Lightweight updating method, apparatus and device for digital twin model, and storage medium

Abstract

The invention discloses a digital twinborn model lightweight updating method, device and equipment and a storage medium, which are applied to an edge gateway, and are used for analyzing an obtained original data message, converting original data in the original data message into standardized data, filtering the standardized data, filtering abnormal data, and updating a twinborn model. Multi-dimensional judgment is carried out on the filtered standardized data, whether the filtered standardized data is effective incremental update data of a target digital device or not is judged, the target digital device is a digital device corresponding to a real device in the digital twin model, and when the filtered standardized data is the effective incremental update data, the target digital device is the target digital device corresponding to the real device. According to the method, the incremental update data is packaged and packaged to form the incremental update package, the incremental update package is published to the digital twin platform to update the target digital equipment, the incremental update package is formed by filtering and multi-dimensional judgment of the original data, network broadband occupation is reduced, computing resource consumption is reduced, and cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to digital twin model technology, in particular to a digital twin model lightweight updating method and device, equipment and storage medium. BACKGROUND

[0002] A digital twin model is a digital model that corresponds to a physical entity in a virtual space using physical models, sensor data, and operation history information. It can reflect the entire life cycle of the entity equipment and simulate and model in the virtual space, thereby realizing monitoring, prediction, and optimization of the physical entity.

[0003] Currently, the updating of digital twin models generally relies on centralized processing in the cloud. The coarse updating granularity leads to resource waste, that is, it cannot identify and synchronize the model parameters that have actually changed. The full or coarse-grained updating method causes a large amount of redundant data to be transmitted in the network, occupies a large network bandwidth, and consumes a large amount of cloud computing resources. SUMMARY

[0004] The present application provides a digital twin model lightweight updating method, device, equipment and storage medium to reduce network bandwidth occupation, reduce computing resource consumption and reduce cost.

[0005] In a first aspect, the present application provides a digital twin model lightweight updating method applied to an edge gateway, comprising:

[0006] Obtaining an original data packet of a real device;

[0007] Analyzing the original data packet and converting original data in the original data packet into standardized data;

[0008] Filtering the standardized data to filter out abnormal data;

[0009] Multi-dimensionally resolving the filtered standardized data to determine whether the filtered standardized data is valid incremental update data of a target digital device, the target digital device being a digital device corresponding to the real device in the digital twin model;

[0010] When the filtered standardized data is valid incremental update data, encapsulating and packaging the incremental update data to form an incremental update package;

[0011] Publishing the incremental update package to a digital twin platform to update the target digital device.

[0012] Optionally, analyzing the original data packet and converting original data in the original data packet into standardized data comprises:

[0013] determining a data transmission protocol with the reality device;

[0014] parsing the original data message by using a protocol adaptation template matching the data transmission protocol, and converting the original data in the original data message into standardized data, wherein the standardized data comprises the following fields: device identification, data standard semantic name, engineering value, quality code and time stamp.

[0015] Optionally, the standardized data is filtered to filter out abnormal data, including:

[0016] filtering out data with a difference from a previous value below a threshold value;

[0017] filtering out abnormal data beyond a range of physical rules;

[0018] filtering out abnormal data with a sampling frequency beyond a highest sampling frequency.

[0019] Optionally, the determination condition of the multi-dimensional arbitration is:

[0020] an absolute value of a difference between the filtered standardized data and current state data of the target digital device is greater than a threshold value;

[0021] a data quality of the filtered standardized data is greater than a preset quality;

[0022] a service priority of the filtered standardized data is greater than a preset priority;

[0023] a change of the filtered standardized data relative to current state data of the target digital device is an effective trend.

[0024] Optionally, determining whether the change of the filtered standardized data relative to current state data of the target digital device is an effective trend comprises:

[0025] comparing the filtered standardized data with a dynamic reference benchmark determined based on historical data;

[0026] if the filtered standardized data does not exceed a dynamic fluctuation range of the dynamic reference benchmark, determining that the change is transient oscillation;

[0027] if the filtered standardized data exceeds the dynamic fluctuation range of the dynamic reference benchmark, calling data records to determine a change direction of K continuous data including current data;

[0028] if the change direction of the K continuous data is the same, determining that the change is an effective trend.

