Intelligent analysis and display method for enterprise energy consumption data

Abstract

The invention discloses an intelligent analysis and display method for enterprise energy consumption data, and relates to the technical field of data processing, and the method comprises the steps: determining equipment installation information, and constructing an equipment tree; constructing a template library; establishing a data visualization analysis platform and carrying out platform cloud test optimization; the energy consumption database receives enterprise energy consumption data and performs internal data logic and distribution updating; reading the target display task, identifying user permission, and activating a task interface; and carrying out data retrieval calling and algorithm matching calculation on the target display task to generate an energy consumption report and carrying out visual display. The technical problems that the enterprise energy consumption data cannot be efficiently managed, the data analysis is inaccurate and the data visualization display flexibility is insufficient due to the fact that the fine change and potential problems of enterprise energy consumption data are difficult to accurately capture in the existing enterprise energy consumption data are solved. The technical effect of improving the accuracy and efficiency of enterprise energy consumption data analysis and the flexibility of visual display is achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to data processing, and specifically to a method for intelligent analysis and display of enterprise energy consumption data. Background Art

[0002] In today's wave of digital transformation, enterprises have an increasingly urgent need for refined and intelligent energy management. With the rapid development of technologies such as the Internet of Things, big data, and cloud computing, traditional energy management models can no longer meet the needs of enterprises for efficient operation, energy conservation and emission reduction, and cost control. The analysis and display of enterprise energy consumption data can provide enterprises with all-round and multi-dimensional insights into energy use, helping enterprises to achieve intelligent upgrades in energy management. However, with the expansion of enterprise scale and the increase of production equipment, the complexity and diversity of energy use have also increased. Traditional energy data analysis is not only inefficient, but also difficult to capture subtle changes and potential problems in energy use. Equipment installation information is often scattered and disordered, and energy usage data is large and real-time, making it difficult to manage and analyze effectively. At the same time, different users have different needs for energy data visualization, and traditional methods cannot meet their diverse display needs.

[0003] Therefore, at the current stage, there are technical problems in the technologies related to enterprise energy consumption data analysis that make it difficult to accurately capture subtle changes and potential problems in enterprise energy use, which in turn leads to the inability to efficiently manage enterprise energy consumption data, inaccurate data analysis, and insufficient flexibility in data visualization. Summary of the invention

[0004] This application provides an intelligent analysis and display method for enterprise energy consumption data. It adopts technical means such as building a device tree, building a template library, and logicalizing and distributing and updating internal data. It solves the technical problems that it is difficult to accurately capture subtle changes and potential problems in enterprise energy use with existing enterprise energy consumption data, which in turn leads to the inability to efficiently manage enterprise energy consumption data, inaccurate data analysis, and insufficient flexibility in data visualization. It achieves the technical effect of improving the accuracy and efficiency of enterprise energy consumption data analysis and the flexibility of visualization display.

[0005] The present application provides a method for intelligent analysis and display of enterprise energy consumption data, the method comprising: determining equipment installation information based on the installed scale of enterprise electrical equipment, performing entity and relationship extraction based on equipment subject, attribute, and indicator, and constructing an equipment tree, wherein the indicator class has an algorithm matrix; constructing a template library, wherein the template library includes a framework layout template sub-library and a display template sub-library of framework internal partitions; based on the equipment tree and the template library, building a data visualization analysis platform and performing platform cloud test optimization, the visualization analysis platform includes a built-in processor; an energy consumption database receives enterprise energy consumption data, and performs internal data logicization and distribution update on the visualization analysis platform; reading target display tasks and identifying user permissions, activating a task interface, wherein the task interface has a locked partition without permission; based on the task interface, triggering a distributed engine, performing data retrieval calls and algorithm matching calculations on the target display tasks, generating energy consumption reports and performing visualization displays.

[0006] In a possible implementation, the device tree is constructed by performing the following processing: determining a device distribution topology based on the installed scale, wherein the device distribution topology is based on device connection relationships and subordinate relationship connections; based on an attribute entity, traversing the device installed information to extract a first relationship; based on an indicator entity, traversing the device installed information to extract a second relationship; and determining the device tree based on the device distribution topology, the first relationship, and the second relationship.

[0007] In a possible implementation, the device tree is determined based on the device distribution topology, the first relationship, and the second relationship, and the following processing is performed: a first structural layer is determined based on the device distribution topology, a second structural layer based on attribute entities, and a third structural layer based on indicator entities are constructed to determine an architecture system, wherein the architecture system is scalable; data analysis tasks in a predetermined time zone are read to determine a task matrix, wherein each matrix node meets a preset frequency; the task matrix is ​​traversed to construct a mapped algorithm matrix; distribution reconstruction and semantic disambiguation are performed based on the architecture system and the algorithm matrix to determine the device tree.

[0008] In a possible implementation, the visualization analysis platform includes a built-in processor that performs the following processing: traverses the algorithm matrix to determine logic rules based on the task matrix, wherein the logic rules include call logic and operation logic; based on the algorithm matrix and the logic rules, determines the built-in processor, and establishes connectivity between the built-in processor and the platform module.

[0009] In a possible implementation, the platform cloud test optimization also performs the following processing: determining the test dimension, and determining the expected matrix based on the dimensional distribution index based on the test dimension, wherein the test dimension at least includes function, layout and compatibility; generating a test plan and performing cloud test deployment guided by the test dimension, wherein the test plan includes multiple parallel plans; generating automatic review rules based on the expected matrix; and performing cloud test optimization analysis on the visualization analysis platform based on the test plan and the automatic review rules.

[0010] In a possible implementation, cloud test optimization analysis is performed on the visualization analysis platform, and the following processing is also performed: obtaining a parallel test sequence and locating the platform optimization target, wherein the positioning determination method is a preset pass ratio based on the parallel test frequency; traversing the platform optimization target, and building an optimization space based on the target degree of freedom, wherein the target degree of freedom includes self-degree of freedom and collaborative degree of freedom; based on the optimization space, configuring a random attention mechanism to lock the optimization target and iteratively optimize, selecting the global optimal strategy as the optimization construction strategy, and debugging the data visualization analysis platform; wherein the random attention mechanism is based on the random optimization target number and random optimization step size of the iteration layer, and the optimal adjustment method of the iteration layer is taboo locked, and the preset number of iteration layers is used as the taboo unlocking method.

[0011] In a possible implementation, the method for intelligent analysis and display of enterprise energy consumption data also performs the following processing: decomposing the enterprise energy consumption data, determining the main data system and the auxiliary data system, and establishing the mapping and synchronization constraints between the main data system and the auxiliary data system; taking the main data system as the task execution target, and the auxiliary data system responds synchronously.

[0012] In a possible implementation, the method for intelligent analysis and display of enterprise energy consumption data also performs the following processing: generating a task flow based on the target display task, the task flow including multiple flow nodes; tracking user operation information, and performing operation guidance and correction management based on the task flow.

