An intelligent agricultural digital management system based on the Internet of Things

Abstract

The application discloses a kind of based on Internet of Things's wisdom agricultural digital management system, it is related to wisdom agriculture and man-machine interaction technical field, system includes field perception and execution layer, edge computing gateway layer, cloud platform layer and GUI interactive rendering layer, GUI interactive rendering layer sets up dual-state graphic object rendering module, based on digital twin prediction model generates the intention virtual image graphic object followed by user manipulation and the entity graphic object that approaches target state according to physical execution track prediction, solve the misoperation problem caused by graphic interaction and equipment state are not synchronized, also set up dynamic boundary rendering module, according to agricultural environment parameter coupling equation renders dynamic blocking area on control control track and clamps disaster instruction, solve the problem that agricultural disaster is caused by coupling parameter overrun, the application is used for wisdom agricultural remote graphical manipulation and safety protection.

Description

Technical Field

[0001] This invention relates to the field of smart agriculture and human-computer interaction technology, specifically to a smart agriculture digital management system based on the Internet of Things. Background Technology

[0002] The Internet of Things (IoT) technology has been widely applied in the field of smart agriculture. Typical systems include field sensor nodes, actuators, edge gateways, cloud management platforms, and graphical user interface clients for user operation. The closest existing technology to this invention is a remote greenhouse environment centralized control system based on a cloud platform. In this system, graphical controls are bound one-to-one with background target setting fields. After the user manipulates the control, the control immediately jumps to the target position, or an interaction method is adopted in which the interface is locked and unlocked after the device completes the execution and sends back the data. Regarding the correlation between environmental parameters, the display and manipulation of each control in the existing system are independent of each other, and the limit is only based on the upper and lower limits of static values.

[0003] The existing technologies have the following drawbacks: First, agricultural physical equipment suffers from mechanical execution delays of several minutes, wide-area IoT suffers from high communication latency, and in the instant response mode, the control position changes prematurely before the device has finished executing, which can easily lead users to misjudge that the operation has not taken effect and repeatedly drag or reverse the operation, resulting in conflicts and damage to the underlying execution mechanism. The user experience is poor in the interface lock-and-wait mode, and no effective status feedback can be provided when the network is interrupted. Second, the existing graphical user interface controls various environmental parameters in isolation. When a user adjusts a parameter, they cannot predict the chain effect of the operation on other coupled parameters. Static numerical limits alone cannot reflect the dynamic safety boundary under coupled conditions, which can easily lead to agricultural disasters. Therefore, we propose a smart agriculture digital management system based on IoT. Summary of the Invention

[0004] The purpose of this invention is to provide a smart agriculture digital management system based on the Internet of Things.

[0005] The technical problems to be solved by this invention include the following two aspects: First, how to solve the problem of asynchronous graphical interaction with the actual state of physical devices caused by the mechanical execution lag of physical devices and the communication delay of wide area networks in agricultural Internet of Things scenarios, so as to avoid users from making repeated dragging or reverse dragging due to the lack of timely physical feedback, and to prevent damage to underlying hardware or system crashes caused by command conflicts. Second, how to solve the problem that existing graphical controls are isolated from each other and cannot reflect the parameter coupling relationship in real time under the background of strong coupling of high-dimensional parameters of crop growth environment, so that non-professional users can predict and be actively prevented from pushing the associated parameters into dangerous thresholds when adjusting a certain environmental parameter, thereby avoiding agricultural disasters and economic losses.

