Campus carbon footprint calculation method and system for middle and primary schools

Abstract

The invention discloses a middle and primary school campus carbon footprint calculation method, which comprises the following steps of S1, identifying people in a campus; s2, identifying vehicles in the campus; s3, trajectory path planning; s4, calculating the carbon emission in the campus; s5, calculating target carbon emission according to the target track information; the invention relates to a middle and primary school campus carbon footprint calculation system, which comprises a camera and an NFC (Near Field Communication), a vehicle access gate; a campus local area network; a trajectory generation platform; a carbon emission prediction model; according to the invention, identification and positioning are carried out through the camera and the NFC, and target track information is generated through the track generation platform; according to the method, the carbon emission in the school is predicted through an artificial intelligence algorithm, a prediction report of the carbon emission is obtained, the carbon emission in the school is conveniently reduced, and an individual chat trajectory is obtained; and different weight ratio distribution is carried out on the use frequency of the building, so that accurate prediction of carbon emission can be conveniently realized.

Description

Technical Field

[0001] The present invention relates to the technical field of campus carbon footprint, and in particular to a method and system for calculating campus carbon footprint of primary and secondary schools. Background Art

[0002] Carbon emissions is a general term or abbreviation for greenhouse gas emissions. Carbon dioxide is the most important gas in greenhouse gases, so the term carbon is used as a representative. Although it is not accurate, the fastest way for the public to understand is to simply understand "carbon emissions" as "carbon dioxide emissions."

[0003] Any human activity may cause carbon emissions. For example, ordinary people's simple cooking can cause carbon emissions, and any waste gas from burning objects will produce carbon emissions. Most scientists and governments admit that greenhouse gases have and will continue to bring disasters to the earth and mankind, so terms such as "(control) carbon emissions" and "carbon neutrality" have become a cultural basis that is easily understood, accepted, and acted upon by most people.

[0004] Carbon footprint is an indicator used to measure the amount of carbon dioxide emissions caused directly or indirectly by an individual, organization, product or country within a certain period of time. The calculation of carbon footprint covers the emissions of the entire life cycle of a product or service from production, transportation, final use to waste disposal. This comprehensive assessment method enables us to more accurately understand and evaluate the impact of human activities on the environment. The introduction of the carbon footprint concept is intended to remind people to be aware of the urgency of responding to climate change. By calculating and understanding the carbon footprint of an individual or organization, people can identify and implement strategies to reduce greenhouse gas emissions and thus combat global warming.

[0005] In the Chinese invention patent with application publication number CN113378014A, a campus personal carbon footprint assessment method and system are disclosed, which belongs to the field of campus management. In the campus personal carbon footprint assessment system, by setting up face recognition devices and location monitoring devices at important locations on campus, the target movement information of the target personnel is accurately obtained, and then the target trajectory information is generated through the trajectory generation platform, and then the target trajectory information is sent to the carbon footprint assessment platform, which alleviates the calculation pressure of the carbon footprint assessment platform; in addition, a carbon emission comprehensive calculation platform is provided to periodically obtain the carbon emission data of each building on campus, and the personal carbon emission data is accurately obtained in combination with the target trajectory information, so as to obtain a carbon footprint assessment report, which plays an important role in improving the low-carbon life awareness of individuals on campus through the report form, and also makes important preparations for the subsequent campus carbon emission big data survey.

[0006] However, in combination with the existing technology and the above application, there are still some problems in the existing technology. For example, it is impossible to calculate and analyze individual carbon emissions and total carbon emissions, it is impossible to accurately predict carbon emissions, and for various buildings on campus, it is impossible to calculate carbon emissions in combination with multiple situations, resulting in relatively general emission calculations. In particular, different buildings and different equipment have different amounts of carbon emissions. General calculations will cause problems such as inaccurate carbon emission predictions.

