Building-oriented energy consumption data correction method and device, electronic equipment and medium

Abstract

The embodiment of the invention provides a building-oriented energy consumption data correction method and device, electronic equipment and a medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring a business purpose type of each unit subspace in a target building; for each unit subspace in the target building, acquiring corresponding energy consumption acquisition data; performing energy consumption fluctuation event analysis on each business purpose type to obtain a compliant energy consumption event type; performing anomaly detection on the energy consumption acquisition data according to the compliance energy consumption event type to obtain abnormal energy consumption data; wherein the acquisition time period corresponding to the abnormal energy consumption data is an energy consumption abnormal time period; acquiring historical energy consumption data, and screening the historical energy consumption data according to the energy consumption abnormal time period to obtain reference energy consumption data. Wherein the historical energy consumption data is earlier than the abnormal energy consumption data; and correcting the abnormal energy consumption data based on the reference energy consumption data. According to the embodiment of the invention, the abnormal energy data in the building can be accurately corrected.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method and apparatus, electronic device and medium for energy consumption data correction in buildings. Background Technology

[0002] In office buildings, shopping malls, and other similar structures, energy consumption (such as electricity, cooling, and water) is typically statistically analyzed periodically to aid in energy management. However, during actual data collection, equipment malfunctions can lead to significant fluctuations or missing data in energy consumption figures. Current techniques often substitute outliers with average values ​​or rely on manual correction based on experience. However, these methods tend to be overly mechanical, lacking sufficient understanding and adaptation to anomalies, thus compromising the accuracy of corrected data.

[0003] Therefore, how to accurately correct abnormal energy consumption data within a building has become an urgent technical problem to be solved. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, electronic device, and medium for correcting energy consumption data in buildings, which aims to accurately correct abnormal energy data within buildings.

[0005] To achieve the above objectives, a first aspect of this application proposes a building-oriented energy consumption data correction method, the method comprising: Obtain the business purpose type of each unit subspace within the target building; For each of the unit subspaces in the target building, acquire the corresponding energy consumption data. Energy consumption fluctuation event analysis is performed on each of the aforementioned business use types to obtain compliant energy consumption event types; Anomaly detection is performed on the energy consumption data collected based on the compliant energy consumption event type to obtain abnormal energy consumption data; wherein, the collection period corresponding to the abnormal energy consumption data is the energy consumption abnormal period. Historical energy consumption data is acquired, and the historical energy consumption data is filtered according to the abnormal energy consumption period to obtain reference energy consumption data; wherein the historical energy consumption data is earlier than the abnormal energy consumption data; The abnormal energy consumption data is corrected based on the reference energy consumption data.

[0006] In some embodiments, the step of performing anomaly detection on the energy consumption collection data according to the compliant energy consumption event type to obtain abnormal energy consumption data includes: Perform time period feature analysis on the current data collection period to obtain the current time period features; Based on the characteristics of the current time period, a homogeneous collection time period is determined from multiple historical collection time periods; The energy consumption data collected during the current collection period is compared with the historical energy consumption data collected during the same collection period to obtain energy consumption deviation data; If the energy consumption deviation data meets the preset deviation anomaly conditions, then the service event corresponding to the unit subspace in the current collection period is obtained; Based on the compliant energy consumption event types, the energy consumption fluctuation compliance of the business events corresponding to the current collection period is determined, and the determination result is obtained; In response to the determination result reflecting that the business event corresponding to the current collection period does not fall into the compliant energy consumption event type, the energy consumption collection data of the current collection period is determined as the abnormal energy consumption data.

[0007] In some embodiments, the step of parsing the time period features to obtain the current time period features includes: The current data collection period is analyzed to obtain the work cycle period characteristics; The business scheduling period features are analyzed for the current collection period to obtain the business scheduling period features; The public event time period features are analyzed based on the current collection time period to obtain the public event time period features; Environmental factor characteristics are analyzed for the current data collection period to obtain the time-period characteristics of environmental factors; The operation and maintenance characteristics of the items are analyzed for the current collection period to obtain the operation and maintenance period characteristics of the items; The current time period characteristics are obtained by integrating the characteristics of the work cycle time period, the business scheduling time period, the public event time period, the environmental factor time period, and the item maintenance time period.

[0008] In some embodiments, after the energy consumption deviation data meets a preset deviation anomaly condition, the following steps are included: Obtain the business change information corresponding to the unit subspace; Based on the aforementioned business change information, the business usage type of the unit subspace during the current data collection period is redefined; Based on the redefined business use type, energy consumption fluctuation event analysis is performed on the unit subspace to update the compliant energy consumption event type.

[0009] In some embodiments, the energy consumption fluctuation event analysis for each of the aforementioned business use types to obtain compliant energy consumption event types includes: Obtain multiple alternative public event subtypes and multiple alternative environmental event subtypes; For each of the aforementioned unit subspaces within the target building, a business nature analysis is performed on the business purpose type to obtain the corresponding business event subtype; The compliant energy consumption event type is determined based on multiple business event subtypes, multiple public event subtypes, and multiple environmental event subtypes.

[0010] In some embodiments, the step of filtering the historical energy consumption data based on the abnormal energy consumption period to obtain reference energy consumption data includes: The abnormal energy consumption periods are analyzed to obtain the abnormal period characteristics; Based on the characteristics of the abnormal time period, a reference collection period is determined from multiple historical collection periods; The historical energy consumption data corresponding to the reference collection period is determined as the reference energy consumption data.