[0006] To address the aforementioned technical problems, this invention provides a smart agriculture digital management system based on the Internet of Things (IoT), comprising a field sensing and execution layer, an edge computing gateway layer, a cloud platform layer, and a GUI interactive rendering layer. The field sensing and execution layer includes sensors for collecting agricultural environmental parameters and execution devices for performing agricultural operations. The edge computing gateway layer communicates with the field sensing and execution layer and is used for localized coupled parameter calculations and digital twin position prediction. The cloud platform layer communicates with the edge computing gateway layer and includes a digital twin model library storing mechanical dynamic parameters of the execution devices and network latency statistical models. The GUI interactive rendering layer communicates with both the edge computing gateway layer and the cloud platform layer and includes a dual-state graphical object rendering module and a dynamic boundary rendering module. The dual-state graphical object rendering module responds to user manipulation of graphical controls and generates a state value synchronized with the user's manipulated target. The following intention-driven phantom graphic object generates a physical execution trajectory prediction result based on the mechanical dynamic parameters in the digital twin model library and the latency statistics of the current network link. Based on the prediction result, the entity graphic object is controlled to gradually approach the target state value through animation interpolation. This allows the intention-driven phantom graphic object and the entity graphic object to be presented simultaneously in the graphical user interface and evolve independently. The dynamic boundary rendering module is used to calculate the predicted change of the associated environmental parameters based on the pre-established agricultural environmental parameter coupling equation and the incremental manipulation of the current graphic control by the user. Based on the relationship between the predicted change and the preset crop survival threshold, a dynamic blocking area is rendered on the track of the current control. The display state of the dynamic blocking area is adjusted as the predicted change approaches the crop survival threshold, thus confining the user's manipulation position within the dynamic boundary position corresponding to the threshold.

[0007] Compared with the prior art, the beneficial effects of the present invention by adopting the above technical solution are as follows:

[0008] 1. This invention uses a dual-state graphical object architecture of intentional virtual graphical objects and physical graphical objects to provide users with immediate visual feedback after dragging operations. At the same time, the smooth animation movement of physical graphical objects based on digital twin prediction models realistically reflects the actual execution progress of physical devices, thereby eliminating user misoperations caused by lack of feedback and avoiding damage to the underlying hardware due to instruction conflicts.

[0009] 2. In network interruption scenarios, this invention enables users to intuitively understand the uncertainty range of the system state by combining local inference with the visualization rendering of the prediction error confidence band, avoiding long-term interface locking and waiting, and improving the robustness of the system. By mapping the calculation results of the agronomic mechanism coupling model to the position linkage of multiple environmental parameter graphical controls in real time, users can predict the impact of a single parameter on the coupled parameters in real time when manipulating a single parameter, breaking the technical bottleneck of existing isolated controls.

[0010] 3. This invention dynamically renders the blocking area on the graphic control track and applies rendering damping to the operation action to restrain the issuance of disaster-causing commands. It actively rejects operation commands that may cause the coupling parameters to exceed the limit from the operation interface level, realizing a technical upgrade from data threshold alarm to physical rejection of the operation interface, and has a significant foolproof protection effect. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of the overall business process of the system in an embodiment of the present invention;

[0012] Figure 2 This is a schematic diagram of the asynchronous rendering process of a dual-state GUI graphical object in an embodiment of the present invention;

[0013] Figure 3 This is a schematic diagram of the dynamic boundary linkage error prevention control process in an embodiment of the present invention. Detailed Implementation

[0014] The following is in conjunction with the appendix Figure 1-3 The specific embodiments of the present invention will be further described below. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0015] Furthermore, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0016] Example 1: System Overall Architecture:

[0017] The smart agriculture digital management system based on the Internet of Things provided by this invention includes field sensing and execution, edge computing gateway, cloud platform and GUI interactive rendering, and data interaction between each level is carried out through the Internet of Things communication protocol;

[0018] Field sensing and execution includes physical equipment nodes such as soil temperature and humidity sensors, light sensors, irrigation valves, roller shutter motors, and fertilizer pumps. Each node is connected to the upper layer through wide area Internet of Things (WAN) communication.

[0019] The edge computing gateway is equipped with a lightweight crop growth mechanism proxy model, which is responsible for performing coupled parameter calculations and local digital twin location predictions nearby, and exchanging data with field sensing and execution.

[0020] The cloud platform includes a digital twin model, a historical data database, and a business rule engine. The digital twin model stores the mechanical dynamics parameters of various execution devices (including execution speed parameters and startup response time) and network latency statistical models. The cloud platform and the edge computing gateway synchronize data through a standard IoT protocol and send the model parameters required for prediction to the edge computing gateway.

