Dynamic updating method of digital twin bottom plate

Abstract

The invention discloses a dynamic updating method for a digital twin bottom plate, and relates to the technical field of data processing. The method comprises the following steps: constructing a periodic influence intensity field according to the influence intensity of a periodic index of a digital twin bottom plate associated service on bottom plate data structure change; constructing a disturbance vector according to the influence intensity of the external event trigger factor of the associated service on the base plate data structure change; based on the historical data structure change sequence of the digital twin bottom plate, determining the data structure change rate of the digital twin bottom plate, and constructing a structure gradient tensor according to the data structure change rate; inputting the structure gradient tensor, the periodic influence intensity field and the disturbance vector as variables of a tensor equation into a preset tensor equation, and determining a change prediction result through a characteristic value decomposition result of the tensor equation; and a new base plate data structure is generated according to the change prediction result, and the base plate data in the current base plate data structure is migrated to the new base plate data structure, so that the change real-time performance is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a dynamic update method for a digital twin baseboard. Background Art

[0002] Digital twin technology is widely used in smart manufacturing, smart cities, intelligent transportation, and other fields. Its core is to use real-time data to drive virtual models, enabling the mapping, analysis, and prediction of real physical entities. In this system, the digital twin backplane serves as the foundation for twin modeling, data access, status presentation, and feedback control. Its data structure and update mechanism are crucial.

[0003] In related digital twin baseplate systems, static or semi-dynamic baseplate structures are mostly used. By presetting the data model structure, a small number of fields are added or statically replaced after initialization to achieve the update of the baseplate structure. The lack of structural change prediction capability leads to a delayed response to the baseplate structure update. Summary of the Invention

[0004] The main purpose of this application is to provide a dynamic update method for a digital twin baseboard, aiming to solve the technical problem of how to improve the real-time performance of the digital twin baseboard update.

[0005] To achieve the above objectives, this application proposes a method for dynamically updating a digital twin baseboard, the method comprising: Construct a periodic impact intensity field based on the impact intensity of the periodic indicators of the digital twin baseboard-related business on the baseboard data structure changes; Constructing a disturbance vector according to the impact intensity of the external event triggering factor of the associated business on the change of the backplane data structure; Determining a data structure change rate of the digital twin baseboard based on a historical data structure change sequence of the digital twin baseboard, and constructing a structural gradient tensor according to the data structure change rate; Inputting the structural gradient tensor, the periodic influence intensity field and the disturbance vector as variables of a tensor equation into a preset tensor equation, and determining an eigenvalue decomposition result through a calculation result of the tensor equation; Determining a change prediction result of the current baseboard data structure based on the eigenvalue decomposition result; A new baseboard data structure is generated according to the change prediction result, and the baseboard data in the current baseboard data structure is migrated to the new baseboard data structure.

[0006] In one embodiment, before the step of constructing a periodic impact intensity field based on the impact intensity of the periodic indicators of the digital twin backplane-related business on the backplane data structure change, the following steps are included: Separate the time series data in the digital twin baseboard through a preset time series decomposition algorithm to obtain the periodic items of the time series data; Determining a peak-to-valley difference of the periodic term within a period length as the periodic amplitude of the periodic term; Performing Fourier transform on the periodic term to obtain a periodic frequency of the periodic term; The periodic amplitude and the periodic frequency are used as the periodicity indicators.

[0007] In one embodiment, the step of constructing a periodic impact intensity field based on the impact intensity of the periodic indicators of the digital twin baseboard-related business on the baseboard data structure change includes: Constructing a node set based on each data structure field in the current baseboard data structure; Constructing a directed edge set based on the change association relationship between each data structure field in the historical data structure change sequence and the node set; Constructing a node topology graph according to the node set and the directed edge set; Determining the correlation influence strength between each node according to the node topology graph, wherein the correlation influence strength represents the dependency strength between the nodes; The associated influence intensity, the periodic amplitude and the periodic frequency are input into a preset periodic influence intensity field equation as variables of the periodic influence intensity field equation to construct the periodic influence intensity field.

[0008] In one embodiment, the step of determining the association influence strength between the nodes according to the node topology graph, wherein the association influence strength represents the dependency strength between the nodes, includes: Determine each associated node of the current node based on the historical data structure change sequence, wherein the current node points to the associated nodes via directed edges; Determining the weight of each directed edge of the current node according to the number of times the current node drives the associated node to change; The association influence strength of the current node is determined according to the sum of the weights of the directed edges of the current node, wherein the association influence strength is proportional to the sum of the weights.

[0009] In one embodiment, the step of constructing a disturbance vector according to the intensity of the impact of the external event triggering factor of the associated business on the change of the backplane data structure includes: Using the spatial position coordinates of the nodes associated with each of the external event triggering factors as the vector direction of the disturbance vector; Based on the historical data structure change sequence, and according to the number and change frequency of nodes associated with each external event triggering factor, the vector size of the disturbance vector is determined.

[0010] In one embodiment, the step of determining the data structure change rate of the digital twin baseboard based on the historical data structure change sequence of the digital twin baseboard includes: Dividing the time period corresponding to the historical data structure change sequence into two or more time windows; Construct a time change sequence based on the number of data structure changes within each time window; Mapping the changed fields in the historical data structure change sequence to the node topology graph, determining the changed nodes, and using the number of changes in the changed fields as the number of changes in the changed nodes to construct a spatial change sequence; Based on the time change sequence and the space change sequence, a structural change rate of the digital twin baseplate is determined.

[0011] In one embodiment, the eigenvalue decomposition result includes an eigenvalue and an eigenvector corresponding to the eigenvalue. The step of determining a change prediction result of the current baseboard data structure based on the eigenvalue decomposition result includes: determining, based on the characteristic value, a change intensity of a data structure field corresponding to the characteristic value; Determine, according to the eigenvector corresponding to the eigenvalue, the change probabilities of different change types corresponding to the data structure field.

[0012] In one embodiment, the step of generating a new baseboard data structure according to the change prediction result includes: generating a candidate baseboard data structure according to the change prediction result; Determining an evaluation score of each of the candidate base plate data structures based on the target optimization parameter; The new base plate data structure is determined in the to-be-selected base plate data structures according to the evaluation score.