[0011] In some embodiments, the reference energy consumption data includes multiple sets of reference sub-data, each of which is configured with a reference weight. The correction of the abnormal energy consumption data based on the reference energy consumption data includes: Obtain the abnormal data sampling interval corresponding to the abnormal energy consumption data; Based on the abnormal data sampling interval, the abnormal energy consumption data is converted into an abnormal data sequence; Based on the abnormal data sampling interval, an alignment operation is performed on each group of reference sub-data to obtain a reference data sequence corresponding to each group of reference sub-data. Based on the reference data sequence and the reference weight, the abnormal data sequence is corrected and analyzed to determine the corresponding data correction parameters; Based on the data correction parameters, the abnormal data sequence is corrected. Data restoration processing is performed on the abnormal data sequence after the correction operation to obtain the corrected abnormal energy consumption data.

[0012] To achieve the above objectives, a second aspect of this application provides a building-oriented energy consumption data correction device, the device comprising: The first acquisition module is used to acquire the business purpose type of each unit subspace within the target building; The second acquisition module is used to acquire corresponding energy consumption data for each of the unit subspaces in the target building. The energy consumption fluctuation analysis module is used to analyze energy consumption fluctuation events for each of the aforementioned business use types to obtain compliant energy consumption event types. An anomaly detection module is used to perform anomaly detection on the energy consumption collection data according to the compliant energy consumption event type to obtain abnormal energy consumption data; wherein, the collection period corresponding to the abnormal energy consumption data is the energy consumption abnormal period. A reference data filtering module is used to acquire historical energy consumption data and filter the historical energy consumption data according to the abnormal energy consumption period to obtain reference energy consumption data; wherein the historical energy consumption data is earlier than the abnormal energy consumption data; The data correction module is used to correct the abnormal energy consumption data based on the reference energy consumption data.

[0013] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0014] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0015] This application proposes a method, apparatus, electronic device, and medium for correcting energy consumption data in buildings. It analyzes energy consumption fluctuation events by combining the business use type of each sub-space within the target building with energy consumption data collected from each sub-space. This analysis yields compliant energy consumption event types corresponding to each business use type. The compliant energy consumption event types are then used to perform anomaly detection on the collected energy consumption data, thereby identifying periods of abnormal energy consumption. These compliant energy consumption event types accurately determine whether current energy consumption fluctuations are normal, thus avoiding misjudgments. Subsequently, reference energy consumption data is obtained from historical energy consumption data earlier than the abnormal energy consumption data, using the abnormal energy consumption period as a filtering condition. Finally, the abnormal energy consumption data is corrected based on the reference energy consumption data, making the corrected data more consistent with the actual energy consumption variation patterns of each sub-space within the target building under the corresponding business use type. Compared to using simple averages to replace abnormal energy consumption data or relying on manual correction based on experience, the method in this embodiment can differentiate the energy consumption fluctuation characteristics caused by different business use types, avoiding the mechanical nature of simple averaging or manual correction in traditional methods, thereby improving the accuracy and reliability of the corrected data. Attached Figure Description

[0016] Figure 1 This is a flowchart of a building-oriented energy consumption data correction method provided in an embodiment of this application; Figure 2 yes Figure 1 The flowchart of step S103 in the process; Figure 3 yes Figure 1 The flowchart of step S104 in the process; Figure 4 yes Figure 3 The flowchart of step S301 in the process; Figure 5 This is another flowchart of the energy consumption data correction method for buildings provided in the embodiments of this application; Figure 6 yes Figure 1 The flowchart of step S105 in the process; Figure 7 yes Figure 1 The flowchart of step S106 in the process; Figure 8 This is a schematic diagram of the structure of the building-oriented energy consumption data correction device provided in the embodiments of this application; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] In office buildings, shopping malls, and other similar structures, energy consumption (such as electricity, cooling, and water) is typically statistically analyzed periodically to aid in energy management. However, during actual data collection, equipment malfunctions can lead to significant fluctuations or missing data in energy consumption figures. Current techniques often substitute outliers with average values ​​or rely on manual correction based on experience. However, these methods tend to be overly mechanical, lacking sufficient understanding and adaptation to anomalies, thus compromising the accuracy of corrected data.

[0021] Therefore, how to accurately correct abnormal energy data within a building has become an urgent technical problem to be solved.

[0022] Based on this, embodiments of this application provide a method, apparatus, electronic device, and medium for correcting energy consumption data in buildings, aiming to accurately correct abnormal energy data within buildings.

[0023] The energy consumption data correction method, apparatus, electronic device, and medium for buildings provided in this application are specifically described through the following embodiments. First, the energy consumption data correction method for buildings in this application is described.

[0024] The energy consumption data correction method for buildings provided in this application relates to the field of artificial intelligence technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the energy consumption data correction method for buildings, but is not limited to the above forms.

[0025] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0026] Figure 1 This is an optional flowchart of the building-oriented energy consumption data correction method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S106.

[0027] Step S101: Obtain the business use type of each unit subspace within the target building.

[0028] Step S102: For each unit subspace in the target building, acquire the corresponding energy consumption data.

[0029] Step S103: Perform energy consumption fluctuation event analysis for each business use type to obtain compliant energy consumption event types.

[0030] Step S104: Perform anomaly detection on the energy consumption data collection based on the compliant energy consumption event type to obtain abnormal energy consumption data. The collection period corresponding to the abnormal energy consumption data is the energy consumption anomaly period.

[0031] Step S105: Obtain historical energy consumption data and filter the historical energy consumption data according to the period of abnormal energy consumption to obtain reference energy consumption data.