[0007] To this end, the present invention provides a method and system for calculating the carbon footprint of primary and secondary school campuses. Summary of the invention

[0008] 1. Technical issues to be solved

[0009] In view of the deficiencies in the prior art, the present invention provides a method and system for calculating the carbon footprint of primary and secondary school campuses. By identifying people and vehicles on campus, the identities of people on campus are determined, and positioning is performed in combination with NFC, so as to generate target trajectory information through a trajectory generation platform, and calculate the carbon emissions of buildings on campus, that is, by calculating and processing the facilities in the buildings on campus separately, the carbon emissions of the buildings can be accurately obtained, and the total carbon emissions can be calculated in combination with the amount of personnel data inside the buildings. In addition, the carbon emissions on campus can be predicted through an artificial intelligence algorithm, and a carbon emission prediction report can be obtained, which is convenient for reducing carbon emissions on campus and obtaining personal trajectory, thereby solving the technical problems recorded in the background technology.

[0010] (II) Technical solution

[0011] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0012] A method for calculating the carbon footprint of primary and secondary school campuses includes the following steps:

[0013] S1. Identification of people on campus: Install cameras on campus to identify people on campus, and install NFC chips in the cameras to locate people on campus;

[0014] S2. Vehicle identification on campus: Vehicles entering the campus and vehicles traveling on campus are identified by license plate numbers through cameras and school gate access control, and are located through the camera's NFC chip;

[0015] S3, trajectory path planning: according to the personnel or vehicle information detected by the camera, the location information of the personnel or vehicle is reported, and the target trajectory information is generated on the trajectory generation platform;

[0016] S4. Calculate the carbon emissions on campus: Calculate the carbon emissions of each building on campus, and the calculation formula is as follows: C = C 1 +C 2 =∑A i ×EF i +∑A e ×EF e ,

[0017] Among them, C is the carbon dioxide emissions from campus buildings, C 1 Direct carbon dioxide emissions from buildings on campus, C 2 Carbon dioxide emissions from campus infrastructure, A i Corresponding to C 1 Carbon emission inventory activity, A e Corresponding to C 2 Carbon emission inventory activities, EF i EF e They correspond to A i , A e Carbon emission factor;

[0018] S5. Calculate the target carbon emissions based on the target trajectory information: Calculate the target carbon emissions by averaging the target’s action trajectory, i.e., the total carbon emissions C in the building where the target is located. 总 , and the total number of people in the target building X 总 , the calculation formula of the carbon emission prediction model is as follows:

[0019] Among them, C r The calculation result of personal carbon emissions;

[0020] S6. Predict and calculate carbon emissions on campus through artificial intelligence algorithms:

[0021]

[0022] Among them, W ij Expressed as weight, C i is the input carbon emissions, y i represents the output activation, i.e. the predicted carbon emissions, and f represents the activation function.

[0023] Preferably, the camera is used to perform facial recognition on the people on campus, determine the identity information of the people after recognition, and determine the location of the people through NFC. The detected location information is combined through multiple camera recognition and NFC positioning, and the target trajectory information is generated through the trajectory generation platform. The target trajectory information is mainly used to determine whether the identified person is in a building on campus.

[0024] Preferably, the camera is installed at the corner of the path on campus. If the length of the path exceeds one kilometer, an additional camera is installed in the middle of the path. The camera uses a panoramic camera with night vision function and can realize all-round rotation detection. The camera is equipped with WIFI communication equipment inside, which communicates with the trajectory generation platform through the local area network on campus, and uploads the identification and positioning of the target.

[0025] Preferably, vehicles entering the campus are divided into on-campus vehicles and off-campus vehicles, and the carbon emissions generated by the vehicles are calculated using the following formula:

[0026] C 车 =C 内 +C 外 =∑A nc ×EF nc +∑A wc ×EF wc ,

[0027] Among them, C 车 Carbon dioxide emissions from campus vehicles, C 内 Carbon dioxide emissions from vehicles within campus, C 外 Carbon dioxide emissions from vehicles entering and leaving the campus, A nc Corresponding to C 内 Carbon emission inventory activity, A wc Corresponding to C 外 Carbon emission inventory activities, EF nc EF wc They correspond to A nc , A wc The carbon emission factor is set as A nc The value of is 2.9251, set A wc The value of is 0.000043.

