Data analysis method and device for digital twinborn scene

Abstract

The invention provides a data analysis method and device for a digital twinborn scene. The method comprises the steps of obtaining a start instruction of at least one analysis task; in response to the start instruction, enabling a scheduler to determine a scheduling rule between the analysis tasks and a task type of each analysis task; determining the priority of each analysis task according to a scheduling rule; determining a data association relationship of the analysis task according to the task type; determining target data according to the data association relationship and the twin scene data; and inputting the target data to the visual platform according to the sequence of the priorities so as to display an analysis result corresponding to the analysis task. According to the method, a scheduler is utilized to reasonably schedule analysis tasks, the priority of each task is regulated and controlled, an appropriate data analysis logic is created in the face of multiple analysis tasks, and multiple and dispersed data in a twin scene are sorted by utilizing a data association relationship, so that a visual platform displays an accurate analysis result, and the analysis efficiency is improved. And accurate monitoring of the digital twinborn scene is achieved.

Description

Technical Field

[0001] The present application relates to the field of digital twin technology, and more specifically, to a data analysis method and device for a digital twin scenario. Background Art

[0002] A digital twin is a virtual, digital entity that corresponds to an entity in the real world. Digital twins usually model and simulate physical entities in the real world through sensors, data analysis, and simulation technology to achieve real-time monitoring, prediction, and optimization of the real world. Compared to the variability of the real world, digital twin scenarios are also diverse.

[0003] During the data analysis process, different digital twin scenarios require different data formats and calculation logics. Traditional data analysis tools cannot cope with the multi-source and scattered data in digital twin scenarios. When faced with multiple analysis tasks, there is no suitable data analysis logic, which leads to inaccurate analysis charts generated, affecting the accurate monitoring of digital twin scenarios. Summary of the invention

[0004] The present invention provides a data analysis method and device for digital twin scenarios. By rationally scheduling analysis tasks and utilizing data association relationships to comb through diverse and scattered data in the twin scenarios, a visualization platform can display accurate analysis results, thereby achieving precise monitoring of the digital twin scenarios.

[0005] In a first aspect, the present invention provides a data analysis method for a digital twin scenario, the method being applied to a digital twin system, the digital twin system comprising a scheduler, a database, and a visualization platform; the method comprising:

[0006] Obtaining a start instruction for at least one analysis task;

[0007] In response to the start instruction, the scheduler determines a scheduling rule between the analysis tasks and a task type of each analysis task;

[0008] Determining the priority of each of the analysis tasks according to the scheduling rule;

[0009] Determining the data association relationship of the analysis task according to the task type;

[0010] Acquire twin scene data corresponding to each of the analysis tasks from the database;

[0011] Determine target data according to the data association relationship and the twin scene data;

[0012] The target data is input into the visualization platform in the order of the priorities to display the analysis results corresponding to the analysis tasks.

[0013] Preferably, in response to the start instruction, causing the scheduler to determine a scheduling rule between the analysis tasks comprises:

[0014] Determining dependencies between the analysis tasks;

[0015] Parallel scheduling of the analysis tasks without dependencies;

[0016] The analysis tasks having dependencies are serially scheduled.

[0017] Preferably, determining the priority of each analysis task according to the scheduling rule includes:

[0018] Determining a first-priority task from among the analysis tasks according to a preset task importance;

[0019] Traversing the plurality of analysis tasks, and adding the analysis tasks that have no dependency relationship with the first priority task to the first task set;

[0020] Each of the analysis tasks in the first task set has the same priority as the first-ranked task.

[0021] Preferably, the task type includes qualitative tasks and quantitative tasks; then determining the data association relationship of the analysis task according to the task type includes:

[0022] Determine the task name and task description of the analysis task according to the qualitative task;

[0023] Determine the text data of the analysis task according to the task name and task description;

[0024] Determine the data association relationship according to the text data;

[0025] Determine the task node of the analysis task according to the quantitative task;

[0026] Determining numerical data of the analysis task according to the task node;

[0027] The data association relationship is determined according to the numerical data.

