Organizational energy management system, method, device and storage medium

Abstract

The present application provides an organizational energy management system, method, device and storage medium, wherein the method includes: an overall visualization module for obtaining a remote sensing image of the entire area to be managed, using an image classification model to mark various types of sub-areas in the remote sensing image, and displaying sub-area distribution information; an energy index determination module for defining the energy index and threshold value to be monitored in the sub-area; a sub-area visualization module for selecting the sub-area to be visualized, slicing and extracting the remote sensing image corresponding to the sub-area from the whole, and visualizing the statistical results of the energy index in the sub-area; a data analysis module for inferring the trend events of the corresponding sub-area based on the historical values ​​in the statistical results using a time series analysis model, and generating a detection report corresponding to the trend event; a detection alarm module for prompting when the energy index is not within the threshold range. The present application can organize energy monitoring from two different angles: the overall or local area.

Description

Technical Field

[0001] The present invention relates to the technical field of data monitoring management, and in particular to an organizational energy management system, method, device and storage medium. Background Art

[0002] Organizing energy management in the ecological environment system during the implementation of the project can make great contributions to comprehensive management, overall protection of mountains, rivers, forests, fields, lakes and grasslands, and optimization of the national space pattern.

[0003] Among the related technologies, most of the existing organizational energy management systems have relatively simple products, mainly focusing on automatic measurement of energy consumption in organizational management, report statistics and simple year-on-year and month-on-month analysis, and can often only analyze from the dimension of energy consumption, unable to dig deep or infer and predict future trend events; in addition, in various types of terrain areas, the organizational energy that needs to be monitored has great differences. For example, in water areas, the focus can be on monitoring water volume, water quality, chemical energy, etc., and the existing organizational energy management systems do not take into account such differences between different regions.

[0004] Based on the above analysis of the development status of this technology field, the existing technology lacks solutions for distinguishing organizational energy monitoring in different areas and mining trend events based on historical data. Summary of the invention

[0005] The object of the present invention is to provide an organizational energy management system, method, device and storage medium, aiming to solve the above-mentioned problems in the prior art.

[0006] According to a first aspect of an embodiment of the present invention, there is provided an organization energy management system, comprising:

[0007] The overall visualization module is used to obtain the remote sensing image of the entire area to be managed, use the image classification model to mark various types of sub-areas in the remote sensing image, and display the sub-area distribution information;

[0008] Energy indicator determination module, used to define the energy indicators and thresholds that need to be monitored in the sub-areas;

[0009] The sub-region visualization module is used to select the sub-region that needs to be visualized, extract the remote sensing image corresponding to the sub-region from the whole slice, and visualize the statistical results of the energy indicators in the sub-region;

[0010] A data analysis module is used to infer the trend events of the corresponding sub-areas based on the historical values ​​in the statistical results using a time series analysis model and generate a detection report corresponding to the trend events;

[0011] The detection alarm module is used to prompt when the energy index is not within the threshold range.

[0012] According to a second aspect of an embodiment of the present invention, there is provided an organizational energy management method, comprising:

[0013] The overall visualization module is used to obtain the remote sensing image of the entire area to be managed, and the image classification model is used to mark various types of sub-areas in the remote sensing image to display the sub-area distribution information;

[0014] The energy indicator determination module defines the energy indicators and thresholds that need to be monitored in the sub-area;

[0015] The sub-region to be visualized is selected through the sub-region visualization module, and the remote sensing image corresponding to the sub-region is extracted from the whole slice to visualize the statistical results of the energy indicators in the sub-region;

[0016] Through the data analysis module, based on the historical values ​​in the statistical results, the time series analysis model is used to infer the trend events of the corresponding sub-areas and generate a detection report corresponding to the trend events;

[0017] The detection alarm module will give a prompt when the energy index is not within the threshold range.

[0018] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the organizational energy management method provided in the second aspect of the present disclosure are implemented.

[0019] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a program for implementing information transmission is stored, and when the program is executed by a processor, the steps of the organizational energy management method provided in the second aspect of the present disclosure are implemented.