[0028] Preferably, the carbon dioxide emissions from infrastructure on campus include gas consumption, coal consumption, electricity consumption, heating gas heat source, central heating, central cooling, tap water and garbage;

[0029] The above carbon emissions are all calculated using C j =∑A×EF for calculation;

[0030] In addition, the carbon emission factor of gas consumption is 0.002162, the carbon emission factor of coal consumption is 2.7725, the carbon emission factor of electricity consumption is 0.00058, the carbon emission factor of heating gas heat source is 0.002162, the carbon emission factor of central heating is 0.000105, the carbon emission factor of central cooling is 0.000161, the carbon emission factor of tap water is 0.000168 and the carbon emission factor of garbage is 0.528.

[0031] Preferably, when predicting carbon emissions, the artificial intelligence algorithm assigns weights to the corresponding building settings or teachers and students based on holidays, teacher and student life cycles, and other campus-specific factors, including the frequency of use of classrooms and dormitories, the opening hours of libraries and laboratories, and the operation of canteens. That is, for buildings with low usage frequency, the weight assigned to them is set below 0.5; for buildings with high usage frequency, the weight assigned to them is set above 0.5; for teaching buildings, the weight ratio is 1, which is set as the maximum weight value.

[0032] Preferably, before the artificial intelligence algorithm performs computational analysis, it normalizes the collected data information to reduce the dimension, maps each data information to [0, 1], reduces the computational pressure of the artificial intelligence algorithm, and improves the computational efficiency;

[0033] The calculation formula is as follows:

[0034]

[0035] Where g is the result of weight normalization calculated by Gaussian function, and the output range is between 0 and 1, G is the weight calculated by Gaussian function, G min is the minimum value calculated by the Gaussian function, G max It is the maximum value calculated by the Gaussian function. The data information is reduced in dimension through normalization.

[0036] Preferably, the target trajectory information is generated by the trajectory generation platform according to the detection and identification information of the target during its movement, and is mainly used to detect and determine whether the target has entered a building on campus, and to count the number of people in the building on campus, and to determine the number of people in the building on campus. The target detection includes the identity information of the target, and the identity information of the target is detected by the camera through face recognition, the target face is obtained, and the database of people on campus is contacted to obtain the target information by comparison, and then the weight value is assigned to the target;

[0037] Then, the trajectory generation platform calculates the target’s carbon emissions based on the artificial intelligence algorithm, and combines the target’s trajectory information to generate the target’s carbon footprint information.

[0038] Preferably, after receiving various data information, the carbon emission prediction model first pre-processes the data information, including cleaning, gaining, converting and filtering the data information, that is, removing abnormal data and erroneous data in the data information, amplifying the data information, and performing analog-to-digital conversion on the data information to facilitate subsequent calculation and filtering of the data information;

[0039] And the calculation of the filtering process is as follows:

[0040] The data information is filtered through a mean filter to improve the accuracy of the data information;

[0041] Set the window length to an odd number, use the average value of the data information to replace the value in the middle, gradually shift the window, filter the data information, and shift the step size to 1 until it slides to the end of the time series data; the calculation formula of the mean filter is as follows:

[0042]

[0043] in, Represents the output data set after mean filtering, m represents the size of the window, v(n) j Represents the jth data information in the input data set.

[0044] A carbon footprint calculation system for primary and secondary school campuses, comprising:

[0045] Camera and NFC: Face recognition of people on campus is performed at various intersections and paths through cameras and NFC. After face recognition, the location of people on campus is located through NFC. After positioning and recognition, the information and location of people on campus are reported and transmitted to the trajectory generation platform.