[0029] Optionally, when the filtered standardized data is valid incremental update data, the incremental update data is packaged to form an incremental update package, including:

[0030] The incremental update data is packaged into an incremental update package in JSON format.

[0031] Optionally, the incremental update package is published to a digital twin platform, including:

[0032] The filtering condition of the standardized data is dynamically adjusted based on the network connection quality of the transmission network.

[0033] In a second aspect, the present application also provides a digital twin model lightweight updating device, applied to an edge gateway, including:

[0034] An original message acquisition module is configured to acquire an original data message of a real device;

[0035] A message analysis module is configured to analyze the original data message, and convert original data in the original data message into standardized data;

[0036] A data filtering module is configured to filter the standardized data to filter out abnormal data;

[0037] A multi-dimensional decision module is configured to perform multi-dimensional decision on the filtered standardized data, and determine whether the filtered standardized data is valid incremental update data for a target digital device, the target digital device being a digital device corresponding to the real device in a digital twin model;

[0038] A data packaging module is configured to, when the filtered standardized data is valid incremental update data, package the incremental update data to form an incremental update package;

[0039] A data publishing module is configured to publish the incremental update package to a digital twin platform to update the target digital device.

[0040] In a third aspect, the present application also provides an electronic device, including:

[0041] One or more processors;

[0042] A storage device configured to store one or more programs;

[0043] When the one or more programs are executed by the one or more processors, the one or more processors implement the digital twin model lightweight updating method according to the first aspect of the present application.

[0044] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method for updating a digital twin model in a light weight manner according to the first aspect of the present application.

[0045] The method for updating a digital twin model in a light weight manner provided by the present application is applied to an edge gateway, original data packets obtained are parsed, original data in the original data packets is converted into standardized data, the standardized data is filtered to filter out abnormal data, the filtered standardized data is subjected to multi-dimensional arbitration to determine whether the filtered standardized data is valid incremental update data for a target digital device, the target digital device is a digital device corresponding to a real device in the digital twin model, when the filtered standardized data is valid incremental update data, the incremental update data is encapsulated and packaged to form an incremental update package, the incremental update package is published to a digital twin platform to update the target digital device, the original data is filtered and subjected to multi-dimensional arbitration to form the incremental update package, network bandwidth occupation is reduced, computing resource consumption is reduced, and cost is reduced.

[0046] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0048] Figure 1 A flow chart of the method for updating a digital twin model in a light weight manner provided by the present application;

[0049] Figure 2 A structural schematic diagram of the device for updating a digital twin model in a light weight manner provided by the present application;

[0050] Figure 3 A structural schematic diagram of an electronic device provided by the present application.

[0051] The above drawings have shown the specific embodiments of the present application, and will be described in more detail hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0052] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the drawings in the embodiments of the present application, so that those skilled in the art can better understand the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0053] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0054] Figure 1 A flowchart of a digital twin model lightweight updating method is provided in the present application. The embodiment can be applied to lightweight updating of a digital twin model. The method can be executed by a digital twin model lightweight updating device provided by the present application. The device can be realized by software and / or hardware, and is usually configured in an electronic device, such as a server, as shown in the figure. The digital twin model lightweight updating method includes the following steps: Figure 1

[0055] S101, obtaining an original data packet of a real device.

[0056] In the embodiment of the present application, the real device is connected with an edge gateway, and reports the original data packet to the edge gateway. For example, one edge gateway can be connected with one or more real devices, which is not limited in the present application. In a specific embodiment, the edge gateway collects real-time original data packets (Modbus TCP frames, OPC UA messages, etc.) from heterogeneous devices (such as PLC, sensor) in an industrial site. The heterogeneous devices in the industrial site usually include various industrial protocols (such as Modbus, MQTT, OPCUA, CAN).

[0057] S102, analyzing the original data packet, and converting the original data in the original data packet into standardized data.