[0020] The technical solution provided by the embodiment of the present invention includes the following beneficial effects: the system is equipped with visualization-related modules and data analysis-related modules, and can monitor organizational energy from two different perspectives: the overall or local area, so as to take into account the differences between different sub-areas. The system has diversified visualization display methods and can mine trend events based on historical data. Overall, it is a fully functional organizational energy management system.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, 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 this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 is a schematic diagram of an organizational energy management system according to an embodiment of the present invention;

[0024] Figure 2 is a schematic diagram of the overall distribution of the system of an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of a water body area in a sub-region of an embodiment of the present invention;

[0026] Figure 4 1 is a schematic diagram of a statistical result of a water area according to an embodiment of the present invention;

[0027] Figure 5 is a schematic diagram of a second statistical result of a water body area according to an embodiment of the present invention;

[0028] Figure 6 is a flow chart of an organizational energy management method according to an embodiment of the present invention;

[0029] Figure 7 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0031] System Example

[0032] According to an embodiment of the present invention, an organizational energy management system is provided. Figure 1 is a schematic diagram of an organizational energy management system according to an embodiment of the present invention. Figure 1 As shown, the organizational energy management according to the embodiment of the present invention specifically includes:

[0033] The overall visualization module 10 is used to obtain the remote sensing image of the entire area to be managed, use the image classification model to mark various types of sub-areas in the remote sensing image, and display the sub-area distribution information, specifically including:

[0034] The remote sensing image import module is used to obtain the remote sensing image data source, correct, crop and convert the remote sensing image data source in turn to obtain the pre-processed data source, and import the pre-processed data source into the GIS geographic information software to obtain the remote sensing image of the entire area to be managed;

[0035] Common remote sensing image data sources include Landsat, Sentinel, MODIS, WorldView, etc. In the embodiment of the present invention, the correction includes radiation correction to eliminate the influence of atmospheric effects, solar altitude angle, terrain and other factors, and geometric correction to convert the pixel coordinates of the remote sensing image data source into geographic coordinates; the image is cropped and format converted through GIS software or programming tools;

[0036] Since the actual situation of the remote sensing images in the entire area to be managed will change over time or development, the organization's energy management system needs to set a time interval, and after each time interval, the remote sensing images that conform to the actual situation need to be re-imported;

[0037] Model setup module for training convolutional neural networks as image classification models;

[0038] The model setting module is specifically used to:

[0039] A convolutional neural network is trained using a remote sensing training set including annotated labels. The convolutional neural network is suitable for processing high-resolution remote sensing images and can capture complex geographic features and spatial relationships. The annotated labels are the types of sub-regions. During the verification process, each pixel in the remote sensing verification set is divided into different types, and the cross entropy loss is used as the loss function of the convolutional neural network.

[0040] In the embodiment of the present invention, the convolutional neural network includes an input layer for receiving an image, an encoding layer including multiple convolutions to extract features, a decoding layer for restoring the spatial resolution of the image, and an output layer for converting the features into a probability distribution of each pixel category, and for each pixel, the category with the highest probability is selected as the final prediction result; the parameters in the convolutional neural network model are not limited in detail;

[0041] Preferably, in daily use, the convolutional neural network trained in the model setting module is selected to re-divide the sub-areas. When the system needs to be updated, the model setting module is called to retrain the convolutional neural network. In each training process, the training set needs to be updated to the most recent remote sensing image.

[0042] The distribution display module is used to use the image classification model to divide the entire remote sensing image into working areas, water areas, green protection areas and desert areas as sub-areas of each type, and to calculate and display the distribution area ratio of each sub-area;

[0043] The working area refers to the area used for industrial production, agricultural activities or other human economic activities, and the interior of the area is usually artificially transformed; the water area is composed of lakes, rivers, reservoirs, and wetlands; the green protection area refers to the characteristic area for protecting natural resources, maintaining ecological balance, and ensuring species diversity; the desert area refers to the area with scarce precipitation and arid climate; the above four types of areas can meet the basic needs of the organization's energy management division. Preferably, each sub-area can be divided into lower-level areas according to actual conditions. For example, the industrial area can be further divided into agricultural areas, industrial areas, etc.;

[0044] It should be noted that the sub-work areas divided by the image classification model are not necessarily regular. There may be irregular interspersed phenomena between the sub-areas. For example, water areas may exist around or in a large work area, but each pixel in the image can only belong to the same type.