[0013] In one embodiment, after the step of migrating the baseboard data in the current baseboard data structure to the new baseboard data structure, the method further includes: Constructing a source hash tree according to the hash value of the baseboard data in the baseboard data structure before the change, and determining a root node of the source hash tree; Constructing a new hash tree according to the hash value of the baseboard data in the new baseboard data structure, and determining a root node of the new hash tree; If the root nodes of the source hash tree and the new hash tree are consistent, it is determined that the digital twin baseboard update is completed.

[0014] In one embodiment, after the steps of constructing a new hash tree based on the hash value of the backplane data in the new backplane data structure and determining the root node of the new hash tree, the method further includes: If the root nodes of the source hash tree and the new hash tree are inconsistent, compare the intermediate nodes of the source hash tree and the new hash tree, and determine the node to be modified based on the comparison result; The backplane data corresponding to the node to be modified in the backplane data structure before the change is re-migrated to the new backplane data structure.

[0015] This application provides a dynamic update method for a digital twin baseboard, which constructs a periodic impact intensity field based on the impact intensity of periodic indicators of digital twin baseboard-related services on baseboard data structure changes; Based on the intensity of the impact of external event triggering factors of related businesses on the change of the baseboard data structure, a disturbance vector is constructed; based on the historical data structure change sequence of the digital twin baseboard, the data structure change rate of the digital twin baseboard is determined, and based on the data structure change rate, a structural gradient tensor is constructed; the structural gradient tensor, periodic influence intensity field and disturbance vector are input as variables of the tensor equation into the preset tensor equation, and the eigenvalue decomposition result is determined by the calculation result of the tensor equation; based on the eigenvalue decomposition result, the change prediction result of the current baseboard data structure is determined; based on the change prediction result, a new baseboard data structure is generated, and the baseboard data in the current baseboard data structure is migrated to the new baseboard data structure.

[0016] The above method quantifies the distribution of the impact of business periodic operations on data structure changes by constructing a periodic impact intensity field, combines the disturbance vector to capture the direction and amplitude of non-business interference of external events on the data structure, and constructs a structural gradient tensor based on the historical change sequence to quantify the spatiotemporal gradient of data structure changes. The three are then integrated into a tensor equation, and the dominant change pattern is extracted using eigenvalue decomposition. The change prediction results are output to guide the generation of a new baseplate structure that meets dynamic needs, realizing the transition from passive response to active prediction, and significantly improving the real-time performance of digital twin baseplate updates. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 A flowchart of the first embodiment of the dynamic update method of the digital twin baseboard of the present application is provided; Figure 2A flowchart of the second embodiment of the dynamic update method of the digital twin baseboard of this application is provided; Figure 3 A flowchart of the third embodiment of the dynamic update method of the digital twin baseboard of this application is provided; Figure 4 A schematic diagram of a node topology diagram provided in Example 3 of the dynamic update method for the digital twin baseboard of this application; Figure 5 A flowchart illustrating a fourth embodiment of a method for dynamically updating a digital twin baseboard of the present application; Figure 6 A flowchart illustrating a sixth embodiment of a method for dynamically updating a digital twin baseboard of the present application; Figure 7 This is a system architecture diagram of the dynamic update method of the digital twin baseboard of this application; Figure 8 This is a flowchart of the dynamic update method of the digital twin baseboard of this application; Figure 9 This is a schematic diagram of the device structure of the hardware operating environment involved in the dynamic update method of the digital twin baseboard in the embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not intended to limit the present application.

[0022] In order to better understand the technical solution of this application, the following will be described in detail with reference to the accompanying drawings and specific implementation methods. It should be noted that all actions of obtaining signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization of the owner of the corresponding device.

[0023] Digital twin technology is widely used in smart manufacturing, smart cities, intelligent transportation, and other fields. Its core is to use real-time data to drive virtual models, enabling the mapping, analysis, and prediction of real physical entities. In this system, the digital twin backplane serves as the foundation for twin modeling, data access, status presentation, and feedback control. Its data structure and update mechanism are crucial.

[0024] In related digital twin baseplate systems, static or semi-dynamic baseplate structures are mostly used. By presetting the data model structure, a small number of fields are added or statically replaced after initialization to achieve the update of the baseplate structure. The lack of structural change prediction capability leads to a delayed response to the baseplate structure update.

[0025] In view of the above problems, the present application proposes a dynamic update method for a digital twin baseboard, which constructs a periodic influence intensity field according to the influence intensity of the periodic indicators of the digital twin baseboard-related business on the baseboard data structure change; constructs a disturbance vector according to the influence intensity of the external event triggering factors of the related business on the baseboard data structure change; determines the data structure change rate of the digital twin baseboard based on the historical data structure change sequence of the digital twin baseboard, and constructs a structural gradient tensor according to the data structure change rate; inputs the structural gradient tensor, periodic influence intensity field and disturbance vector as variables of the tensor equation into a preset tensor equation, and determines the eigenvalue decomposition result through the calculation result of the tensor equation; determines the change prediction result of the current baseboard data structure based on the eigenvalue decomposition result; generates a new baseboard data structure according to the change prediction result, and migrates the baseboard data in the current baseboard data structure to the new baseboard data structure.

[0026] The above method quantifies the distribution of the impact of business periodic operations on data structure changes by constructing a periodic impact intensity field, combines the disturbance vector to capture the direction and amplitude of non-business interference of external events on the data structure, and constructs a structural gradient tensor based on the historical change sequence to quantify the spatiotemporal gradient of data structure changes. The three are then integrated into a tensor equation, and the dominant change pattern is extracted using eigenvalue decomposition. The change prediction results are output to guide the generation of a new baseplate structure that meets dynamic needs, realizing the transition from passive response to active prediction, and significantly improving the real-time performance of digital twin baseplate updates.

[0027] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, personal computer, etc., or an electronic device, system, etc. that can realize the above functions.

[0028] Based on this, the first embodiment proposed in this application provides a dynamic update method of a digital twin baseboard, referring to Figure 1 In this embodiment, the dynamic update method of the digital twin baseboard includes steps S10 to S50: Step S10: construct a periodic impact intensity field based on the impact intensity of the periodic indicators of the digital twin baseboard-related business on the baseboard data structure change.