[0013] The present application also provides an intelligent analysis and display system for enterprise energy consumption data, including: a device tree construction module, which is used to determine the equipment installation information based on the installed scale of the enterprise's electrical equipment, perform entity and relationship extraction based on the equipment body, attributes, and indicators, and construct a device tree, wherein the indicator class has an algorithm matrix; a template library construction module is used to construct a template library, wherein the template library includes a framework layout template sub-library and a display template sub-library of the framework internal partition; a platform cloud test optimization module, which is used to build a data visualization analysis platform and perform platform cloud test optimization based on the device tree and the template library, wherein the visualization analysis platform includes a built-in processor; an enterprise energy consumption data receiving module is used to receive the enterprise energy consumption data in the energy database, and perform internal data logicization and distribution update on the visualization analysis platform; a task interface activation module, which is used to read the target display task and identify user permissions, and activate the task interface, wherein the task interface has a locked partition without permission; an energy consumption report generation module, which is used to trigger the distributed engine based on the task interface, perform data retrieval calls and algorithm matching calculations on the target display task, generate an energy consumption report, and perform visual display.

[0014] The intelligent analysis and display method of enterprise energy consumption data proposed in this application is to determine the equipment installation information based on the installed scale of the enterprise's electrical equipment, perform entity and relationship extraction based on the equipment body, attributes, and indicators, and construct an equipment tree, wherein the indicator class has an algorithm matrix; construct a template library, wherein the template library includes a framework layout template sub-library and a display template sub-library of the framework internal partition; based on the equipment tree and the template library, build a data visualization analysis platform and perform platform cloud testing optimization, wherein the visualization analysis platform includes a built-in processor; the energy consumption database receives the enterprise's energy consumption data, and performs internal data logicization and distribution updates on the visualization analysis platform; reads the target display task and identifies the user authority, and activates the task interface, wherein the task interface has a locked partition without authority; based on the task interface, triggers the distributed engine, performs data retrieval and algorithm matching calculations on the target display task, generates an energy consumption report, and performs visualization. It solves the technical problems that existing enterprise energy consumption data is difficult to accurately capture subtle changes and potential problems in enterprise energy use, which in turn leads to the inability to efficiently manage enterprise energy consumption data, inaccurate data analysis and insufficient flexibility in data visualization. It achieves the technical effect of improving the accuracy and efficiency of enterprise energy consumption data analysis and the flexibility of visualization. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0016] Figure 1 A schematic diagram of a process flow of an intelligent analysis and display method for enterprise energy consumption data provided in an embodiment of the present application;

[0017] Figure 2 A schematic diagram of the process of constructing a device tree in a method for intelligent analysis and display of enterprise energy consumption data provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application embodiment provides a method for intelligent analysis and display of enterprise energy consumption data, such as Figure 1As shown, the method includes:

[0022] Step S100, based on the installed capacity of the enterprise's electrical equipment, determine the equipment installation information, perform entity and relationship extraction based on the equipment subject, attributes, and indicators, and construct an equipment tree, where the indicator class has an algorithm matrix. The installed capacity refers to the basic information such as the quantity, type, and power of all electrical equipment in the enterprise. Specifically, determine the installed capacity of the enterprise's electrical equipment, and then collect detailed installed information for each device, which may include but is not limited to the model, manufacturer, installation location, rated power, actual operating power, production date, maintenance records, etc. of the equipment. After collecting the equipment installation information, extract entities and relationships from this information. For example, identify entities (such as equipment subjects, attributes, indicators, etc.) and their relationships (such as the relationship between attributes and equipment subjects, the relationship between indicators and equipment, etc.) from text or structured data, where the equipment subject refers to a specific electrical equipment, attributes refer to various inherent characteristics of the equipment (such as model, manufacturer, etc.), and indicators refer to data points used to evaluate equipment performance or status (such as energy consumption, efficiency, runtime, etc.). The algorithm matrix is ​​a set used to define, manage and apply various algorithms to process or evaluate specific indicators or data points. The algorithm matrix is ​​particularly related to various indicators in the equipment installation information. Specifically, the algorithm matrix defines the corresponding processing algorithm for each indicator, such as data cleaning, conversion, aggregation, prediction, anomaly detection and other types. The most appropriate algorithm is selected according to the characteristics of the indicator, data availability, analysis purpose and other factors (such as considering the accuracy of the algorithm, computational efficiency, scope of application, etc.). For each selected algorithm, it is necessary to configure the corresponding parameters (including the granularity of data processing, the complexity of the model, and the prediction time window), define the execution order and process of the algorithm, and ensure that the various algorithms can work together to complete the analysis and processing of the indicators. Based on the decision tree principle, according to the extraction results of entities and relationships, a device tree is constructed to represent the parent-child relationship or inclusion relationship between electrical equipment. Each node in the device tree represents an electrical equipment, and the lines between the nodes represent the relationship between them. By constructing the device tree, complex enterprise electrical equipment can be presented in a systematic and structured manner, which is convenient for subsequent data analysis, monitoring and management. By combining with the algorithm matrix, the automatic analysis and processing of equipment indicators can be realized, thereby improving the intelligent level of energy management.

[0023] In one possible implementation, Figure 2As shown, step S100 further includes step S110, determining the equipment distribution topology based on the installed capacity, wherein the equipment distribution topology is based on equipment connection relationships and affiliation connections. Based on a given equipment installed capacity (i.e., the number, type, configuration, and other information of the equipment), a network structure diagram that reflects the physical connection relationships and affiliation relationships between devices is constructed, i.e., the equipment distribution topology. It not only shows the location layout of the equipment in space or in the network, but also describes in detail how the equipment is connected to each other and the affiliation relationships between them, including equipment connection relationships and affiliation relationships. Specifically, the equipment connection relationship refers to the connection established between devices through physical media (such as cables, optical fibers, wireless signals, etc.) or logical protocols (such as network protocols, communication protocols, etc.). This connection enables devices to communicate with each other, exchange data, or work together. In the equipment distribution topology, the connection relationship is usually represented by lines or arrows, and the starting point and end point of the connection line correspond to the connected devices respectively; the affiliation relationship refers to the hierarchy or relationship between devices. A device is a component or sub-device of another device. For example, in a data center, a server may be connected to a switch, and the switch may be connected to a router or a core switch, forming a hierarchical structure. At the same time, there may be multiple hard disks, memories, processors and other components inside the server, and these components and the server have a subordinate relationship. In the device distribution topology, the subordinate relationship is usually represented by nested graphics or indented layouts to clearly show the hierarchical structure between devices. Specifically, building a device distribution topology includes collecting all relevant information about the installed capacity of the equipment, sorting out the connection relationship and subordinate relationship between the devices, and drawing the device distribution topology map based on the sorted out relationship. After drawing, the topology map is verified and optimized to ensure that the topology map accurately reflects the actual relationship between the devices.

[0024] Step S120, based on the attribute entities, traverse the device installation information to extract the first relationship. By traversing the device installation information (i.e., detailed records of installed devices), first relationships between devices are extracted based on these attribute entities. These relationships may include associations between devices of the same model, associations between devices in the same location or region, or groupings between devices with similar attributes.

[0025] Step S130, based on the indicator entity, traverse the equipment installation information to extract the second relationship. By traversing the equipment installation information, these indicator entities are used to extract the second relationship between the devices. These relationships may be based on the similarity or difference of the performance indicators of the devices, for example, the distinction between high-energy consumption devices and low-energy consumption devices, or the comparison between high-failure rate devices and stable-operating devices.

