Urban carbon emission prediction and control method and system based on deep learning

Abstract

The invention discloses an urban carbon emission prediction and control method and system based on deep learning, and relates to the technical field of carbon emission prediction. Comprising the steps of obtaining carbon content data released by residents in a public area based on smoking behaviors, obtaining action data of the smoking behaviors of the residents in the public area based on the carbon content data, and obtaining target crowds in the public area based on the carbon content data and the action data, according to the method, the action data of the target population and the action data of the other target individuals are compared and analyzed, the difference data can be extracted from the behavior mode, the difference data are utilized to adjust the numerical value of the correction data, the accuracy and the real-time performance of carbon emission prediction are further improved, and in addition, the accuracy of carbon emission prediction is improved by automatically adjusting the correction data. And the real-time action data are compared, so that the future smoking behavior and carbon emission setting of the residents are predicted, and the accuracy of carbon emission prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission prediction, and specifically to a method and system for predicting and controlling urban carbon emissions based on deep learning. Background Art

[0002] The scope of urban carbon emissions usually refers to greenhouse gas emissions caused by human activities within the city, especially carbon dioxide, and other greenhouse gases (such as methane, nitrogen oxides, etc.). These emission sources can be classified from multiple fields, usually including the following major categories: urban energy consumption, industrial emissions, transportation, agricultural emissions, waste management, land use and urban development, as well as residents' lives and consumption behaviors.

[0003] After searching, the Chinese invention patent with publication number "CN116596095A" discloses "a training method and device for a carbon emission prediction model based on machine learning". The application obtains multiple initial training sets of initial enterprise training samples related to carbon emissions of each enterprise and corresponding label data; for any initial training set, based on the initial samples of each minority class in the initial training set, and the Euclidean distance between the initial samples of each minority class and the initial samples of each majority class, obtain the current training set; based on a preset graph convolutional network, extract features of the training samples of each enterprise in the current training set to obtain the graph feature vector corresponding to the current training set; using a preset loss function, input the graph feature vectors corresponding to different current training sets into the multi-layer neural network classifier to be trained for training, and obtain a trained multi-task prediction model.

[0004] Smoking behavior is an existence and a specific lifestyle in residents' lives and consumption behaviors. From the perspective of lifestyle, smoking behavior will aggravate the carbon emission problem in the city. However, the above-mentioned public prediction methods and similar methods mainly focus on carbon emission prediction at the enterprise or industrial level. Although they can accurately capture the carbon emission data of enterprises, they lack attention to the dynamic impact of individual behavior on carbon emissions. Therefore, in actual operation, the prediction accuracy is limited. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for predicting and controlling urban carbon emissions based on deep learning to solve the problems raised in the above-mentioned background technology.

[0006] First, in order to solve the above problems, a method for predicting and controlling urban carbon emissions based on deep learning is proposed, including:

[0007] Obtain data on the carbon content released by residents in public areas based on their smoking behavior;

[0008] Based on the carbon content data, the action data of residents’ smoking behavior in public areas is obtained. The action data consists of the moving positions of limb nodes.

[0009] Acquire target groups in public areas based on carbon content data and motion data;

[0010] Acquire first target action data, where the first target is any one in the target population;

[0011] Acquire the action data of the second target, where the second target is any one of the people in the public area whose carbon content data matches the smoking behavior;

[0012] Interacting the first target action data and the second target action data, and obtaining difference data, the difference data being used to analyze the smoking behavior pattern of the target population in the public area;

[0013] Parse the difference data and obtain additional data;

[0014] Additional data adjusts the action data based on smoking behavior and obtains correction data;

[0015] Predict residents' carbon emission actions based on smoking behavior based on the comparison of correction data and real-time action data;

[0016] Based on the correction data and carbon content data, control rules are formulated, and the control rules are executed based on the matching degree between the target object's action data and the correction data and carbon content data.

[0017] As a further preferred embodiment of the present technical solution, a method for acquiring action data of smoking behavior of residents in a public area includes:

[0018] Mark residents’ limb nodes based on image acquisition technology, including hand nodes, arm nodes and head nodes;

[0019] Get a time series of carbon content data;

[0020] Obtain the motion trajectory and motion frequency of limb nodes based on time series;

[0021] A smoking behavior determination formula is constructed based on the duration of carbon content data, the duration of movement trajectory, and the movement frequency;

[0022] Based on the smoking behavior determination formula, it is determined whether the acquired action data matches the smoking behavior.