[0021] The GUI interactive rendering runs on the user's browser or mobile device and is internally divided into three sub-modules: a dual-state graphical object rendering module, a dynamic boundary rendering module, and a user interaction acquisition module. The dual-state graphical object rendering module is responsible for the independent rendering and animation interpolation of the intentional virtual graphical object and the physical graphical object. The dynamic boundary rendering module is responsible for the real-time drawing of coupled linkage displacement and dynamic blocking areas. The user interaction acquisition module is responsible for collecting the user's manipulation events on the graphical controls. The GUI interactive rendering maintains bidirectional real-time communication with the network, edge computing gateway, and cloud platform, transmitting sensor data and status feedback uplink and control commands and prediction parameters downlink.

[0022] Existing remote greenhouse control systems generally adopt an instant synchronization paradigm that strongly binds graphical controls to background target values. This invention breaks through this conventional understanding by actively splitting the graphical control into two rendering instances: an independently evolving intentional virtual graphical object and a physical graphical object. The animation trajectory of the physical graphical object is driven by a digital twin prediction model. This eliminates the erroneous operation caused by execution lag while sacrificing the instantaneous strong binding relationship between the control and the background value. This technical approach is not a simple superposition of the existing instant response mode and the lock-and-wait mode, but a substantial improvement to the existing strong binding synchronization paradigm.

[0023] Example 2: An asynchronous virtual-real decoupling GUI graphical manipulation method based on a digital twin prediction model:

[0024] The core idea of ​​this method is to split traditional graphical controls into two independent but related rendering instances, an intentional virtual graphical object and a physical graphical object, at the rendering layer, and to introduce a digital twin prediction model to drive the animation trajectory of the physical graphical object.

[0025] Step 1, User Interaction Event Acquisition: The user interaction acquisition module listens for drag-and-drop and click events on the graphical control, and obtains the target state value expected to be reached after the user's operation, denoted as... ;

[0026] Step Two, Real-time Rendering of the Intent Ghost Image: Upon detecting the user action in Step One, the dual-state graphics object rendering module immediately generates or updates the intent ghost image graphics object in the GUI interface, adjusting its rendering position accordingly. It maintains synchronous tracking without any animation delay, providing users with instant visual feedback that their actions have been responded to by the system;

[0027] Step 3, Control command issuance and twin model invocation: The system will... The corresponding control commands are sent to the edge computing gateway and the field execution device via the IoT communication link, while simultaneously invoking the mechanical dynamic parameters of the execution device (including execution speed parameters) in the digital twin model. (Startup response time) and current network link latency statistics (round-trip time) ), generate physical execution trajectory prediction results;

[0028] Step 4, Entity Graphics Object Animation Interpolation Rendering: The dual-state graphics object rendering module, based on the physical trajectory prediction results generated in Step 3, controls the entity graphics object to move smoothly frame by frame in animation, so that after deducting the delay time, it approaches the target position at the predicted speed. The entity graphics object at each moment... Rendering position Determined by the following formula:

[0029] ;

[0030] In the above formula, Represents the entity graphic object at time. The corresponding rendering state value, This indicates the initial state value of the entity graphic object before the current operation occurred. This represents the user's desired target state value obtained in step one. This is a symbolic function used to determine the execution direction of a physical device. This refers to the execution speed parameter of the execution device. For the current moment, The network round-trip time obtained in step three is the waiting time before the actual start of the action. The function is used to ensure that the entity state value does not exceed the user's target state value, thus preventing prediction overshoot;

[0031] Step 5, Network Interruption Detection and Local Inference: The system continuously monitors the IoT connection status. If a connection interruption is detected, the lightweight twin agent model running in the edge computing gateway takes over the prediction calculation and continues to infer the position of the entity graphic object based on the locally known parameters according to the formula in Step 4, without relying on cloud confirmation.

[0032] Step Six, Prediction Error Confidence Band Rendering: During the network interruption in Step Five, the Dynamic Boundary Rendering module draws a semi-transparent gradient prediction error confidence band around the entity graphic object, with a width of... The increase is due to the length of the interruption, and the calculation method is as follows:

[0033] ;

[0034] In the above formula, Indicates the confidence band at time... width, This is the initial reference width, reflecting the accuracy error of the device itself. The uncertainty growth factor is derived from historical execution error statistics of this type of equipment. Indicates the duration of the network outage, starting from the moment the outage occurred;

[0035] Step 7, State Correction and Error Convergence: Once the IoT connection is restored and the system receives the actual state data transmitted back from the execution device, the rendering position of the entity graphic object is corrected to the actual transmitted value using a short-term animation. Simultaneously, the prediction error confidence band width is converged to... This completes the closed loop of virtual-real decoupling manipulation in this round;

[0036] Example 3: Dynamic Boundary Linkage and Mistake-Proof Mapping Mechanism for Multidimensional GUI Controls Based on Agronomic Mechanism Models

[0037] The core idea of ​​this mechanism is to map the calculation results of the lightweight crop growth mechanism model to the position linkage and safety boundary rendering of multiple environmental parameter graphical controls in the front end in real time.