[0026] Step S140, based on the device distribution topology, the first relationship and the second relationship, determine the device tree. The device tree is constructed by integrating the physical connection relationship, the subordinate relationship (information provided by the device distribution topology), and the attribute characteristics and performance indicators of the device (extracted from the first relationship and the second relationship, respectively) between the devices. Specifically, the device connection relationship and the subordinate relationship in the device distribution topology are used as the basic framework for constructing the device tree, and the parent-child relationship between the devices is determined, that is, which device is the main device (parent node) and which device is the subordinate device (child node). According to the first relationship, the attribute information of the device (such as device name, model, serial number, location, etc.) is added to the corresponding node of the device tree. According to the second relationship, the performance indicators of the device (such as energy consumption, running time, failure rate, processing capacity, etc.) are also added to the corresponding node of the device tree. Then, the device tree is constructed, that is, the hierarchical structure is used to represent the connection and subordinate relationship between the devices. In each node of the device tree, the attribute information and performance indicators of the device are included, so as to ensure that the structure of the device tree is clear and logically reasonable, and easy to understand and use.

[0027] In a possible implementation, step S140 further includes step S141, determining a first structural layer based on the device distribution topology, constructing a second structural layer based on attribute entities, and a third structural layer based on indicator entities, to determine an architecture system, wherein the architecture system is extensible. The first structural layer is the basis of the architecture system, directly reflecting the physical connection and affiliation between devices, and is represented by the device distribution topology, including the layout, connection mode and hierarchical structure of the devices; in the second structural layer, an information model of the device is constructed according to the attribute entities of the device (such as device name, model, serial number, location, etc.), and the attribute entities are integrated into the architecture system, so that each device node contains rich metadata; in the third structural layer, a performance model of the device is constructed according to the indicator entities of the device (such as energy consumption, running time, failure rate, processing power, etc.), and these performance indicators are integrated into the architecture system to reflect the operating status and performance characteristics of the device; the extensibility of the architecture system refers to its ability to be flexibly expanded and adjusted according to actual needs, including adding new device nodes, modifying the connection relationship between devices, adding new attributes or indicator entities, etc.

[0028] Step S142, read the data analysis tasks in the predetermined time zone, and determine the task matrix, wherein each matrix node meets the preset frequency. Read the data analysis tasks in the predetermined time zone, and determine a task matrix based on these tasks. Each node of the task matrix represents a data analysis task, and the connection relationship between the nodes may reflect the dependency or parallel relationship between the tasks. At the same time, each matrix node is required to meet the preset frequency, that is, each task needs to be executed a certain number of times within a certain time period to ensure the timeliness and accuracy of the data.

[0029] Step S143, traverse the task matrix to construct a mapped algorithm matrix. The structure and content of the task matrix are clarified, and then an algorithm matrix corresponding to the task matrix is ​​initialized. The size and structure of the algorithm matrix are the same as those of the task matrix, but each element is no longer the task itself, but an algorithm or algorithm set associated with the task. These algorithms are used to perform the corresponding task, process task data, or optimize the task execution process. Each node in the task matrix is ​​traversed, and for each task represented by each node, according to its task type (different types of tasks may require different types of algorithms), data features (for example, for large-scale data sets, parallel algorithms or distributed algorithms are required to improve processing efficiency), performance requirements (such as response time, accuracy, resource consumption, etc.), select a suitable algorithm or algorithm combination, and map it to the corresponding position of the algorithm matrix, and finally obtain a mapped algorithm matrix, which can find the most suitable algorithm or algorithm combination for each task, thereby improving the efficiency and accuracy of task execution.

[0030] Step S144, based on the architecture system and the algorithm matrix, perform distribution reconstruction and semantic disambiguation to determine the device tree. Based on the constructed architecture system and algorithm matrix, perform distribution reconstruction and semantic disambiguation. Specifically, distribution reconstruction refers to reallocating and adjusting device resources according to data analysis task requirements, device performance, and resource conditions to achieve efficient execution of tasks. For example, according to the task volume, task type, and dependencies between tasks in the task matrix, reasonably allocate device resources to ensure that each task can obtain sufficient computing resources; according to performance indicators such as device processing power, storage capacity, and network bandwidth, assign tasks to the most suitable device nodes for execution; through load balancing, resource scheduling and other strategies, optimize resource utilization efficiency and reduce overall system energy consumption and cost. Semantic disambiguation refers to solving the fuzziness, ambiguity or inconsistency in the expression of device information to ensure that each node in the device tree can be accurately understood and identified. For example, standardized naming, establishing a unified naming specification for devices to avoid naming conflicts; attribute verification, verifying and cleaning device attribute information to ensure the accuracy and consistency of information; providing detailed description information for devices, including functions, performance, interfaces, etc., to better understand and use the devices. After distributed reconstruction and semantic disambiguation processing, a clear, accurate and scalable device tree can be obtained. The device tree displays the connection relationship, functional division and attribute information between devices in a tree structure, ensuring the efficiency, accuracy and scalability of the system.

[0031] Step S200, construct a template library, wherein the template library includes a framework layout template sub-library and a display template sub-library of the internal partition of the framework. When constructing a template library for enterprise energy consumption data visualization or information display, the template library is usually subdivided into different sub-libraries to facilitate the management and use of different types of templates. The template library includes a framework layout template sub-library and a display template sub-library of the internal partition of the framework. Specifically, the framework layout template sub-library contains a variety of templates for constructing the overall page or interface layout, and defines the basic structure of the page, such as the layout method and position relationship of the header, navigation bar, main content area, sidebar, footer and other parts. By using the framework layout template, a basic page structure that meets the design requirements and information display needs can be quickly built without designing the layout of each page from scratch, thereby improving development efficiency and page consistency. The templates in the framework layout template sub-library may include responsive layout templates (suitable for devices with different screen sizes), fixed layout templates (suitable for devices or application scenarios with specific screen sizes), and customizable layout templates (providing certain The display template sub-library of the internal partition of the framework focuses on the display mode and style design of each area (such as cards, tables, charts, text blocks, etc.) inside the page or interface, and defines how to display specific data or information in the area determined by the framework layout template. By using display templates, the data display mode inside the page or interface can be further refined to improve the readability and attractiveness of information. Different display templates are suitable for different types of data and information, and can be selected and adjusted according to different display requirements. The templates in the display template sub-library of the internal partition of the framework may include data table templates (for displaying structured data), chart templates (such as bar charts, line charts, pie charts, etc., for visual display of data trends and relationships), card templates (card-style layouts for displaying information such as pictures, titles, descriptions, etc.), text templates (templates for displaying long text information), etc. When building a template library, subdividing the template library into the framework layout template sub-library and the display template sub-library of the internal partition of the framework helps to achieve effective management and flexible application of the overall and detailed layout of the page or interface. By selecting the appropriate template, a data visualization or information display platform that meets the requirements can be quickly built.