[0046] Vehicle entry and exit gates: Vehicles entering and leaving the campus are detected through the vehicle entry and exit gates, and the license plates of the vehicles are recognized, and the locations of the vehicles are reported to the trajectory generation platform;

[0047] The campus LAN is used to connect the camera and NFC to the vehicle entry and exit gates, and transmit the detected trajectory information and identification to the trajectory generation platform and carbon emission prediction model to generate target trajectory information and predict carbon emissions;

[0048] The trajectory generation platform obtains the collected information and location information of the personnel in the school, as well as the information and location information of the vehicles, and combines all the action location information to generate the target trajectory information;

[0049] The carbon emission prediction model processes the collected data information, that is, cleans, gains, converts and filters the data information to improve the accuracy of the data information, and then uses artificial intelligence algorithms to calculate and analyze the data information, so that the data can be used to predict carbon emissions within the school, and combine the target trajectory information to generate an individual's carbon trajectory, which is convenient for the management of carbon emissions within the school.

[0050] (III) Beneficial effects

[0051] The present invention provides a method and system for calculating carbon footprint of primary and secondary school campuses, which has the following beneficial effects:

[0052] The present invention is provided with cameras in the school, and especially at the intersections, the cameras are used to identify the people in the school and obtain the identity information of the people in the school, and the vehicles entering and leaving the school are identified and detected through the vehicle entry and exit gates, that is, the identities of the people in the school are determined by identifying the people and vehicles in the school, and the positioning is performed in combination with NFC, and the NFC is arranged inside the camera, and the positioning of the camera is facilitated to indirectly locate the people in the school, and to obtain accurate positioning information. The collected identification information and location information of the people in the school are then transmitted to the trajectory generation platform, so that the target trajectory information is generated by the trajectory generation platform;

[0053] The carbon emissions of buildings on campus are calculated. When various equipment in the buildings are in operation, they have different carbon emissions, which need to be calculated separately and then merged. That is, by calculating the facilities in the buildings on campus separately, the carbon emissions of the buildings can be accurately obtained. In addition, the total carbon emissions can be calculated by combining the personnel data inside the buildings. The carbon emissions on campus can be predicted through artificial intelligence algorithms, and a carbon emissions prediction report can be obtained to reduce the carbon emissions on campus and obtain personal conversation trajectories.

[0054] Different weight ratios are allocated according to different on-campus personnel and infrastructure, as well as for different building openings. When the artificial intelligence algorithm predicts carbon emissions, it can allocate weights to the corresponding building settings or teachers and students based on holidays, teacher and student life cycles, and other factors unique to the campus, including the frequency of use of classrooms and dormitories, the opening hours of libraries and laboratories, and the operation of canteens. That is, if the building setting is used less frequently, it will be assigned a small weight value, and if the building setting is used more frequently, it will be assigned a large weight value. This can achieve accurate calculation of carbon emissions and facilitate accurate prediction of carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of the steps of the carbon footprint management method for primary and secondary school campuses of the present invention;

[0056] Figure 2 It is a structural schematic diagram of the carbon footprint management system for primary and secondary school campuses of the present invention. DETAILED DESCRIPTION

[0057] 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.

[0058] See also Figure 1 The present invention provides a method for calculating the carbon footprint of primary and secondary school campuses, comprising the following steps:

[0059] S1. Identification of people on campus: Install cameras on campus to identify people on campus, and install NFC chips in the cameras to locate people on campus;

[0060] S2. Vehicle identification on campus: Vehicles entering the campus and vehicles traveling on campus are identified by license plate numbers through cameras and school gate access control, and are located through the camera's NFC chip;

[0061] S3, trajectory path planning: according to the personnel or vehicle information detected by the camera, the location information of the personnel or vehicle is reported, and the target trajectory information is generated on the trajectory generation platform;

[0062] S4. Calculate the carbon emissions on campus: Calculate the carbon emissions of each building on campus, and the calculation formula is as follows: C = C 1 +C 2 =∑A i ×EF i +∑A e ×EF e ,

[0063] Among them, C is the carbon dioxide emissions from campus buildings, C 1 Direct carbon dioxide emissions from buildings on campus, C 2 Carbon dioxide emissions from campus infrastructure, A i Corresponding to C 1 Carbon emission inventory activity, A e Corresponding to C 2 Carbon emission inventory activities, EF i EF e They correspond to A i , Ae Carbon emission factor;