[0038] Step 1, Incremental Manipulation Acquisition: The user interaction acquisition module acquires the incremental drag manipulation of a certain environmental parameter control (e.g., the irrigation volume slider) by the user, and records it as... ,in Indicates the flow rate of irrigation water;

[0039] Step 2, Coupling Relationship Deduction: Lightweight Crop Growth Mechanism Proxy Model Received in Edge Computing Gateway Then, based on the pre-established water-fertilizer-thermal coupling equation, the effects of changes in irrigation volume on soil temperature and fertilizer concentration were calculated in real time. The dynamic relationship of soil temperature change is as follows:

[0040] ;

[0041] In the above formula, Indicates soil temperature, Indicates time, Indicates the irrigation water flow rate. This represents the coupling coefficient between irrigation water and soil cooling, and is determined by soil type and crop species. Indicates ambient air temperature. This represents the heat exchange coefficient between the soil and the ambient air;

[0042] The dynamic relationship between fertilizer concentration and irrigation dilution is as follows:

[0043] ;

[0044] In the above formula, Indicates time Soil fertilizer concentration, This indicates the initial fertilizer concentration before irrigation. This indicates the initial soil moisture content before irrigation. Indicates the irrigation water flow rate. Indicates the duration of irrigation;

[0045] Step 3, Linked Control Rendering: The dual-state graphics object rendering module is based on the output of Step 2. , The prediction results drive the graphical objects of related controls such as the soil temperature slider and fertilizer concentration display bar to generate synchronous displacement animations, so that their display positions reflect the results of the coupled calculations in real time;

[0046] Step 4, Safety Boundary Position Mapping: The system pre-establishes a monotonic mapping function between the positions of each environmental parameter control and its corresponding physical quantity. And set a crop survival threshold value for each physical quantity. Based on this, the dynamic boundary position of the control under the current coupling condition is calculated:

[0047] ;

[0048] In the above formula, This indicates the dynamic boundary position on the current control track, that is, the critical scale that the user cannot exceed when dragging. Represents mapping function The inverse function is used to reverse-map the critical values ​​of physical quantities to position scales on the control track. This represents the preset crop survival threshold, which is dynamically updated based on coupled conditions such as irrigation volume, current season, and crop growth stage.

[0049] Step 5, Dynamic Obstruction Area Rendering: The dynamic boundary rendering module is located on the control track, using... Render the color blocks that block the boundary, and the color blocks themselves Extending towards the dangerous side of the control and dynamically adjusting the transparency of the color block according to how close the coupling parameter is to the critical value, a progressive visual warning is achieved;

[0050] Step Six, Operation Damping and Disaster Command Interception: When the user drags the position... Approaching At this time, the system applies rendered damping feedback force to further drag the control, simulating the feel of physical resistance. The calculation method is as follows:

[0051] ;

[0052] In the above formula, Indicates the current drag position The damping feedback force applied to the system, This represents the damping coefficient, used to adjust the overall strength of the damping force. This indicates the dynamic boundary position calculated in step four. This indicates the current position of the control that the user is dragging. This represents a very small positive number introduced to avoid a denominator of zero, when the user manipulates the position beyond... At that time, the system will restrict the drag command, limiting the actual control commands issued to [specific areas]. Within the corresponding safety values, physical rejection of disaster-causing manipulation commands is achieved;

[0053] Step 7, Closed-loop feedback: The system synchronously feeds back the actual effective value after clamping to the display status of the intention virtual graphic object and associated controls, and continues to receive the next user drag operation, returning to step 1 to form a complete dynamic foolproof mapping closed loop.