[0058] ​In the embodiments of the present application, the original data in the original data message is converted into standardized data by analyzing the original data message. This step converts the original data of various protocols into standardized intermediate data objects in the system.

[0059] In some embodiments of the present application, the edge gateway determines the data transmission protocol between the real device, and analyzes the original data message by using a protocol adaptation template matched with the data transmission protocol to convert the original data in the original data message into standardized data, wherein the standardized data includes the following fields: device identification (productId), data standard semantic name (data_name, standard semantic name such as motor_temperature), engineering value (value), quality code (quality), and timestamp (timestamp). For example, the protocol conversion engine analyzes the original message according to the predefined protocol adaptation template, for example, the template defines “read INT16 value from Modbus register 10001, scale factor 0.1, and name it as'motor_temperature'”.

[0060] The quality code is a comprehensive data reliability index, which is derived from multiple sources and determined by quality code generation logic. The specific sources include:

[0061] 1. Device self-diagnosis information: Many intelligent sensors or industrial controllers will attach an original quality status word (such as StatusCode in OPC UA standard) when outputting data. For example:

[0062] Good (0x0000): Good data.

[0063] Uncertain (0x4000): Data value is uncertain, but may still be usable.

[0064] Bad (0x8000): Data is not reliable.

[0065] The protocol conversion engine will first read and analyze this status word.

[0066] 2. Communication link health: The edge gateway will monitor the link state of communication with the device.

[0067] Communication timeout: If no device response is received within the preset time, the quality code of this batch of data is determined as “Bad_CommunicationTimeout”.

[0068] CRC / checksum error: The message has an error during transmission, and the quality code is set to “Bad_ChecksumError”.

[0069] 3. Check result of protocol conversion engine:

[0070] Data range check: In the protocol template, a reasonable theoretical range [min, max] can be predefined for each data point. If the converted value is out of this range, the quality code will be marked as "Bad_OutOfRange".

[0071] Data format legality: If the data type conversion fails (for example, trying to convert non-numeric characters to a floating point number), it is marked as "Bad_FormatError".

[0072] Example of generation logic:

[0073] The system will preferentially use the device self-diagnosis information. If the device information is Good, further communication link and engine checks are performed. If any of the checks fail, the quality code is overwritten according to the failure reason. Finally, a unified numerical or enumerated code (such as 0-100, 100 being the best) is assigned to the quality field for use by subsequent modules.

[0074] Timestamps play a key role in the scheme in terms of "data timeliness" and "causality". The specific roles include:

[0075] 1. Ensuring the accuracy of state calculation: In the "signal stability" judgment, the algorithm needs to know the accurate collection time of the data point to calculate the correct change rate and trend. Without accurate timestamps, it is impossible to distinguish between slow drift and transient pulses.

[0076] 2. Realizing the time alignment of multi-source data: A digital twin model may be driven by multiple data sources (such as the need for temperature, pressure, and vibration at the same time). High-precision timestamps (preferably source timestamps) ensure that these different sources of data can be correctly synchronized and fused in the cloud, truly representing the complete state of the physical entity at a certain time.

[0077] 3. Supporting the logic of incremental updates: Timestamps are the only basis for judging the "newness" of data. The system relies on timestamps to maintain the time point corresponding to the "last successful update value", ensuring that the model state does not "backtrack" due to data packet out-of-order caused by network delay.

[0078] 4. Used for diagnosis and audit: When the system is abnormal, accurate timestamp sequences are valuable logs for fault tracing and root cause analysis.

[0079] S103, filter the aligned data to filter out abnormal data.

[0080] In embodiments of the present application, the above-mentioned standardized data is filtered to filter out abnormal data. For example, in some embodiments of the present application, three filtering procedures are sequentially performed to form a filtering chain:

[0081] 1) Dynamic dead zone filtering: compare the current value with the previous value, and only when the change exceeds the threshold dynamically adjusted by the business priority (such as ±0.1% of the key parameter), is the pass allowed.

[0082] 2) Physical rule verification: verify whether the value is within the reasonable physical range defined by the digital twin model (such as the motor temperature cannot be -10°C), and eliminate obviously abnormal data.