[0028] Preferably, the acquiring the twin scene data corresponding to each of the analysis tasks from the database includes:

[0029] Determining the analysis object of each of the analysis tasks;

[0030] Determining a data extraction scope in the database according to the analysis object;

[0031] The twin scene data is extracted according to the data extraction range.

[0032] Preferably, determining the target data according to the data association relationship and the twin scene data includes:

[0033] The twin scene data is logically sorted according to the data association relationship to determine the target data.

[0034] Preferably, it also includes:

[0035] Determining a task scheduling frequency for each of the analysis tasks according to the analysis object;

[0036] Determining the target data according to the task scheduling frequency and the twin scenario data;

[0037] The target data is input into the visualization platform to determine the analysis result corresponding to the analysis task.

[0038] In a second aspect, the present invention provides a data analysis device for a digital twin scenario, comprising:

[0039] A start instruction acquisition module, used to acquire a start instruction of at least one analysis task;

[0040] a scheduling module, configured to enable the scheduler to determine a scheduling rule between the analysis tasks and a task type of each analysis task in response to the start instruction;

[0041] A priority determination module, used to determine the priority of each of the analysis tasks according to the scheduling rules;

[0042] A data association relationship determination module, used to determine the data association relationship of the analysis task according to the task type;

[0043] A twin scene data acquisition module, used to acquire the twin scene data corresponding to each of the analysis tasks from the database;

[0044] A target data determination module, used to determine the target data according to the data association relationship and the twin scene data;

[0045] An analysis result determination module is used to input the target data into the visualization platform in the order of priority to display the analysis result corresponding to the analysis task.

[0046] In a third aspect, the present invention provides a readable medium, comprising execution instructions. When a processor of an electronic device executes the execution instructions, the electronic device executes any method described in the first aspect.

[0047] In a fourth aspect, the present invention provides an electronic device, comprising a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor executes any method described in the first aspect.

[0048] The present invention provides a data analysis method and device for a digital twin scene, by obtaining a start instruction of at least one analysis task; in response to the start instruction, a scheduler determines the scheduling rules between the analysis tasks and the task type of each analysis task; determines the priority of each analysis task according to the scheduling rules; determines the data association relationship of the analysis task according to the task type; obtains the twin scene data corresponding to each analysis task from the database; determines the target data according to the data association relationship and the twin scene data; and inputs the target data into the visualization platform in the order of priority to display the analysis results corresponding to the analysis task. The present invention utilizes the reasonable scheduling of the analysis tasks by the scheduler to adjust the priority of each task. When facing multiple analysis tasks, a suitable data analysis logic is created, and the data association relationship is used to sort out the multivariate and dispersed data in the twin scene, so that the visualization platform displays accurate analysis results, and achieves accurate monitoring of the digital twin scene.

[0049] The further effects of the above-mentioned non-conventional preferred manner will be described below in conjunction with specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the existing technical solutions, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0051] Figure 1 A schematic diagram of a data analysis method for a digital twin scenario provided by an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of another data analysis method for a digital twin scenario provided by an embodiment of the present invention;

[0053] Figure 3 A schematic diagram of a data analysis device for a digital twin scenario provided by an embodiment of the present invention;

[0054] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Today, as human society is highly developing digital technology, digital twins have become a popular technology application in more and more industries. Digital twins can help humans digitally replicate objects, systems, processes, etc. in the real physical world to achieve the goal of integrating virtual and real things and improve business efficiency and operational value in different industries. It is a concept that combines the physical world with the digital world.

[0057] A digital twin is a virtual, digital entity that corresponds to an entity in the real world. Digital twins usually model and simulate physical entities in the real world through sensors, data analysis, and simulation technology to achieve real-time monitoring, prediction, and optimization of the real world. Compared to the variability of the real world, digital twin scenarios are also diverse.

[0058] During the data analysis process, different digital twin scenarios require different data formats and calculation logics. Traditional data analysis tools cannot cope with the multi-source and scattered data in digital twin scenarios. When faced with multiple analysis tasks, there is no suitable data analysis logic, which leads to inaccurate analysis charts generated, affecting the accurate monitoring of digital twin scenarios.