[0032] Step S106: Correct the abnormal energy consumption data based on the reference energy consumption data.

[0033] Steps S101 to S106 of this embodiment involve analyzing energy consumption fluctuation events based on the business use type of each sub-space within the target building and the energy consumption data collected for each sub-space. This yields compliant energy consumption event types corresponding to each business use type. The compliant energy consumption event types are then used to perform anomaly detection on the collected energy consumption data to determine abnormal energy consumption periods. These compliant energy consumption event types accurately determine whether current energy consumption fluctuations are normal data fluctuations, thus avoiding misjudgments. Subsequently, reference energy consumption data is obtained from historical energy consumption data earlier than the abnormal energy consumption data, using the abnormal energy consumption period as a filtering condition. Finally, the abnormal energy consumption data is corrected based on the reference energy consumption data, making the corrected abnormal energy consumption data more consistent with the actual energy consumption change patterns of each sub-space within the target building under the corresponding business use type. Compared to using a simple average value to replace abnormal energy consumption data or relying on manual correction based on human experience, the method of this embodiment can differentiate the energy consumption fluctuation characteristics caused by different business use types, avoiding the mechanical nature of simple averaging or manual correction in traditional methods, thereby improving the accuracy and reliability of the corrected data.

[0034] In step S101 of some embodiments, the target building refers to the specific building where energy management and data collection are performed, typically including various types of buildings such as office buildings, shopping malls, and residential areas. A unit subspace refers to a spatial unit within the target building defined according to function and leasing arrangements. This could be a space leased by each resident company in an office building or the space of each independent shop in a shopping mall, or it could include public facilities within the target building such as restrooms. Unit subspaces can be clearly divided according to the building's internal structural diagram and usage plan, based on standards such as floor and room numbering. The business usage type refers to the actual business function of each unit subspace, typically reflecting the main business activities conducted in that unit subspace, and may include, but is not limited to, catering, e-commerce retail, cosmetics, consulting services, etc.

[0035] In step S102 of some embodiments, energy consumption data refers to energy consumption information collected for each unit subspace within the target building, including, but not limited to, electricity consumption, water consumption, and air conditioning cooling capacity. Energy consumption data can be collected in real-time or periodically by energy metering devices installed in the target building to monitor the energy use of each unit subspace. The devices record the energy consumption data of each unit subspace and upload it to a data storage system.

[0036] In step S103 of some embodiments, the compliant energy consumption event type can reflect the situation where energy consumption fluctuations for certain business use types within the building are within a reasonable range and in line with expectations. These fluctuations are usually caused by special events, such as holidays, severe weather, temporary events, etc., but do not necessarily indicate abnormal energy consumption data. For example, during extreme weather, the power consumption of the office building may decrease due to work stoppages. Although such fluctuations in energy consumption data are relatively obvious, they do not indicate a malfunction in the data acquisition equipment. Furthermore, for unit subspaces with different business use types, their energy consumption may differ from that of ordinary workdays due to their business characteristics. For example, for a unit subspace whose business use type is retail e-commerce, during specific promotional activities of the e-commerce platform, most employees will work longer hours, resulting in a significant increase in energy consumption for the corresponding unit subspace compared to ordinary workdays. Therefore, it is necessary to analyze energy consumption fluctuation events from multiple dimensions.

[0037] Specifically, please refer to Figure 2 In some embodiments, step S103 may include, but is not limited to, steps S201 to S203: Step S201: Obtain multiple alternative public event subtypes and multiple alternative environmental event subtypes.

[0038] Step S202: Analyze the business nature of each unit subspace within the target building to obtain the corresponding business event subtypes.

[0039] Step S203: Determine the compliant energy consumption event type based on multiple business event subtypes, multiple public event subtypes, and multiple environmental event subtypes.

[0040] In step S201 of some embodiments, the public event subtype refers to event types that can affect the energy consumption changes of multiple unit subspaces within a building, typically including holidays, major festivals, fire drills, etc., but not limited to these. The environmental event subtype refers to event types caused by natural environmental factors, including seasonal changes, extreme weather, etc.

[0041] In step S202 of some embodiments, the business event subtype is the type of energy consumption fluctuation caused by changes in the business nature of a specific unit subspace within the target building. These changes are typically closely related to the operational activities or specific events of that unit subspace. For example, in a shopping mall, certain promotional activities or seasonal discounts may lead to a significant increase in energy consumption. As another example, for electronics R&D companies, in situations where product testing of new products needs to be completed as quickly as possible, testing equipment often needs to be kept powered on for extended periods, resulting in increased energy consumption. In some embodiments, the business event subtype can be obtained by analyzing the business usage type of the unit subspace currently being analyzed using a pre-trained predictive analytics model.

[0042] In step S203 of some embodiments, in order to determine the compliant energy consumption event type, it is necessary to comprehensively consider the event types of multiple dimensions, and take all public event subtypes, environmental event subtypes, and business event subtypes related to the business of the unit subspace as the compliant energy consumption event type of the current unit subspace.

[0043] Steps S201 to S203, as illustrated in this embodiment, utilize multi-dimensional event type analysis to more comprehensively identify compliant energy consumption event types within the building. This ensures that when detecting energy consumption anomalies, normal fluctuations caused by external or special factors can be excluded, thereby accurately identifying genuine data anomalies. Compared to existing technologies that rely solely on simple rules or manual judgment, this approach significantly improves the accuracy of energy consumption data correction, reduces the risk of misjudgments and omissions, and provides more reliable data support for building energy management, ensuring the system's stability and effectiveness when handling complex situations.