[0023] As a further preferred embodiment of the present technical solution, the smoking behavior determination formula is:

[0024] ;

[0025] Where P smokingIt is used to indicate the probability of smoking behavior. The value range is usually between 0 and 1. The closer to 1, the greater the possibility of smoking. emission Used to represent known carbon emissions, f motion Used to represent the movement frequency of the limb nodes, f threshold The motion frequency threshold used to indicate the smoking action, f threshold Based on the observation and analysis of normal smoking behavior, t carbon The duration used to represent carbon content data, t motion It is used to represent the duration of the movement trajectory, and β is an artificially set adjustment coefficient used to adjust the correlation between carbon emissions and smoking behavior;

[0026] Based on P smoking The numerical value of determines whether the acquired action data matches the smoking behavior.

[0027] As a further preferred embodiment of the present technical solution, the interaction method between the first target action data and the second target action data is:

[0028] Based on the image acquisition technology, half-body images of the first target and the second target are respectively acquired;

[0029] Based on the time series, the number of half-body images of the first target and the number of half-body images of the second target are accumulated, and the image sequence of the first target and the second target in the same time period is obtained;

[0030] analyzing the motion trajectories of the limb nodes in the first image sequence and the second image sequence;

[0031] Analyze the difference between the first motion trajectory and the second motion trajectory based on the motion trajectory analogy formula;

[0032] Acquire feature data of the first target half-body image and the second target half-body image, the feature data including: environment data and target action data;

[0033] The difference value and the feature data are integrated to form difference data.

[0034] As a further preferred embodiment of the present technical solution, a two-dimensional coordinate system is constructed based on the half-body image, and the two-dimensional coordinate system is used to record the motion trajectory of the target limb node;

[0035] At each time point t in the time series, the target's limb node position is S(t)=(X (t) ,Y (t) ) indicates that the motion trajectory of the first target is S1={S1(t) / t=t0,t1,……t n}, the motion trajectory of the second target is S2={S2(t) / t=t0,t1,……t n};

[0036] The formula for obtaining the distance d(t) between the first target limb node position and the second target limb node position is:

[0037] , where [x1(t), y1(t)] is the limb node position of the first target at time point t, [x2(t), y2(t)] is the limb node position of the second target at time point t, and the motion trajectory analogy formula is:

[0038] , where D weighted is the difference between the first target behavior data and the second target behavior data.

[0039] As a further preferred embodiment of the present technical solution, the method for obtaining carbon content data includes:

[0040] Obtain the area of ​​public areas based on smoking behavior of urban residents;

[0041] Collect gas content in public areas based on unit time;

[0042] Obtain carbon content data based on gas content and urban tobacco combustion carbon emission formula;

[0043] The carbon emission formula for urban tobacco combustion is:

[0044] ;

[0045] The E carbon,total It is used to represent the carbon content data of tobacco combustion carbon emissions in public areas, where n is the number of gas types, C i and EF i are the content of the i-th gas and the carbon emission factor, respectively. T represents the unit time, and A represents the area of ​​the public area based on smoking behavior.

[0046] As a further preferred embodiment of the present technical solution, the comparison method of the correction data and the real-time action data includes:

[0047] Integrate alignment correction data and real-time motion data based on time series;

[0048] Obtain feature vectors that match the correction data and real-time motion data;

[0049] Retrieve features from the smoking behavior action data of residents in public areas based on the categories of feature vectors.

[0050] Secondly, in order to further improve the above technical solution, a system using the above urban carbon emission prediction and control method based on deep learning is also proposed, and includes: a data collection module for collecting real-time action data of the target population and carbon content data in public areas;

[0051] The data processing module is used to process and analyze the data collected by the data acquisition module, including preprocessing, feature extraction and pattern recognition of the data;

[0052] A data analysis module, used to analyze the data processed by the processing module, identify smoking behavior patterns in public areas, and adjust action data based on smoking behavior;

[0053] The prediction control module is used to formulate control rules according to the prediction results of the data analysis module, and adjust the ventilation system or other environmental conditioning facilities in the public area based on the control rules to reduce carbon emissions;

[0054] The user interface module is used to display real-time data and prediction results, provide user interaction functions, and enable managers to monitor system status and manually adjust control rules.