[0059] In view of this, the present invention provides a data analysis method for digital twin scenarios. Figure 1 As shown, a specific embodiment of a data analysis method for a digital twin scenario provided by the present invention is shown. In this embodiment, the method is applied to a digital twin system, and the method includes:

[0060] Step 101: Obtain a start instruction for at least one analysis task;

[0061] Specifically, the digital twin system in this embodiment includes a scheduler, a database, and a visualization platform. The scheduler, database, and visualization platform are connected through corresponding ports or connection tools to achieve data transmission, reading, and processing. The digital twin system models and simulates physical entities in the real world through sensors, data analysis, and simulation technology to achieve real-time monitoring, prediction, and optimization of the real world.

[0062] Among them, the scheduler can be DolphinScheduler, which is a distributed, easily scalable visual DAG workflow scheduling platform that can solve the intricate dependencies in the data processing process and is suitable for various digital twin scenarios. The database can be TDengine, which is an open source database management system designed for the Internet of Things (IoT) and time series data (Time Series Data), which can be used for data analysis and storage of monitoring data in digital twin scenarios. The visualization platform can be Grafana, which is an open source interactive data visualization platform where users can view their data through tables and images, and unify these tables and images on one (or more) dashboards. Indicators of relevant information can be queried and configured from any location where the information is stored, and data of digital twin scenarios can be queried, visualized and understood, thereby achieving real-time monitoring, prediction and optimization of the real world.

[0063] The start instruction in this embodiment can be a natural language input instruction or an interface input instruction. The start instruction can be input through the above-mentioned digital twin system. The start instruction represents the beginning of the analysis task. There are multiple scenes in the digital twin scene, including energy, personnel, equipment, capacity, indicators, etc. The analysis of each scene also needs to be started from multiple dimensions. Therefore, the analysis of data needs to be analyzed from multiple angles. There are multiple analysis tasks, and each start instruction represents the beginning of an analysis task.

[0064] Step 102: In response to the start instruction, the scheduler determines the scheduling rules between the analysis tasks and the task type of each analysis task;

[0065] In the data analysis of digital twin scenarios, there are often complex dependencies between analysis tasks. The scheduler needs to identify and process these dependencies to ensure that the analysis tasks are executed in the correct order. For example, Task B needs to be executed after Task A is completed. The scheduler needs to ensure that Task A is completed first, and then Task B is started. Therefore, in response to the start instruction, the scheduler determines the scheduling rules between the analysis tasks, which may include: determining the dependencies between the analysis tasks, parallel scheduling of analysis tasks without dependencies, and serial scheduling of analysis tasks with dependencies. In other words, analysis tasks with dependencies are executed in the correct order, and analysis tasks without dependencies are executed together, which can improve the execution efficiency and accuracy of the analysis tasks.

[0066] The task types of analysis tasks can include qualitative tasks and quantitative tasks. Qualitative tasks can be seen as analyzing certain characteristics of things or phenomena, such as energy consumption in different regions, comparison of the number of users in different units, and comparison of income in different departments in the digital twin scenario. Quantitative tasks can be used to compare before and after time to know whether the development of things is good or bad, such as the growth rate of the number of users compared with the previous month and the growth rate compared with the same period last year. This is a comparison in time. Of course, quantitative tasks are not limited to time, and can also be analysis of numerical directions such as income, consumption, and age.

[0067] Step 103: Determine the priority of each analysis task according to the scheduling rules;

[0068] It can be seen from the above steps that the scheduling rules analyze the dependencies of each analysis task, thereby determining the execution order of each analysis task according to the dependencies, thereby improving the execution efficiency and accuracy of the analysis task. Then, many analysis tasks need to have a starting task, and the dependencies are determined by taking the starting task as a benchmark. Specifically, the first-order task can be determined from each analysis task according to the pre-set task importance, and multiple analysis tasks are traversed. The analysis tasks that have no dependencies with the first-order task are added to the first task set, and each analysis task in the first task set has the same priority as the first-order task. The first-order task is the starting task, and the determination of the first-order task can be pre-set based on experience or the accumulation and analysis of historical data. The priority is determined, starting with the first-order task, and other analysis tasks that have no dependencies or no intersections with the first-order task are executed first with the first-order task. In another case, other analysis tasks that have no dependencies with the first-order task still have dependencies among these analysis tasks, so the above scheduling rules can still be followed to confirm other order tasks, and execute them in sequence in a loop to determine the priority.

