Park carbon emission management configuration parameter recommendation system and electronic device

Abstract

The application provides a park carbon emission management configuration parameter recommendation system and electronic equipment, which are used in the technical field of carbon emission configuration parameter recommendation. The system is used for: determining first trajectories from each residential point in a preset geographical area to each park; determining travel recommendation information according to park attribute information and pedestrian flow information in the park; determining travel probabilities of reaching the park along the first trajectories by each traffic mode according to distance of the first trajectories, speed information of each traffic mode and the travel recommendation information; determining park-outside traffic carbon emission information of the multiple residential points reaching the park according to the travel probabilities, carbon emission information of each traffic mode, traffic selection probabilities of each traffic mode, population information of the residential points, park travel frequencies and distances of each first trajectory; determining comprehensive carbon emission information of each park; and outputting carbon emission management configuration parameters of each park according to the comprehensive carbon emission information of each park.

Description

Technical Field

[0001] This invention relates to the field of carbon emission configuration parameter recommendation technology, and more specifically, to a system and electronic device for recommending carbon emission management configuration parameters for parks. Background Technology

[0002] Greenhouse gas emissions have been rising year by year, having a significant impact on climate change, and carbon emissions are one of the important factors contributing to this phenomenon.

[0003] The accuracy of recommended carbon emission management configuration parameters depends on the precise determination of carbon emissions. Currently, methods for determining carbon emissions for parks include: the emission factor method, the life cycle assessment method, and the dynamic monitoring method. The emission factor method uses the resource consumption (such as electricity, fuel, and materials) of various activities within the park, as well as the emission factors of various resources (such as electricity carbon intensity and fuel combustion coefficient), to determine carbon emissions. This method is simple to operate, low in cost, and suitable for quickly determining a park's carbon emissions. The life cycle assessment method determines carbon emissions during the park's construction, operation, and maintenance, covering the entire life cycle from raw material extraction to waste disposal. The dynamic monitoring method uses IoT sensors, smart meters, and other devices to monitor energy consumption data in real time, or simulates the carbon cycle process through ecological models to determine carbon emissions.

[0004] However, dynamic monitoring methods require a large number of monitoring devices, resulting in high equipment costs and time-consuming and labor-intensive processes. Furthermore, emission factor methods and life cycle assessment methods primarily focus on static carbon emissions from the park itself, neglecting additional carbon emissions generated by users' use of public facilities (such as parks), i.e., ignoring carbon emissions caused by dynamic factors. Dynamic monitoring methods currently cannot, and find it difficult to, accurately detect carbon emissions caused by dynamic factors. For example, carbon emissions caused by dynamic factors include: carbon emissions from users' transportation to the park, carbon emissions from transportation within the park, and carbon emissions from consumer goods over their entire life cycle. Consequently, recommendation systems for relevant carbon emission management configuration parameters suffer from low accuracy due to measurement errors in park carbon emissions. Summary of the Invention

[0005] In view of this, the present invention provides a recommendation system and electronic device for park carbon emission management configuration parameters.

[0006] One aspect of the present invention provides a recommendation system for park carbon emission management configuration parameters, comprising: a data interface module for determining a first trajectory from various residential points within a preset geographical area to various parks; for each park: a first processing module for determining travel recommendation information based on park attribute information and pedestrian flow information within the park; for each first trajectory, determining the travel probability of reaching the park via each mode of transportation according to the first trajectory based on the distance of the first trajectory, the speed information of various modes of transportation, and the travel recommendation information; a second processing module for determining off-site transportation carbon emission information from multiple residential points to the park based on the travel probability, carbon emission information of each mode of transportation, the transportation selection probability of each mode of transportation, population information of the residential point, park travel frequency, and the distance of each first trajectory; a carbon emission comprehensive processing module for determining comprehensive carbon emission information for each park based on off-site transportation carbon emission information, on-site transportation carbon emission information, and visit carbon emission information and operation carbon emission information generated by visit and operation behaviors within the park, respectively; and a recommendation module for outputting carbon emission management configuration parameters for each park based on the comprehensive carbon emission information for each park.

[0007] According to an embodiment of the present invention, determining a first trajectory from each residence to each park within a preset geographical area includes: determining a second trajectory between each residence and each park based on the mobile terminal trajectory represented by the signaling information of the mobile terminal; determining a geographically feasible trajectory from each residence to each park based on the location information of each residence and each park; and selecting the first trajectory from multiple geographically feasible trajectories based on the similarity between the second trajectory and the geographically feasible trajectory.