[0044] In step S104 of some embodiments, abnormal energy consumption data refers to data in the energy consumption collection data that cannot accurately reflect the actual energy consumption status of the target building. This is usually caused by equipment failure, data collection errors, or other abnormal factors. Specifically, it can manifest as a sudden surge, sharp drop, missing data, or a significant deviation from the normal energy consumption level. It is understood that when energy consumption collection data is missing, the missing blank data is directly identified as abnormal energy consumption data.

[0045] Specifically, please refer to Figure 3 In some embodiments, step S104 may include, but is not limited to, steps S301 to S306: Step S301: Perform time period feature analysis for the current collection time period to obtain the current time period features.

[0046] Step S302: Based on the characteristics of the current time period, determine the homogeneous collection time period from multiple historical collection time periods.

[0047] Step S303: Compare the energy consumption data collected during the current collection period with the historical energy consumption data collected during the same collection period to obtain energy consumption deviation data.

[0048] Step S304: If the energy consumption deviation data meets the preset deviation anomaly conditions, then obtain the service events corresponding to the unit subspace in the current collection period.

[0049] Step S305: Based on the compliant energy consumption event type, determine the compliance of energy consumption fluctuations of the business events corresponding to the current collection period, and obtain the determination result.

[0050] Step S306: In response to the judgment result reflecting that the business event corresponding to the current collection period does not fall into the compliant energy consumption event type, the energy consumption data collected during the current collection period is determined as abnormal energy consumption data.

[0051] In step S301 of some embodiments, the current collection period refers to the collection period during which abnormal phenomena such as sudden increase, decrease, loss, or significant deviation from normal energy consumption levels occur.

[0052] Current time period characteristics refer to representative features extracted from energy consumption data collected during the current time period. These features can be extracted through multiple evaluation dimensions. Please refer to [link / reference]. Figure 4 In some embodiments, step S301 may include, but is not limited to, steps S401 to S406: Step S401: Perform job cycle feature analysis for the current collection period to obtain job cycle period features.

[0053] Step S402: Perform business scheduling feature analysis for the current collection period to obtain business scheduling period features.

[0054] Step S403: Analyze the public event features for the current collection period to obtain the public event period features.

[0055] Step S404: Analyze the environmental factors for the current data collection period to obtain the environmental factors time period characteristics.

[0056] Step S405: Analyze the operation and maintenance characteristics of the items for the current collection period to obtain the operation and maintenance period characteristics of the items.

[0057] Step S406: Based on the characteristics of the work cycle time period, the characteristics of the business scheduling time period, the characteristics of the public event time period, the characteristics of the environmental factors time period, and the characteristics of the item operation and maintenance time period, the characteristics of the current time period are integrated to obtain the characteristics of the current time period.

[0058] In step S401 of some embodiments, the work cycle time period characteristics refer to extracting features related to the work cycle by analyzing the periodic position of the current collection period. These features are typically periodic features related to the business's production cycle, seasonal changes, financial settlement cycles, etc. For example, the energy consumption of a manufacturing company may differ between peak and off-peak seasons, or the frequency of equipment use and energy consumption patterns may change at the end of the month or quarter for financial settlement. The periodic position of the current collection period can be identified through a pre-trained model, thereby extracting the periodic features of that period. For example, by combining annual, quarterly, monthly, or weekly cycles, it can be identified whether the current period belongs to the peak production season or the end-of-month financial settlement period, thereby extracting the corresponding work cycle features. For example, in a manufacturing company, production activities are typically concentrated in the peak seasons of the first and third quarters, while the second and fourth quarters are relatively quiet. Energy consumption is higher during peak seasons and lower during off-peak seasons. Assuming the current data collection period is from 9:00 AM to 10:00 AM on January 10th, the characteristics of the work cycle during the "peak season morning" are obtained through work cycle feature analysis.

[0059] In step S402 of some embodiments, the business scheduling period characteristics refer to extracting energy consumption fluctuation characteristics related to the business scheduling by analyzing the specific business arrangements within the current data collection period. These characteristics reflect the direct impact of various business activities within the building on energy consumption. For example, an office building consumes more energy when holding large-scale meetings.

[0060] By connecting to a company's Manufacturing Execution System (MES) and office building meeting room reservation platforms, specific business arrangements for the current time period can be extracted. These arrangements yield business scheduling characteristics, including specific production activity schedules and meeting activities within the office building, allowing for the analysis of energy consumption fluctuations related to the current time period. For example, in a research and development laboratory currently in a "project sprint cycle," requiring 24-hour uninterrupted power supply, energy consumption should remain high during this period. Through business scheduling characteristic analysis, the time period characteristics of the "project sprint cycle" can be derived.

[0061] In step S403 of some embodiments, the public event time period characteristic refers to analyzing public events within the current data collection period. These public events are typically caused by internal and external factors of the building, such as holidays, major events, and unified maintenance of the park. By introducing management records from the park management, public events that significantly impact energy consumption during the current data collection period can be identified as public event characteristics. Examples include regular inspections of the park's power distribution room, fire drills organized by the park, and celebrations held in the office building lobby during holidays, among others.

[0062] In step S404 of some embodiments, environmental factor time-period characteristics refer to extracting energy consumption characteristics related to environmental factors by analyzing the impact of external conditions such as weather changes and seasonal transitions on energy consumption during the current data collection period. For example, under high-temperature weather conditions, the cooling and electricity consumption in buildings may increase significantly. Real-time data such as temperature, humidity, and wind speed can be obtained by accessing a meteorological API and mapped to environmental factor time-period characteristics affecting energy consumption.