[0054] Example 4: Synergistic operation of the two core mechanisms:

[0055] The dual-state graphical object rendering module corresponding to Example 2 outputs the animation position and prediction error confidence band of the entity graphical object, while the dynamic boundary rendering module corresponding to Example 3 outputs the linked position of associated controls and the dynamic blocking area. The outputs of both modules converge to the unified GUI rendering engine, which completes the final interface frame rendering. When the dynamic boundary rendering module clamps the user's drag command, the clamping result is reversed and acts on the target state value of the intended phantom graphical object in the dual-state graphical object rendering module. That is, after the disaster-causing command is intercepted, the target state value of the intended phantom graphic object is also synchronously corrected to the clamped safe value, so that the two mechanisms form a closed-loop data flow collaboration, rather than a simple parallel relationship;

[0056] Example 5: An alternative implementation based on state machines and delay-compensated lookup tables:

[0057] In scenarios where edge computing resources are limited, the technical effect of Embodiment 2 can be achieved by the following simplified method: the average execution time and network latency experience value of each type of execution device under different working conditions are pre-calibrated, and an offline latency compensation lookup table is established. After receiving the user's drag command, the system does not perform real-time mechanism calculation, but directly looks up the table to obtain the expected execution time of the corresponding device, and controls the entity graphic object to approach the target position according to the preset fixed rate curve, which can also achieve the asynchronous separation display effect of the shadow and the entity.

[0058] Example 6: An alternative implementation method based on a rule engine and a linkage coefficient matrix:

[0059] In scenarios where a lightweight mechanism proxy model is not deployed, the technical effect of Example 3 can be achieved in the following simplified way: Agricultural experts pre-calibrate the coupling relationship between key environmental parameters of different crops and different growth stages offline, forming a parameter linkage coefficient matrix and a corresponding static threshold rule base. After the system detects the user's drag operation on a parameter control, it directly calculates the linkage displacement and dangerous boundary position of the associated parameters by querying the coefficient matrix, instead of solving the water, fertilizer and heat coupling differential equation in real time. This can also achieve the technical effect of linkage display of associated controls and dynamic blocking area rendering.

[0060] Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of the present invention. Therefore, any modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall fall within the protection scope defined by the claims of the present invention.

Claims

1. An Internet of Things-based smart agriculture digital management system, characterized in that, include: The field sensing and execution layer includes sensors for collecting agricultural environmental parameters and execution devices for performing agricultural operations; The edge computing gateway layer communicates with the field sensing and execution layer and is used to perform localized coupled parameter calculations and digital twin location prediction. The cloud platform layer, which is communicatively connected to the edge computing gateway layer, includes a digital twin model library, which stores the mechanical dynamics parameters of the execution device and a network latency statistical model. The GUI interactive rendering layer is communicatively connected to the edge computing gateway layer and the cloud platform layer, and is used to display a graphical user interface to the user. The GUI interactive rendering layer includes a dual-state graphical object rendering module and a dynamic boundary rendering module. The dual-state graphical object rendering module is used to respond to the user's manipulation of the graphical controls, generating an intentional virtual graphical object that synchronously follows the user's target state value. At the same time, the dual-state graphical object rendering module generates a physical execution trajectory prediction result based on the mechanical dynamic parameters of the execution device in the digital twin model library and the delay statistics of the current network link. Based on the physical execution trajectory prediction result, the module controls the physical graphical object to gradually approach the target state value in the following manner: the rendering state value of the physical graphical object is the sum of the smaller of the initial state value and the target direction sign function, the execution speed parameter of the execution device and the time after deducting the network round-trip delay, and the absolute value of the difference between the initial state value and the target state value. This allows the intentional virtual graphical object and the physical graphical object to be presented simultaneously in the graphical manipulation interface and to evolve independently. The dynamic boundary rendering module is used to calculate the predicted change of the associated environmental parameters based on the pre-established agricultural environmental parameter coupling equation and the incremental manipulation of the current graphical control by the user. Based on the relationship between the predicted change and the preset crop survival threshold, the module renders a dynamic blocking area on the track of the current control and adjusts the display state of the dynamic blocking area as the predicted change approaches the crop survival threshold, thereby confining the user's manipulation position of the current graphical control within the dynamic boundary position corresponding to the crop survival threshold. The dynamic boundary position is calculated by the inverse function of the monotonic mapping function between the pre-established environmental parameter control position and the corresponding physical quantity. It is updated in real time according to the coupling conditions of irrigation amount, season and crop growth stage, which is different from the existing technology that uses fixed upper and lower limits for positioning.