[0045] The entire area to be managed in the embodiment of the present invention is the Wuliangsuhai Basin. Figure 2 Schematic diagram of the overall distribution of the system of the embodiment of the present invention, such as Figure 2 As shown, the interface diagram of the overall remote sensing image in the system is displayed. At this time, the image area describes the overall geographical situation of the Wulansuhai Basin, and the distribution of different sub-areas is analyzed on the interface.

[0046] An energy index determination module 12, used to define energy indexes and thresholds to be monitored in the sub-areas;

[0047] Specifically include:

[0048] The energy index definition module is used to configure the energy indexes to be monitored in the sub-area according to the correlation between the energy indexes and the sub-area, or search the energy indexes from the index library to add to the configuration;

[0049] The system maintains a database of all energy indicators. All energy indicators in the database can be selected as energy indicators to be monitored, that is, there are devices or third-party data institutions that can obtain data sources;

[0050] The degree of correlation between each energy indicator and the sub-region is obtained by calculating the Pearson correlation coefficient method to evaluate the correlation between each energy indicator and the events or economic indicators occurring in the sub-region. When it is necessary to configure the corresponding energy indicator for the sub-region, the system can automatically generate a recommendation list based on the correlation score. Users can directly import the recommendation list as the energy indicator to be monitored, or manually select some energy indicators in the inference list, or search for the required energy indicators from the database maintained by the system for customized configuration.

[0051] The threshold definition module is used to set the corresponding threshold for each energy indicator and use the Bayesian method to adaptively adjust the threshold as the seasonal cycle changes. The thresholds of the same energy indicator in different sub-areas in the same cycle are different.

[0052] For example, for a certain energy consumption index, the importance of this energy index is different between the working area and the green protection area. The green protection area has a higher demand for energy consumption monitoring because excessive energy consumption may cause irreversible impacts on the ecosystem. Therefore, the threshold of this energy consumption index in the working area is higher, and the threshold of this energy consumption index in the green protection area is lower, which means that when the energy consumption level reaches a lower value, the system should give timely feedback;

[0053] The Bayesian method can dynamically adjust the threshold according to the new observation data to make it more in line with the current actual situation. The prior distribution is an initial estimate of the threshold based on historical data or expert experience. The likelihood function describes the probability of observing the current data given the threshold. The posterior distribution in the Bayesian method is the result of combining the prior distribution and the likelihood function. The threshold is updated using formula 1:

[0054]

[0055] Where P(θ|D) represents the posterior distribution, that is, the estimated result of the threshold θ after observing the current data D; P(θ) represents the prior distribution, which represents the estimated result of the threshold θ when no new data is observed; P(D|θ) represents the likelihood function, and P(D) represents the total probability of observing data D, which is usually calculated by integration;

[0056] In addition, the threshold is affected by seasonal changes, so the threshold results for the same energy consumption indicator in different seasons are also different, that is, the prior distribution only considers the situation in the same season.

[0057] The sub-region visualization module 14 is used to select the sub-region to be visualized, extract the remote sensing image corresponding to the sub-region from the whole slice, and visualize the statistical results of the energy index in the sub-region, specifically including:

[0058] The real-time statistics module is used to perform real-time statistics on the data monitored by the current energy indicators, and the results of the real-time statistics are in the form of tables or graphs. In the embodiment of the present invention, multiple statistical forms are supported, such as the mean, median, and mode that can reflect the central trend index, and the variance, standard deviation, and range that can reflect the degree of dispersion. Preferably, the organizational energy system can add diversified display methods such as video and voice according to development needs.