[0063] In step S405 of some embodiments, the item maintenance period feature refers to the extraction of event features related to non-productive actions such as equipment maintenance and repair by analyzing the equipment maintenance status within the unit subspace during the current collection period. Equipment maintenance-related events can be identified and used as item maintenance period features by obtaining maintenance work orders, emergency repair records, etc., from the equipment management system of the unit subspace. For example, a data center needs to conduct a no-load start-up test of a diesel generator monthly, during which the generator's energy consumption is low.

[0064] In step S406 of some embodiments, the characteristics of the work cycle time period, the characteristics of the business scheduling time period, the characteristics of the public event time period, the characteristics of the environmental factors time period, and the characteristics of the item maintenance time period are merged to obtain the comprehensive characteristics of the current time period, i.e., the characteristics of the current time period.

[0065] Steps S401 to S406, as illustrated in the embodiments of this application, combine energy consumption fluctuation characteristics from multiple dimensions to more comprehensively and accurately analyze abnormal fluctuations in energy consumption data. This multi-dimensional feature integration method is more intelligent than simply relying on simple threshold judgments and can effectively avoid misjudgments caused by external environmental factors or holidays. Through this method, the detection and correction of anomalies in energy consumption data can be more accurate, further improving the stability and refinement of the building energy consumption management system.

[0066] In step S302 of some embodiments, the historical acquisition period refers to a completed data acquisition period. A homogeneous acquisition period refers to a historical acquisition period that is highly similar to or completely identical to the current acquisition period in terms of time period characteristics. Specifically, a homogeneous acquisition period should have the same or similar characteristics in multiple dimensions as the current acquisition period.

[0067] For example, suppose the current data collection period is energy consumption data from 3 PM to 4 PM on November 1, 2025, and the characteristics of the current period are "peak season, no business scheduling, rest day, rainy day with cooling, no equipment maintenance required". Then, periods with the same characteristics can be identified from historical data collection periods as homogeneous data collection periods. It is understood that if there is a sub-period in the historical data collection periods that has the same characteristics in all dimensions as the current period, then that sub-period is preferred as a homogeneous data collection period. If there is no period in the historical data collection periods that completely matches the current period, then the historical periods with most of the same characteristics are considered homogeneous data collection periods. For example, suppose the period from 3 PM to 4 PM on October 1, 2025, in the historical data collection period has the characteristics of "peak season, no business scheduling, rest day, rainy day with cooling, no equipment maintenance required", then that period is considered a homogeneous data collection period. If the time period corresponding to this period is characterized as "peak season, no business scheduling, weekday, sunny day, no equipment maintenance required", and the time period corresponding to 3 pm to 4 pm on September 1, 2025 is characterized as "peak season, no business scheduling, rest day, sunny day, no equipment maintenance required", then select 3 pm to 4 pm on September 1, 2025 as the homogeneous data collection period.

[0068] In step S303 of some embodiments, the energy consumption deviation data refers to the difference between the energy consumption data of the current collection period and the historical energy consumption data of a similar collection period. By comparing the energy consumption data of the current collection period and the historical energy consumption data of a selected similar collection period, the deviation value between the collected values ​​at the corresponding time is calculated, and this deviation value is the energy consumption deviation data. In other embodiments, the energy consumption deviation data may be the difference between the energy consumption data of the current collection period and the average value of the historical energy consumption data of a similar collection period.

[0069] In step S304 of some embodiments, the deviation anomaly condition is a preset judgment rule, which can be: when the energy consumption deviation data exceeds a certain preset threshold (for example, the corresponding threshold for electricity consumption can be 50kWh), it is determined that the energy consumption deviation data meets the preset deviation anomaly condition. If the energy consumption deviation data does not meet the preset deviation anomaly condition, no data processing operation is performed. For example, assuming that the electricity consumption data collected during the current collection period is arranged in the order of collection time, it is represented as {A1,A2,A3,A4,A5}. The electricity consumption data collected during the same collection period is arranged in the order of collection time, represented as {B1,B2,B3,B4,B5}. Then the energy consumption deviation data can be represented as... If any item in the energy consumption deviation data exceeds the preset threshold, then the energy consumption deviation data is determined to meet the preset deviation anomaly conditions.

[0070] In other embodiments, there are more than a preset number of consecutive time intervals where the energy consumption deviation data all exceed a preset threshold. Continuing with the example from the above embodiments, assuming the preset number is 3, the energy consumption deviation data... If all values ​​are greater than the preset threshold, then the energy consumption deviation data is determined to meet the preset deviation anomaly conditions.

[0071] In some embodiments, a business event refers to a specific activity performed in a cell subspace during the current collection period.

[0072] In step S305 of some embodiments, the determination result is obtained by comparing the event type to which the business event belongs with the compliant energy consumption event type: the event type to which the business event belongs falls into the compliant energy consumption event type, and the event type to which the business event belongs does not fall into the compliant energy consumption event type.

[0073] In step S306 of some embodiments, when the determination result reflects that the business event corresponding to the current collection period falls into the compliant energy consumption event type, the corresponding energy consumption collection data is not considered abnormal data. If the determination result reflects that the business event corresponding to the current collection period does not fall into the compliant energy consumption event type, then the energy consumption collection data is considered to be energy consumption data that has actually occurred abnormally. It can be understood that the collection period corresponding to the abnormal energy consumption data is the energy consumption abnormal period.

