A method, device and storage medium for predicting carbon emissions of a building

Abstract

The present application relates to carbon emission management technical field, specifically to a kind of method, equipment and storage medium for predicting carbon emission of building, comprising: real-time acquisition building carbon emission data and building entrance and exit barrier traffic data, set building carbon emission prediction period, based on carbon emission prediction period, cumulative measurement building carbon emission data and traffic data in each period;The present application combines building carbon emission data with traffic data, to predict the indirect carbon emission of building electricity, in the prediction process, by constructing the trend chart representing carbon emission data and traffic data to provide building management user with visual data reading conditions, while the trend chart is segmented and compared with similarity, effectively capture similar carbon emission scenarios in historical data, so as to predict the future carbon emission of building, so that building management personnel can accurately make predictive carbon emission planning and management.

Description

Technical Field

[0001] This invention relates to the field of carbon emission management technology, specifically to a method, device, and storage medium for predicting carbon emissions from buildings. Background Technology

[0002] Building carbon management aims to effectively control carbon emissions throughout the entire life cycle of a building. From building material production and transportation, construction, to operation, use, demolition, and recycling, it reduces energy consumption and greenhouse gas emissions by adopting energy-saving technologies, optimizing energy structures, and improving management efficiency, thereby promoting the construction industry towards a low-carbon and sustainable development.

[0003] A method for obtaining carbon emission prediction data is disclosed in invention patent application number 202310758660.5. The method comprises: obtaining target historical parameter information of a transformer, wherein the target historical parameter information is historical operating data of the target parameters of the transformer; inputting the target historical parameter information into a long short-term memory network for time series prediction to obtain the prediction result of the target parameters; obtaining carbon emission prediction data of the transformer for a preset time period based on the prediction result, wherein the target parameters include at least load power, three-phase current balance, and harmonic distortion rate; the target historical parameter information includes first historical data, second historical data, and third historical data, wherein the first historical data is historical data information of the load power of the transformer, the second historical data is historical data information of the three-phase current balance of the transformer, and the third historical data is historical data information of the harmonic distortion rate of the transformer; and inputting the target historical parameter information into a long short-term memory network for time series prediction to obtain the prediction result of the target parameters.

[0004] The application aims to address the problem that "existing technologies cannot effectively and accurately count the carbon emissions of power transformers, which indirectly leads to an increase in the carbon emission data of the power grid and causes unnecessary power loss."

[0005] However, current building carbon emission management mainly focuses on the statistics of historical building carbon emission data and the planning of future carbon emission, without making predictions about future building carbon emissions. As a result, building managers can only make certain experience-based decisions on future building carbon emission planning based on historical data, and the effectiveness of such planning is poor.

[0006] To this end, a method, equipment, and storage medium for predicting carbon emissions from buildings are proposed. Summary of the Invention

[0007] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a method, device and storage medium for predicting carbon emissions from buildings, which solves the technical problems mentioned in the background.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] Firstly, a method for predicting carbon emissions from buildings includes:

[0010] The system collects real-time building carbon emission data and pedestrian flow data at building entrances and exits, sets a building carbon emission prediction cycle, and accumulates and measures building carbon emission data and pedestrian flow data within each cycle based on the carbon emission prediction cycle. It then constructs a trend map representing the changes in building carbon emission data and pedestrian flow data. The system iterates through the trend map, segments it based on linear trends, obtains sub-trend maps based on the segmentation results, and stores these sub-trend maps separately. A prediction target is selected within the trend map, and the system predicts the building's future carbon emissions based on the target. After the prediction of future building carbon emissions is completed, the system simultaneously evaluates the reliability of the prediction results. Finally, the system feeds back the building's future carbon emission prediction results and the evaluation results of the prediction results to the user.

[0011] Furthermore, the building carbon emission data refers to the cumulative electricity consumption measured by all meters within the building, the pedestrian flow data comes from all entrance and exit gates of the building, and the building carbon emission prediction cycle is set according to:

[0012] ;

[0013] In the formula: For building carbon emission cycles; It is a constant; This represents the total number of days from which historical parameters are derived. Total number of barrier gates; The cumulative pedestrian flow entering the building is measured for the j-th barrier gate on day i. Accumulate and measure the number of people leaving the building for the j-th barrier gate on day i.