[0083] 3) Business-aware frequency control: limit the maximum sampling frequency according to the parameter characteristics (such as temperature 1Hz, position 50Hz), and reduce data flow from the time dimension.

[0084] Through the above filtering, a clean, effective and low-redundancy standardized data object is output, providing high-quality input for model-level processing.

[0085] S104, multi-dimensional decision is made on the filtered standardized data to determine whether the filtered standardized data is valid incremental update data for the target digital device.

[0086] In embodiments of the present application, multi-dimensional decision is made on the filtered standardized data to determine whether the filtered standardized data is valid incremental update data for the target digital device, the target digital device being a digital device corresponding to the real device in the digital twin model.

[0087] Among them, the determination condition of multi-dimensional decision is:

[0088] 1. The absolute value of the difference between the filtered standardized data and the current state data of the target digital device is greater than a threshold.

[0089] The engineering value in the filtered standardized data is compared with the current state data of the target digital device to determine whether the absolute value of the difference between the filtered standardized data and the current state data of the target digital device is greater than a threshold.

[0090] 2. The data quality of the filtered standardized data is greater than a preset quality.

[0091] After determining the quality code of the filtered standardized data, it is determined whether the data quality represented by the quality code of the filtered standardized data is better than the preset quality. For example, it is determined whether the quality code is "good" or above.

[0092] 3. The business priority of the filtered standardized data is greater than a preset priority.

[0093] The service priority of the filtered standardized data is greater than the preset priority. The service priority is not automatically generated by the system, but is injected into the system by domain experts or system administrators according to business rules and operation needs through pre-configuration. Its source and setting method are as follows:

[0094] 3.1, static pre-defined configuration:

[0095] The system maintains a "business priority mapping table", which is configured by the administrator when the system is initialized or the device is accessed. This is a typical key-value pair structure, taking JSON format data as an example:

[0096] {

[0097] "business_priority_mapping": {

[0098] "emergency_stop": 10, / / Highest priority: safety class signal

[0099] "circuit_breaker_status": 9, / / High priority: protection class signal

[0100] "total_power_consumption": 7, / / Medium-high priority: billing and core energy consumption

[0101] "lighting_switch_status": 3, / / Medium priority: control class signal

[0102] "ambient_temperature": 1 / / Low priority: ordinary environmental monitoring

[0103] }

[0104] }

[0105] In the "model rule mapping engine", each data_name is associated with a priority score in the mapping table.

[0106] 3.2, dynamic context adjustment (optional advanced feature):

[0107] In some advanced implementations, the priority can be dynamically fine-tuned according to the system running mode. For example:

[0108] 1) In "night energy-saving mode", the priority of all parameters related to energy consumption (such as total power consumption total_power_consumption) will be temporarily increased.

[0109] 2) When the system detects an alarm in a certain area, the priority of all relevant parameters in that area will be temporarily increased so that resources can be concentrated for in-depth monitoring.

[0110] Its core idea is that business prioritization is the bridge that transforms human business decisions into machine-executable rules, and is the key to achieving "intelligent" adjudication.

[0111] 4. The changes in the filtered standardized data relative to the current state data of the target digital device are effective trends.

[0112] Changes in state data can be categorized into valid trends and transient oscillations. This step determines whether the changes in the filtered, standardized data relative to the current state data of the target digital device represent valid trends.

[0113] In some embodiments of the present invention, determining whether the change of the filtered standardized data relative to the current state data of the target digital device is a valid trend includes:

[0114] 1) Compare the filtered standardized data with a dynamic reference benchmark determined based on historical data.

[0115] In this embodiment of the invention, a dynamic reference benchmark can be pre-determined based on historical data. For example, the system maintains a fixed-length first-in-first-out queue for each monitored data point (e.g., "electrical box A - temperature"). This queue records the health values ​​(i.e., values ​​that have passed previous data quality checks) of that data point for the most recent N times (e.g., the most recent 10 times). This queue serves as the system's "memory." When new data arrives, the system calculates two key dynamic reference benchmarks based on this "historical data window":

[0116] Dynamic mean: Calculates the average of all data within the historical window. This represents the recent "normal level" of this parameter.