[0069] Step 104: Determine the data association relationship of the analysis task according to the task type;

[0070] As can be seen from step 102, the task types of the analysis task can include qualitative tasks and quantitative tasks. Qualitative tasks can be regarded as analyzing certain characteristics of things or phenomena, such as energy consumption in different regions, comparison of the number of users in different units, and comparison of income in different departments in the digital twin scene. Quantitative tasks can be to compare before and after time, so as to know whether the development of things is good or bad. For example, the number of users increased by 10% month-on-month and 20% year-on-year. This is a comparison in time. Of course, quantitative tasks are not limited to time, but can also be analysis of numerical directions such as income, consumption, and age. Whether it is a qualitative task or a quantitative task, it is necessary to analyze the relevant data according to the corresponding logic or sequence. The data association relationship can reflect the characteristics of the corresponding analysis task and the analysis direction of the analysis task on the data. Therefore, it is necessary to determine the data association relationship, that is, to straighten out the specific logic or direction of the corresponding analysis task, which can also be called specific content.

[0071] Specifically, determining the data association relationship of the analysis task according to the task type may include: determining the task name and task description of the analysis task according to the qualitative task, determining the text data of the analysis task according to the task name and task description, and determining the data association relationship according to the text data. Among them, the task description reflects the analysis direction of the qualitative task, such as the comparison of a common indicator between region A and region B. The task name can be a summary of the task description, and the task name and task description basically represent the data title related to the task. Therefore, the text data of the analysis task can be determined based on this, that is, the corresponding character data, such as region, gender, equipment, etc. The data association relationship is the logical relationship of the text data. For example, comparison, cause and effect, conditional relationship, etc.

[0072] Determine the task node of the analysis task based on the quantitative task, determine the numerical data of the analysis task based on the task node, and determine the data association relationship based on the numerical data. Quantitative tasks are generally analyzed based on task nodes, which can be nodes with numerical changes. For example, from time point A to time point B, the change trend of a certain indicator, each task node corresponds to corresponding numerical data, that is, numerical data, such as time, income, age, etc. The data association relationship is the grouping processing relationship of numerical data. For example, time from far to near, income from low to high, age from young to old, etc.

[0073] Based on the above data association relationships, the extracted data has more obvious rules and clearer logic.

[0074] Step 105: Obtain twin scene data corresponding to each analysis task from the database;

[0075] During the operation of the digital twin system, advanced technologies such as big data, cloud computing, and the Internet of Things are used to create a virtual model that reflects the physical world by collecting various data from the physical world during operation, from design to manufacturing, operation, maintenance, and scrapping. The virtual model can map various scenes in the real world. For example: community service scenes, property service scenes, traffic operation scenes, etc. Among them, the twin scene data can be the state data of the physical world corresponding to the virtual model, the simulation data related to the model, etc. Assuming that the mapping scene of the virtual model is a community, the twin scene data can be the current number of people in the community, the number of community facilities, the operating status of community facilities, etc. Because the state of the actual scene changes at any time, the twin scene data is transformed in real time and stored in the database in real time.

[0076] At this time, the twin scene data is a variety of unordered data stored at any time during the operation of the scene. By determining the analysis object of each analysis task, the data extraction range in the database is determined according to the analysis object, and the twin scene data is extracted according to the data extraction range. For example, if the analysis object of the analysis task is the community population, then the data extraction range can be the number of people collected in the community at all times; assuming that the analysis object of the analysis task is a certain device, then the data extraction range can be the status data of the device from the start of operation to the present. Extracting twin scene data according to the data extraction range can further reduce the workload of the data processing process, reduce the scope, and reduce the scope of data sorting in advance through precise targets.