[0074] Steps S301 to S306 of this embodiment, by comprehensively considering the energy consumption characteristics of the current collection period and historical energy consumption data from homogeneous collection periods, can more accurately identify whether energy consumption fluctuations are normal fluctuations. This avoids the previous method of relying solely on simple thresholds or human experience, significantly improving the accuracy of energy consumption data correction. The method of this embodiment can not only effectively reduce misjudgments of energy consumption fluctuations caused by external environmental changes, holidays, and other factors, but also perform more precise energy consumption fluctuation analysis for unit subspaces with different business uses within a building, thereby achieving more accurate identification of abnormal data.

[0075] Please see Figure 5 After step S304 in some embodiments, the method provided in this application embodiment may also include, but is not limited to, steps S501 to S503: Step S501: Obtain the business change information corresponding to the unit subspace.

[0076] Step S502: Based on the business change information, redetermine the business usage type of the unit subspace in the current collection period.

[0077] Step S503: Perform energy consumption fluctuation event analysis on the unit subspace based on the redefined business use type to update the compliant energy consumption event type.

[0078] In step S501 of some embodiments, business change information refers to information reflecting changes in the business use of a certain unit subspace within the building, which may include new tenant occupancy, changes in the business nature of existing tenants, or temporary business adjustments. This business change information of the unit subspace can be obtained in real time by connecting with the building's property management system, leasing management system, or other information platforms.

[0079] In step S502 of some embodiments, as the service of a unit subspace changes, the service usage type of the unit subspace may change, thus requiring a redeter determination of the service usage type of the unit subspace. The current service usage type of the unit subspace can be directly extracted from the service change information.

[0080] In some embodiments, the specific implementation principle of step S503 is the same as that of step S103, and will not be repeated here.

[0081] Steps S501 to S503, as illustrated in this embodiment, enable more accurate analysis and correction of energy consumption fluctuations in building unit subspaces by introducing business change information. When the business usage type of a unit subspace changes, the business nature of the unit subspace is reconfirmed, thereby achieving a more accurate determination of energy consumption anomalies. This dynamic adjustment method based on real-time business changes avoids misjudgments of abnormal energy consumption data caused by ignoring business changes, ensuring that building energy consumption anomaly detection can adapt to and respond to different business environments in real time, thus guaranteeing the accuracy of abnormal energy consumption data correction.

[0082] In step S105 of some embodiments, historical energy consumption data refers to past energy consumption data of each unit subspace within the target building, which is earlier than abnormal energy consumption data.

[0083] Reference energy consumption data refers to normal energy consumption data selected from historical energy consumption data that corresponds to the current abnormal energy consumption data. For details on the process of determining reference energy consumption data, please refer to [link to relevant documentation]. Figure 6 In some embodiments, step S105 includes, but is not limited to, steps S601 to S603: Step S601: Analyze the time period characteristics for abnormal energy consumption periods to obtain the abnormal time period characteristics.

[0084] Step S602: Based on the characteristics of abnormal time periods, determine the reference collection period from multiple historical collection periods.

[0085] Step S603: Determine the historical energy consumption data corresponding to the reference collection period as the reference energy consumption data.

[0086] In step S601 of some embodiments, the abnormal time period feature refers to the ability to evaluate from multiple dimensions by analyzing the current time period features corresponding to the abnormal energy consumption period. The parsing of this time period feature is similar to the specific embodiment of step S301, and will not be described in detail here.

[0087] In step S602 of some embodiments, the reference collection period refers to a historical collection period that is highly similar to or completely identical to the period of abnormal energy consumption in terms of time period characteristics. The logic for determining this period is consistent with that for determining the homogeneous collection period in step S302, and will not be elaborated upon here.

[0088] In step S603 of some embodiments, the reference energy consumption data refers to normal energy consumption data extracted from a selected reference acquisition period.

[0089] Steps S601 to S603, as illustrated in this embodiment, involve detailed analysis of the time-period characteristics of abnormal energy consumption periods and, through comparative analysis with historical data collection periods, accurately selecting reference energy consumption data corresponding to the current abnormal energy consumption data. This process enables precise correction of abnormal energy consumption data, improving the accuracy of energy consumption data correction.

[0090] In step S106 of some embodiments, the average value of the reference energy consumption data can be directly used to replace the abnormal energy consumption data.

[0091] Please see Figure 7 In other embodiments, the reference energy consumption data includes multiple sets of reference sub-data, each of which is configured with a reference weight. Specifically, there may be multiple reference collection periods, and the historical energy consumption data corresponding to each reference collection period constitutes a set of reference sub-data. The reference weight is used to measure the confidence level of the corresponding reference sub-data. Further, step S106 may include, but is not limited to, steps S701 to S706: Step S701: Obtain the abnormal data sampling interval corresponding to the abnormal energy consumption data.

[0092] Step S702: Based on the abnormal data sampling interval, the abnormal energy consumption data is converted into an abnormal data sequence.

[0093] Step S703: Based on the abnormal data sampling interval, perform alignment operations on each group of reference sub-data to obtain the reference data sequence corresponding to each group of reference sub-data.

[0094] Step S704: Based on the reference data sequence and reference weights, perform correction analysis on the abnormal data sequence to determine the corresponding data correction parameters.

[0095] Step S705: Based on the data correction parameters, perform correction operations on the abnormal data sequence.

[0096] Step S706: Perform data restoration processing based on the abnormal data sequence after the correction operation to obtain the corrected abnormal energy consumption data.