[0117] Dynamic fluctuation range: This calculates the normal fluctuation range of historical data. This range is not fixed but dynamically calculated based on the dispersion of the historical data. If the historical data is highly concentrated, this range is narrow; if the historical data itself is highly volatile, this range is wide.

[0118] After receiving the filtered and standardized data, the filtered and standardized data is compared with a dynamic reference benchmark determined based on historical data.

[0119] 2) If the filtered standardized data does not exceed the dynamic fluctuation range of the dynamic reference benchmark, the change is determined to be an instantaneous oscillation.

[0120] If the filtered standardized data changes compared to the previous value, but still falls within the "dynamic fluctuation range" and fluctuates erratically around the "dynamic mean," it is considered noise or transient oscillation, filtered out, and no model update is triggered. For example, the historical average temperature of the electrical box is 75℃, with a normal fluctuation range of ±0.3℃. The new reading is 75.2℃, which is 0.2℃ higher than the previous 75.0℃, but it still oscillates within the normal "box" of [74.7℃, 75.3℃]. The system considers this normal fluctuation and ignores it.

[0121] 3) If the filtered standardized data exceeds the dynamic fluctuation range of the dynamic reference benchmark, the data records are called to determine the direction of change of the first K consecutive data, including the current data.

[0122] If the filtered, standardized data exceeds the boundary of the "dynamic fluctuation range," more importantly, the system will check whether this is a "continuous" action, that is, it will call the data records to determine the direction of change of the previous K consecutive data, including the current data.

[0123] 4) If the first K consecutive data points change in the same direction, then the change is considered a valid trend.

[0124] If the system detects that the first K consecutive data points all change in the same direction (continuously upward or downward), even if the individual changes are small, it will consider a valid trend to be forming. For example, if the temperature of an electrical box fluctuates steadily around 75℃, and suddenly a new reading of 76.0℃ arrives, far exceeding the upper limit of the normal fluctuation range, the system will immediately determine it as a valid (and abnormal) change. Another example is that the electrical box temperature readings are: 75.0, 75.1, 75.3, 75.5, 75.8. Although each change is small, the system, through its "memory," detects that it is continuously rising and has steadily exceeded the initial fluctuation range. The system will determine this as a valid temperature rise trend and allow the latest value of 75.8℃ to update the model, even if it only changes by 0.3℃ relative to the previous value.

[0125] This invention intelligently distinguishes between signal noise and actual state transitions by maintaining a dynamic, adaptive reference frame (mean and fluctuation range) and analyzing the position and behavior of new data relative to this reference frame (whether it is internal oscillation or boundary breach, and whether it has directionality). This method significantly reduces the frequent and meaningless jitter of the digital twin model caused by field interference, ensuring the stability of the model and the accuracy of update decisions.

[0126] After the above multi-dimensional decision-making process, a final list of valid incremental updates is generated. This list only includes data that has passed all decisions and is truly necessary to synchronize; a large number of unimportant updates are filtered out at this stage.

[0127] S105. When the filtered standardized data is valid incremental update data, the incremental update data is encapsulated and packaged to form an incremental update package.

[0128] In this embodiment of the invention, when the filtered standardized data is valid incremental update data, the incremental update data is packaged into an incremental update package in JSON format.

[0129] The incremental packetization engine packages all entries in the updated list after the decision into a single, compact incremental update data packet. This is achieved by using a minimalist JSON format and abbreviated key names to minimize file size.

[0130] Result: The final lightweight incremental update package is generated, as shown in the example below:

[0131] {

[0132] "modeId": "robot_1_model",

[0133] "time": 1629999123456,

[0134] "updateList": [

[0135] {"prop": "arm.joint.temp", "value": 45.1}

[0136] ]}

[0137] “modeId” is the model ID of the target digital device.

[0138] S106. Publish the incremental update package to the digital twin platform to update the target digital device.