[0064] S5. Calculate the target carbon emissions based on the target trajectory information: Calculate the target carbon emissions by averaging the target’s action trajectory, i.e., the total carbon emissions C in the building where the target is located. 总 , and the total number of people in the target building X 总 , the calculation formula of the carbon emission prediction model is as follows:

[0065] Among them, C r The calculation result of personal carbon emissions;

[0066] S6. Predict and calculate carbon emissions on campus through artificial intelligence algorithms:

[0067]

[0068] Among them, W ij Expressed as weight, C i is the input carbon emissions, y i represents the output activation, i.e. the predicted carbon emissions, and f represents the activation function.

[0069] In order to identify people on campus and perform positioning through NFC during identification to facilitate obtaining the movement trajectory of people on campus, in this embodiment, preferably, the camera is used to perform facial recognition on people on campus, determine the identity information of the person after recognition, and determine the location of the person through NFC, and then combine the detected location information through multiple camera recognition and NFC positioning, and generate target trajectory information through the trajectory generation platform, and the target trajectory information is mainly used to determine whether the identified person is in a building on campus.

[0070] In order to prevent people on campus from changing lanes midway and to upload the collected location information and identification information, in this embodiment, preferably, the camera is installed at the corner of the path on campus, and if the path length exceeds one kilometer, an additional camera is set in the middle of the path. The camera uses a panoramic camera with night vision function and can realize all-round rotation detection. The camera is equipped with WIFI communication equipment inside, which realizes communication connection with the trajectory generation platform through the local area network on campus, and uploads the identification and positioning of the target.

[0071] In order to calculate and process on-campus vehicles and off-campus vehicles separately and improve the accuracy of carbon emissions calculation, in this embodiment, preferably, vehicles entering the campus are divided into on-campus vehicles and off-campus vehicles, and the carbon emissions generated by the vehicles are calculated using the following formula:

[0072] C车 =C 内 +C 外 =∑A nc ×EF nc +∑A wc ×EF wc ,

[0073] Among them, C 车 Carbon dioxide emissions from campus vehicles, C 内 Carbon dioxide emissions from vehicles within campus, C 外 Carbon dioxide emissions from vehicles entering and leaving the campus, A nc Corresponding to C 内 Carbon emission inventory activity, A wc Corresponding to C 外 Carbon emission inventory activities, EF nc EF wc They correspond to A nc , A wc The carbon emission factor is set as A nc The value of is 2.9251, set A wc The value of is 0.000043.

[0074] In order to calculate and process the carbon emissions of buildings on campus, in this embodiment, preferably, the carbon dioxide emissions of infrastructure on campus include gas consumption, coal consumption, electricity consumption, heating gas heat source, central heating, central cooling, tap water and garbage;

[0075] The above carbon emissions are all calculated using C j =∑A×EF for calculation;

[0076] In addition, the carbon emission factor of gas consumption is 0.002162, the carbon emission factor of coal consumption is 2.7725, the carbon emission factor of electricity consumption is 0.00058, the carbon emission factor of heating gas heat source is 0.002162, the carbon emission factor of central heating is 0.000105, the carbon emission factor of central cooling is 0.000161, the carbon emission factor of tap water is 0.000168 and the carbon emission factor of garbage is 0.528.

[0077] In order to assign weight values ​​to different usage frequencies and facilitate accurate calculation and prediction, in this embodiment, preferably, when predicting carbon emissions, the artificial intelligence algorithm assigns weight values ​​to the corresponding building settings or teachers and students based on holidays, teacher and student life cycles and other factors unique to the campus, including the frequency of use of classrooms and dormitories, the opening hours of libraries and laboratories, and the operation of canteens. That is, if the building setting is used less frequently, its assigned weight value is set below 0.5; if the building setting is used more frequently, its assigned weight value is set above 0.5; for teaching buildings, the assigned weight ratio is 1, which is set to the maximum weight value.