[0055] As a further preferred embodiment of the present technical solution, the data acquisition module includes: an image acquisition unit and a gas content acquisition unit, the image acquisition unit captures the behavior images of residents in the public area based on the image acquisition technology, and the gas content acquisition unit is used to collect the gas content of the public area based on unit time;

[0056] The data processing module includes: a motion data acquisition unit, a carbon content data calculation unit and a target population identification unit. The motion data acquisition unit marks the limb nodes of residents based on image acquisition technology, and obtains the motion trajectory and motion frequency of these nodes, so as to identify smoking behavior. The carbon content data calculation unit is used to calculate the carbon content data of tobacco burning in the public area according to the collected gas content and the urban tobacco burning carbon emission formula. The target population identification unit identifies the target population in the public area based on the carbon content data and the motion data.

[0057] The data analysis module includes: a difference data acquisition unit and a correction data generation unit. The difference data acquisition unit acquires difference data by comparing the action data of different individuals in the target population and analyzes the smoking behavior pattern. The correction data generation unit adjusts the action data based on the smoking behavior based on the difference data and the additional data to generate correction data.

[0058] The prediction and control module includes: a carbon emission prediction unit and a management and control rule formulation unit. The carbon emission prediction unit predicts the carbon emission actions of residents based on smoking behavior based on the comparison of correction data and real-time action data. The management and control rule formulation unit formulates management and control rules based on the correction data and carbon content data.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] The urban carbon emission prediction and control method and system based on deep learning identifies the target population in the public area by collecting carbon content data and action data, and obtains difference data and analyzes the smoking behavior patterns differentiated by the difference data by comparing the action data of the target individual with that of other targets. By deeply analyzing the smoking behavior patterns of the target population and combining the difference data, the carbon emission characteristics of different smoking individuals are identified. By collecting multiple data and setting based on deep learning, it can not only predict the smoking behavior of the target population, but also adjust the personalized control strategy based on the difference data.

[0061] In addition, the present invention realizes the ability to extract difference data from behavior patterns by comparing and analyzing the action data of the target population and other target individuals, and uses these difference data to adjust the value of the correction data, thereby improving the accuracy and real-time performance of carbon emission prediction;

[0062] Finally, based on the analysis of behavioral patterns, the present invention further analyzes the difference data, automatically adjusts the correction data, and compares it with the real-time action data, so as to predict the future smoking behavior and carbon emission settings of residents, which not only improves the accuracy of carbon emission prediction, but also promotes the dynamic optimization of management and control rules. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is an operation flow chart of the method of the present invention;

[0064] Figure 2 It is a module composition diagram of the system of the present invention;

[0065] Figure 3 It is an auxiliary diagram of step S101 in the specific implementation process of the present invention;

[0066] Figure 4 This is a two-dimensional coordinate system diagram constructed based on the half-body image of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Before understanding the technical solution proposed in the present invention, it should be clear that when the technical solution proposed in the present invention is put into the existing technical field, it can be put into any monitoring equipment with image acquisition technology installed in public places, for example, integrated into traffic monitoring cameras, shopping mall security monitoring systems and smart street lamp equipment. In addition, it should be noted that in order to further improve the prediction accuracy, when it is actually put into use, it can also cooperate with mobile devices (mobile phones or smart watches) apps commonly used by residents, so that these apps can obtain the urban location of residents without causing information leakage, which is used to determine high-emission public areas where smoking behavior is frequent, thereby identifying potential high-carbon emission areas by analyzing the movement trajectories and behavioral habits of residents, and providing data support for urban planning and environmental management, so as to achieve more scientific and effective carbon emission control.

[0069] refer to Figure 1 It can be seen that the present invention proposes a method for predicting and controlling urban carbon emissions based on deep learning, including: steps S100 to S800.

[0070] Step S100: Acquire carbon content data released by residents in a public area based on their smoking behavior.

[0071] Specifically, the method for obtaining the carbon content in step S100 includes: step S101 to step S103.

[0072] Specifically, step S101: obtaining the public area based on the smoking behavior of urban residents.

[0073] It should be added that the determination and calculation of the public area area in step S101 are obtained by obtaining the number of monitoring devices implanted with the method disclosed in the present invention in the public area and the distance between two adjacent monitoring devices.

[0074] Specifically, refer to Figure 3 It can be seen that, assuming that three surveillance devices are installed in different areas of the commercial street (such as the entrance passage, snack area and rest area), the surveillance range of these surveillance devices is 50 square meters. Among them, A is located at the entrance of the commercial area, covering the entire entrance passage of the commercial street, surveillance device B is located in the snack area of ​​the commercial street, covering the main passage of the area, and surveillance device C is located in the rest area of ​​the commercial street, covering a quarter of the area. At this time, the surveillance ranges of surveillance devices A, B, and C are 50 square meters, 50 square meters, and 12.5 square meters respectively. By calculating the sum of the surveillance ranges of these surveillance devices, the public area is calculated to be 112.5 square meters.