[0032] Step S300, based on the device tree and the template library, build a data visualization analysis platform and perform platform cloud test optimization, the visualization analysis platform includes a built-in processor. Building a data visualization analysis platform based on the device tree and the template library, and performing platform cloud test optimization, specifically refers to providing enterprises with efficient and flexible data visualization solutions by integrating device information, template resources and cloud computing technology. The visualization analysis platform includes a built-in processor, which refers to the computing processing unit integrated within the platform, responsible for performing core tasks such as data processing, analysis, and visualization. Specifically, the device tree, as the basis of the data visualization analysis platform, provides structured information of the enterprise's electrical equipment, including the extraction results of entities and relationships such as equipment entities, attributes, and indicators; the template library is used to quickly build a visualization interface that meets the needs. By selecting a suitable template, users can easily create beautiful and intuitive data visualization reports; the built-in processor is the core computing component in the data visualization analysis platform, similar to the CPU (central processing unit) in a computer, but may be optimized for data processing and visualization tasks. The built-in processor has powerful data processing capabilities and is responsible for acquiring data from the data source, data cleaning, For a series of tasks such as conversion, aggregation, analysis and final visualization, the built-in processor may adopt advanced technologies such as parallel computing and distributed computing to make full use of computing resources, reduce processing time, and improve the efficiency of data processing and visualization; according to the results of data processing and analysis, the visualization analysis platform will generate corresponding charts, graphics and other visualization elements, and display them in the user interface. These visualization elements can intuitively reflect the characteristics and laws of the data and help users better understand the information hidden in the data; after the data visualization analysis platform is built, cloud testing is carried out to verify its performance and stability. Cloud testing can perform stress testing and compatibility testing on the platform in a simulated real environment to discover potential problems and optimize them. According to the results of cloud testing, a series of optimization strategies can be adopted to improve the performance and stability of the platform, such as optimizing data processing algorithms, adjusting system architecture, adding caching mechanisms, etc. These optimization strategies will help improve the response speed and stability of the platform, reduce resource consumption and enhance user experience.

[0033] In a possible implementation, step S300 further includes step S310, traversing the algorithm matrix to determine the logic rules based on the task matrix, wherein the logic rules include calling logic and operation logic. The tasks defined in the task matrix and their dependencies, parallel relationships or independent relationships are clarified. Next, each algorithm or algorithm combination in the algorithm matrix is ​​traversed. These algorithms correspond to the task nodes in the task matrix and are used to perform specific data processing, calculation or optimization tasks. According to the requirements of the task and the characteristics of the algorithm, multiple logic rules are determined, including calling logic and operation logic. Specifically, the calling logic defines how to call the corresponding algorithm according to the task execution process, including the selection, loading and execution order of the algorithm; the operation logic defines how the algorithms work together and how the algorithms process task data, including rules on data input, processing flow, output results, etc.

[0034] Step S320, based on the algorithm matrix and the logic rules, determine the built-in processor, and establish the connection between the built-in processor and the platform module. According to the algorithm matrix and the determined logic rules, formulate the specific requirements of the built-in processor, including processing power, memory capacity, interface type, power consumption requirements, etc., to ensure that the built-in processor can meet the operation requirements of all algorithms in the algorithm matrix and has good scalability and compatibility; according to the interface type of the built-in processor and the requirements of the platform module, design a suitable interface circuit or communication protocol to ensure that the data communication and control signal exchange between the processor and the platform module can proceed smoothly, and then physically connect the built-in processor and the platform module according to the designed interface, integrate the built-in processor and the platform module into the entire system, such as performing software configuration, driver installation, system parameter setting, etc., to ensure that the processor can work normally and run in coordination with the platform module, and perform performance verification, and verify whether the connection between the built-in processor and the platform module meets the requirements through testing, including verification of algorithm execution efficiency, data processing accuracy, system stability and reliability, etc.

[0035] In a possible implementation, step S300 further includes step S330, determining a test dimension, and determining an expected matrix based on a dimensional distribution indicator based on the test dimension, wherein the test dimension at least includes function, layout, and compatibility. Determine the test dimensions, including function, layout and compatibility. Specifically, the function dimension focuses on whether the software or platform implements all necessary functions as expected, including the degree of satisfaction of user needs, the completeness and correctness of each functional module, and whether the interaction and collaboration between functions are smooth; the layout dimension focuses on whether the user interface (UI) layout of the software or platform is reasonable, beautiful and easy to use, including the arrangement of interface elements, color matching, font selection, space utilization, etc.; the compatibility dimension focuses on the running ability and performance of the software or platform in different environments (such as different operating systems, browsers, devices, etc.), including whether the platform can be successfully installed, started, and run in various environments, and maintain consistent performance and user experience; based on the test dimensions, determine the expectation matrix based on the dimension distribution indicators, where the expectation matrix is ​​a two-dimensional table, where the rows represent the test dimensions (functions, layouts, compatibility, etc.), and the columns represent specific test items or test scenarios. In each cell of the matrix, fill in the expected results or evaluation indicators for the test dimension and test item, such as "the interface is clear and easy to read" and "the response time does not exceed 2 seconds".

[0036] Step S340, based on the test dimension, generate a test plan and perform cloud test deployment, wherein the test plan includes multiple parallel plans. Based on the test dimension and the expectation matrix, multiple parallel test plans are generated, each of which includes a series of test cases and test steps to verify the performance of the platform in different scenarios. The test plan covers all key test dimensions and test items to ensure the comprehensiveness and effectiveness of the test. Then, using the resources and services of the cloud platform, the test plan is deployed to the cloud for testing, providing a more flexible and efficient test environment, supporting multi-user concurrent testing, and speeding up the test progress. During the cloud test deployment process, it is necessary to configure the test environment, install necessary test tools, upload test data and scripts, etc.

[0037] Step S350, based on the expectation matrix, automatic audit rules are generated. Automatic audit rules are used to automatically evaluate whether the test results meet expectations. By defining automatic audit rules, problems and anomalies in the test can be quickly identified, reducing the workload of manual audits, including functional test rules, checking whether the platform functions are executed as expected, such as whether the data processing results are correct, whether the analysis report is generated, etc.; layout test rules, checking whether the interface layout meets the design specifications, such as whether the button position is correct, whether the text is clear and readable, etc.; compatibility test rules, checking whether the platform performs consistently in different environments, such as whether it can be displayed and operated normally on different browsers, etc.

[0038] Step S360, based on the test plan and the automatic review rules, the visualization analysis platform is subjected to cloud test optimization analysis. According to the test cases in the test plan, they are executed one by one in the cloud test environment, user operations are simulated, test results are recorded, various data generated during the test process are collected, including response time, throughput, error logs, resource utilization, etc., the pre-defined automatic review rules are integrated into the test process, and the test results are quickly reviewed according to the automatic review rules to identify problems that do not meet expectations, including detailed descriptions of the problems, screenshots, logs and other information, and then cloud test optimization analysis is performed, including performance analysis such as response time and throughput, functional verification of the platform, rationality of the layout, aesthetics and ease of use and user experience analysis, compatibility testing, etc., based on the test results and user feedback, the platform is continuously iterated and optimized.