[0059] The statistics display module is used to display the results of real-time statistics, or obtain the statistical results of historical values ​​through a drop-down menu.

[0060] Taking the water area as an example, Figure 3 is a schematic diagram of a water body area in a sub-region of an embodiment of the present invention, such as Figure 3 As shown, when the sub-region is selected as a water body area, the remote sensing image of the water body area is extracted by slicing from the whole;

[0061] Figure 4 Schematic diagram of the statistical result of the water area of ​​the embodiment of the present invention. Figure 4 As shown, some statistical results of water area are shown; Figure 5 is a schematic diagram of the second statistical result of the water area of ​​an embodiment of the present invention, such as Figure 5 As shown, some statistical results of the water area are displayed.

[0062] The data analysis module 16 is used to infer the trend events of the corresponding sub-areas based on the historical values ​​in the statistical results using the time series analysis model and generate a detection report corresponding to the trend events, specifically including:

[0063] The data inference module is used to normalize and label the energy indicators corresponding to the sub-regions to obtain an inference data set, and input the inference data set into a long short-term memory network with a pre-trained attention mechanism, namely, an LSTM model. The attention mechanism is used to select energy features as inference features, output the predicted values ​​of each inference feature through the long short-term memory network, and infer trend events based on the predicted values;

[0064] For a certain sub-area, not all energy indicators can assist in reasoning about trend events, so the attention mechanism only filters some energy indicators as reasoning features; data analysis tools are used to identify whether the predicted value is abnormal or exceeds the threshold to determine the trend event.

[0065] A report generation module, used to generate detection reports corresponding to trend events using structured templates;

[0066] The format of the test report is customized in the structured template, for example, it needs to include a title, content, etc.

[0067] The detection alarm module 18 is used to give a prompt when the energy index is not within the threshold range, specifically for:

[0068] The prompt is marked on the remote sensing graphic interface of the corresponding sub-area, and a prompt voice is issued through a buzzer alarm.

[0069] To sum up, in response to the existing problems, this invention has an organizational energy management system. The system is equipped with visualization-related modules and data analysis-related modules, and can monitor organizational energy from two different perspectives: overall or local area. In the local area mode, the differences between different sub-areas are taken into account, and the user can customize the organizational energy that needs to be monitored in each sub-area according to actual needs, and taking into account the different demand emphases of the same organizational energy in different sub-areas, the corresponding thresholds are set, which can more accurately grasp the actual situation. The system has diversified visualization display methods and supports display forms such as pictures and texts. It can also mine trend events based on historical data. Overall, it is a fully functional organizational energy management system.

[0070] Method Embodiment

[0071] According to an embodiment of the present invention, a method for organizing energy management is provided, which is used to organize an energy management system. Figure 6 is a flow chart of the organizational energy management method according to an embodiment of the present invention. Figure 6 As shown, the organizational energy management method according to an embodiment of the present invention specifically includes:

[0072] In step S610, the remote sensing image of the entire area to be managed is obtained through the overall visualization module, and each type of sub-area is marked in the remote sensing image using the image classification model to display the sub-area distribution information, including:

[0073] The remote sensing image data source is obtained through the remote sensing image import module, and the remote sensing image data source is corrected, cropped and format converted in sequence to obtain the pre-processed data source, and the pre-processed data source is imported into the GIS geographic information software to obtain the remote sensing image of the entire area to be managed;

[0074] Train a convolutional neural network as an image classification model through the Model Setup module;

[0075] The model setting module is specifically used to:

[0076] A convolutional neural network is trained using a remote sensing training set including annotated labels, where the annotated labels are the types of sub-regions. During the verification process, each pixel in the remote sensing verification set is divided into different types, and the cross entropy loss is used as the loss function of the convolutional neural network.

[0077] The distribution display module uses an image classification model to divide the overall remote sensing image into working areas, water areas, green protection areas and desert areas as sub-areas of each type, and the distribution area proportion of each sub-area is calculated and displayed.