[0075] Step S102: Collecting the gas content in the public area based on unit time.

[0076] It should be clear that when step S102 is implemented, the unit time is 2.5 minutes, and the gas content is obtained by real-time monitoring through gas sensors installed in the monitoring equipment in the prior art. These sensors in the prior art can be specifically gas-sensitive smoke sensors, which mainly obtain the gas content in the public area by detecting the concentration of smoke particles in the air.

[0077] Step S103: Obtaining carbon content data based on the gas content and the urban tobacco combustion carbon emission formula.

[0078] It should be noted that the urban tobacco combustion carbon emission formula disclosed in step S103 is:

[0079] , where E carbon,total It is used to represent the carbon content data of tobacco combustion carbon emissions in public areas, where n is the number of gas types, C i and EF i are the content of the i-th gas and the carbon emission factor, respectively. T represents the unit time, and A represents the area of ​​the public area based on smoking behavior.

[0080] Specifically, when the urban tobacco combustion carbon emission formula is applied to actual places, assuming that in the public area of ​​a commercial street, if the monitoring range of monitoring device A is used as a reference, if the smoke particle concentration detected in the area per unit time is C i , the specific value is 1000μg / m³, and the public area A caused by smoking in this area is 100 square meters. Assuming that the smoke particle concentration C i Corresponding carbon emission factor EF i is 0.001 g / μg, and this gas is the only gas species detected, then E carbon,total The calculated result is 1000μg / m³ × 0.001g / μg × 2.5min = 2.5g / m 3 Therefore, in the public area of ​​the commercial street, the carbon emission per unit time from tobacco burning is 2.5g / m 3 .

[0081] Step S200: Based on the carbon content data, the action data of the smoking behavior of residents in the public area is obtained.

[0082] It should be clear that in step S200, the motion data is composed of the moving positions of the limb nodes. In addition, in step S200, the method for obtaining the motion data of the smoking behavior of residents in the public area includes: steps S201-S204.

[0083] Specifically, step S201: marking the limb nodes of residents based on image acquisition technology.

[0084] It should be clear that in step S201, the limb nodes include: hand nodes, arm nodes and head nodes. In addition, the image acquisition technology in step S201 is a mature technical method in the current image field. Specifically, in the present invention, it is mainly set in the monitoring equipment. When the monitoring equipment is actually running, it realizes the marking of the residents' limb nodes by identifying and tracking the positions of the limb nodes.

[0085] Step S202: Acquire the time series of carbon content data.

[0086] It should be clear that step S202 can make a temporal correspondence between the acquired carbon content data and the action data of the residents' smoking behavior, thereby accurately analyzing the relationship between the residents' smoking behavior and the carbon emissions.

[0087] Specifically, the acquisition of the time series in step S202 is achieved by pre-installing a clock synchronization function in the monitoring device, thereby ensuring the accuracy of data collection. The clock synchronization function is specifically achieved in the present invention by adding a GPS module to the monitoring device. The GPS module can be synchronized with the global positioning system to ensure that the time information of the monitoring device is consistent with the global standard time. In this way, even when multiple monitoring devices are working at the same time, it can be ensured that the data collected by all devices have a unified timestamp, which is convenient for subsequent data analysis and processing.

[0088] Step S203: Acquire the motion trajectory and motion frequency of the limb node based on the time series.

[0089] It should be clear that obtaining the motion trajectory and motion frequency of the limb node through the time series in step S203 is achieved through the image capture function in the prior art.

[0090] Specifically, the limb nodes are marked in step S201, and the time series of carbon content data is obtained in step S202. Since step S201 and step S202 are both in the same area (public area), the monitoring equipment is equipped with image capture function, and the motion trajectory and frequency information of the acquired limb nodes are combined with the time series of carbon content data to analyze the correlation between residents' activity patterns in public areas and carbon emissions, thereby providing more accurate data support for the prediction and control of urban carbon emissions.

[0091] Step S204: construct a smoking behavior determination formula based on the duration of the carbon content data, the duration of the motion trajectory, and the motion frequency, and determine whether the acquired motion data matches the smoking behavior based on the smoking behavior determination formula.