[0039] In a possible implementation, step S360 further includes step S361, obtaining a parallel test sequence and locating a platform optimization target, wherein the positioning determination method is based on a preset pass ratio of the parallel test frequency. Parallel test sequence refers to running multiple test plans at the same time during the optimization or testing process. These test plans test different parts, different functions or different scenarios of the same platform to obtain more comprehensive test results and comprehensively evaluate the performance and stability of the platform. By analyzing the results of parallel tests, it is possible to identify which functions, performance or user experience are deficient, so as to locate the platform targets that need to be optimized. The positioning determination method is based on the preset pass ratio of the parallel test frequency. The preset pass ratio refers to a pass ratio threshold set during the parallel testing process to determine whether a test item or function needs to be optimized. It is usually determined based on historical data. For example, if the preset pass ratio is 90%, any test item or function below this ratio will be regarded as a potential problem point and needs further analysis and optimization. Specifically, the pass rate of each test item or function in multiple tests is counted and compared with the preset pass ratio. If the average pass rate of a test item or function in multiple tests is higher than or equal to the preset pass ratio, it is considered that the test item or function performs well in the current test environment and does not need to be optimized for the time being. Otherwise, the test item or function has performance bottlenecks, defects or unstable factors and needs further analysis and improvement.

[0040] Step S362, traverse the platform optimization objectives, and build an optimization space based on the target degrees of freedom, wherein the target degrees of freedom include self-degrees of freedom and collaborative degrees of freedom. The target degree of freedom refers to the dimensions or aspects in which the optimization target can be adjusted or optimized, including self-freedom and collaborative freedom. Self-freedom refers to the parameters or configurations that can be adjusted independently within a single optimization target (such as the number of algorithm iterations, learning rate, regularization coefficient, server CPU, memory, disk and other resource allocation, as well as system-level configurations such as network bandwidth and number of concurrent connections, interface layout, color matching, interaction mode, etc.). These parameters or configurations directly affect the performance or performance of the optimization target; collaborative freedom refers to the mutual influence and collaborative relationship that may exist between different optimization targets. During the optimization process, when adjusting the parameters or configuration of an optimization target, it is necessary to consider the influence and constraints of other optimization targets, which may include dependencies between functions. For example, the optimization of a function may need to rely on the support or cooperation of other functions; resource sharing and competition, such as the possible competition between different functions when sharing system resources; comprehensive consideration of user needs. During the optimization process, it is necessary to comprehensively consider the needs and preferences of different users to balance the conflicts between various optimization targets. Based on the target degrees of freedom (including self-degrees of freedom and collaborative degrees of freedom), a multi-dimensional optimization space is constructed, which includes all possible combinations of optimization solutions. Each dimension represents an adjustable parameter or configuration. Specifically, the goals and indicators that need to be optimized are clarified, the self-degrees of freedom and collaborative degrees of freedom of each optimization goal are identified, the dimension and scope of the optimization space are defined according to the degrees of freedom, and the appropriate optimization algorithm (such as random search, genetic algorithm, particle swarm optimization, etc.) is selected according to the characteristics and requirements of the problem. The optimization algorithm is executed in the optimization space, the optimal solution is traversed and searched, and the optimization results are evaluated and verified to ensure that the optimization goals and constraints are met.

[0041] Step S363, based on the optimization space, configure the random attention mechanism to lock the optimization target and iteratively optimize, select the global optimal strategy as the optimization construction strategy, and debug the data visualization analysis platform. The random attention mechanism is a mechanism that dynamically adjusts the focus of attention during the optimization process, allowing the algorithm to randomly select or adjust certain parameters in the optimization space in order to explore potential optimization solutions in a wider range. By introducing randomness to increase the diversity and flexibility of the search, it helps to avoid the algorithm from falling into the local optimal solution. When configuring the random attention mechanism, it is necessary to define the rules and strategies for attention allocation, such as the proportion of randomly selected parameters, the step size of the adjustment, etc., to guide the algorithm to search and optimize in the optimization space, and then lock the optimization target and iteratively optimize, that is, adjust the selected parameters or configurations according to the random attention mechanism, and evaluate the impact of these adjustments on the optimization target. If the adjustment brings a positive effect (that is, closer to the optimization target), then retain these. Adjustment; otherwise, undo these adjustments and try other possible adjustment schemes, gradually approaching the global optimal solution through continuous iteration. After multiple iterative optimizations, identify the global optimal strategy, that is, the parameter or configuration combination that can maximize the satisfaction of all optimization objectives, and select it as the optimization construction strategy to guide the final construction and debugging of the data visualization analysis platform, including building the basic framework and functional modules of the data visualization analysis platform according to the optimization construction strategy, testing each function of the platform one by one to ensure that they can run normally and meet user needs, and tuning the performance of the platform, including optimizing data processing procedures, improving system response speed, reducing resource consumption, etc. Through continuous debugging and optimization, the platform can reach the best state in terms of performance and functionality.

[0042] Step S364, wherein the random attention mechanism is based on the random optimization target number and random optimization step size of the iteration layer, taboo locking the optimal adjustment method of the iteration layer, and using the preset number of iteration layers as the taboo unlocking method. During the iteration process, the algorithm randomly selects a certain number of optimization targets to focus on in order to increase the diversity of the search and avoid falling into the local optimum. When adjusting the optimization target, a random step size is used to update the parameters. The size of the step size determines the amplitude and speed of the parameter update. By randomizing the step size, it can be flexibly adjusted in different search directions to explore a wider solution space. When the algorithm finds that the adjustment method of a certain iteration layer (or iteration stage) is significantly better than other methods, it will "taboo lock" the adjustment method, which means that in the next iteration, the algorithm will try to avoid or limit further adjustments to these parameters that have performed well to maintain the current optimization effect and prevent the destruction of the good solutions that have been found due to excessive adjustments. In order to balance the relationship between exploration and utilization, a threshold for the number of iteration layers is preset. When the number of iterations reaches this threshold, the constraints on the previously taboo locked parameters are released, allowing them to participate in the optimization adjustment again, which helps the algorithm to continue to explore new solution spaces and find possible better solutions while maintaining the current optimization effect.

[0043] Step S400, the energy usage database receives the energy usage data of the enterprise, and performs internal data logicization and distribution updates on the visualization analysis platform. The enterprise collects its energy usage data in real time through various sensors, smart meters, energy management systems and other equipment, including consumption data of various energy types such as electricity, gas, water, steam, etc., which usually contain key information such as timestamp, energy consumption, equipment identification, etc., for subsequent analysis and visualization. The collected energy usage data is transmitted to the enterprise's energy usage database via wired or wireless means. The energy usage database is responsible for receiving and storing energy usage data from the enterprise; specifically, the received energy usage data may contain noise, missing values, outliers and other problems, and data cleaning (such as removing noise, filling missing values, identifying and processing outliers, etc.) is performed to improve data quality, and then the cleaned energy usage data is converted according to predetermined logical rules. and processing for subsequent analysis and visualization, which may include data aggregation, classification, sorting and other operations, as well as generating new data fields or indicators according to business needs. For example, real-time energy consumption data can be converted into energy consumption data of time dimensions such as day, week, month, etc., or data can be classified and counted according to dimensions such as region and equipment type. Within the visualization analysis platform, the distribution of data is updated according to the latest energy consumption data. When the energy consumption database receives new data, the platform can immediately perform logical processing and update it to the corresponding data structure. It may include real-time data update or scheduled update mechanism to ensure that the data on the platform is always the latest, that is, calculate new statistical data, update the display content of charts and reports, etc. The data visualization analysis platform displays the processed energy consumption data intuitively in the form of charts, graphs, etc., and also provides a wealth of data analysis tools and functions, such as trend analysis, comparative analysis, anomaly detection, etc. Based on the results of visualization analysis and data analysis, the platform can provide strong support for the energy management decision-making of enterprises, such as adjusting energy use plans, optimizing energy configuration, and improving energy utilization efficiency according to the analysis results.