[0097] In step S701 of some embodiments, the abnormal data sampling interval refers to the time span of energy consumption data collected at certain time intervals (such as every minute, every hour, etc.). It can be 1 second, 1 minute, or 1 hour. The specific length of the abnormal data sampling interval is not strictly limited in the embodiments of this application.

[0098] In step S702 of some embodiments, the abnormal data sequence refers to converting the energy consumption data within the abnormal data range into a sequence arranged in chronological order.

[0099] In step S703 of some embodiments, the reference data sequence refers to the historical energy consumption data sequence adjusted according to the same sampling interval as the abnormal data sequence within the reference acquisition period. Since the sampling interval corresponding to the reference sub-data may differ from the sampling interval of the abnormal data, an alignment operation is required. For example, suppose the abnormal data sampling interval is 2 minutes, and the abnormal data sequence is {C1, C2, C3}. The reference sub-data sampling interval is 1 minute. Under the same duration, the sequence of reference sub-data obtained without alignment is {D1, D2, D3, D4, D5, D6}. After aligning the reference sub-data, the resulting reference data sequence is {D1, D3, D5}.

[0100] In step S704 of some embodiments, the numerical range of each item in the abnormal data sequence is compared with that of the corresponding item in the reference data sequence. If the value of the current item in the abnormal data sequence is not in the range of the corresponding item in the reference data sequence, the average value of the corresponding item in the reference data sequence is used as the data correction parameter. If the value of the current item in the abnormal data sequence is in the range of the corresponding item in the reference data sequence, this step is repeated for the next item. For example, there are two reference data sequences {1,3,5} and {2,2,4}, with corresponding reference weights of 0.4 and 0.6. The abnormal data sequence is {0,2,4}. For the first item of the sequence, the numerical range of the first item in the reference data sequence is [1,2]. The value of the first item in the abnormal data sequence is 0, which is not in this range. Therefore, the corresponding data correction parameter is the weighted average of the first item in the reference data sequence and the corresponding reference weight, i.e. For the second and third terms of the sequence, the numerical ranges of the reference data sequence are [2,3] and [4,5], respectively. The second and third terms in the anomalous data sequence fall within the corresponding numerical ranges, therefore, there is no need to calculate the data correction parameter.

[0101] In step S705 of some embodiments, the data correction parameter is replaced with the corresponding data. Continuing with the example from the previous step, the corrected abnormal data sequence is {1.6,2,4}.

[0102] In step S706 of some embodiments, it means that after the correction operation is completed, the corrected data is restored to the final energy consumption data form.

[0103] Steps S701 to S706, as illustrated in this embodiment, achieve dynamic correction and precise calibration of abnormal energy consumption data by introducing multiple sets of reference sub-data and reference weights. The method of this embodiment improves the accuracy of correcting abnormal energy consumption data through a refined correction process.

[0104] Please see Figure 8 This application also provides a building-oriented energy consumption data correction device, which can implement the above-mentioned building-oriented energy consumption data correction method. The device includes: The first acquisition module 801 is used to acquire the business purpose type of each unit subspace within the target building.

[0105] The second acquisition module 802 is used to acquire corresponding energy consumption data for each unit subspace in the target building.

[0106] The energy consumption fluctuation analysis module 803 is used to analyze energy consumption fluctuation events for each business application type to obtain compliant energy consumption event types.

[0107] The anomaly detection module 804 is used to perform anomaly detection on the energy consumption collection data according to the type of compliant energy consumption event, and obtain abnormal energy consumption data; wherein, the collection period corresponding to the abnormal energy consumption data is the energy consumption abnormal period.

[0108] The reference data filtering module 805 is used to obtain historical energy consumption data and filter the historical energy consumption data according to the period of abnormal energy consumption to obtain reference energy consumption data; wherein, the historical energy consumption data is earlier than the abnormal energy consumption data.

[0109] The data correction module 806 is used to correct abnormal energy consumption data based on reference energy consumption data.

[0110] The specific implementation of this building-oriented energy consumption data correction device is basically the same as the specific implementation of the building-oriented energy consumption data correction method described above, and will not be repeated here.

[0111] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described building-oriented energy consumption data correction method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0112] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 to implement the building-oriented energy consumption data correction method of the embodiments of this application. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0113] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described building-oriented energy consumption data correction method.

[0114] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0115] The energy consumption data correction method, device, electronic equipment, and storage medium for buildings provided in this application's embodiments analyze energy consumption fluctuation events by combining the business use type of each sub-space within the target building with energy consumption data collected from each sub-space. This yields compliant energy consumption event types corresponding to each business use type. The compliant energy consumption event types are then used to perform anomaly detection on the collected energy consumption data, thereby identifying abnormal energy consumption periods. The compliant energy consumption event types accurately determine whether current energy consumption fluctuations are normal data fluctuations, thus avoiding misjudgments. Subsequently, reference energy consumption data is obtained from historical energy consumption data earlier than the abnormal energy consumption data, using the abnormal energy consumption period as a filtering condition. Finally, the abnormal energy consumption data is corrected based on the reference energy consumption data, so that the abnormal energy consumption data after correction is more consistent with the actual energy consumption change pattern of each unit subspace in the target building under the corresponding business use type. Compared with the method of using a simple average value to replace abnormal energy consumption data or relying on human experience for manual correction, the method of this embodiment can perform differentiated processing on the energy consumption fluctuation characteristics caused by different business use types, avoiding the mechanical nature of simple averaging or manual correction in traditional methods, thereby improving the accuracy and reliability of the corrected data.