[0092] It should be added that the smoking behavior determination formula proposed in step S204 of the present invention is:

[0093] ;

[0094] Where P smoking It is used to indicate the probability of smoking behavior. The value range is usually between 0 and 1. The closer to 1, the greater the possibility of smoking. emission Used to represent known carbon emissions, f motion Used to represent the movement frequency of the limb nodes, f threshold The motion frequency threshold used to indicate the smoking action, f threshold Based on the observation and analysis of normal smoking behavior, t carbon The duration used to represent carbon content data, t motion It is used to represent the duration of the movement trajectory, and β is an artificially set adjustment coefficient used to adjust the degree of correlation between carbon emissions and smoking behavior.

[0095] Specifically, when the smoking behavior determination formula is actually used, when C emission When the specific value of is 10.32g, f motion The value is 0.5Hz, t carbon The value of t is 15min, motion The value of f is 10min, threshold Set to 0.4Hz, β to 0.6, based on these parameters, P is calculated smoking =0.6×10.32g×0.5Hz / 0.4Hz×(15min / 10min)=0.934. According to the calculation results, P smoking The value of is close to 1, indicating that the action data is highly matched with the smoking behavior. Therefore, it can be determined that the action data does reflect the smoking behavior.

[0096] Step S300: Acquire a target population in a public area based on the carbon content data and the action data.

[0097] It should be clear that the specific method of obtaining the target population in step S300 is to identify and classify the behavior patterns of the population by analyzing the carbon content data and motion data in the public area. The carbon emission data in the public area is first collected from fixed monitoring equipment, and then combined with the motion data, which includes body movements, movement speed, direction changes, etc., possible smoking behaviors are identified to distinguish which groups of people may have smoked within a specific time, thereby locating the target population, which not only improves the efficiency of data processing, but also enhances the ability to control carbon emission behaviors in public areas.

[0098] Step S400: Obtain difference data.

[0099] It should be clear that the difference data in step S400 is used to analyze the smoking behavior pattern of the target population in the public area. Specifically, in the present invention, the method for obtaining the difference data is to collect the action data of the first target, wherein the first target refers to any individual in the target group, collect the action data of the second target, and the second target specifically refers to any individual in the public area population who has a smoking behavior that matches the carbon content data. The action data of the first target and the action data of the second target are interactively analyzed to extract the difference data between the two.

[0100] It should be added that the method for interactively analyzing the action data of the first target and the action data of the second target includes: steps S401 to S406.

[0101] Step S401: Based on the image acquisition technology, half-body images of the first target and the second target are respectively obtained. It should be supplemented that the half-body images contain action data.

[0102] Step S402: stacking the number of half-body images of the first target and the number of half-body images of the second target based on the time sequence, and acquiring the image sequence of the first target and the second target in the same time period.

[0103] It should be noted that step S402 is used to ensure that the behavior pattern of the target individual is analyzed in the same time context.

[0104] Step S403: analyzing the motion trajectories of the limb nodes in the first image sequence and the second image sequence.

[0105] Step S404: analyzing the difference between the first motion trajectory behavior data and the second motion trajectory behavior data based on the motion trajectory analogy formula.

[0106] Step S405: Acquire feature data of the first target half-body image and the second target half-body image, wherein the feature data includes: environment data and target action data.

[0107] Step S406: Integrate the difference value and the feature data to form difference data.

[0108] It should be supplemented that, in step S406, the integration of the difference value and the feature data adopts the assignment method, that is, the difference data is generated by adjusting the value of the feature data.

[0109] In addition, it should be pointed out that between step S401 and step S402, preprocessing must be performed in order to analyze the motion trajectory of the limb node.

[0110] Specifically, a two-dimensional coordinate system is constructed based on the half-body image, which is used to track and record the motion trajectory of the target limb nodes. It should be noted that the two-dimensional coordinate system is implemented through the graphics drawing function of existing computer programs. The horizontal and vertical coordinates of the two-dimensional coordinate system respectively represent the positions of two different limb nodes in the motion data.

[0111] It should be added that at each time point t in the time series, the target's limb node position is S(t)=(X (t) ,Y (t) ), indicating that the motion trajectory of the first target is S1={S1(t) / t=t0,t1,……t n}, the motion trajectory of the second target is S2={S2(t) / t=t0,t1,……t n};

[0112] The formula for obtaining the distance d(t) between the first target limb node position and the second target limb node position is:

[0113] , where [x1(t), y1(t)] is the limb node position of the first target at time point t, [x2(t), y2(t)] is the limb node position of the second target at time point t, and the motion trajectory analogy formula is:

[0114] , where D weighted is the difference between the first target behavior data and the second target behavior data.