[0044] Step S500, read the target display task and identify the user authority, and activate the task interface, wherein the task interface has a non-authorized locked partition. Reading the target display task refers to identifying and reading the specific task that the user wants to display or perform, which may be data query, report generation, system configuration change, etc. The target display task may come from the user's direct request, or it may come from the system's internal automated process or external trigger. Before activating the task interface, the current user's permission is checked to determine whether the user has the right to perform the task. It is usually based on a certain permission model, such as role-based access control (RBAC), attribute-based access control (ABAC), etc. If the user does not have sufficient permissions, the system may refuse to execute the task and display the corresponding insufficient permission prompt to the user; after confirming that the user has sufficient permissions, the system will activate and display the interface related to the task, usually including task description, operation options, data display, etc. Among them, there are unauthorized locked partitions in the task interface, that is, in the task interface, there may be some specific areas or functions that are locked due to permission restrictions and cannot be accessed or operated by users. When the system detects that the user does not have sufficient permissions to access these areas or functions, it will automatically lock these areas to prevent the user from performing illegal operations. In order to improve the user experience, a clear lock prompt will be displayed to the user to inform the user which areas or functions cannot be accessed due to insufficient permissions.

[0045] Step S600, based on the task interface, trigger the distributed engine, perform data retrieval calls and algorithm matching calculations on the target display task, generate an energy consumption report and perform visual display. After the user selects or defines the target display task through the task interface, such as time range, region, equipment type, etc., the system triggers the distributed engine according to the user's operation. The triggering mechanism may include button clicks, timed task triggers, etc., and performs data retrieval calls and algorithm matching calculations on the target display task. Specifically, the distributed engine refers to an engine that uses distributed computing resources to improve data processing efficiency and system performance through technical means such as parallel processing and load balancing. The distributed engine can support rapid retrieval and processing of large-scale data; data retrieval call means that according to the needs of the target display task, the distributed engine will adopt appropriate retrieval strategies, such as full-text retrieval, range retrieval, fuzzy retrieval, etc., to quickly and accurately retrieve data related to the target display task from the energy consumption database, which may include various energy equipment real-time data, historical data, statistical data, etc.; algorithm matching calculation means that according to the specific needs of the target display task, the system will select the corresponding algorithm for matching calculation, and the distributed engine will use the selected algorithm to process and analyze the retrieved data. The calculation process may include data cleaning, data conversion, feature extraction, model training, predictive analysis, etc.; finally, based on the data retrieval call and algorithm matching results of the target task, select the appropriate report template to generate an energy consumption report and perform a visual display, including energy usage, energy consumption trends, energy consumption comparative analysis and other information, including a variety of display forms, such as tables, charts, graphics, etc., that is, the energy consumption report is presented to the user in an intuitive and easy-to-understand form, which improves data processing efficiency and system performance, and provides users with an intuitive energy usage information display and analysis tool.

[0046] In a possible implementation, a method for intelligent analysis and display of enterprise energy consumption data also includes step S710, decomposing the enterprise energy consumption data, determining a primary data system and a secondary data system, and establishing mapping and synchronization constraints between the primary data system and the secondary data system. The master data system refers to the core business entity data shared across departments, businesses, and systems in an enterprise, usually including data that is critical to energy management and decision-making analysis, such as energy consumption data of key equipment, total energy consumption of major production lines, energy usage trends, etc. The auxiliary data system refers to data that is associated with the master data but is not necessarily globally unique or stable, and may include specific equipment operating status, data on the impact of environmental factors on energy consumption, temporary energy usage records, equipment attributes and annotation information, etc. The mapping relationship refers to the association rules between the master data system and the auxiliary data system. The enterprise needs to clarify which auxiliary data is a supplement or explanation of the master data, and how they are associated. For example, the total energy consumption of a production line (master data) may be the sum of the energy consumption of each device on the line (auxiliary data), or it may be affected by environmental factors such as ambient temperature and humidity (auxiliary data). Synchronization constraints refer to the rules and requirements for ensuring data consistency and synchronization between the master data system and the auxiliary data system, including clarifying the frequency of auxiliary data updates to ensure synchronization with the master data; determining the specific method of data synchronization; performing data verification during data synchronization to ensure data accuracy and consistency, etc.

[0047] Step S720, the main data system is used as the task execution target, and the auxiliary data system responds synchronously. The main data system is used as the main target for task execution, that is, when performing energy management, decision analysis or optimization and improvement, it is mainly based on the data in the main data system. The auxiliary data system plays an auxiliary and supporting role in the task execution process. When the main data system changes or more detailed information is required, the auxiliary data system can respond synchronously and provide corresponding data support. For example, when analyzing the cause of abnormal energy consumption of a production line, it may be necessary to refer to the real-time energy consumption data (auxiliary data) of each device on the line to assist in judgment.

[0048] In a possible implementation, a method for intelligent analysis and display of enterprise energy consumption data further includes step S730, generating a task flow based on the target display task, wherein the task flow includes multiple flow nodes. According to the target display task, multiple flow nodes are designed to ensure that the target display task can be completed efficiently and accurately, and each node represents an independent and manageable task unit, that is, a task flow is generated, which describes the entire process from the start to the end of the task, including all necessary activities, decision points, resource allocation and interaction links, such as the task start-up phase, planning phase, execution phase, testing phase, task display phase, etc.

[0049] Step S740, tracking user operation information, and performing operation guidance and correction management based on the task process. Through user behavior tracking system, log records, front-end embedding, etc., various operation information of users in the process of executing task processes is collected, including user click, browse, input, submit, exit and other behavior data, as well as device information, network environment and other auxiliary data, and the collected operation information is deeply analyzed. Then, based on the user's behavior data and analysis results, personalized operation guidance is provided to users to help users complete tasks faster and more accurately. For example, the steps, requirements and precautions of the task process are shown to users through interface prompts, guide pages, help documents, video tutorials, etc. In the process of users performing tasks, the operation results and status information are fed back in real time to help users understand the current progress and possible problems. For example, the operation results and guidance for subsequent steps are shown to users through progress bars, prompt boxes, message push, etc. Through data analysis and user feedback, we identify deviations or errors that may occur when users perform tasks, including problems caused by operational errors, misunderstandings, system failures, etc. For minor problems or deviations, we guide users to correct them through interface prompts or warning messages. For operations that may lead to serious consequences, we prevent problems by restricting or blocking user operations. For task steps that are difficult for users to understand or perform, we provide detailed guidance and help information to assist users in completing tasks smoothly, thereby optimizing task processes and operation guidance strategies, and improving user experience and satisfaction.