[0029] It should be noted that periodic indicators refer to the regular fluctuation characteristics inherent in the business activities associated with the digital twin baseboard. For example, the shift cycle of a manufacturing production line, the morning and evening peak hours of smart city traffic flow, etc. Periodic indicators can quantify the regularity of business activities and provide benchmark data for periodic changes for the dynamic update of the baseboard data structure. The periodic impact intensity field is a continuous space-time field function obtained by quantifying the mapping relationship between periodic indicators and baseboard data structure changes extracted by a physical field driven model. The purpose is to map discrete business cycle data such as peak hours and trough hours into energy field intensity values ​​with spatial distribution characteristics. The energy field intensity value refers to the intensity of changes to the data structure fields in the digital twin baseboard, including the number of expansions or deletions of data structure fields, the size of changes in data structure field values, etc.

[0030] Optionally, all baseboard data in the digital twin baseboard are obtained, and time series analysis algorithms such as Fourier transform or wavelet analysis are applied to identify periodic data such as daily cycles, weekly cycles, and monthly cycles in the historical data, and the amplitude and phase of each periodic data are calculated to characterize the regular periodic characteristics of business activities. According to the above-mentioned periodic characteristics and the historical data structure change sequence associated with the digital twin baseboard, the historical data structure change intensity corresponding to each periodic characteristic is determined to reflect the potential impact intensity of the business cycle on the baseboard data structure change. According to the mapping relationship between the above-mentioned periodic characteristics and the historical data structure change intensity, a continuous impact intensity curve or surface is constructed to form a periodic impact intensity field with spatiotemporal distribution. Among them, the periodic characteristics and business impact intensity values ​​can be input into a preset physical field driving model, and the preset physical field driving model learns its mapping relationship based on the input periodic characteristics and historical data structure change intensity values, and outputs a periodic impact intensity field.

[0031] Step S20: constructing a disturbance vector according to the impact intensity of the external event triggering factor of the associated business on the change of the backplane data structure.

[0032] External event triggers refer to non-periodic, sudden external interference factors, including unforeseen events such as equipment failures and external commands. These factors are irregular and highly dynamic, and can be acquired through real-time monitoring and incorporated into physical field-driven models for calculation. The disturbance vector is a vector parameter quantified by mathematically extracting the mapping relationship between external event triggers and changes to the baseboard data structure. Its purpose is to characterize the intensity of changes to the data structure fields in the digital twin baseboard caused by external interference, providing a basis for predicting baseboard data structure changes.

[0033] Optionally, historical external event triggers associated with historical data structure changes are determined based on the historical data structure change sequence associated with the digital twin backplane. The direction of the disturbance vector is determined based on the change fields corresponding to each historical external event trigger, and the magnitude of the disturbance vector is determined based on the data structure change frequency corresponding to each historical external event trigger. The data structure change frequency can be expressed as the change frequency in each vector direction, that is, the change frequency of each change field.

[0034] Step S30: Determine the data structure change rate of the digital twin baseboard based on the historical data structure change sequence of the digital twin baseboard, and construct a structural gradient tensor according to the data structure change rate.

[0035] It should be noted that the historical data structure change sequence is a collection of ordered change events that represent the evolution of the digital twin backplane's data structure over time during its historical operation. This includes events such as the addition, deletion, and modification of data structure fields. The structural gradient tensor is a quantitative representation of backplane data structure changes, formed by performing spatiotemporal gradient analysis on the historical data structure change sequence to quantify the rate of change of the backplane data structure in both time and space.

[0036] For example, historical data structure change records are obtained from the digital twin baseboard's update log and sorted by timestamp to form a historical data structure change sequence. Using a sliding window algorithm, the historical data structure change sequence is divided into multiple subsequences, each covering a fixed time range such as a week or a month. For each subsequence, statistics are collected on change characteristics such as the change type, change frequency, and change intensity for each data structure field in the historical data structure. The change rate of these change characteristics is used as the structural gradient tensor.

[0037] Optionally, when the change type is a field value change, the change intensity indicates the size of the change in the field value.

[0038] For example, when the data structure field type is numeric, the change intensity can be expressed as the difference between the data structure field values ​​before and after the change. For example, if a data structure field represents foot traffic, and its field value changes from 10 to 100 during a data structure change, the change intensity can be expressed as 90. When the data structure field type is non-numeric, the change intensity can be determined based on the semantic similarity of the data structure field characters before and after the change, where semantic similarity is inversely proportional to the change intensity.

[0039] Optionally, when the change type is data structure field expansion or deletion, the change intensity represents the number of data structure fields expanded or deleted. The number of data structure fields expanded or deleted can be normalized to serve as the change intensity.

[0040] Optionally, when the change type is a data field type change, such as from a numeric type to a character type, the change intensity can be represented by a preset value.

[0041] Step S40: Input the structural gradient tensor, the periodic influence intensity field and the disturbance vector as variables of the tensor equation into a preset tensor equation, and determine the eigenvalue decomposition result through the calculation result of the tensor equation.

[0042] It can be understood that the structural gradient tensor described above can characterize the gradient changes in the backplane data structure in both time and space. The periodic impact intensity field can reflect the distribution of the impact of business operations of different periods on data structure changes. The perturbation vector describes the direction and magnitude of the non-business impact of external events on the data structure. By integrating the structural gradient tensor, periodic impact intensity field, and perturbation vector into a unified mathematical model, it is possible to quantify the dynamic change mechanism of the backplane data structure.

[0043] Optionally, the tensor equation may be in the form of a linear combination or a nonlinear coupling. Preferably, the expression of the tensor T(x, y, t) may refer to the following formula: ) in, Indicates that at time t, the spatial position ( ) corresponds to the tensor of the data structure field. Where x represents the data table row and y represents the data table column. represents the structural gradient tensor, represents the perturbation vector, represents the periodic influence intensity field, ( ) represents the unit tensor, α, β and γ are weight coefficients. The structural gradient tensor is coupled with the periodic impact intensity field to reflect how the business periodic operation amplifies or suppresses the baseboard data structure changes; The cumulative effect of external disturbances is expressed through quadratic forms; ) is used to ensure that the tensor equation maintains static equilibrium when there is no input. It should be noted that the expression of the preset tensor equation can be obtained by training the preset physical field-driven model based on historical data structure change sequence data, and quantizing the mapping relationship between the learned tensor and the structural gradient tensor, the periodic influence intensity field, and the disturbance vector.