[0077] Step 106: Determine the target data according to the data association relationship and the twin scene data;

[0078] Although the twin scene data in the above steps has been precisely scoped according to the analysis object, it is disordered or illogical. Direct analysis of the twin scene data will make the analysis results chaotic, irregular, and inaccurate. It is necessary to logically sort the twin scene data according to the data association relationship to determine the target data. The target data is data arranged according to text logic or numerical transformation rules. For example, comparative data on the consumption of a certain energy in different areas of the community; consumption change data of a certain energy in the community over a period of time.

[0079] Step 107: Input the target data into the visualization platform in order of priority to display the analysis results corresponding to the analysis task.

[0080] Priority is used to sort the execution order of each analysis task to prevent confusion in the analysis process. The target data corresponds to the corresponding analysis task and is logically sorted. Input the target data into the visualization platform in the order of priority, and the visualization platform can generate corresponding analysis results based on the target data. The analysis results are displayed in the form of charts through the transformation of the visualization platform, which can be in the form of time series, tables, status timelines, dashboards, bar charts, maps, etc., relying on the provision of fast and flexible visualization functions to visualize various data in the analysis tasks, so as to understand all relevant data and the relationship between them, so as to discover root events and identify unexpected system behaviors.

[0081] It can be seen from the above technical solutions that the beneficial effects of this embodiment are: by utilizing the scheduler to reasonably schedule analysis tasks and adjust the priority of each task, when facing multiple analysis tasks, a suitable data analysis logic is created, and data association relationships are used to sort out the diverse and scattered data in the twin scene, so that the visualization platform can display accurate analysis results, thereby achieving accurate monitoring of the digital twin scene.

[0082] Figure 1 What is shown is only a basic embodiment of the method of the present invention. By performing certain optimization and expansion on this basis, other preferred embodiments of the method can be obtained.

[0083] like Figure 2 As shown, another specific embodiment of the data analysis method for a digital twin scenario of the present invention is shown. This embodiment is further described on the basis of the above embodiment. In this embodiment, the method includes the following steps:

[0084] Step 201: determine the analysis object of each analysis task;

[0085] When outputting visualized analysis results, a reasonable time span is important. Different analysis objects have different time spans, which can be better expressed in the analysis results. The analysis object is the target of the analysis task. Determining the analysis object can not only reduce the scope of data analysis, but also further determine the density of data in the analysis task. The density of the data is reflected in the time span, which is used to determine the appropriate data node interval.

[0086] Step 202: Obtain twin scene data corresponding to each analysis task from the database;

[0087] During the operation of the digital twin system, advanced technologies such as big data, cloud computing, and the Internet of Things are used to create a virtual model that reflects the physical world by collecting various data from the physical world during operation, from design to manufacturing, operation, maintenance, and scrapping. The virtual model can map various scenes in the real world. For example: community service scenes, property service scenes, traffic operation scenes, etc. Among them, the twin scene data can be the state data of the physical world corresponding to the virtual model, the simulation data related to the model, etc. Assuming that the mapping scene of the virtual model is a community, the twin scene data can be the current number of people in the community, the number of community facilities, the operating status of community facilities, etc. Because the state of the actual scene changes at any time, the twin scene data is transformed in real time and stored in the database in real time.

[0088] At this time, the twin scene data is a variety of unordered data stored at any time during the operation of the scene. By determining the analysis object of each analysis task, the data extraction range in the database is determined according to the analysis object, and the twin scene data is extracted according to the data extraction range. For example, if the analysis object of the analysis task is the community population, then the data extraction range can be the number of people collected in the community at all times; assuming that the analysis object of the analysis task is a certain device, then the data extraction range can be the status data of the device from the start of operation to the present. Extracting twin scene data according to the data extraction range can further reduce the workload of the data processing process, reduce the scope, and reduce the scope of data sorting in advance through precise targets.