[0078] In order to effectively reduce the pressure of the artificial intelligence algorithm during calculation and improve the calculation efficiency, in this embodiment, preferably, the artificial intelligence algorithm performs dimensionality reduction processing on the collected data information through normalization processing before performing calculation and analysis processing, and maps each data information to [0, 1], thereby reducing the calculation pressure of the artificial intelligence algorithm and improving the calculation efficiency;

[0079] The calculation formula is as follows:

[0080]

[0081] Where g is the result of weight normalization calculated by Gaussian function, and the output range is between 0 and 1, G is the weight calculated by Gaussian function, G min is the minimum value calculated by the Gaussian function, G max It is the maximum value calculated by the Gaussian function. The data information is reduced in dimension through normalization.

[0082] In order to realize the identity recognition of the personnel in the school and calculate the number of people in the building, the carbon emissions of the individual are calculated and analyzed through the carbon emissions of the building to generate the carbon footprint information of the target. In this embodiment, preferably, the target trajectory information is generated by the trajectory generation platform according to the detection and identification information during the movement of the target, which is mainly used to detect and determine that the target enters the school building, and count the people in the school building to determine the number of people in the school building. The target detection includes the identity information of the target. The identity information of the target is detected by the camera through face recognition, the target face is obtained, and the school personnel database is contacted to compare and obtain the target information, and then the weight value is assigned to the target;

[0083] Then, the trajectory generation platform calculates the target’s carbon emissions based on the artificial intelligence algorithm, and combines the target’s trajectory information to generate the target’s carbon footprint information.

[0084] In order to realize preprocessing of data information, improve the accuracy of data information, and facilitate calculation and processing of data information, in this embodiment, preferably, after receiving various data information, the carbon emission prediction model first preprocesses the data information, including cleaning, gain, conversion and filtering the data information, that is, removing abnormal data and erroneous data in the data information, amplifying the data information, and performing analog-to-digital conversion on the data information, so as to facilitate subsequent calculation and processing, and filter the data information;

[0085] And the calculation of the filtering process is as follows:

[0086] The data information is filtered through a mean filter to improve the accuracy of the data information;

[0087] Set the window length to an odd number, use the average value of the data information to replace the value in the middle, gradually shift the window, filter the data information, and shift the step size to 1 until it slides to the end of the time series data; the calculation formula of the mean filter is as follows:

[0088]

[0089] in, Represents the output data set after mean filtering, m represents the size of the window, v(n) j Represents the jth data information in the input data set.

[0090] See also Figure 2 , a carbon footprint calculation system for primary and secondary school campuses, including,

[0091] Camera and NFC: Face recognition of people on campus is performed at various intersections and paths through cameras and NFC. After face recognition, the location of people on campus is located through NFC. After positioning and recognition, the information and location of people on campus are reported and transmitted to the trajectory generation platform.

[0092] Vehicle entry and exit gates: Vehicles entering and leaving the campus are detected through the vehicle entry and exit gates, and the license plates of the vehicles are recognized, and the locations of the vehicles are reported to the trajectory generation platform;

[0093] The campus LAN is used to connect the camera and NFC to the vehicle entry and exit gates, and transmit the detected trajectory information and identification to the trajectory generation platform and carbon emission prediction model to generate target trajectory information and predict carbon emissions;

[0094] The trajectory generation platform obtains the collected information and location information of the personnel in the school, as well as the information and location information of the vehicles, and combines all the action location information to generate the target trajectory information;

[0095] The carbon emission prediction model processes the collected data information, that is, cleans, gains, converts and filters the data information to improve the accuracy of the data information, and then uses artificial intelligence algorithms to calculate and analyze the data information, so that the data can be used to predict carbon emissions within the school, and combine the target trajectory information to generate an individual's carbon trajectory, which is convenient for the management of carbon emissions within the school.