[0044] Step S50: determining a change prediction result of the current baseboard data structure based on the eigenvalue decomposition result.

[0045] After constructing the tensor equation, the dominant mode and intensity of the base plate data structure change can be extracted by analyzing the eigenvalue decomposition results of the tensor equation.

[0046] For example, the spatial position (x, y) of the baseboard data structure is discretized into a grid, the time t is discretized into time steps Δt, and at each grid point (xi, yj) and time step tk, the tensor is calculated The specific value of the tensor for each spatial position (xi, yj) , perform eigenvalue decomposition:

[0047] in, It is an eigenvalue, which indicates the change intensity and direction of the data structure field corresponding to the spatial position. A positive eigenvalue indicates that the data structure field tends to change, and a negative eigenvalue indicates that the field tends to be stable or rolled back. is a feature vector, representing the change probability corresponding to each change type.

[0048] To better understand the solution provided in this example, this example is further explained in conjunction with specific application scenarios.

[0049] Assume that after performing eigenvalue decomposition on a tensor equation, the following two eigenvalues ​​and their corresponding eigenvectors are obtained: =0.8, =[0.9,-0.1], =0.2, =[0.3,0.9]. If the eigenvector represents the probability of "new addition" and "field value change", then the eigenvalue =0.8 means that the change intensity value of the data structure field corresponding to the spatial position (1, 3) in the third time step is 0.8, and the probability of change is relatively high; and its eigenvector =[0.9, -0.1] means that the probability of the change type of the data structure field corresponding to the spatial position (1, 3) being "new" is 0.9, and the probability of "field value change" is -0.1. Similarly, the eigenvalue =0.2 means that the change intensity value of the data structure field corresponding to the spatial position (1, 2) in the third time step is 0.2, and the probability of change is small; and its eigenvector =[0.3, 0.9] means that the probability that the change type of the data structure field corresponding to the spatial position (1, 2) is "newly added" is 0.3, and the probability that the "field value changed" is 0.9.

[0050] Step S60: Generate a new baseboard data structure according to the change prediction result, and migrate the baseboard data in the current baseboard data structure to the new baseboard data structure.

[0051] After obtaining the aforementioned change prediction results, a new baseboard data structure can be generated based on the change prediction structure. For example, thresholds for change intensity and change probability corresponding to each change type can be preset. When the change prediction structure result for any data structure field exceeds its corresponding threshold, new baseboard data is generated based on the change prediction structure, and the data in the current baseboard data is migrated to the new baseboard data structure, completing the change of the digital twin baseboard.

[0052] It is understood that when the change type is data structure field deletion, the corresponding structure field will be deleted in the new baseboard data structure. Therefore, when performing data migration, the corresponding field value in the pre-change baseboard data structure is found based on the data structure field in the new baseboard data structure and migrated to the new baseboard data structure.

[0053] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 Before step S10, the dynamic update method of the digital twin baseboard further includes steps S70 to S100: Step S70: Separate the time series data in the digital twin baseboard through a preset time series decomposition algorithm to obtain periodic items of the time series data.

[0054] Optionally, time series data X(t) is acquired in real time or in batches from the data interface of the digital twin backplane. The corresponding timestamp sequence x covers the business operation cycle. The time series data X(t) is separated into the periodic term S(t) using the seasonality-trend decomposition algorithm. Seasonal-trend decomposition using Loess (STL) is a time series decomposition method used to decompose time series data into a trend term (Trend), a seasonal term (Seasonal), and a residual term (Residual). In this embodiment, the seasonal parameter in the seasonality-trend decomposition algorithm can be modified using a periodicity indicator, and then decomposed to obtain the periodic term.

[0055] Optionally, the time series data X(t) can be subjected to the empirical mode decomposition (EMD) algorithm to isolate the periodic term S(t). EMD decomposes the time series data X(t) into multiple intrinsic mode functions (IMFs), each representing an oscillation mode at a different time scale. Specifically, first perform step 1: initialize the residual r(t) = X(t) and set the IMF set to empty. Then, perform step 2: extract the kth IMF, determine all local maxima and minima of r(t), and generate the upper and lower envelopes through interpolation. Then, calculate the mean envelope m(t) to obtain a candidate IMF: h(t) = r(t) - m(t). Repeat this process until h(t) meets the preset IMF conditions, such as symmetry or zero mean. Once h(t) meets the preset IMF conditions, perform step 3: add h(t) to the IMF set and update the residual r(t) = r(t) - h(t). Repeat steps 2 and 3 until the residual r(t) is a monotonic function or a constant. The resulting IMF is used as the periodic term S(t).

[0056] Step S80: determining the peak-to-valley difference of the periodic term within the period length as the periodic amplitude of the periodic term.

[0057] Step S90: Perform Fourier transform on the periodic term to obtain the periodic frequency of the periodic term.

[0058] Step S100: Using the periodic amplitude and the periodic frequency as the periodicity index.

[0059] For example, within each period length Lk of the periodic term S(t), the maximum value Smax and the minimum value Smin of the periodic term are identified, and the difference between Smax and Smin is used as the peak-to-valley difference to determine the periodic amplitude. Next, a Fourier transform is performed on the periodic term S(t), converting the time domain signal to the frequency domain. The main peak frequency in the spectrum, i.e., the frequency value corresponding to the maximum amplitude, is used as the periodic frequency. Finally, the periodic amplitude and periodic frequency are used as the periodicity indicators.

[0060] Based on the above embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later. Figure 3 , step S10 includes steps S11 to S15: Step S11: constructing a node set based on each data structure field in the current baseboard data structure.

[0061] Step S12: constructing a directed edge set based on the change association relationship between each data structure field in the historical data structure change sequence and the node set.

[0062] Step S13: construct a node topology graph based on the node set and the directed edge set.

[0063] Parse the current digital twin baseboard data structure, treat each data structure field as a node, and generate a node set , each node may include field metadata such as field value, field type, etc. Then, according to the historical data structure change sequence, according to the change association relationship between the data structure fields corresponding to each node in the historical data structure change sequence, a directed edge set E={eij} is constructed. Among them, the change association relationship between data structure fields refers to the dynamic dependency or driving relationship between different data structure fields, i.e., nodes, during the historical data structure change process. Specifically, when a data structure field changes, it will directly trigger or require another data structure field to make a corresponding change. For example, if the change of node vi directly drives the change of node vj, a directed edge eij from node vi to node vj is established. Based on the node set and the directed edge set, a node topology graph is constructed.