[0078] In step S620, the energy index and thresholds to be monitored in the sub-area are defined by the energy index determination module, including:

[0079] Through the energy indicator definition module, according to the correlation between the energy indicator and the sub-area, configure the energy indicators that need to be monitored in the sub-area, or search for energy indicators from the indicator library and add them to the configuration;

[0080] The threshold definition module is used to set a corresponding threshold for each energy indicator, and the threshold is adaptively adjusted using the Bayesian method as the seasonal cycle changes. The thresholds of the same energy indicator in different sub-areas within the same cycle are different.

[0081] In step S630, the sub-region to be visualized is selected through the sub-region visualization module, and the remote sensing image corresponding to the sub-region is extracted from the whole slice, and the statistical results of the energy index in the sub-region are visualized, which specifically includes:

[0082] The real-time statistics module is used to conduct real-time statistics on the data monitored by the current energy indicators, and the results of the real-time statistics are in the form of tables or graphs;

[0083] The real-time statistical results are displayed through the statistical display module, or the statistical results of historical values ​​are obtained through the drop-down menu.

[0084] In step S640, the data analysis module uses the time series analysis model to infer the trend events of the corresponding sub-area based on the historical values ​​in the statistical results, and generates a detection report corresponding to the trend events, which specifically includes:

[0085] The energy indicators corresponding to the sub-regions are normalized and labeled through the data inference module to obtain an inference data set, which is then input into a long short-term memory network with a pre-trained attention mechanism. The attention mechanism is used to select energy features as inference features, and the predicted values ​​of each inference feature are output through the long short-term memory network. Trend events are inferred based on the predicted values.

[0086] The report generation module uses structured templates to generate detection reports corresponding to trend events.

[0087] In step S650, a prompt is given by the detection alarm module when the energy index is not within the threshold range, specifically including: marking the prompt on the remote sensing graphic interface of the corresponding sub-area, and issuing a prompt voice through a buzzer alarm.

[0088] To sum up, in response to the existing problems, the organizational energy management method invented this time is used in the corresponding organizational energy management system. The system sets up visualization-related modules and data analysis-related modules, and can monitor organizational energy from two different angles: overall or local area. In the local area mode, the differences between different sub-areas are taken into account. The user can customize the organizational energy that needs to be monitored in each sub-area according to actual needs, and taking into account the different demand emphases of the same organizational energy in different sub-areas, the corresponding thresholds are set, which can more accurately grasp the actual situation. The system has diversified visualization display methods and supports display forms such as pictures and texts. It can also mine trend events based on historical data. Overall, it is a fully functional organizational energy management system.

[0089] Electronic device embodiment

[0090] Figure 7 7 is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device 700 may include at least one processor 710 and a memory 720. The processor 710 may execute instructions stored in the memory 720. The processor 710 is connected to the memory 720 through a data bus. In addition to the memory 720, the processor 710 may also be connected to an input device 730, an output device 740, and a communication device 750 through a data bus.

[0091] The processor 710 may be any conventional processor, such as a commercially available CPU. The processor may also include a graphics processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable Gate Array, FPGA), a system on chip (System on Chip, SOC), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) or a combination thereof.

[0092] The memory 720 may be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0093] In the embodiment of the present disclosure, executable instructions are stored in the memory 720, and the processor 710 can read the executable instructions from the memory 720 and execute the instructions to implement all or part of the steps of any of the organizational energy management methods in the above exemplary embodiments.

[0094] Computer Readable Storage Medium Embodiments

[0095] In addition to the above-mentioned methods and devices, the exemplary embodiments of the present disclosure may also be a computer program product or a computer-readable storage medium storing the computer program product, wherein the computer product includes computer program instructions that can be executed by a processor to implement all or part of the steps described in any of the organizational energy management methods in the above-mentioned exemplary embodiments.