[0115] It should be further explained that the reference Figure 4 , the motion trajectory analogy formula is actually running, setting the time point t 0， At this time, the first target limb node position S1(t0)=(X 1(t0) ,Y 1(t0) )=(3,4), the second target limb node position S2(t0)=(X 2(t0) ,Y 2(t0) )=(7,1), at this time, .

[0116] Since there is only one time point t0, The value of is approximately 1, so D weighted =1×d(t0)=5, so the difference value of this behavior is 5 unit nodes.

[0117] In addition, when the limb node position is a negative value, the first target limb node position S1(t1)=(-2,3). At this time, the value of -2 represents that the first target limb node position is shifted backward relative to the limb node position based on smoking behavior. The second target limb node position is S2(t2)=(X 2(t0) ,Y 2(t0) )=(8,-2), at this time the distance d(t1) between the first target limb node position and the second target limb node position is approximately , so the difference in this behavior is 11 unit nodes.

[0118] Step S500: parse the difference data and obtain additional data.

[0119] It should be noted that, in step S500, the additional data includes the difference value and the environmental data between the first target and the second target.

[0120] Step S600: Additional data is used to adjust the action data based on the smoking behavior and obtain correction data.

[0121] It should be added that the additional data in step S600 adjusts the action data based on the smoking behavior by fine-tuning the position of the limb nodes in the action data through the positive and negative difference values.

[0122] Specifically, when the difference value is positive, it means that the limb node position of the first target is ahead of the second target. At this time, the motion data of the first target needs to be adjusted backward. Conversely, when the difference value is negative, it means that the limb node position of the first target lags behind the second target. The motion data of the first target needs to be adjusted forward. It should be added that the correction data is obtained to ensure the accuracy of the motion data so as to more accurately predict and control urban carbon emissions.

[0123] Step S700: Predicting the carbon emission actions of residents based on their smoking behaviors based on the comparison between the correction data and the real-time action data.

[0124] It should be understood that, in step S700 , the method for comparing the correction data and the real-time motion data includes steps S701 to S703 .

[0125] Specifically, step S701: integrating the alignment correction data and the real-time motion data based on the time series.

[0126] It should be added that step S701 is used to integrate the data collected at different time points to ensure the consistency and comparability of the data, which is achieved by collecting the correction data and real-time motion data with the same timestamp.

[0127] Step S702: Obtain feature vectors that match the correction data and the real-time motion data.

[0128] It should be added that step S702 is used to extract common feature information from the two sets of data. Specifically, step S702 is completed through a feature extraction algorithm in the prior art, with the aim of finding key features that can represent the similarity between the two sets of data. In this way, the correspondence between the correction data and the real-time action data can be effectively identified, thereby providing accurate input for subsequent prediction models.

[0129] Step S703: Retrieve features in the smoking behavior action data of residents in the public area based on the category of the feature vector.

[0130] It should be noted that step S703 aims to identify a smoking behavior pattern that matches the feature vector by analyzing the smoking behavior action data of residents in the public area.

[0131] Step S800: Formulate control rules based on the correction data and carbon content data.

[0132] It should be noted that the control rules are executed based on the matching degree between the action data of the target object and the correction data and the carbon content data.

[0133] In addition, it should be added that in step S800, the control rules include: determining the action data of the target object, including age, gender, and occupational information, analyzing the correlation between the correction data and the carbon content data to determine the impact of different action data on carbon emissions, formulating corresponding control measures, such as restricting smoking behavior in specific areas, or imposing economic penalties on high-emission behaviors, implementing a dynamic adjustment mechanism, and continuously optimizing the control rules based on real-time monitoring data and feedback from the prediction model.

[0134] It should be added that the control rules are executed based on the matching degree between the target object's action data and the correction data and the carbon content data, and the matching degree is determined based on the smoking behavior determination formula in step S204 and the method of obtaining the difference value in step S400.

[0135] refer to Figure 2 It can be seen that, in order to improve the above technical solution, the present invention also proposes a city carbon emission prediction and control system based on deep learning, including: a data collection module for collecting real-time action data of the target population and carbon content data in the public area;

[0136] The data processing module is used to process and analyze the data collected by the data acquisition module, including preprocessing, feature extraction and pattern recognition of the data;

[0137] A data analysis module, used to analyze the data processed by the processing module, identify smoking behavior patterns in public areas, and adjust action data based on smoking behavior;

[0138] The prediction control module is used to formulate control rules according to the prediction results of the data analysis module, and adjust the ventilation system or other environmental conditioning facilities in the public area based on the control rules to reduce carbon emissions;

[0139] The user interface module is used to display real-time data and prediction results, provide user interaction functions, and enable managers to monitor system status and manually adjust control rules.