[0064] For example, if the value of the "Device Temperature" field is modified in the digital twin baseboard, the "Temperature Risk Value" field may need to be adjusted synchronously. At this time, the change of the "Device Temperature" field directly drives the change of the "Temperature Risk Value", and a directed edge is constructed from the "Device Temperature" field to the "Temperature Risk Value" field.

[0065] Reference Figure 4 , Figure 4 On the left is a data table with the following data structure fields: "Oeder_id" (V1), "Varchar" (V2), "ORD202310010001" (V3), "status" (V4), "Enum" (V5), "paid" (V6), "Pay_time" (V7), "Datetime" (V8), and "2023-10-01 14:30:00" (V9). Varchar (V2), Enum, and Datetime (V8) are field types, and changes in their values ​​directly trigger changes in the field types of "ORD202310010001" (V3), "paid" (V6), and "2023-10-01 14:30:00" (V9). Furthermore, "paid" (V6) indicates the order status and directly triggers changes in the payment time field value of "2023-10-01 14:30:00" (V9). Therefore, in the generated node topology graph, directed edges will be generated between V2 and V3, between V5 and V6, between V8 and V9, and between V6 and V9.

[0066] The node topology diagram above transforms the abstract field change relationship into a graphical representation of the data structure change. When a data structure field changes, the topology diagram can quickly locate other data structure fields directly driven by it and the data structure fields subsequently affected, thereby predicting the scope of impact of the data structure change.

[0067] Step S14: determining the correlation influence strength between the nodes according to the node topology graph, where the correlation influence strength represents the dependency strength between the nodes.

[0068] Optionally, for each directed edge connecting a source node and a target node, a weight is determined based on the number of times the source node drives changes in the target node, representing the strength of the dependency between the source and target nodes. The strength of the association influence between the source and target nodes is then determined based on the weight of the directed edge.

[0069] In a feasible implementation, step S14 includes steps S141 to S143: Step S141 : determining each associated node of the current node based on the historical data structure change sequence, wherein the current node points to the associated nodes via directed edges.

[0070] Step S142 : determining the weight of each directed edge of the current node according to the number of times the current node drives the associated node to change.

[0071] Step S143 : determining the association influence strength of the current node according to the sum of the weights of the directed edges of the current node, wherein the association influence strength is proportional to the sum of the weights.

[0072] For example, assuming that the current node Associated nodes Connected by directed edges. Determine the current node based on the historical data structure change sequence Driver-related nodes Number of changes , as the interaction frequency between the two nodes. Then, according to the interaction frequency between the two nodes, the weight of the directed edge between the two nodes is determined. Among them, the weight of the directed edge is proportional to the interaction frequency between the two nodes. Then, according to the weight sum of the directed edges, the current node is determined. The strength of the associated impact.

[0073] It can be understood that the greater the association influence strength of a node, the more changes in the data structure field corresponding to the node will cause changes in more other data structure fields, that is, the more significant the changes in the twin baseboard data structure will be. The association influence strength can reveal the impact of the association between data structure fields on data structure changes.

[0074] Step S15: Input the associated influence intensity, the periodic amplitude and the periodic frequency as variables of a periodic influence intensity field equation into a preset periodic influence intensity field equation to construct the periodic influence intensity field.

[0075] For example, the periodic influence intensity field equation can refer to the following formula:

[0076] in, Indicates that at time t, the spatial position ( ) corresponds to the periodic impact intensity field value. Where x represents the data table row and y represents the data table column. is the attenuation coefficient, represents the periodic amplitude of the kth period, represents the periodic frequency of the kth period, The strength of the association between nodes and data structure fields. Isolated nodes can be for .

[0077] Based on the above embodiments of the present application, in the fourth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later. Figure 5 , step S30 further includes steps S31 to S34: Step S31: Divide the time period corresponding to the historical data structure change sequence into two or more time windows.

[0078] Step S32: construct a time change sequence according to the number of data structure changes in each time window.

[0079] For example, the historical data structure change sequence of the digital twin baseboard ΔS={Δ |i=1,2,…,m}, where a single change event is defined as a four-tuple: Δ =( , ). Timestamp for when the change occurred, To change the node identifier such as field ID, Code the operation type, for example, "0" indicates adding, "1" indicates deleting, and "2" indicates modifying the field type. The intensity of the change. The preset time period is divided into time windows according to a fixed period. Preferably, it can be divided according to a periodicity index. Then, by counting the number of changes in each time window, time series data is generated to quantify the frequency change of the data structure change, and the time change sequence is obtained. .

[0080] Step S33 , mapping the changed fields in the historical data structure change sequence to the node topology map, determining the changed nodes, and using the number of changes of the changed fields as the number of changes of the changed nodes to construct a spatial change sequence.

[0081] For example, based on the historical data structure change sequence, each changed field is determined, and the changed field is mapped to the node topology map. Based on the quotient of the number of changes of the changed node corresponding to each change field and the number of changes of all changed nodes in the node topology map, the spatial change sequence is determined. For example, the spatial change sequence It can be expressed as the following formula:

[0082] in, Indicates spatial position ( ) corresponds to the number of changes in the change node, Indicates the number of changes of all changed nodes in the node topology graph.

[0083] Step S34: determining the structural change rate of the digital twin baseplate based on the time change sequence and the space change sequence.

[0084] For example, the structural change equation is constructed based on the time change sequence and the space change sequence. .in, Indicates the average change intensity of all changed fields.

[0085] Then, according to the above structural change equation, the structural change rate of the digital twin baseplate is determined to generate the structural gradient tensor :

[0086] Understandably, traditional change prediction may rely solely on time series, such as "number of changes in the last hour," or spatial distribution, such as "which field changes most frequently." However, the Structural Gradient Tensor (SGT) uses joint time-space modeling to simultaneously capture both "when" and "where" changes occur, thereby more comprehensively capturing the global patterns of change. By incorporating directed edges (i.e., change associations) in the node topology graph, the SGT can reflect the change propagation logic between different data structure fields, making predictions more relevant to real-world business scenarios.