[0008] According to an embodiment of the present invention, travel recommendation information is determined based on park attribute information and pedestrian flow information within the park, including: using the entropy weight method to determine the information weight of each park attribute information based on multiple park attribute information of each park; the park attribute information includes: the number of surrounding transportation facilities and shopping facilities within a preset distance, the park area, the park level, and the park type; determining static recommendation information for each park based on each park attribute information and the information weight of each park attribute information; determining dynamic recommendation information related to congestion based on pedestrian flow information and park capacity information; and correcting the static recommendation information using the dynamic recommendation information to obtain travel recommendation information.

[0009] According to an embodiment of the present invention, determining the probability of reaching a park via each mode of transportation along the first trajectory based on the distance of the first trajectory, the speed information of each of the multiple modes of transportation, and travel recommendation information includes: determining the travel time to reach the park via each mode of transportation based on the distance of the first trajectory and the speed information of each of the multiple modes of transportation; determining distance recommendation information for the first trajectory based on the distance of the first trajectory and the travel time to reach the park via each mode of transportation; and determining the probability of reaching a park via each mode of transportation along the first trajectory based on the distance recommendation information of the residence for the first trajectory and the distance recommendation information of the residence to the first trajectory corresponding to each park.

[0010] According to an embodiment of the present invention, determining distance recommendation information for the first trajectory based on the distance of the first trajectory and the travel time to the park via each mode of transportation includes: determining a time distance cost coefficient for reaching the park via each mode of transportation based on the distance of the first trajectory and the travel time to the park via each mode of transportation; determining a distance sensitive parameter matching the comparison results between the time distance cost coefficient and multiple preset cost intervals; and determining distance recommendation information for the first trajectory based on the product of the time distance cost coefficient and the distance sensitive parameter.

[0011] According to an embodiment of the present invention, carbon emission information of external transportation from multiple residences to the park is determined based on the travel probability, carbon emission information of each mode of transportation, travel selection probability of each mode of transportation, population information of the residence, frequency of park visits, and distance of each first trajectory. This includes: determining intermediate carbon emission information for each mode of transportation based on the product of the travel selection probability, carbon emission information, and distance of the first trajectory; summing the intermediate carbon emission information for each mode of transportation for each first trajectory, and multiplying the summed intermediate carbon emission information, travel probability, population information of the residence corresponding to the first trajectory, and frequency of park visits to obtain carbon emission information of external transportation from the residence corresponding to each first trajectory to the park; and summing the carbon emission information of external transportation from the residence corresponding to each first trajectory to the park to obtain carbon emission information of external transportation from multiple residences to the park.

[0012] According to an embodiment of the present invention, the frequency of park visits is determined as follows: based on the signaling information of the mobile terminal, multiple third trajectories with different destinations in a preset geographical area are determined at the same time; based on the ratio of the second trajectory with the destination of the park to the multiple third trajectories at the same time, the park visit ratio is determined; and based on the park visit ratio and the average annual frequency of users' park visits in the preset geographical area, the park visit frequency is determined.

[0013] According to an embodiment of the present invention, the system is further configured to: determine the park traffic carbon emissions generated by visiting the park through multiple modes of transportation based on the number of passengers, annual mileage, and carbon emission information of each mode of transportation within the park; determine the park visit carbon emissions generated by visiting activities based on the carbon emission information of consumed goods, the carbon emission information of recycled waste, and the carbon emission information of equipment used within the park; and determine the operational carbon emissions based on the first operational carbon emission sub-information generated by landscape maintenance activities and the second operational carbon emission sub-information generated by garden maintenance activities.

[0014] According to an embodiment of the present invention, based on the comprehensive carbon emission information of each park, the carbon emission management configuration parameters of each park are output, including: determining the carbon emission management configuration parameters that match the comprehensive carbon emission information from the database, and outputting the carbon emission management configuration parameters of each park.

[0015] Another aspect of the present invention provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the operations performed by the system described above.

[0016] Another aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the method described above.

[0017] Another aspect of the present invention provides a computer program product comprising computer-executable instructions which, when executed, are used to implement the method described above.

[0018] In embodiments of the present invention, when determining carbon emissions caused by external traffic to users, the accuracy of external traffic carbon emission information can be improved by replacing the straight-line distance between the residence and the park with the actual trajectory between the two locations. On the other hand, by adding dynamic attraction factors (pedestrian flow information) based on static park attribute information, the accuracy of external traffic carbon emission information can be improved by more realistically simulating users' park selection behavior. In addition, besides the static operational carbon emission information directly generated by the park's own operation, the present invention also introduces the dynamic carbon emissions of the park, such as external traffic carbon emission information caused by user behavior, internal traffic carbon emission information, and visit carbon emission information. Thus, embodiments of the present invention can improve the accuracy of determining the overall carbon emissions of the park by improving the carbon emission sources and accurately determining the carbon emissions generated by dynamic user behavior, thereby improving the accuracy of recommending carbon emission management configuration parameters based on carbon emissions. Attached Figure Description

[0019] The above and other objects, features and advantages of the present invention will become more apparent from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0020] Figure 1 A schematic diagram of the architecture of a recommendation system for park carbon emission management configuration parameters is shown according to an embodiment of the present invention.