[0089] Step 203: Determine the task scheduling frequency of each analysis task according to the analysis object;

[0090] The task scheduling frequency in this embodiment is the data node interval mentioned in step 201, specifically the number of data nodes within the time length. The time length can be seconds, minutes, hours, days, weeks, months, years, etc., depending on the analysis object. For example, if the analysis object is energy consumption, personnel statistics, equipment operation, traffic status, environmental monitoring, etc., the task scheduling frequencies of these analysis objects are different. The data extraction range can determine the time length, so it is also necessary to determine the number of data nodes within the time length.

[0091] Suppose the analysis object is community demographics, and the time length may be 5 years, then the task scheduling frequency can be 2, that is, extracting demographic data twice a year to analyze the changes in community population within 5 years. Suppose the analysis object is noise detection in a community, and the time length is 12 hours, then the task scheduling frequency can be 1, that is, extracting noise data once a minute to analyze the noise generation process within 12 hours.

[0092] Different analysis objects are configured with appropriate task scheduling frequencies, which can reasonably allocate the reading resources within the system, reduce the system operation load, and provide reasonable continuous data for the generation of analysis results.

[0093] Step 204: Determine target data according to the task scheduling frequency and the twin scene data;

[0094] The twin scene data in the above steps is precisely scoped according to the analysis object, and the interval and quantity of the twin scene data can be limited according to the task scheduling frequency. The target data determined according to the task scheduling frequency and the twin scene data has a reasonable time series, and the analysis results generated by the target data can better reflect the relevant characteristics of the analysis object.

[0095] Step 205: Input the target data into the visualization platform to determine the analysis result corresponding to the analysis task.

[0096] The target data can better reflect the relevant characteristics of the analysis object, and the visualization platform can generate corresponding analysis results based on the target data. The analysis results are displayed in the form of charts through the transformation of the visualization platform, which can be in the form of time series, tables, status timelines, dashboards, bar charts, maps, etc., relying on the provision of fast and flexible visualization functions to visualize various data in the analysis task, so as to understand all relevant data and the relationship between them, so as to discover root events and identify unexpected system behaviors.

[0097] It can be seen from the above technical solutions that the beneficial effects of this embodiment are: determining target data of a reasonable time series according to the characteristics of the analysis object, and the analysis results generated based on the target data are more linear and accurate.

[0098] like Figure 3 As shown in the figure, a specific embodiment of a data analysis device for a digital twin scenario of the present invention is shown. The device of this embodiment is used to perform Figures 1-2 The physical device of the method. Its technical solution is essentially consistent with the above embodiment, and the corresponding description in the above embodiment is also applicable to this embodiment. The device in this embodiment includes:

[0099] A start instruction acquisition module 301 is configured to acquire a start instruction of at least one analysis task;

[0100] The scheduling module 302 is configured to enable the scheduler to determine the scheduling rules between the analysis tasks and the task type of each analysis task in response to the start instruction;

[0101] The priority determination module 303 is configured to determine the priority of each analysis task according to the scheduling rule;

[0102] The data association relationship determination module 304 is configured to determine the data association relationship of the analysis task according to the task type;

[0103] A twin scene data acquisition module 305 is configured to acquire twin scene data corresponding to each analysis task from a database;

[0104] A target data determination module 306 is configured to determine target data according to the data association relationship and the twin scene data;

[0105] The analysis result determination module 307 is configured to input the target data into the visualization platform in order of priority to display the analysis result corresponding to the analysis task.

[0106] Figure 4 : is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.

[0107] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0108] The memory is used to store execution instructions. Specifically, the execution instructions are computer programs that can be executed. The memory may include internal memory and non-volatile memory, and provides execution instructions and data to the processor.

[0109] In one possible implementation, the processor reads the corresponding execution instructions from the non-volatile memory into the memory and then runs them, and can also obtain the corresponding execution instructions from other devices to form a data analysis device for the digital twin scene at the logical level. The processor executes the execution instructions stored in the memory to implement a data analysis method for the digital twin scene provided in any embodiment of the present invention through the execution of the execution instructions.