[0087] Based on the above embodiments of the present application, in the fifth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be repeated hereafter. On this basis, step S20 further includes steps S21~S22: Step S21 : Using the spatial position coordinates of the nodes associated with each of the external event triggering factors as the vector direction of the disturbance vector.

[0088] Step S22 : Based on the historical data structure change sequence and according to the number and change frequency of nodes associated with each external event triggering factor, determine the vector size of the disturbance vector.

[0089] Exemplarily, the historical data structure change sequence is queried to identify the data structure fields that have changed due to external event triggering factors, that is, the associated nodes, and the spatial position coordinates (x, y) of the node are used as the vector direction of the disturbance vector.

[0090] Then, based on the historical data structure change sequence, the change frequency of the data structure fields that are changed due to each external event triggering factor and the number of data structure fields that are changed due to each external event triggering factor are counted.

[0091] Optionally, the sum of the change frequency of the above-mentioned changed data structure fields and the number of the changed data structure fields is used as the vector strength of the disturbance vector, or the sum of the weighted change frequency and number is used as the vector strength of the disturbance vector.

[0092] Based on the above embodiments of the present application, in the sixth embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be described in detail later. Figure 6 , step S60 further includes steps S61 to S63: Step S61: Generate a to-be-selected baseboard data structure according to the change prediction result.

[0093] The predicted results include the change location, change type, and change probability. The change location refers to the node in the node topology graph, i.e., the data structure field corresponding to the spatial coordinates (x, y) of the baseboard data structure. Based on these predicted change results, a new candidate baseboard data structure is generated.

[0094] Optionally, the prediction results are prioritized based on the change probability, the nodes to be changed corresponding to the first k change positions are selected according to the sorting results, and the data structure fields to be changed corresponding to the nodes to be changed are changed according to the change type.

[0095] For example, if the change type is "new," the field in the data structure to be changed is added to the selected backplane data structure, and its attributes, such as field type, default value, and constraints, are initialized. Simultaneously, the parent node of the node to be changed (i.e., the upstream node in the topology graph pointing to the node to be changed) can be checked to see if a new dependency relationship is required. For example, the index value of the field in the data structure to be changed can be added to the "child field list" of the parent node.

[0096] For example, if the change type is "delete", the data structure field to be changed is removed from the selected baseboard data structure; if the change type is "modify", the properties of the data structure field to be changed are adjusted, such as changing the field type from "string" to "integer", or modifying the default value.

[0097] Optionally, the prediction results are prioritized based on the probability of change. Based on the sorting results, the changes are propagated along the directed edges in the node topology graph starting from the node to be changed with the highest probability of change. After adjusting the current node to be changed according to the change type, the structure of its downstream nodes is recursively adjusted to ensure that the cascading effect of the change is correctly captured and a new candidate baseboard data structure that conforms to the topological logic is generated.

[0098] Step S62: determining the evaluation score of each of the candidate baseboard data structures based on the target optimization parameters.

[0099] Step S63: Determine the new base plate data structure in the to-be-selected base plate data structures according to the evaluation score.

[0100] Optionally, the target optimization parameters may include performance optimization parameters, cost optimization parameters, stability optimization parameters, and other preset optimization parameters. The performance optimization parameters can be obtained by calculating the query efficiency or computational complexity of the candidate baseboard data structure; the cost optimization parameters can be obtained by calculating the storage space or computing resource usage of the candidate baseboard data structure; and the stability optimization parameters can be obtained by calculating the abnormality rate after field changes. The weighted sum of each target optimization parameter is used as the evaluation score for the candidate baseboard data structure, and the one with the highest evaluation score is selected as the new baseboard data structure.

[0101] Optionally, the target optimization parameters are regarded as a multi-objective optimization problem, and the non-dominated solutions are screened out from the candidate base plate data structure through the Pareto front, that is, the candidate base plate data structure in which one of the target optimization parameters cannot be further optimized without damaging the other target optimization parameters among multiple target optimization parameters, as the new base plate data structure.

[0102] For example, an objective function is defined for each target optimization parameter, and for each candidate baseboard data structure, its score on all objective functions is calculated to form a solution set. The optimal solution is selected from the solution set based on the pre-set Pareto front screening conditions.

[0103] Based on the above embodiments of the present application, in the seventh embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be repeated hereafter. On this basis, after step S60, the dynamic update method of the digital twin baseboard further includes steps S110 to S130: Step S110 : constructing a source hash tree according to the hash value of the baseboard data in the baseboard data structure before the change, and determining the root node of the source hash tree.

[0104] Step S120: Construct a new hash tree according to the hash value of the baseboard data in the new baseboard data structure, and determine the root node of the new hash tree.

[0105] Step S130: If the root node of the source hash tree is consistent with the root node of the new hash tree, it is determined that the update of the digital twin baseboard is completed.

[0106] Exemplarily, the baseboard data in the baseboard data structure before the change is divided into data blocks of a preset size, the hash value of each data block is calculated, a leaf node is generated, and then the hash values ​​of the two adjacent leaf nodes are merged to generate a parent node and the hash of the parent node is calculated. Repeat this process of merging until the last root node is left. After the data migration is completed, a new hash tree is constructed for the baseboard data in the new baseboard data structure according to the above method to obtain the root node of the new hash tree. The source hash tree is compared with the root node of the new hash tree. If the comparison results are consistent, it means that the data migration is successful.

[0107] Based on the above embodiments of the present application, in the embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction and will not be repeated hereafter. On this basis, after step S120, the dynamic update method of the digital twin baseboard further includes steps S140 to S150: Step S140: If the root nodes of the source hash tree and the new hash tree are inconsistent, compare the intermediate nodes of the source hash tree and the new hash tree, and determine the node to be modified based on the comparison result; Step S150 , re-migrating the backplane data corresponding to the node to be modified in the backplane data structure before the change to the new backplane data structure.

[0108] Exemplarily, if the root nodes of the source hash tree and the new hash tree are inconsistent, the hash values ​​of the intermediate nodes of the source hash tree and the new hash tree can be further compared to determine the nodes to be modified and quickly narrow the scope of the migration error. For example, assume that the second-level nodes of the source hash tree are H1 (H(B1||B2)) and H2 (H(B3||B4)). The second-level nodes of the new hash tree are H1' and H2'. If H1≠H1', but H2=H2', the error range is narrowed to B1 or B2. Further compare H(B1) and H(B1'): if they are inconsistent, B1 is wrong; if they are consistent, B2 is wrong. The baseboard data corresponding to the above-mentioned nodes to be modified in the baseboard data structure before the change is re-migrated to the new baseboard data structure.