[0096] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages ​​and scripting languages ​​(e.g., Python). The program code may be executed entirely on the user computing device, partially on the user computing device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0097] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of readable storage media include: a static random access memory (SRAM) with one or more wires electrically connected, an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk, or any suitable combination of the above.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An organizational energy management system, characterized in that: include: The overall visualization module is used to obtain the remote sensing image of the entire area to be managed, use the image classification model to mark various types of sub-areas in the remote sensing image, and display the distribution information of the sub-areas; An energy index determination module, used to define energy indexes and thresholds required to be monitored in the sub-area; A sub-region visualization module is used to select a sub-region to be visualized, extract a remote sensing image corresponding to the sub-region from the whole by slicing, and visualize the statistical results of the energy indicators in the sub-region; A data analysis module, configured to infer trend events of corresponding sub-regions using a time series analysis model based on historical values ​​in the statistical results, and generate a detection report corresponding to the trend events; The detection alarm module is used to give a prompt when the energy indicator is not within the threshold range.

2. The system according to claim 1, characterized in that The overall visualization module specifically includes: A remote sensing image import module is used to obtain a remote sensing image data source, correct, crop and convert the remote sensing image data source in sequence to obtain a pre-processed data source, and import the pre-processed data source into geographic information software to obtain a remote sensing image of the entire area to be managed; A model setting module, used for training a convolutional neural network as the image classification model; The distribution display module is used to use the image classification model to divide the overall remote sensing image into working area, water area, green protection area and desert area as sub-areas of each type, and to count and display the distribution area proportion of each sub-area.

3. The system according to claim 2, characterized in that The model setting module is specifically used for: The convolutional neural network is trained using a remote sensing training set including annotated labels, wherein the annotated labels are types of sub-regions, and during a verification process, each pixel in the remote sensing verification set is divided into different types, and a cross entropy loss is used as a loss function of the convolutional neural network.

4. The system according to claim 1, characterized in that The energy index determination module specifically includes: The energy index definition module is used to configure the energy indexes to be monitored in the sub-area according to the correlation between the energy indexes and the sub-area, or search the energy indexes from the index library to add to the configuration; The threshold definition module is used to set a corresponding threshold for each energy indicator, and adaptively adjust the threshold using the Bayesian method as the seasonal cycle changes, wherein the thresholds of the same energy indicator in different sub-areas within the same cycle are different.

5. The system according to claim 1, characterized in that The sub-area visualization module specifically includes: A real-time statistics module is used to perform real-time statistics on the data monitored by the current energy indicators, and to take the results of the real-time statistics in the form of tables or graphs; The statistical display module is used to display the real-time statistical results, or obtain the statistical results of the historical values ​​through a drop-down menu.

6. The system according to claim 1, characterized in that The data analysis module specifically includes: A data inference module is used to normalize and label the energy indicators corresponding to the sub-regions to obtain an inference data set, and input the inference data set into a long short-term memory network with a pre-trained attention mechanism, wherein the attention mechanism is used to select energy features as inference features, output the predicted values ​​of each inference feature through the long short-term memory network, and infer trend events based on the predicted values; The report generation module is used to generate a detection report corresponding to the trend event using a structured template.

7. The system according to claim 1, characterized in that The detection alarm module is specifically used for: The prompt is marked on the remote sensing graphic interface of the corresponding sub-area, and a prompt voice is issued through a buzzer alarm.

8. A method for organizational energy management, characterized in that: An organizational energy management system for use in any one of claims 1 to 7, comprising: Obtain the entire remote sensing image of the area to be managed through the overall visualization module, use the image classification model to mark various types of sub-areas in the remote sensing image, and display the distribution information of the sub-areas; The energy index and threshold value required to be monitored in the sub-area are defined by an energy index determination module; Select a sub-region to be visualized through a sub-region visualization module, extract a remote sensing image corresponding to the sub-region from the whole by slicing, and visualize the statistical results of the energy index in the sub-region; Based on the historical values ​​in the statistical results, the data analysis module uses a time series analysis model to infer the trend events of the corresponding sub-areas and generate a detection report corresponding to the trend events; The detection alarm module will give a prompt when the energy indicator is not within the threshold range.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the organizational energy management method as claimed in claim 8 when executed by the processor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by a processor, the steps of the organizational energy management method as described in claim 8 are implemented.

Images