[0139] In this embodiment of the invention, the incremental update package is published to the digital twin platform via the network to update the target digital device.

[0140] For example, during the deployment process, the edge gateway dynamically adjusts the filtering conditions of standardized data based on the network connection quality of the transmission network. The core idea is to enable the system to sense the pressure of the external environment (network) and proactively and intelligently sacrifice non-core accuracy to preserve core functions and overall stability. This upgrades the system from a static, passive data processing pipeline to an intelligent agent with self-regulating capabilities. It can sense environmental pressure and make intelligent trade-offs.

[0141] Taking the monitoring system of the smart street light distribution box in the city as an example, we will explain its working mechanism in detail.

[0142] Suppose there are 1000 street light electrical boxes connected to the cloud via a 4G network.

[0143] 1. Normal mode (good network conditions)

[0144] 1) Transmission level monitoring showed: network latency < 100ms, packet loss rate ≈ 0%.

[0145] 2) Data-level execution: All data points are filtered according to their normal and fine thresholds.

[0146] 2.1) Current (key parameter): Dead zone threshold = ±0.1A (any change exceeding 0.1A is reported).

[0147] 2.2) Lampshade temperature (normal parameter): Dead zone threshold = ±2℃ (reporting is only required if the change exceeds 2℃).

[0148] 2. Network congestion

[0149] 1) Monitoring and Diagnosis (Transmission Level)

[0150] 1.1) Continuous monitoring by the transmission engine revealed that network latency remained above 500ms and the packet loss rate increased to 10%.

[0151] 1.2) Diagnostic Decision: The engine determines the network status as "congested." Based on a predefined strategy, it generates a control command: "Raise the filtering threshold for all data points to three times the current value." This command is immediately sent to the data-level intelligent filtering module via the system's internal bus.

[0152] 2) Execution and Degradation (Data Level)

[0153] 2.1) Upon receiving the instruction, the intelligent filtering module immediately and dynamically adjusts all filtering thresholds:

[0154] 2.1.1) Current: The threshold is temporarily relaxed from ±0.1A to ±0.3A.

[0155] 2.1.2) Lampshade temperature: The threshold is temporarily relaxed from ±2℃ to ±6℃.

[0156] 2.2) Effect:

[0157] A current change from 10.2A to 10.4A (a change of 0.2A) would normally be reported, but it is now being filtered out because 0.2A < 0.3A.

[0158] A temperature change of 5°C from 45°C to 50°C would normally be reported, but now it is being filtered out because 5°C < 6°C.

[0159] Result: The total amount of data that can pass through filtering, enter subsequent processing pipelines, and ultimately need to be transmitted over the network is drastically reduced. This may reduce the number of data packets that need to be transmitted by more than 70%.

[0160] 3) System recovery

[0161] The transmission engine continuously monitors the network. When it detects that the latency has recovered to <150ms and the packet loss rate has dropped to approximately 1%, it determines that the network status has recovered to "good". It then issues a new control command: "Restore the filtering thresholds for all data points to normal values." Upon receiving the command, the intelligent filtering module immediately restores the current and lampshade temperature thresholds to their original states, and the system re-enters fine-tuning monitoring mode.

[0162] The core value brought by this mechanism:

[0163] 1. Ensuring Core Functions: The system does not crash during network congestion but continues to operate. While some minor changes are ignored, any truly significant anomalies (e.g., a sudden current spike to 15A, far exceeding the 0.3A threshold) will still be captured and reported. This ensures that core functions such as alarms are never interrupted.

[0164] 2. Avoiding the cascading failure effect: Without this mechanism, the system would still attempt to transmit massive amounts of data during network congestion, leading to overflowing network interface queues, packet retransmissions, and further exacerbating the CPU load on the network and edge gateways, potentially causing the entire edge service to crash. This mechanism avoids this vicious cycle by "throttling at the source."

[0165] 3. Achieve optimal resource allocation: It dynamically and preferentially allocates valuable network bandwidth and cloud processing resources to the most important data changes.