[0014] Where, constant The value is an integer and is defined by the user; the historical parameter is derived from the total number of days. That is: building carbon emission cycle The total number of days from which historical pedestrian traffic data is sourced during the calculation, where the historical parameter is the total number of days from which the data is sourced. ≥3, When storing building carbon emission data and pedestrian traffic data for each period based on the cumulative measurement of carbon emission prediction cycle, a cloud database is set up and the cloud database is used to store building carbon emission data and pedestrian traffic data for each period based on the cumulative measurement.

[0015] Furthermore, when constructing the trend map of changes in building carbon emission data and pedestrian flow data, the system retrieves and stores building carbon emission data and pedestrian flow data from the cloud database, constructs the trend map, and simultaneously deletes the building carbon emission data and pedestrian flow data represented in the trend map from the cloud database.

[0016] The trend chart of changes in building carbon emission data and pedestrian flow data shows that the horizontal axis represents the building carbon emission cycle, and the vertical axis represents the cumulative electricity consumption within the cycle and the ratio of pedestrian flow entering the building to leaving the building within the cycle.

[0017] Among them, the trend chart of changes in building carbon emission data and pedestrian flow data is a line graph with two broken lines, which is drawn based on the changes in building carbon emission data and pedestrian flow data and updated synchronously with the building carbon emission cycle.

[0018] Furthermore, the segmentation logic of the situation diagram is represented as follows:

[0019] Set the situation map segmentation conditions:

[0020] Condition 1: The two broken lines in the situation chart show a continuous upward trend;

[0021] Condition 2: The two broken lines in the situation chart show a continuous downward trend;

[0022] Condition 3: The line representing building carbon emissions in the trend chart shows a continuous upward trend, while the line representing pedestrian traffic data shows a continuous downward trend.

[0023] Condition 4: The line representing building carbon emissions in the trend chart shows a continuous decrease, while the line representing pedestrian traffic data shows a continuous increase.

[0024] Condition 5: Any situation other than the four conditions above;

[0025] When performing the segmentation operation, each sub-situation map contains no fewer than two building carbon emission cycles.

[0026] Furthermore, the operation of selecting a prediction target in the situation map is to select several segments of the latest updated partial lines in the situation map. The selected partial lines contain no less than 2 building carbon emission cycles and meet any one of the situation map segmentation conditions.

[0027] The logic for predicting the future carbon emissions of the building is as follows:

[0028] Identify the situation map segmentation conditions corresponding to the selected partial polyline, use the selected partial polyline as the similarity identification target, and capture the sub-situation map with the highest similarity among the sub-situation maps to which the situation map segmentation conditions corresponding to the selected partial polyline belong:

[0029] ;

[0030] In the formula: The similarity between the selected partial polyline A and the q-th sub-situation map B in the sub-situation map to which the corresponding situation map segmentation condition of the selected partial polyline A belongs; This represents the total number of vertices in the situation diagram; , Let V represent the values ​​of the v-th and v+1-th points in the selected polyline A; , The values ​​of the v-th and v+1-th points in the q-th sub-situation map B to which the selected partial polyline A belongs for the situation map segmentation condition;

[0031] Specifically, based on the above formula, the similarity between the sub-situation map corresponding to the situation map segmentation condition of each selected partial line A and the selected partial line A is calculated. Based on the above formula, the similarity between the lines representing building carbon emission data and pedestrian flow data in the situation map is calculated separately. Then, we have: , The mean is denoted as .

[0032] Furthermore, in After calculating, obtain the maximum value. The corresponding sub-situation map is further used to obtain building carbon emission data for each building carbon emission cycle in adjacent sub-situation maps, as well as the latest building carbon emission data obtained from the sub-situation map. Then, the latest building carbon emission data from the prediction target is selected to predict the future carbon emissions of the building.

[0033] ;

[0034] In the formula: The latest building carbon emission data is shown in the sub-situation diagram; The building carbon emission data is represented by a specified building carbon emission cycle in the sub-situation map adjacent to the sub-situation map. To select the most recent representation of building carbon emissions from the forecast targets; To specify building carbon emission data in terms of building carbon emission cycles for the future of a building;

[0035] Among them, building carbon emission data refers to building carbon emissions. and Each refers to a building's carbon emission cycle, and the distance from... and The intervals between carbon emission cycles originating from buildings are equal, as shown in the above formula. The computational target is unknown.