[0116] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0117] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0118] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0119] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0120] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0121] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0122] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0123] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0124] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0125] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for correcting energy consumption data for buildings, characterized in that, The method includes: Obtain the business purpose type of each unit subspace within the target building; For each of the unit subspaces in the target building, acquire the corresponding energy consumption data. Energy consumption fluctuation event analysis is performed on each of the aforementioned business use types to obtain compliant energy consumption event types; Anomaly detection is performed on the energy consumption data collected based on the compliant energy consumption event type to obtain abnormal energy consumption data; wherein, the collection period corresponding to the abnormal energy consumption data is the energy consumption abnormal period. Historical energy consumption data is acquired, and the historical energy consumption data is filtered according to the abnormal energy consumption period to obtain reference energy consumption data; wherein the historical energy consumption data is earlier than the abnormal energy consumption data; The abnormal energy consumption data is corrected based on the reference energy consumption data.

2. The method according to claim 1, characterized in that, The step of performing anomaly detection on the energy consumption data based on the compliant energy consumption event type to obtain abnormal energy consumption data includes: Perform time period feature analysis on the current data collection period to obtain the current time period features; Based on the characteristics of the current time period, a homogeneous collection time period is determined from multiple historical collection time periods; The energy consumption data collected during the current collection period is compared with the historical energy consumption data collected during the same collection period to obtain energy consumption deviation data; If the energy consumption deviation data meets the preset deviation anomaly conditions, then the service event corresponding to the unit subspace in the current collection period is obtained; Based on the compliant energy consumption event types, the energy consumption fluctuation compliance of the business events corresponding to the current collection period is determined, and the determination result is obtained; In response to the determination result reflecting that the business event corresponding to the current collection period does not fall into the compliant energy consumption event type, the energy consumption collection data of the current collection period is determined as the abnormal energy consumption data.

3. The method according to claim 2, characterized in that, The process of parsing the time period features for the current data collection period to obtain the current time period features includes: The current data collection period is analyzed to obtain the work cycle period characteristics; Perform business scheduling feature analysis on the current collection period to obtain business scheduling period features; The public event time period features are analyzed based on the current collection time period to obtain the public event time period features; Environmental factor characteristics are analyzed for the current data collection period to obtain the time-period characteristics of environmental factors; The operation and maintenance characteristics of the items are analyzed for the current collection period to obtain the operation and maintenance period characteristics of the items; The current time period characteristics are obtained by integrating the characteristics of the work cycle time period, the business scheduling time period, the public event time period, the environmental factor time period, and the item maintenance time period.

4. The method according to claim 2, characterized in that, After the energy consumption deviation data meets the preset deviation anomaly condition, the following is included: Obtain the business change information corresponding to the unit subspace; Based on the aforementioned business change information, the business usage type of the unit subspace during the current data collection period is redefined; Energy consumption fluctuation event analysis is performed on the unit subspace based on the redefined business use type to update the compliant energy consumption event type.

5. The method according to any one of claims 1 to 4, characterized in that, The energy consumption fluctuation event analysis for each of the aforementioned business use types yields compliant energy consumption event types, including: Obtain multiple alternative public event subtypes and multiple alternative environmental event subtypes; For each of the aforementioned unit subspaces within the target building, a business nature analysis is performed on the business purpose type to obtain the corresponding business event subtype; The compliant energy consumption event type is determined based on multiple business event subtypes, multiple public event subtypes, and multiple environmental event subtypes.

6. The method according to any one of claims 1 to 4, characterized in that, The step of filtering the historical energy consumption data based on the abnormal energy consumption period to obtain reference energy consumption data includes: The abnormal energy consumption periods are analyzed to obtain the abnormal period characteristics; Based on the characteristics of the abnormal time period, a reference collection period is determined from multiple historical collection periods; The historical energy consumption data corresponding to the reference collection period is determined as the reference energy consumption data.

7. The method according to any one of claims 1 to 4, characterized in that, The reference energy consumption data includes multiple sets of reference sub-data, each of which is configured with a reference weight. The correction of the abnormal energy consumption data based on the reference energy consumption data includes: Obtain the abnormal data sampling interval corresponding to the abnormal energy consumption data; Based on the abnormal data sampling interval, the abnormal energy consumption data is converted into an abnormal data sequence; Based on the abnormal data sampling interval, an alignment operation is performed on each group of reference sub-data to obtain a reference data sequence corresponding to each group of reference sub-data. Based on the reference data sequence and the reference weight, the abnormal data sequence is corrected and analyzed to determine the corresponding data correction parameters; Based on the data correction parameters, the abnormal data sequence is corrected. Data restoration processing is performed on the abnormal data sequence after the correction operation to obtain the corrected abnormal energy consumption data.

8. An energy consumption data correction device for buildings, characterized in that, The device includes: The first acquisition module is used to acquire the business purpose type of each unit subspace within the target building; The second acquisition module is used to acquire corresponding energy consumption data for each of the unit subspaces in the target building. The energy consumption fluctuation analysis module is used to analyze energy consumption fluctuation events for each of the aforementioned business use types to obtain compliant energy consumption event types. An anomaly detection module is used to perform anomaly detection on the energy consumption collection data according to the compliant energy consumption event type to obtain abnormal energy consumption data; wherein, the collection period corresponding to the abnormal energy consumption data is the energy consumption abnormal period. A reference data filtering module is used to acquire historical energy consumption data and filter the historical energy consumption data according to the abnormal energy consumption period to obtain reference energy consumption data; wherein the historical energy consumption data is earlier than the abnormal energy consumption data; The data correction module is used to correct the abnormal energy consumption data based on the reference energy consumption data.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images