[0140] It should be added that the data acquisition module includes: an image acquisition unit and a gas content acquisition unit. The image acquisition unit captures the behavior images of residents in the public area based on image acquisition technology, and the gas content acquisition unit is used to collect the gas content of the public area based on unit time.

[0141] The data processing module includes: a motion data acquisition unit, a carbon content data calculation unit and a target population identification unit. The motion data acquisition unit marks the limb nodes of residents based on image acquisition technology, and obtains the motion trajectory and motion frequency of these nodes, so as to identify smoking behavior. The carbon content data calculation unit is used to calculate the carbon content data of tobacco burning in the public area according to the collected gas content and the urban tobacco burning carbon emission formula. The target population identification unit identifies the target population in the public area based on the carbon content data and motion data.

[0142] The data analysis module includes: a difference data acquisition unit and a correction data generation unit. The difference data acquisition unit obtains difference data by comparing the action data of different individuals in the target population and analyzes the smoking behavior pattern. The correction data generation unit adjusts the action data based on the smoking behavior based on the difference data and the additional data to generate correction data.

[0143] The prediction and control module includes: a carbon emission prediction unit and a management and control rule formulation unit. The carbon emission prediction unit predicts the carbon emission actions of residents based on their smoking behaviors based on the comparison of correction data and real-time action data. The management and control rule formulation unit formulates management and control rules based on the correction data and carbon content data.

[0144] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. A method for predicting and controlling urban carbon emissions based on deep learning, characterized in that: include: Obtain data on the carbon content released by residents in public areas based on their smoking behavior; Based on the carbon content data, the action data of residents’ smoking behavior in public areas is obtained. The action data consists of the moving positions of limb nodes. Acquire target groups in public areas based on carbon content data and motion data; Acquire first target action data, where the first target is any one in the target population; Acquire the action data of the second target, where the second target is any one of the people in the public area whose carbon content data matches the smoking behavior; Interacting the first target action data and the second target action data, and obtaining difference data, the difference data being used to analyze the smoking behavior pattern of the target population in the public area; Parse the difference data and obtain additional data; Additional data adjusts the action data based on smoking behavior and obtains correction data; Predict residents' carbon emission actions based on smoking behavior based on the comparison of correction data and real-time action data; Based on the correction data and carbon content data, control rules are formulated, and the control rules are executed based on the matching degree between the target object's action data and the correction data and carbon content data.

2. According to claim 1, a method for predicting and controlling urban carbon emissions based on deep learning is characterized in that: The method for acquiring action data of residents' smoking behavior in public areas includes: Mark residents’ limb nodes based on image acquisition technology, including hand nodes, arm nodes and head nodes; Get a time series of carbon content data; Obtain the motion trajectory and motion frequency of limb nodes based on time series; A smoking behavior determination formula is constructed based on the duration of carbon content data, the duration of movement trajectory, and the movement frequency; Based on the smoking behavior determination formula, it is determined whether the acquired action data matches the smoking behavior.

3. The method for predicting and controlling urban carbon emissions based on deep learning according to claim 2 is characterized in that: The smoking behavior determination formula: ； Where P smoking It is used to indicate the probability of smoking behavior. The value range is usually between 0 and 1. The closer to 1, the greater the possibility of smoking. emission Used to represent known carbon emissions, f motion Used to represent the movement frequency of the limb nodes, f threshold The motion frequency threshold used to indicate the smoking action, f threshold Based on the observation and analysis of normal smoking behavior, t carbon The duration used to represent carbon content data, t motion It is used to represent the duration of the movement trajectory, and β is an artificially set adjustment coefficient used to adjust the correlation between carbon emissions and smoking behavior; Based on P smoking The numerical value of determines whether the acquired action data matches the smoking behavior.