[0166] The lightweight update method for digital twin models provided by this invention is applied to edge gateways. It parses the acquired raw data packets, converts the raw data in the packets into standardized data, filters the standardized data to remove abnormal data, and performs multi-dimensional adjudication on the filtered standardized data to determine whether it is valid incremental update data for the target digital device (the digital device in the digital twin model corresponding to the real-world device). When the filtered standardized data is valid incremental update data, it is packaged into an incremental update package and published to the digital twin platform to update the target digital device. By filtering the raw data and performing multi-dimensional adjudication to form incremental update packages, the method reduces network bandwidth usage, computational resource consumption, and costs.

[0167] Figure 2 This is a schematic diagram of the structure of a lightweight update device for a digital twin model provided by the present invention, as shown below. Figure 2 As shown, the lightweight update device for digital twin models includes:

[0168] The raw message acquisition module 201 is used to acquire the raw data messages of the actual device.

[0169] The message parsing module 202 is used to parse the original data message and convert the original data in the original data message into standardized data;

[0170] Data filtering module 203 is used to filter the standardized data and remove abnormal data;

[0171] The multidimensional adjudication module 204 is used to perform multidimensional adjudication on the filtered standardized data to determine whether the filtered standardized data is valid incremental update data for the target digital device, wherein the target digital device is the digital device in the digital twin model that corresponds to the real device.

[0172] The data packaging module 205 is used to encapsulate and package the incremental update data to form an incremental update package when the filtered standardized data is valid incremental update data.

[0173] The data publishing module 206 is used to publish the incremental update package to the digital twin platform to update the target digital device.

[0174] In some embodiments of the present invention, the message parsing module 202 includes:

[0175] The protocol determination submodule is used to determine the data transmission protocol with the actual device;

[0176] The parsing submodule is used to parse the original data packet using a protocol adaptation template that matches the data transmission protocol, and convert the original data in the original data packet into standardized data, wherein the standardized data includes the following fields: device identifier, data standard semantic name, engineering value, quality code and timestamp.

[0177] In some embodiments of the present invention, the data filtering module 203 includes:

[0178] The first filtering submodule is used to filter out data whose difference from the previous value is less than a threshold.

[0179] The second filtering submodule is used to filter out abnormal data that exceeds the scope of physical rules;

[0180] The third filtering submodule is used to filter out abnormal data whose sampling frequency exceeds the maximum sampling frequency.

[0181] In some embodiments of the present invention, the determination criteria for the multidimensional decision are as follows:

[0182] The absolute value of the difference between the filtered standardized data and the current state data of the target digital device is greater than a threshold.

[0183] The quality of the filtered, standardized data is greater than the preset quality.

[0184] The business priority of the filtered standardized data is higher than the preset priority.

[0185] The changes in the filtered, standardized data relative to the current state data of the target digital device represent an effective trend.

[0186] In some embodiments of the present invention, determining whether the change in the filtered standardized data relative to the current state data of the target digital device is a valid trend includes:

[0187] The filtered standardized data is compared with a dynamic reference benchmark determined based on historical data;

[0188] If the filtered standardized data does not exceed the dynamic fluctuation range of the dynamic reference benchmark, then the change is determined to be an instantaneous oscillation.

[0189] If the filtered standardized data exceeds the dynamic fluctuation range of the dynamic reference benchmark, then the data records are called to determine the direction of change of the first K consecutive data, including the current data.

[0190] If the first K consecutive data points change in the same direction, then the change is considered a valid trend.

[0191] In some embodiments of the present invention, the data packaging module 205 includes:

[0192] The packaging submodule is used to package incremental update data into incremental update packages in JSON format.

[0193] In some embodiments of the present invention, the data publishing module 206 includes:

[0194] The adjustment submodule is used to dynamically adjust the filtering conditions of the standardized data based on the network connection quality of the transmission network.

[0195] The aforementioned lightweight digital twin model update device can execute the lightweight digital twin model update method provided in the foregoing embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the lightweight digital twin model update method.

[0196] Figure 3 This is a schematic diagram of an electronic device provided by the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0197] like Figure 3 As shown, the electronic device includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0198] Multiple components in the electronic device are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the electronic device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0199] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the lightweight update method for digital twin models.