[0096] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0097] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0099] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0100] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0102] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0103] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0104] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for calculating carbon footprint of primary and secondary school campuses, characterized by: The following steps are included: S1. Identification of people on campus: Install cameras on campus to identify people on campus, and install NFC chips in the cameras to locate people on campus; S2. Vehicle identification on campus: Vehicles entering the campus and vehicles traveling on campus are identified by license plate numbers through cameras and school gate access control, and are located through the camera's NFC chip; S3, trajectory path planning: according to the personnel or vehicle information detected by the camera, the location information of the personnel or vehicle is reported, and the target trajectory information is generated on the trajectory generation platform; S4. Calculate the carbon emissions on campus: Calculate the carbon emissions of each building on campus, and the calculation formula is as follows: C = C1 + C2 = ∑A i ×EF i +∑A e ×EF e , Among them, C is the carbon dioxide emissions from campus buildings, C1 is the direct carbon dioxide emissions from people in campus buildings, C2 is the carbon dioxide emissions from infrastructure on campus, A i The carbon emission inventory activity corresponding to C1, A e The carbon emission inventory activity corresponding to C2, EF i EF e They correspond to A i , A e Carbon emission factor; S5. Calculate the target carbon emissions based on the target trajectory information: Calculate the target carbon emissions by averaging the target’s action trajectory, i.e., the total carbon emissions C in the building where the target is located. 总 , and the total number of people in the target building X 总 , the calculation formula of the carbon emission prediction model is as follows: Among them, C r The calculation result of personal carbon emissions; S6. Predict and calculate carbon emissions on campus through artificial intelligence algorithms: Among them, W ij Expressed as weight, C i is the input carbon emissions, y i represents the output activation, i.e. the predicted carbon emissions, and f represents the activation function.

2. A method for calculating carbon footprint of primary and secondary school campuses according to claim 1, characterized in that: The camera is used to perform facial recognition on people on campus, determine the person's identity information after recognition, and determine the person's location through NFC. Through multiple camera recognition and NFC positioning, the detected location information is combined, and the target trajectory information is generated through the trajectory generation platform. The target trajectory information is mainly used to determine whether the identified person is in a building on campus.

3. A method for calculating carbon footprint of primary and secondary school campuses according to claim 1, characterized in that: The camera is installed at the corner of the path on campus. If the length of the path exceeds one kilometer, an additional camera will be set up in the middle of the path. The camera uses a panoramic camera with night vision function and can realize all-round rotation detection. The camera is equipped with WIFI communication equipment inside, which can communicate with the trajectory generation platform through the local area network on campus to upload the target identification and positioning.

4. A method for calculating carbon footprint of primary and secondary school campuses according to claim 3, characterized in that: Vehicles entering the campus are divided into on-campus vehicles and off-campus vehicles, and the carbon emissions generated by the vehicles are calculated using the following formula: C 车 =C 内 +C 外 =∑A nc ×EF nc +∑A wc ×EF wc , Among them, C 车 Carbon dioxide emissions from campus vehicles, C 内 Carbon dioxide emissions from vehicles within campus, C 外 Carbon dioxide emissions from vehicles entering and leaving the campus, A nc Corresponding to C 内 Carbon emission inventory activity, A wc Corresponding to C 外 Carbon emission inventory activities, EF nc EF wc They correspond to A nc , A wc The carbon emission factor is set as A nc The value of is 2.9251, set A wc The value of is 0.000043.

5. A method for calculating carbon footprint of primary and secondary school campuses according to claim 4, characterized in that: The carbon dioxide emissions from campus infrastructure include gas consumption, coal consumption, electricity consumption, heating gas heat source, central heating, central cooling, tap water and garbage; The above carbon emissions are all calculated using C j =∑A×EF for calculation; In addition, the carbon emission factor of gas consumption is 0.002162, the carbon emission factor of coal consumption is 2.7725, the carbon emission factor of electricity consumption is 0.00058, the carbon emission factor of heating gas heat source is 0.002162, the carbon emission factor of central heating is 0.000105, the carbon emission factor of central cooling is 0.000161, the carbon emission factor of tap water is 0.000168 and the carbon emission factor of garbage is 0.

528.