[0109] For example, in order to help understand the implementation process of a dynamic update method of a digital twin baseboard obtained by combining this embodiment with the above embodiments, please refer to Figure 7 , Figure 7 A system architecture diagram of a dynamic update method for a digital twin baseboard is provided. Specifically: The system architecture includes data entity layer, intelligent prediction layer, adaptive scheduling layer, execution verification layer and twin backplane layer.

[0110] The data entity layer, as the data foundation of the entire architecture, is responsible for collecting and integrating historical data structure change sequences within the digital twin backplane. This includes backplane data within each data structure, such as sensor data, business data, and environmental data. This data provides a rich source of information for subsequent intelligent analysis and decision-making, ensuring that the system operates based on authentic and comprehensive data. The intelligent prediction layer, based on data provided by the data entity layer, performs backplane data structure change prediction, trend analysis, and pattern recognition. Using pre-set tensor equations, it mines the underlying patterns and change trends within the data, providing forward-looking predictive information for system adaptive adjustments and enabling the system to proactively detect potential changes. The adaptive scheduling layer, based on the results of the intelligent prediction layer, performs multi-objective optimization operations. It prioritizes candidate backplane data structures based on different business requirements and target optimization parameters to achieve efficient utilization of system resources and optimize overall performance, ensuring a flexible and appropriate system response to various changes. Based on the decisions made by the adaptive scheduling layer, the execution verification layer performs consistency checks, gradual rollbacks, and intelligent diagnostics. It verifies and monitors the results of data migration. When anomalies occur, it can restore stability through mechanisms such as gradual rollback and identify the root cause through intelligent diagnosis. The twin backplane layer, as the system's final presentation layer, implements functions such as real-time synchronization and version management for the dynamic backplane. It integrates and displays the results processed and verified by the previous layers. The twin backplane can promptly and accurately reflect the latest system status and changes. It also records the system's evolution through version management, facilitating subsequent queries and backtracking.

[0111] Please refer to Figure 8 , Figure 8 A flowchart of a dynamic update method for a digital twin baseboard is provided, specifically: First, during the "Data Monitoring" phase, the system monitors various data sources in real time, acquiring the latest sensor data, business data, and environmental data. Feature Extraction then extracts key features from the massive amount of raw data, providing a streamlined and effective data foundation for subsequent analysis. Pattern Recognition then analyzes the extracted features to identify patterns and regularities within the data. Based on the results of pattern recognition, the system performs "Change Prediction" to anticipate potential changes to the data structure and generate multiple candidate backplane data structures. Next, the "Multi-Objective Optimization" phase comprehensively considers multiple objectives, including performance, resource utilization, and stability, for each candidate backplane data structure. Priority Assessment then determines the priority of each candidate backplane data structure, ultimately leading to "Strategy Selection" to develop a suitable candidate backplane data structure for the current situation. Based on the selected new backplane data structure, the "Update" operation is performed to implement the actual changes to the digital twin backplane. After completion, the "Consistency Check Passed" decision node is reached. If the verification fails, the system will perform a "gradual rollback," gradually restoring the system to its pre-update stable state. It will also perform "exception handling" to troubleshoot and resolve the issue that caused the verification failure. If the verification passes, the subsequent process will continue. After the consistency check passes, the system "completes the update," at which point "performance monitoring" will be performed to monitor the updated system's performance in real time. Simultaneously, through "model feedback optimization," feedback and optimization of the model will be provided based on the results of performance monitoring and actual operation, continuously improving system performance and accuracy.

[0112] It should be noted that the above examples are only used to understand this application and do not constitute a limitation on the dynamic update method of a digital twin baseboard of this application. More forms of simple transformations based on this technical concept are all within the scope of protection of this application.

[0113] The present application provides a dynamic update device for a digital twin baseboard, which includes: a processor; and a memory communicatively connected to the processor; wherein the memory stores instructions that can be executed by the processor, and the instructions are executed by the processor so that the processor can execute the dynamic update method of the digital twin baseboard in the above-mentioned embodiment one.

[0114] Reference below Figure 9 , which shows a schematic diagram of the structure of a dynamic update device suitable for implementing the digital twin baseboard of the embodiment of the present application. The dynamic update device of the digital twin baseboard in the embodiment of the present application can include, but is not limited to, mobile terminals such as laptops and tablet computers (PADs) and fixed terminals such as desktop computers. Figure 9The dynamic update device of the digital twin baseboard shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0115] like Figure 9 As shown, the dynamic update device for the digital twin baseboard may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the dynamic update device for the digital twin baseboard. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow the dynamic update device of the digital twin baseboard to communicate wirelessly or wired with other devices to exchange data. Although the figure shows the dynamic update device of the digital twin baseboard with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0116] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0117] The dynamic update device for a digital twin baseboard provided in this application, employing the dynamic update method for a digital twin baseboard in the above-described embodiment, can solve the technical problem of how to improve the real-time performance of digital twin baseboard updates. Compared to the prior art, the beneficial effects of the dynamic update device for a digital twin baseboard provided in this application are the same as those of the dynamic update method for a digital twin baseboard provided in the above-described embodiment. Other technical features of the dynamic update device for a digital twin baseboard are the same as those disclosed in the method in the previous embodiment and are not further elaborated here.

[0118] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0119] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any modification or substitution that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0120] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the dynamic update method of the digital twin baseboard in the above-mentioned embodiment.

[0121] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0122] The above-mentioned computer-readable storage medium can be included in the dynamic update device of the digital twin baseboard; or it can exist independently without being assembled into the dynamic update device of the digital twin baseboard.

[0123] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the dynamic update device of the digital twin baseboard, the dynamic update device of the digital twin baseboard can be used to write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The 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 programming languages. The program code can be executed entirely on the user computer, partially on the user computer, or as a separate software package, partially on the user computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0124] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0125] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0126] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for dynamically updating a digital twin baseboard. This computer-readable storage medium can address the technical problem of improving the real-time performance of digital twin baseboard updates. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the method for dynamically updating a digital twin baseboard provided in the aforementioned embodiments, and will not be further elaborated here.