[0021] Figure 2 A data flow diagram for determining a first trajectory according to an embodiment of the present invention is shown.

[0022] Figure 3 A data flow diagram for determining travel probabilities according to an embodiment of the present invention is shown.

[0023] Figure 4 A scenario diagram of a recommendation system for park carbon emission management configuration parameters according to an embodiment of the present invention is shown.

[0024] Figure 5 A block diagram of an electronic device suitable for implementing a recommendation system for park carbon emission management configuration parameters according to an embodiment of the present invention is shown. Detailed Implementation

[0025] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the invention for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0026] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0027] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0028] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0029] In the embodiments of this invention, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures are taken to prevent unauthorized access to user personal information data and to maintain the security of user personal information, network security, and other security.

[0030] In the embodiments of the present invention, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.

[0031] On the one hand, most current carbon emission determinations are based on the energy consumption of public facilities (such as parks) themselves, without taking into account users' dynamic behavior towards public facilities, especially the carbon emissions caused by users' external transportation behavior to reach public facilities. This results in unclear identification of carbon emission sources during the operation of public facilities and incomplete source elements, which in turn leads to low accuracy in recommending carbon emission management configuration parameters based on carbon emission.

[0032] On the other hand, the accuracy of the methods used to determine carbon emissions is poor. Most methods for determining carbon emissions in parks are based on a macroscopic perspective, relying solely on overall fuel usage data during park operation to determine the total carbon emissions. This results in low accuracy and poor timeliness, and the carbon emission figures tend to be idealized, making it difficult to accurately reflect the carbon emissions situation during park operation. Consequently, the recommended carbon emission management configuration parameters based on carbon emissions are of low accuracy.

[0033] In summary, this invention provides a recommendation system for carbon emission management configuration parameters in parks. This system integrates the carbon emissions generated by the park's static operational behavior and the dynamic behavior of users, accurately determines the carbon emissions caused by factors both within and outside the park, and thus improves the accuracy of recommending carbon emission management configuration parameters based on carbon emissions.

[0034] Figure 1 A schematic diagram of the architecture of a recommendation system for park carbon emission management configuration parameters according to an embodiment of the present invention is shown. Figure 1As shown, the park carbon emission management configuration parameter recommendation system 100 includes a data interface module 110, a first processing module 120, a second processing module 130, a carbon emission comprehensive processing module 140, and a recommendation module 150.

[0035] Data interface module 110 is used to determine the first trajectory from each residence within a preset geographical area to each park. For each park: First processing module 120 is used to determine travel recommendation information based on park attribute information and pedestrian flow information within the park; for each first trajectory, based on the distance of the first trajectory, the speed information of each of the various transportation modes, and the travel recommendation information, it determines the probability of reaching the park via each transportation mode along the first trajectory. Second processing module 130 is used to determine the off-site transportation carbon emission information from multiple residences to the park based on the travel probability, carbon emission information of each transportation mode, transportation selection probability of each transportation mode, population information of the residence, park travel frequency, and the distance of each first trajectory. Carbon emission comprehensive processing module 140 is used to determine the comprehensive carbon emission information of each park based on the off-site transportation carbon emission information, on-site transportation carbon emission information, and visit carbon emission information and operation carbon emission information generated by visit and operation behaviors within the park, respectively. Recommendation module 150 is used to output the carbon emission management configuration parameters for each park based on the comprehensive carbon emission information of each park.

[0036] In embodiments of the present invention, the recommendation system 100 can execute computer instructions to invoke the aforementioned modules to perform corresponding operations. The data interface module 110 can act as a bridge between the recommendation system 100 and various data sources. The data interface module 110 can directly obtain corresponding data from each data source, or process the data obtained from each data source.

[0037] In an embodiment of the present invention, the data interface module can obtain the following data from multiple data sources so that the first processing module 120, the second processing module 130, the carbon emission comprehensive processing module 140, and the recommendation module 150 can use the corresponding data to perform corresponding operations.

[0038] For example, the data interface module 110 can acquire data including: location information of various residential areas and parks within a preset geographical area; signaling information of mobile terminals collected by various signal base stations within the preset geographical area; park attribute information; pedestrian flow information within the park; speed information of various modes of transportation; carbon emission information of each mode of transportation; population information of residential areas; average annual frequency of user park visits within the preset geographical area; passenger capacity of each mode of transportation; annual mileage; carbon emission information of various consumer goods; carbon emission information of waste recycling; and carbon emission information of equipment within the park. Among these, the carbon emission information of various modes of transportation and consumer goods can be carbon emission factors obtained from a greenhouse gas emission factor database. These carbon emission factors characterize the amount of carbon emissions generated per standard unit (corresponding to each mode of transportation and consumer good).