4. The method for predicting and controlling urban carbon emissions based on deep learning according to claim 1, characterized in that: Interaction method between the first target action data and the second target action data: Based on the image acquisition technology, half-body images of the first target and the second target are respectively acquired; Based on the time series, the number of half-body images of the first target and the number of half-body images of the second target are accumulated, and the image sequence of the first target and the second target in the same time period is obtained; analyzing the motion trajectories of the limb nodes in the first image sequence and the second image sequence; Analyze the difference between the first motion trajectory and the second motion trajectory based on the motion trajectory analogy formula; Acquire feature data of the first target half-body image and the second target half-body image, the feature data including: environment data and target action data; The difference value and the feature data are integrated to form difference data.

5. The method for predicting and controlling urban carbon emissions based on deep learning according to claim 4 is characterized in that: A two-dimensional coordinate system is constructed based on the half-body image, and the two-dimensional coordinate system is used to record the motion trajectory of the target limb node; At each time point t in the time series, the target's limb node position is S(t)=(X (t) ,Y (t) ) indicates that the motion trajectory of the first target is S1={S1(t) / t=t0,t1,……t n }, the motion trajectory of the second target is S2={S2(t) / t=t0,t1,……t n }; The formula for obtaining the distance d(t) between the first target limb node position and the second target limb node position is: , where [x1(t), y1(t)] is the limb node position of the first target at time point t, [x2(t), y2(t)] is the limb node position of the second target at time point t, and the motion trajectory analogy formula is: , where D weighted is the difference between the first target behavior data and the second target behavior data.

6. The method for predicting and controlling urban carbon emissions based on deep learning according to claim 1, characterized in that: Methods for obtaining carbon content data include: Obtain the area of ​​public areas based on smoking behavior of urban residents; Collect gas content in public areas based on unit time; Obtain carbon content data based on gas content and urban tobacco combustion carbon emission formula; The carbon emission formula for urban tobacco combustion is: ； The E carbon,total It is used to represent the carbon content data of tobacco combustion carbon emissions in public areas, where n is the number of gas types, C i and EF i are the content of the i-th gas and the carbon emission factor, respectively. T represents the unit time, and A represents the area of ​​the public area based on smoking behavior.

7. The method for predicting and controlling urban carbon emissions based on deep learning according to claim 1, characterized in that: The comparison method between the correction data and the real-time motion data includes: Integrate alignment correction data and real-time motion data based on time series; Obtain feature vectors that match the correction data and real-time motion data; Retrieve features from the smoking behavior action data of residents in public areas based on the categories of feature vectors.

8. A system for predicting and controlling urban carbon emissions based on deep learning, using a method for predicting and controlling urban carbon emissions based on deep learning as described in any one of claims 1 to 7, characterized in that: include: Data collection module, used to collect real-time action data of target groups and carbon content data in public areas; The data processing module is used to process and analyze the data collected by the data acquisition module, including preprocessing, feature extraction and pattern recognition of the data; A data analysis module, used to analyze the data processed by the processing module, identify smoking behavior patterns in public areas, and adjust action data based on smoking behavior; The prediction control module is used to formulate control rules according to the prediction results of the data analysis module, and adjust the ventilation system or other environmental conditioning facilities in the public area based on the control rules to reduce carbon emissions; The user interface module is used to display real-time data and prediction results, provide user interaction functions, and enable managers to monitor system status and manually adjust control rules.

9. The urban carbon emission prediction and control system based on deep learning according to claim 8, characterized in that: The data acquisition module includes: an image acquisition unit and a gas content acquisition unit, the image acquisition unit captures the behavior images of residents in the public area based on image acquisition technology, and the gas content acquisition unit is used to collect the gas content of the public area based on unit time; The data processing module includes: a motion data acquisition unit, a carbon content data calculation unit and a target population identification unit. The motion data acquisition unit marks the limb nodes of residents based on image acquisition technology, and obtains the motion trajectory and motion frequency of these nodes, so as to identify smoking behavior. The carbon content data calculation unit is used to calculate the carbon content data of tobacco burning in the public area according to the collected gas content and the urban tobacco burning carbon emission formula. The target population identification unit identifies the target population in the public area based on the carbon content data and the motion data. The data analysis module includes: a difference data acquisition unit and a correction data generation unit. The difference data acquisition unit acquires difference data by comparing the action data of different individuals in the target population and analyzes the smoking behavior pattern. The correction data generation unit adjusts the action data based on the smoking behavior based on the difference data and the additional data to generate correction data. The prediction and control module includes: a carbon emission prediction unit and a management and control rule formulation unit. The carbon emission prediction unit predicts the carbon emission actions of residents based on smoking behavior based on the comparison of correction data and real-time action data. The management and control rule formulation unit formulates management and control rules based on the correction data and carbon content data.

Images