[0110] As described above, the present invention Figure 3 The method provided by the illustrated embodiment for executing a data analysis device for a digital twin scenario can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0111] The steps of the method disclosed in the embodiment of the present invention can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0112] The embodiment of the present invention further proposes a readable medium, which stores an execution instruction. When the stored execution instruction is executed by a processor of an electronic device, the electronic device can execute a data analysis method for a digital twin scenario provided in any embodiment of the present invention, and is specifically used to execute the following Figure 1 , Figure 2 The method shown.

[0113] The electronic device in each of the aforementioned embodiments may be a computer.

[0114] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods or computer program products. Therefore, the present invention may be implemented in the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware.

[0115] The various embodiments of the present invention are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0116] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0117] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A data analysis method for a digital twin scenario, characterized in that: The method is applied to a digital twin system, which includes a scheduler, a database, and a visualization platform; the method includes: Obtaining a start instruction for at least one analysis task; In response to the start instruction, the scheduler determines a scheduling rule between the analysis tasks and a task type of each analysis task; Determining the priority of each of the analysis tasks according to the scheduling rule; Determining the data association relationship of the analysis task according to the task type; Acquire twin scene data corresponding to each of the analysis tasks from the database; Determine target data according to the data association relationship and the twin scene data; The target data is input into the visualization platform in the order of the priorities to display the analysis results corresponding to the analysis tasks.

2. The method according to claim 1, characterized in that The step of causing the scheduler to determine a scheduling rule between the analysis tasks in response to the start instruction comprises: Determining dependencies between the analysis tasks; Parallel scheduling of the analysis tasks without dependencies; The analysis tasks having dependencies are serially scheduled.

3. The method according to claim 2, characterized in that Determining the priority of each of the analysis tasks according to the scheduling rule includes: Determining a first-priority task from among the analysis tasks according to a preset task importance; Traversing the plurality of analysis tasks, and adding the analysis tasks that have no dependency relationship with the first priority task to the first task set; Each of the analysis tasks in the first task set has the same priority as the first-ranked task.

4. The method according to claim 1, characterized in that The task types include qualitative tasks and quantitative tasks; then determining the data association relationship of the analysis task according to the task type includes: Determine the task name and task description of the analysis task according to the qualitative task; Determine the text data of the analysis task according to the task name and task description; Determine the data association relationship according to the text data; Determine the task node of the analysis task according to the quantitative task; Determining numerical data of the analysis task according to the task node; The data association relationship is determined according to the numerical data.

5. The method according to claim 1, characterized in that The acquiring the twin scene data corresponding to each of the analysis tasks from the database includes: Determining the analysis object of each of the analysis tasks; Determining a data extraction scope in the database according to the analysis object; The twin scene data is extracted according to the data extraction range.

6. The method according to claim 1, characterized in that The determining the target data according to the data association relationship and the twin scene data includes: The twin scene data is logically sorted according to the data association relationship to determine the target data.

7. The method according to any one of claims 1 to 6, characterized in that: Also includes: Determining a task scheduling frequency for each of the analysis tasks according to the analysis object; Determining the target data according to the task scheduling frequency and the twin scenario data; The target data is input into the visualization platform to determine the analysis result corresponding to the analysis task.

8. A data analysis device for digital twin scenarios, characterized in that: include: A start instruction acquisition module, used to acquire a start instruction of at least one analysis task; a scheduling module, configured to enable the scheduler to determine a scheduling rule between the analysis tasks and a task type of each analysis task in response to the start instruction; A priority determination module, used to determine the priority of each of the analysis tasks according to the scheduling rules; A data association relationship determination module, used to determine the data association relationship of the analysis task according to the task type; A twin scene data acquisition module, used to acquire the twin scene data corresponding to each of the analysis tasks from the database; A target data determination module, used to determine the target data according to the data association relationship and the twin scene data; An analysis result determination module is used to input the target data into the visualization platform in the order of priority to display the analysis result corresponding to the analysis task.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 7 when executed.

10. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement any one of the methods described in claims 1 to 7.

Images