[0036] Furthermore, the logic for assessing the reliability of the predicted future carbon emissions of the building is expressed as follows:

[0037] ;

[0038] In the formula: To ensure the reliability of predictions for future carbon emissions from buildings; Compared to The previous building carbon emission data; Compared to The previous building carbon emission data;

[0039] Among them, the reliability of the prediction results of future carbon emissions from buildings The larger the value, the higher the reliability of the prediction results for the building's future carbon emissions; conversely, the smaller the value, the lower the reliability of the prediction results for the building's future carbon emissions.

[0040] Furthermore, when the predicted carbon emissions of the building and the assessment results of the reliability of the prediction results are fed back to the user, the feedback operation is performed through a wireless network using the mobile computer device held by the user as the feedback target. The user reads the predicted carbon emissions of the building and the assessment results of the reliability of the prediction results on the mobile computer device.

[0041] In a second aspect, there is an apparatus for predicting carbon emissions from a building, the apparatus 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, it implements the execution steps of a method for predicting carbon emissions from a building.

[0042] A storage medium for predicting carbon emissions from buildings, the storage medium storing a computer program that, when executed by a processor, implements the execution steps of a method for predicting carbon emissions from buildings.

[0043] Compared with known public technologies, the technical solution provided by this invention has the following beneficial effects:

[0044] This invention provides a method, device, and storage medium for predicting carbon emissions from buildings. During execution, the method combines building carbon emission data with pedestrian traffic data to predict indirect carbon emissions from building electricity consumption. In the prediction process, a situational map representing carbon emission and pedestrian traffic data is constructed to provide building management users with visualized data access conditions. Simultaneously, the situational map is segmented and compared for similarity to effectively capture similar carbon emission scenarios in historical data, thereby predicting future building carbon emissions. This enables building managers to make accurate and predictive carbon emission planning and management. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0046] Figure 1 This is a flowchart illustrating a method for predicting carbon emissions from buildings. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0048] The present invention will be further described below with reference to embodiments.

[0049] Example:

[0050] This embodiment provides a method for predicting carbon emissions from buildings, such as... Figure 1 As shown, it includes:

[0051] Real-time collection of building carbon emission data and pedestrian flow data at building entrances and exits; setting of building carbon emission prediction cycles; and accumulation of building carbon emission data and pedestrian flow data within each cycle based on the carbon emission prediction cycle.

[0052] Building carbon emission data refers to the cumulative electricity consumption measured by all meters within the building, while pedestrian flow data comes from all entrance and exit gates of the building. The building carbon emission prediction cycle is set according to:

[0053] ;

[0054] In the formula: For building carbon emission cycles; It is a constant; This represents the total number of days from which historical parameters are derived. Total number of barrier gates; The cumulative pedestrian flow entering the building is measured for the j-th barrier gate on day i. Accumulate and measure the number of people leaving the building for the j-th barrier gate on day i.

[0055] Where, constant The value is an integer and is defined by the user; the historical parameter is derived from the total number of days. That is: building carbon emission cycle The total number of days from which historical pedestrian traffic data is sourced during the calculation, and the total number of days from which historical parameters are sourced. ≥3, When storing building carbon emission data and pedestrian traffic data for each period based on the cumulative measurement of carbon emission prediction cycle, a cloud database is set up and the cloud database is used to store building carbon emission data and pedestrian traffic data for each period based on the cumulative measurement.

[0056] By setting the above logic formula, a specified setting logic is provided for the building carbon emission cycle, ensuring that building carbon emission data and traffic flow data can be stably obtained at the specified cycle, thus guaranteeing the stable execution of the method in this embodiment.

[0057] A trend chart of changes in building carbon emission data and pedestrian flow data is constructed based on building carbon emission data and pedestrian flow data;

[0058] Iterate through the trend map representing changes in building carbon emission data and pedestrian flow data, segment the trend map according to the linear trend in the trend map, obtain sub-trend maps based on the segmentation results, and distinguish and store the sub-trend maps.

[0059] The segmentation logic of the situation diagram is represented as follows:

[0060] Set the situation map segmentation conditions:

[0061] Condition 1: The two broken lines in the situation chart show a continuous upward trend;

[0062] Condition 2: The two broken lines in the situation chart show a continuous downward trend;

[0063] Condition 3: The line representing building carbon emissions in the trend chart shows a continuous upward trend, while the line representing pedestrian traffic data shows a continuous downward trend.