[0050] In the above, refer to Figure 1 A method for intelligent analysis and display of enterprise energy consumption data according to an embodiment of the present invention is described in detail. Next, a system for intelligent analysis and display of enterprise energy consumption data according to an embodiment of the present invention will be described, the system comprising:

[0051] The device tree construction module is used to determine the equipment installation information based on the installed scale of the enterprise's electrical equipment, extract entities and relationships based on the equipment subject, attributes, and indicators, and construct the device tree, where the indicator class has an algorithm matrix.

[0052] The template library construction module is used to construct a template library, wherein the template library includes a frame layout template sub-library and a display template sub-library of the frame internal partitions.

[0053] The platform cloud test optimization module is used to build a data visualization analysis platform and perform platform cloud test optimization based on the device tree and the template library, and the visualization analysis platform includes a built-in processor.

[0054] The enterprise energy consumption data receiving module is used to receive the enterprise energy consumption data from the energy consumption database, and to perform internal data logicization and distribution update on the visual analysis platform.

[0055] The task interface activation module is used to read the target display task and identify the user authority, and activate the task interface, wherein the task interface has a non-authorized locked partition.

[0056] The energy consumption report generation module is used to trigger the distributed engine based on the task interface, perform data retrieval and algorithm matching calculations on the target display task, generate an energy consumption report and perform visual display.

[0057] In a possible implementation, an intelligent analysis and display system for enterprise energy consumption data also includes: an equipment distribution topology determination module, used to determine the equipment distribution topology based on the installed capacity, the equipment distribution topology is based on equipment connection relationship and subsidiary relationship connection; a first relationship extraction module, used to traverse the equipment installation information to extract the first relationship based on the attribute entity; a second relationship extraction module, used to traverse the equipment installation information to extract the second relationship based on the indicator entity; and an equipment tree determination module, used to determine the equipment tree based on the equipment distribution topology, the first relationship and the second relationship.

[0058] In one possible implementation, an intelligent analysis and display system for enterprise energy consumption data also includes: an architecture system determination module, which is used to determine the first structure layer based on the device distribution topology, construct the second structure layer based on the attribute entity, and the third structure layer based on the indicator entity, to determine the architecture system, wherein the architecture system is scalable; a task matrix determination module, which is used to read the data analysis tasks in a predetermined time zone and determine the task matrix, wherein each matrix node meets the preset frequency; an algorithm matrix construction module, which is used to traverse the task matrix and construct a mapped algorithm matrix; a distribution reconstruction and semantic disambiguation module, which is used to perform distribution reconstruction and semantic disambiguation based on the architecture system and the algorithm matrix to determine the device tree.

[0059] In one possible implementation, an intelligent analysis and display system for enterprise energy consumption data also includes: a logic rule determination module, which is used to traverse the algorithm matrix and determine the logic rules based on the task matrix, and the logic rules include calling logic and operation logic; a built-in processor determination module, which is used to determine the built-in processor based on the algorithm matrix and the logic rules, and establish connectivity between the built-in processor and the platform module.

[0060] In a possible implementation, an intelligent analysis and display system for enterprise energy consumption data also includes: an expectation matrix determination module, which is used to determine the test dimension, and determine the expectation matrix based on the dimensional distribution index based on the test dimension, wherein the test dimension at least includes function, layout and compatibility; a test plan generation module, which is used to generate a test plan and perform cloud test deployment based on the test dimension, wherein the test plan includes multiple parallel plans; an automatic audit rule generation module, which is used to generate automatic audit rules based on the expectation matrix; and a cloud test optimization analysis module, which is used to perform cloud test optimization analysis on the visualization analysis platform based on the test plan and the automatic audit rules.

[0061] In one possible implementation, an intelligent analysis and display system for enterprise energy consumption data also includes: a platform optimization target positioning module, which is used to obtain a parallel test sequence and locate the platform optimization target, wherein the positioning determination method is based on a preset pass ratio of the parallel test frequency; an optimization space construction module, which is used to traverse the platform optimization target and build an optimization space based on the target degree of freedom, wherein the target degree of freedom includes self-degree of freedom and collaborative degree of freedom; a target locking and iterative optimization module, which is used to configure a random attention mechanism based on the optimization space to perform optimization target locking and iterative optimization, select the global optimal strategy as the optimization construction strategy, and debug the data visualization analysis platform; wherein the random attention mechanism is based on the random optimization target number and random optimization step size of the iteration layer, and the optimal adjustment method of the iteration layer is taboo locked, and the preset number of iteration layers is used as the taboo unlocking method.

[0062] In one possible implementation, an intelligent analysis and display system for enterprise energy consumption data also includes: a main data system and an auxiliary data system determination module, which is used to decompose the enterprise energy consumption data, determine the main data system and the auxiliary data system, and establish the mapping and synchronization constraints between the main data system and the auxiliary data system; a data system execution module, which is used to use the main data system as the task execution target, and the auxiliary data system responds synchronously.

[0063] In one possible implementation, an intelligent analysis and display system for enterprise energy consumption data also includes: a task process generation module, which is used to generate a task process based on the target display task, and the task process includes multiple process nodes; a user operation information tracking module, which is used to track user operation information and perform operation guidance and correction management based on the task process.

[0064] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for intelligent analysis and display of enterprise energy consumption data, characterized in that: The method comprises: Based on the installed capacity of the enterprise's electrical equipment, determine the equipment installation information, perform entity and relationship extraction based on the equipment subject, attributes, and indicators, and build a device tree, where the indicator class has an algorithm matrix; Constructing a template library, wherein the template library includes a frame layout template sub-library and a display template sub-library of the frame internal partitions; Based on the device tree and the template library, a data visualization analysis platform is built and platform cloud test optimization is performed, wherein the visualization analysis platform includes a built-in processor; The energy consumption database receives the energy consumption data of the enterprise and performs internal data logicization and distribution update on the visual analysis platform; Read the target display task and identify the user authority, and activate the task interface, wherein the task interface has a locked partition without authority; Based on the task interface, the distributed engine is triggered to perform data retrieval and algorithm matching calculations on the target display task, generate an energy consumption report and perform visual display.

2. The method for intelligent analysis and display of enterprise energy consumption data according to claim 1, characterized in that: The device tree construction includes: Determine a device distribution topology based on the installed capacity, wherein the device distribution topology is based on device connection relationships and affiliation relationships; Based on the attribute entity, traverse the equipment installation information to extract the first relationship; Based on the indicator entity, traverse the equipment installation information to extract the second relationship; The device tree is determined based on the device distribution topology, the first relationship, and the second relationship.

3. The method for intelligent analysis and display of enterprise energy consumption data according to claim 2, characterized in that: Determining the device tree based on the device distribution topology, the first relationship, and the second relationship includes: Determine a first structural layer based on the device distribution topology, construct a second structural layer based on attribute entities, and a third structural layer based on indicator entities to determine an architecture system, wherein the architecture system is scalable; Read the data analysis tasks in the predetermined time zone and determine the task matrix, wherein each matrix node meets the preset frequency; Traversing the task matrix to construct a mapping algorithm matrix; Based on the architecture system and the algorithm matrix, distribution reconstruction and semantic disambiguation are performed to determine the device tree.