[0200] In some embodiments, the lightweight update method for the digital twin model can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on an electronic device via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the lightweight update method for the digital twin model described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the lightweight update method for the digital twin model by any other suitable means (e.g., by means of firmware).

[0201] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0202] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0203] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0204] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0205] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0206] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0207] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the lightweight update method for digital twin models as provided in any embodiment of this application.

[0208] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0209] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0210] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for lightweight updating of a digital twin model, characterized in that, The application is applied to an edge gateway, and comprises the following steps: Obtaining original data messages of a real device; Analyzing the original data messages to convert original data in the original data messages into standardized data; Filtering the standardized data to filter out abnormal data; Multi-dimensionally determining whether the filtered standardized data is valid incremental update data of a target digital device, the target digital device being a digital device corresponding to the real device in a digital twin model; When the filtered standardized data is valid incremental update data, encapsulating and packaging the incremental update data to form an incremental update package; Publishing the incremental update package to a digital twin platform to update the target digital device. 2.The method of claim 1, wherein, The step of analyzing the original data messages to convert original data in the original data messages into standardized data comprises the following steps: Determining a data transmission protocol between the real device; Analyzing the original data messages by using a protocol adaptation template matched with the data transmission protocol to convert original data in the original data messages into standardized data, wherein the standardized data comprises the following fields: device identification, data standard semantic name, engineering value, quality code and time stamp. 3.The method of claim 1, wherein, The step of filtering the standardized data to filter out abnormal data comprises the following steps: Filtering out data with a difference from a previous numerical value lower than a threshold value; Filtering out abnormal data beyond a physical rule range; Filtering out abnormal data with a sampling frequency beyond a highest sampling frequency. 4.The method of claim 1, wherein, The determination condition of the multi-dimensionally determining step is that: An absolute value of a difference between the filtered standardized data and current state data of the target digital device is greater than a threshold value; Data quality of the filtered standardized data is greater than a preset quality; A business priority of the filtered standardized data is greater than a preset priority; A change of the filtered standardized data relative to the current state data of the target digital device is an effective trend. 5.The method of claim 4, wherein, The step of determining whether the change of the filtered standardized data relative to the current state data of the target digital device is an effective trend comprises the following steps: Comparing the filtered standardized data with a dynamic reference benchmark determined based on historical data; If the filtered standardized data does not exceed a dynamic fluctuation range of the dynamic reference benchmark, determining that the change is transient oscillation; If the filtered standardized data exceeds the dynamic fluctuation range of the dynamic reference benchmark, calling a data record to determine a change direction of K continuous data including current data; If the change direction of the K continuous data is the same, determining that the change is an effective trend. 6.The method of claim 1, wherein, The step of, when the filtered standardized data is valid incremental update data, encapsulating and packaging the incremental update data to form an incremental update package comprises the following step: Packaging the incremental update data into a JSON format incremental update package. 7.The method of claim 1, wherein, The step of publishing the incremental update package to a digital twin platform comprises the following step: Dynamically adjusting a filtering condition of the standardized data based on network connection quality of a transmission network. 8.A digital twin model lightweight updating apparatus, characterized in that, The application is applied to an edge gateway, and comprises the following steps: An original message obtaining module is configured to obtain original data messages of a real device; The message analysis module is configured to analyze the original data message, and convert original data in the original data message into standardized data. The data filtering module is configured to filter the standardized data, and filter out abnormal data. The multi-dimensional decision module is configured to perform multi-dimensional decision on the filtered standardized data, and determine whether the filtered standardized data is valid incremental update data for a target digital device. The data packaging module is configured to, when the filtered standardized data is valid incremental update data, encapsulate and package the incremental update data to form an incremental update package. The data publishing module is configured to publish the incremental update package to a digital twin platform to update the target digital device.

9. An electronic device, comprising: The one or more processors; The storage device is configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the digital twin model lightweight update method of any one of claims 1-7. The program is executed by the processor to implement the digital twin model lightweight update method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, ​

Images