[0064] Condition 4: The line representing building carbon emissions in the trend chart shows a continuous decrease, while the line representing pedestrian traffic data shows a continuous increase.

[0065] Condition 5: Any situation other than the four conditions above;

[0066] When performing the segmentation operation, each sub-situation map contains no less than 2 building carbon emission cycles.

[0067] The operation of selecting a prediction target in the situation map is to select several segments of the latest updated partial lines in the situation map. The selected partial lines contain no less than 2 building carbon emission cycles and meet any of the situation map segmentation conditions.

[0068] The logic for predicting future carbon emissions from buildings is as follows:

[0069] Identify the situation map segmentation conditions corresponding to the selected partial polyline, use the selected partial polyline as the similarity identification target, and capture the sub-situation map with the highest similarity among the sub-situation maps to which the situation map segmentation conditions corresponding to the selected partial polyline belong:

[0070] ;

[0071] In the formula: The similarity between the selected partial polyline A and the q-th sub-situation map B in the sub-situation map to which the corresponding situation map segmentation condition of the selected partial polyline A belongs; This represents the total number of vertices in the situation diagram; , Let V represent the values ​​of the v-th and v+1-th points in the selected polyline A; , The values ​​of the v-th and v+1-th points in the q-th sub-situation map B to which the selected partial polyline A belongs for the situation map segmentation condition;

[0072] Specifically, based on the above formula, the similarity between the sub-situation map corresponding to the situation map segmentation condition of each selected partial line A and the selected partial line A is calculated. Based on the above formula, the similarity between the lines representing building carbon emission data and pedestrian flow data in the situation map is calculated separately. Then, we have: , The mean is denoted as ;

[0073] exist After calculating, obtain the maximum value. The corresponding sub-situation map is further used to obtain building carbon emission data for each building carbon emission cycle in adjacent sub-situation maps, as well as the latest building carbon emission data obtained from the sub-situation map. Then, the latest building carbon emission data from the prediction target is selected to predict the future carbon emissions of the building.

[0074] ;

[0075] In the formula: The latest building carbon emission data is shown in the sub-situation diagram; The building carbon emission data is represented by a specified building carbon emission cycle in the sub-situation map adjacent to the sub-situation map. To select the most recent representation of building carbon emissions from the forecast targets; To specify building carbon emission data in terms of building carbon emission cycles for the future of a building;

[0076] Among them, building carbon emission data refers to building carbon emissions. and Each refers to a building's carbon emission cycle, and the distance from... and The intervals between carbon emission cycles originating from buildings are equal, as shown in the above formula. For unknown computational targets;

[0077] The logic for assessing the reliability of building future carbon emission predictions is expressed as follows:

[0078] ;

[0079] In the formula: To ensure the reliability of predictions for future carbon emissions from buildings; Compared to The previous building carbon emission data; Compared to The previous building carbon emission data;

[0080] Among them, the reliability of the prediction results of future carbon emissions from buildings The larger the value, the higher the reliability of the prediction results for the building's future carbon emissions; conversely, the smaller the value, the lower the reliability of the prediction results for the building's future carbon emissions.

[0081] Select a prediction target in the situation map, predict the future carbon emissions of the building based on the prediction target, and simultaneously evaluate the reliability of the prediction results after the prediction of the future carbon emissions of the building is completed.

[0082] The results of the building's future carbon emissions forecast and the assessment of the reliability of the forecast will be fed back to the user.

[0083] When the prediction results of the building's future carbon emissions and the assessment results of the reliability of the prediction results are fed back to the user, the feedback operation is performed through the mobile computer device held by the user on the wireless network. The user reads the prediction results of the building's future carbon emissions and the assessment results of the reliability of the prediction results on the mobile computer device.

[0084] In this embodiment, the execution of the method described above brings about a prediction effect on the future carbon emissions of buildings for building carbon emission management, assisting users of building carbon emission management to make more adaptive and accurate subsequent carbon emission management plans, optimize indirect carbon emissions from building electricity consumption, and promote sustainable environmental development.

[0085] like Figure 1 As shown, when the trend chart of changes in building carbon emission data and pedestrian flow data is constructed, the building carbon emission data and pedestrian flow data stored in the cloud database are retrieved from the cloud database to construct the trend chart. The building carbon emission data and pedestrian flow data represented in the trend chart are simultaneously deleted from the cloud database.