[0127] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the dynamic update method of the digital twin baseboard as described above.

[0128] The computer program product provided in this application can solve the technical problem of how to improve the real-time performance of digital twin baseboard updates. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the dynamic update method for the digital twin baseboard provided in the above embodiment, and will not be repeated here.

[0129] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A dynamic update method for a digital twin baseboard, characterized in that: The dynamic update method of the digital twin baseboard includes: Construct a periodic impact intensity field based on the impact intensity of the periodic indicators of the digital twin baseboard-related business on the baseboard data structure changes; Constructing a disturbance vector according to the impact intensity of the external event triggering factor of the associated business on the change of the backplane data structure; Determining a data structure change rate of the digital twin baseboard based on a historical data structure change sequence of the digital twin baseboard, and constructing a structural gradient tensor according to the data structure change rate; Inputting the structural gradient tensor, the periodic influence intensity field and the disturbance vector as variables of a tensor equation into a preset tensor equation, and determining an eigenvalue decomposition result through a calculation result of the tensor equation; Determining a change prediction result of the current baseboard data structure based on the eigenvalue decomposition result; A new baseboard data structure is generated according to the change prediction result, and the baseboard data in the current baseboard data structure is migrated to the new baseboard data structure.

2. A dynamic update method for a digital twin baseboard according to claim 1, characterized in that: Before the step of constructing a periodic impact intensity field based on the impact intensity of the periodic indicators of the digital twin baseboard-related business on the baseboard data structure change, the following steps are included: Separate the time series data in the digital twin baseboard through a preset time series decomposition algorithm to obtain the periodic items of the time series data; Determining a peak-to-valley difference of the periodic term within a period length as the periodic amplitude of the periodic term; Performing Fourier transform on the periodic term to obtain a periodic frequency of the periodic term; The periodic amplitude and the periodic frequency are used as the periodicity indicators.

3. A dynamic update method for a digital twin baseboard according to claim 2, characterized in that: The step of constructing a periodic impact intensity field based on the impact intensity of the periodic indicators of the digital twin baseboard-related business on the baseboard data structure change includes: Constructing a node set based on each data structure field in the current baseboard data structure; Constructing a directed edge set based on the change association relationship between each data structure field in the historical data structure change sequence and the node set; Constructing a node topology graph according to the node set and the directed edge set; Determining the correlation influence strength between each node according to the node topology graph, wherein the correlation influence strength represents the dependency strength between the nodes; The associated influence intensity, the periodic amplitude and the periodic frequency are input into a preset periodic influence intensity field equation as variables of the periodic influence intensity field equation to construct the periodic influence intensity field.

4. A dynamic update method for a digital twin baseboard according to claim 3, characterized in that: The step of determining the association influence strength between the nodes according to the node topology graph, wherein the association influence strength represents the dependency strength between the nodes, comprises: Determine each associated node of the current node based on the historical data structure change sequence, wherein the current node points to the associated nodes via directed edges; Determining the weight of each directed edge of the current node according to the number of times the current node drives the associated node to change; The association influence strength of the current node is determined according to the sum of the weights of the directed edges of the current node, wherein the association influence strength is proportional to the sum of the weights.

5. The dynamic update method of a digital twin baseboard according to claim 3, characterized in that: The step of constructing a disturbance vector according to the intensity of the influence of the external event triggering factor of the associated business on the change of the backplane data structure includes: Using the spatial position coordinates of the nodes associated with each of the external event triggering factors as the vector direction of the disturbance vector; Based on the historical data structure change sequence, and according to the number and change frequency of nodes associated with each external event triggering factor, the vector size of the disturbance vector is determined.

6. A dynamic update method for a digital twin baseboard according to claim 3, characterized in that: The step of determining the data structure change rate of the digital twin baseboard based on the historical data structure change sequence of the digital twin baseboard includes: Dividing the time period corresponding to the historical data structure change sequence into two or more time windows; Construct a time change sequence based on the number of data structure changes within each time window; Mapping the changed fields in the historical data structure change sequence to the node topology graph, determining the changed nodes, and using the number of changes in the changed fields as the number of changes in the changed nodes to construct a spatial change sequence; Based on the time change sequence and the space change sequence, a structural change rate of the digital twin baseplate is determined.

7. The dynamic update method of a digital twin baseboard according to claim 1, characterized in that: The eigenvalue decomposition result includes an eigenvalue and an eigenvector corresponding to the eigenvalue. The step of determining a change prediction result of the current baseboard data structure based on the eigenvalue decomposition result includes: determining, based on the characteristic value, a change intensity of a data structure field corresponding to the characteristic value; Determine, according to the eigenvector corresponding to the eigenvalue, the change probabilities of different change types corresponding to the data structure field.

8. The dynamic update method of a digital twin baseboard according to claim 1, characterized in that: The step of generating a new baseboard data structure according to the change prediction result includes: generating a candidate baseboard data structure according to the change prediction result; Determining an evaluation score of each of the candidate base plate data structures based on the target optimization parameter; The new base plate data structure is determined in the to-be-selected base plate data structures according to the evaluation score.

9. The method for dynamically updating a digital twin baseboard according to claim 1, wherein: After the step of migrating the baseboard data in the current baseboard data structure to the new baseboard data structure, the method further includes: Constructing a source hash tree according to the hash value of the baseboard data in the baseboard data structure before the change, and determining a root node of the source hash tree; Constructing a new hash tree according to the hash value of the baseboard data in the new baseboard data structure, and determining a root node of the new hash tree; If the root nodes of the source hash tree and the new hash tree are consistent, it is determined that the digital twin baseboard update is completed.

10. A dynamic update method for a digital twin baseboard according to claim 9, characterized in that: After the steps of constructing a new hash tree according to the hash value of the baseboard data in the new baseboard data structure and determining the root node of the new hash tree, the method further includes: If the root nodes of the source hash tree and the new hash tree are inconsistent, compare the intermediate nodes of the source hash tree and the new hash tree, and determine the node to be modified based on the comparison result; The backplane data corresponding to the node to be modified in the backplane data structure before the change is re-migrated to the new backplane data structure.

Images