectory data; generate a fused trajectory feature based on the moving speed, the moving direction change rate, the moving acceleration, a distance between the initial position before the occlusion and a surrounding occlusion, the signal attenuation rate, and the moving regularity feature; input the fused trajectory feature into a trajectory prediction model to obtain a predicted positioning coordinate of the target object; determine physical positioning data of the target object in the current position scene based on the predicted positioning coordinate.

Images