[0086] The graph showing the changes in building carbon emission data and pedestrian flow data shows that the horizontal axis represents the building carbon emission cycle, and the vertical axis represents the cumulative electricity consumption within the cycle and the ratio of pedestrian flow entering the building to leaving the building within the cycle.

[0087] Among them, the trend chart of changes in building carbon emission data and pedestrian flow data is a line graph with two broken lines, which is drawn based on the changes in building carbon emission data and pedestrian flow data and updated synchronously with the building carbon emission cycle.

[0088] The above settings provide further execution logic and data support for the execution of the method in this embodiment, ensuring the stable execution of the method in this embodiment and bringing effective predictive management to building carbon emissions.

[0089] An apparatus for predicting carbon emissions from buildings, the apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program, when executed by the processor, implementing the execution steps of a method for predicting carbon emissions from buildings;

[0090] A storage medium for predicting carbon emissions from buildings, the storage medium storing a computer program that, when executed by a processor, implements the execution steps of a method for predicting carbon emissions from buildings.

[0091] In summary, the method described in the above embodiments combines building carbon emission data with pedestrian traffic data during execution to predict indirect carbon emissions from building electricity consumption. During the prediction process, a situation map representing carbon emission data and pedestrian traffic data is constructed to provide building management users with visualized data reading conditions. At the same time, the situation map is segmented and similarity is compared to effectively capture similar carbon emission scenarios in historical data, thereby predicting future carbon emissions from buildings. This enables building managers to make accurate and predictive carbon emission planning and management.

[0092] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting carbon emissions from buildings, characterized in that, include: Real-time collection of building carbon emission data and pedestrian flow data at building entrances and exits; setting of building carbon emission prediction cycles; and accumulation of building carbon emission data and pedestrian flow data within each cycle based on the carbon emission prediction cycle. A trend chart of changes in building carbon emission data and pedestrian flow data is constructed based on building carbon emission data and pedestrian flow data; Iterate through the trend map representing changes in building carbon emission data and pedestrian flow data, segment the trend map according to the linear trend in the trend map, obtain sub-trend maps based on the segmentation results, and distinguish and store the sub-trend maps. Select a prediction target in the situation map, predict the future carbon emissions of the building based on the prediction target, and simultaneously evaluate the reliability of the prediction results after the prediction of the future carbon emissions of the building is completed. The project will provide feedback to users on the projected future carbon emissions of buildings and the assessment results of the reliability of the forecasts.

2. The method for predicting carbon emissions from buildings according to claim 1, characterized in that, The building carbon emission data refers to the cumulative electricity consumption measured by all meters within the building; the pedestrian flow data comes from all entrance and exit gates of the building; and the building carbon emission prediction cycle is set according to: ； In the formula: For building carbon emission cycles; It is a constant; The total number of days from which historical parameters are derived; Total number of barrier gates; The cumulative pedestrian flow entering the building is measured for the j-th barrier gate on day i. Accumulate and measure the number of people leaving the building for the j-th barrier gate on day i. Where, constant The value is an integer and is defined by the user; the historical parameter is derived from the total number of days. That is: building carbon emission cycle The total number of days from which historical pedestrian traffic data is sourced during the calculation, where the historical parameter is the total number of days from which the data is sourced. ≥3, When storing building carbon emission data and pedestrian traffic data for each period based on the cumulative measurement of carbon emission prediction cycle, a cloud database is set up and the cloud database is used to store building carbon emission data and pedestrian traffic data for each period based on the cumulative measurement.

3. The method for predicting carbon emissions from buildings according to claim 1, characterized in that, When constructing the trend map of changes in building carbon emission data and pedestrian flow data, the system retrieves and stores building carbon emission data and pedestrian flow data from the cloud database, constructs the trend map, and simultaneously deletes the building carbon emission data and pedestrian flow data represented in the trend map from the cloud database. The trend chart of changes in building carbon emission data and pedestrian flow data shows that the horizontal axis represents the building carbon emission cycle, and the vertical axis represents the cumulative electricity consumption within the cycle and the ratio of pedestrian flow entering the building to leaving the building within the cycle. Among them, the trend chart of changes in building carbon emission data and pedestrian flow data is a line graph with two broken lines, which is drawn based on the changes in building carbon emission data and pedestrian flow data and updated synchronously with the building carbon emission cycle.