2. The Internet of Things-based smart agriculture digital management system according to claim 1, characterized in that: The edge computing gateway layer is also used to continuously monitor the IoT connection status. When the IoT connection is interrupted, the edge computing gateway layer takes over the inference calculation of the physical execution trajectory prediction result. The dynamic boundary rendering module is also used to render a prediction error confidence band around the entity graphic object. The width of the prediction error confidence band increases with the duration of the network interruption. 3.The IoT-based smart agricultural digital management system according to claim 2, characterized in that: The width of the prediction error confidence band is determined by an initial baseline width and an incremental width that is proportional to the duration of the network outage. The proportionality coefficient of the incremental width is calibrated based on the historical execution error statistics of the execution device.

4. The wisdom agricultural digital management system based on the Internet of Things according to claim 2, characterized in that: After the IoT connection is restored and the real state data is received from the execution device, the dual-state graphics object rendering module is further used to correct the rendering position of the entity graphics object to the position corresponding to the real state data, and to converge the width of the prediction error confidence band to the initial reference width.

5. The wisdom agricultural digital management system based on the Internet of Things according to claim 1, characterized in that: The agricultural environmental parameter coupling equation includes a first coupling relationship characterizing the effect of irrigation water volume on soil temperature and a second coupling relationship characterizing the effect of irrigation water volume on fertilizer concentration dilution. The dynamic boundary rendering module is also used to drive the graphical objects of other environmental parameter graphical controls associated with the current manipulation control to generate synchronous displacement animation based on the calculation results of the first coupling relationship and the second coupling relationship.

6. The smart agriculture digital management system based on the Internet of Things according to claim 1, characterized in that: The system has a pre-established monotonic mapping function between the position of the environmental parameter control and the corresponding physical quantity. The dynamic boundary rendering module, based on the inverse function of the monotonic mapping function, reverses the crop survival threshold to the dynamic boundary position on the current control track.

7. The smart agriculture digital management system based on the Internet of Things according to claim 1, characterized in that: The dynamic boundary rendering module is also used to apply a rendering damping feedback force to the current graphical control when the distance between the user's manipulation position of the current graphical control and the dynamic boundary position decreases. The rendering damping feedback force increases as the distance decreases. When the user's manipulation position of the current graphical control exceeds the dynamic boundary position, the actual control command issued is clamped within the value corresponding to the dynamic boundary position.

8. The smart agriculture digital management system based on the Internet of Things according to claim 7, characterized in that: The dual-state graphics object rendering module is also used to receive the value corresponding to the clamped control command, and synchronously correct the target state value of the intentional phantom graphics object to the value corresponding to the clamped control command.

9. An asynchronous rendering method for GUI graphical objects, used for displaying the manipulation state of graphical controls in a graphical user interface, characterized in that, include: Obtain the target state value of the user's manipulation of the graphical control; In response to obtaining the state value of the manipulation target, an intention phantom graphic object that is synchronized and follows the state value of the manipulation target is generated; Obtain the mechanical dynamics parameters of the corresponding execution device and the delay statistics parameters of the current network link, and generate a physical execution trajectory prediction result based on the mechanical dynamics parameters and the delay statistics parameters; Based on the physical execution trajectory prediction results, the control entity graphical object gradually approaches the manipulation target state value through animation interpolation, so that the entity graphical object and the intention virtual graphical object are presented simultaneously in the graphical user interface and evolve independently.

10. The asynchronous rendering method for GUI graphical objects according to claim 9, characterized in that, Also includes: The communication connection status is continuously monitored. When a communication connection interruption is detected, the position of the entity graphic object is further deduced based on the locally known mechanical dynamic parameters. A prediction error confidence band is rendered around the entity graphic object. The width of the prediction error confidence band increases with the duration of the communication connection interruption. After the communication connection is restored and the real state data is received from the execution device, the rendering position of the entity graphic object is corrected to the position corresponding to the real state data, and the width of the prediction error confidence band is converged to the initial reference width.

Images