4. The method for intelligent analysis and display of enterprise energy consumption data according to claim 3, characterized in that: The visual analysis platform includes a built-in processor, including: Traversing the algorithm matrix, determining a logic rule based on the task matrix, wherein the logic rule includes a call logic and an operation logic; Based on the algorithm matrix and the logic rules, a built-in processor is determined, and communication between the built-in processor and the platform module is established.

5. The method for intelligent analysis and display of enterprise energy consumption data according to claim 1, characterized in that: The platform cloud test optimization includes: Determine a test dimension, and determine an expectation matrix based on a dimensional distribution indicator based on the test dimension, wherein the test dimension at least includes function, layout, and compatibility; Based on the test dimension, a test plan is generated and cloud test deployment is performed, wherein the test plan includes multiple parallel plans; Based on the expectation matrix, generating automatic audit rules; Based on the test plan and the automatic review rules, a cloud test optimization analysis is performed on the visual analysis platform.

6. The method for intelligent analysis and display of enterprise energy consumption data according to claim 5, characterized in that: Performing cloud test optimization analysis on the visual analysis platform includes: Obtain a parallel test sequence and locate the optimization target of the positioning platform, wherein the positioning determination method is a preset pass ratio based on the parallel test frequency; Traversing the platform optimization objectives, and building an optimization space based on the target degrees of freedom, wherein the target degrees of freedom include self-degrees of freedom and collaborative degrees of freedom; Based on the optimization space, a random attention mechanism is configured to perform optimization target locking and iterative optimization, a global optimal strategy is selected as an optimization construction strategy, and the data visualization analysis platform is debugged; Among them, the random attention mechanism is based on the random optimization target number and random optimization step size of the iteration layer, the optimal adjustment method of the iteration layer is taboo locked, and the preset number of iteration layers is used as the taboo unlocking method.

7. The method for intelligent analysis and display of enterprise energy consumption data according to claim 1, characterized in that: The method further comprises: Decompose the enterprise energy consumption data, determine the main data system and the auxiliary data system, and establish the mapping and synchronization constraints between the main data system and the auxiliary data system; The primary data system is used as a task execution target, and the secondary data system responds synchronously.

8. The method according to claim 1, characterized in that The method further comprises: Based on the target display task, a task flow is generated, wherein the task flow includes a plurality of flow nodes; Track user operation information, and provide operation guidance and correction management based on the task flow.

9. An intelligent analysis and display system for enterprise energy consumption data, characterized in that: The system is used to implement the method for intelligent analysis and display of enterprise energy consumption data according to any one of claims 1 to 8, and the system includes: The device tree construction module is used to determine the equipment installation information based on the installed capacity of the enterprise's electrical equipment, extract entities and relationships based on the equipment subject, attributes, and indicators, and construct the device tree, where the indicator class has an algorithm matrix; The template library construction module is used to construct a template library, wherein the template library includes a frame layout template sub-library and a display template sub-library of the frame internal partition; A platform cloud test optimization module, used to build a data visualization analysis platform and perform platform cloud test optimization based on the device tree and the template library, wherein the visualization analysis platform includes a built-in processor; The enterprise energy consumption data receiving module is used to receive the enterprise energy consumption data from the energy consumption database, and to perform internal data logicization and distribution update on the visual analysis platform; A task interface activation module, used to read the target display task and identify the user authority, and activate the task interface, wherein the task interface has a locked partition without authority; The energy consumption report generation module is used to trigger the distributed engine based on the task interface, perform data retrieval and algorithm matching calculations on the target display task, generate an energy consumption report and perform visual display.

10. The intelligent analysis and display system for enterprise energy consumption data according to claim 9, characterized in that: The system comprises: A device distribution topology determination module, used to determine a device distribution topology based on the installed capacity, wherein the device distribution topology is based on a device connection relationship and a subsidiary relationship connection; A first relationship extraction module, configured to traverse the equipment installation information to extract a first relationship based on an attribute entity; A second relationship extraction module, configured to traverse the equipment installation information to extract a second relationship based on the indicator entity; A device tree determination module is used to determine the device tree based on the device distribution topology, the first relationship, and the second relationship.

11. The intelligent analysis and display system for enterprise energy consumption data according to claim 10, characterized in that: The system comprises: An architecture system determination module, used to determine a first structure layer based on the device distribution topology, construct a second structure layer based on attribute entities, and a third structure layer based on indicator entities, to determine an architecture system, wherein the architecture system is scalable; A task matrix determination module is used to read the data analysis tasks in a predetermined time zone and determine a task matrix, wherein each matrix node meets a preset frequency; An algorithm matrix building module, used for traversing the task matrix and building a mapped algorithm matrix; The distribution reconstruction and semantic disambiguation module is used to perform distribution reconstruction and semantic disambiguation based on the architecture system and the algorithm matrix to determine the device tree.

12. The intelligent analysis and display system for enterprise energy consumption data according to claim 11, characterized in that: The system comprises: A logic rule determination module, used for traversing the algorithm matrix and determining logic rules based on the task matrix, wherein the logic rules include calling logic and operation logic; The built-in processor determination module is used to determine the built-in processor based on the algorithm matrix and the logic rules, and establish communication between the built-in processor and the platform module.

13. The intelligent analysis and display system for enterprise energy consumption data according to claim 9, characterized in that: The system comprises: An expected matrix determination module, used to determine a test dimension, and determine an expected matrix based on a dimensional distribution index based on the test dimension, wherein the test dimension at least includes function, layout and compatibility; A test plan generation module, used to generate a test plan and perform cloud test deployment based on the test dimension, wherein the test plan includes multiple parallel plans; An automatic audit rule generation module, used to generate automatic audit rules based on the expectation matrix; The cloud test optimization analysis module is used to perform cloud test optimization analysis on the visual analysis platform based on the test plan and the automatic review rules.

14. The intelligent analysis and display system for enterprise energy consumption data according to claim 13, characterized in that: The system comprises: A platform optimization target positioning module is used to obtain a parallel test sequence and locate the platform optimization target, wherein the positioning determination method is a preset pass ratio based on the parallel test frequency; An optimization space building module, used for traversing the platform optimization objectives and building an optimization space based on target degrees of freedom, wherein the target degrees of freedom include self-degrees of freedom and collaborative degrees of freedom; The target locking and iterative optimization module is used to configure the random attention mechanism to perform optimization target locking and iterative optimization based on the optimization space, select the global optimal strategy as the optimization construction strategy, and debug the data visualization analysis platform; wherein the random attention mechanism is based on the random optimization target number and random optimization step size of the iteration layer, the optimal adjustment method of the iteration layer is taboo locked, and the preset number of iteration layers is used as the taboo unlocking method.

15. The intelligent analysis and display system for enterprise energy consumption data according to claim 9, characterized in that: The system comprises: A main data system and auxiliary data system determination module is used to decompose the enterprise energy consumption data, determine the main data system and the auxiliary data system, and establish the mapping and synchronization constraints between the main data system and the auxiliary data system; The data system execution module is used to take the main data system as the task execution target, and the auxiliary data system responds synchronously.

16. The intelligent analysis and display system for enterprise energy consumption data according to claim 9, characterized in that: The system comprises: A task flow generation module, used to generate a task flow based on the target display task, wherein the task flow includes multiple flow nodes; The user operation information tracking module is used to track user operation information and perform operation guidance and correction management based on the task flow.

Images