4. The method for predicting carbon emissions from buildings according to claim 1, characterized in that, The segmentation logic of the situation diagram is represented as follows: Set the situation map segmentation conditions: Condition 1: The two broken lines in the situation chart show a continuous upward trend; Condition 2: The two broken lines in the situation chart show a continuous downward trend; Condition 3: The line representing building carbon emissions in the trend chart shows a continuous upward trend, while the line representing pedestrian traffic data shows a continuous downward trend. Condition 4: The line representing building carbon emissions in the trend chart shows a continuous decrease, while the line representing pedestrian traffic data shows a continuous increase. Condition 5: Any situation other than the four conditions above; When performing the segmentation operation, each sub-situation map contains no fewer than two building carbon emission cycles.

5. The method for predicting carbon emissions from buildings according to claim 4, characterized in that, The operation of selecting a prediction target in the situation map is to select several segments of the latest updated partial lines in the situation map. The selected partial lines contain no less than 2 building carbon emission cycles and meet any of the situation map segmentation conditions. The logic for predicting the future carbon emissions of the building is as follows: Identify the situation map segmentation conditions corresponding to the selected partial polyline, use the selected partial polyline as the similarity identification target, and capture the sub-situation map with the highest similarity among the sub-situation maps to which the situation map segmentation conditions corresponding to the selected partial polyline belong: ； In the formula: The similarity between the selected partial polyline A and the q-th sub-situation map B in the sub-situation map to which the corresponding situation map segmentation condition of the selected partial polyline A belongs; This represents the total number of vertices in the situation diagram; , Let V represent the values ​​of the v-th and v+1-th points in the selected polyline A; , The values ​​of the v-th and v+1-th points in the q-th sub-situation map B to which the selected partial polyline A belongs for the situation map segmentation condition; Specifically, based on the above formula, the similarity between the sub-situation map corresponding to the situation map segmentation condition of each selected partial line A and the selected partial line A is calculated. Based on the above formula, the similarity between the lines representing building carbon emission data and pedestrian flow data in the situation map is calculated separately. Then, we have... , The mean is denoted as .

6. The method for predicting carbon emissions from buildings according to claim 5, characterized in that, exist After calculating, obtain the maximum value. The corresponding sub-situation map is further used to obtain building carbon emission data for each building carbon emission cycle in adjacent sub-situation maps, as well as the latest building carbon emission data obtained from the sub-situation map. Then, the latest building carbon emission data from the prediction target is selected to predict the future carbon emissions of the building. ； In the formula: The latest building carbon emission data is shown in the sub-situation diagram; The building carbon emission data is represented by a specified building carbon emission cycle in the sub-situation map adjacent to the sub-situation map. To select the most recent representation of building carbon emissions from the forecast targets; To specify building carbon emission data in terms of building carbon emission cycles for the future of a building; Among them, building carbon emission data refers to building carbon emissions. and Each refers to a building's carbon emission cycle, and the distance from... and The intervals between carbon emission cycles originating from buildings are equal, as shown in the above formula. The computational target is unknown.

7. The method for predicting carbon emissions from buildings according to claim 6, characterized in that, The logic for assessing the reliability of the predicted future carbon emissions of the building is expressed as follows: ； In the formula: To ensure the reliability of predictions for future carbon emissions from buildings; Compared to The previous building carbon emission data; Compared to The previous building carbon emission data; Among them, the reliability of the prediction results of future carbon emissions from buildings The larger the value, the higher the reliability of the predicted future carbon emissions of the building; conversely, the smaller the value, the lower the reliability of the predicted future carbon emissions of the building.

8. The method for predicting carbon emissions from buildings according to claim 1, characterized in that, When the predicted carbon emissions of the building and the assessment results of the reliability of the prediction results are fed back to the user, the feedback operation is performed through the mobile computer device held by the user on the wireless network. The user reads the predicted carbon emissions of the building and the assessment results of the reliability of the prediction results on the mobile computer device.

9. A device for predicting carbon emissions from buildings, characterized in that, The processing device includes 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, it performs the execution steps of a method for predicting carbon emissions from buildings as described in claims 1 to 8.

10. A storage medium for predicting carbon emissions from buildings, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the execution steps of a method for predicting carbon emissions from buildings as described in claims 1-8.

Images