6. A method for calculating carbon footprint of primary and secondary school campuses according to claim 1, characterized in that: When predicting carbon emissions, the artificial intelligence algorithm assigns weights to the corresponding building settings or teachers and students based on holidays, the life cycles of teachers and students, and other factors unique to the campus, including the frequency of use of classrooms and dormitories, the opening hours of libraries and laboratories, and the operation of canteens. That is, for buildings with low frequency of use, the weight value assigned to them is set below 0.5; for buildings with high frequency of use, the weight value assigned to them is set above 0.5; for teaching buildings, the weight ratio is 1, which is set as the maximum weight value.

7. A method for calculating carbon footprint of primary and secondary school campuses according to claim 1, characterized in that: Before the artificial intelligence algorithm performs computational analysis, it normalizes the collected data and reduces its dimensionality, mapping each piece of data to [0, 1], thus reducing the computational pressure of the artificial intelligence algorithm and improving computational efficiency. The calculation formula is as follows: Where g is the result of weight normalization calculated by Gaussian function, and the output range is between 0 and 1, G is the weight calculated by Gaussian function, G min is the minimum value calculated by the Gaussian function, G max It is the maximum value calculated by the Gaussian function. The data information is reduced in dimension through normalization.

8. A method for calculating carbon footprint of primary and secondary school campuses according to claim 1, characterized in that: The target trajectory information is generated by the trajectory generation platform based on the detection and identification information of the target during its movement. It is mainly used to detect and determine whether the target has entered the campus building, and to count the number of people in the campus building and determine the number of people in the campus building. The target detection includes the identity information of the target. The identity information of the target is detected by the camera through face recognition, the target face is obtained, and the campus personnel database is contacted for comparison to obtain the target information, and then the weight value is assigned to the target. Then, the trajectory generation platform calculates the target’s carbon emissions based on the artificial intelligence algorithm, and combines the target’s trajectory information to generate the target’s carbon footprint information.

9. A method for calculating carbon footprint of primary and secondary school campuses according to claim 8, characterized in that: After receiving various data information, the carbon emission prediction model first pre-processes the data information, including cleaning, gaining, converting and filtering the data information, that is, removing abnormal data and erroneous data in the data information, amplifying the data information, and performing analog-to-digital conversion on the data information to facilitate subsequent calculation and filtering of the data information; And the calculation of the filtering process is as follows: The data information is filtered through a mean filter to improve the accuracy of the data information; Set the window length to an odd number, use the average value of the data information to replace the value in the middle, gradually shift the window, filter the data information, and shift the step size to 1 until it slides to the end of the time series data; the calculation formula of the mean filter is as follows: in, Represents the output data set after mean filtering, m represents the size of the window, v(n) j Represents the jth data information in the input data set.

10. A carbon footprint calculation system for primary and secondary school campuses, characterized by: Including, Camera and NFC: Face recognition of people on campus is performed at various intersections and paths through cameras and NFC. After face recognition, the location of people on campus is located through NFC. After positioning and recognition, the information and location of people on campus are reported and transmitted to the trajectory generation platform. Vehicle entry and exit gates: Vehicles entering and leaving the campus are detected through the vehicle entry and exit gates, and the license plates of the vehicles are recognized, and the locations of the vehicles are reported to the trajectory generation platform; The campus LAN is used to connect the camera and NFC to the vehicle entry and exit gates, and transmit the detected trajectory information and identification to the trajectory generation platform and carbon emission prediction model to generate target trajectory information and predict carbon emissions; The trajectory generation platform obtains the collected information and location information of the personnel in the school, as well as the information and location information of the vehicles, and combines all the action location information to generate the target trajectory information; The carbon emission prediction model processes the collected data information, that is, cleans, gains, converts and filters the data information to improve the accuracy of the data information, and then uses artificial intelligence algorithms to calculate and analyze the data information, so that the data can be used to predict carbon emissions within the school, and combine the target trajectory information to generate an individual's carbon trajectory, which is convenient for the management of carbon emissions within the school.

Images