[0039] For example, the data interface module 110 can determine the first trajectory from each residence to each park based on the location information of each residence and each park within a preset geographical area. It is understood that for a residence and a park, there can be multiple geographically feasible first trajectories. For instance, if the residence and the park are located diagonally opposite each other in a square, the trajectory along either side of the square can be the first trajectory, and the trajectory along the diagonal of the square can also be the first trajectory, as long as it is geographically feasible. If there is no road on the diagonal or if there is an inaccessible road, then the diagonal is not one of the aforementioned first trajectories. Alternatively, for a user's mobile terminal (which can be uniquely identified by a device identifier), the signaling information of the mobile terminal can be used to determine the location changes of the mobile terminal within a preset area, thereby determining the first trajectory from each residence to each park.

[0040] According to embodiments of the present invention, a residence may include a residential area, a hotel, an apartment, or other habitable geographical location.

[0041] Understandably, although a primary trajectory exists between each residence and each park, in reality, this trajectory is influenced by various factors, such as distance, mode of transportation, and the probability of a user choosing to travel to the park. Therefore, for each primary trajectory from each park to each residence, the first processing module 120 can determine the probability of reaching the park via each mode of transportation according to the primary trajectory; subsequently, the second processing module 130 determines the off-park transportation carbon emission information from multiple residences to the park. Then, the off-park transportation carbon emission information resulting from user dynamic behavior is used in the process of determining comprehensive carbon emission information, and carbon emission management configuration parameters are recommended.

[0042] According to an embodiment of the present invention, for the park attribute information and pedestrian flow information within the park obtained through the data interface module 110, the first processing module 120 can determine travel recommendation information for each park for different residential locations based on the park's own attractiveness and the aforementioned indicators. For example, in one embodiment, the park attribute information and pedestrian flow information within the park can be weighted to obtain a comprehensive value, and then the travel recommendation information for each park for different residential locations can be determined based on the comprehensive value.

[0043] Furthermore, the first processing module 120 can also correct the travel recommendation information based on the characteristics of the first trajectory itself (such as distance, convenience of transportation modes, speed information of various transportation modes, and time required to travel along the first trajectory), and determine the probability of reaching the park by each transportation mode along each first trajectory. It is understood that different transportation modes produce different carbon emissions; for example, the carbon emissions from bicycles are less than those from buses. However, the probability of using multiple transportation modes differs under different first trajectories. Therefore, embodiments of the present invention determine the probability of reaching the park by each transportation mode for each first trajectory, so as to accurately determine the carbon emissions generated by user travel behavior, thereby improving the recommendation accuracy of carbon emission management configuration parameters.

[0044] According to embodiments of the present invention, in addition to the carbon emissions generated by the initial trajectory from the residence to the park, user traffic behavior and user sightseeing behavior within the park also generate carbon emissions. Therefore, to accurately determine the carbon emissions generated by the park, in addition to determining the operational carbon emissions generated by the park's own operations, dynamic external traffic carbon emissions, internal traffic carbon emissions, and sightseeing carbon emissions generated by user behavior are also determined, and comprehensive carbon emissions information is determined based on the above information. In one embodiment, internal traffic carbon emissions information can be the carbon emissions generated by each user when using various modes of transportation within the park; operational carbon emissions information and sightseeing carbon emissions information can be determined using a life-cycle approach.

[0045] According to an embodiment of the present invention, the recommendation system 100 may pre-store the correspondence between comprehensive carbon emission information and carbon emission management configuration parameters. After determining the comprehensive carbon emission information of each park, carbon emission management configuration parameters matching each park can be determined based on the above correspondence. The carbon emission management configuration parameters can uniquely determine a set of processing strategies for monitoring or managing the carbon emissions of the park. For example, the carbon emission management configuration parameters may include processing strategies for specific information such as park traffic behavior, carbon emission information of traffic within the park, and carbon emission information of visitors.

[0046] In embodiments of the present invention, when determining carbon emissions caused by external traffic to users, the accuracy of external traffic carbon emission information can be improved by replacing the straight-line distance between the residence and the park with the actual trajectory between the two locations. On the other hand, by adding dynamic attraction factors (pedestrian flow information) based on static park attribute information, the accuracy of external traffic carbon emission information can be improved by more realistically simulating users' park selection behavior. In addition, besides the static operational carbon emission information directly generated by the park's own operation, the present invention also introduces the dynamic carbon emissions of the park, such as external traffic carbon emission information caused by user behavior, internal traffic carbon emission information, and visit carbon emission information. Thus, embodiments of the present invention can improve the accuracy of determining the overall carbon emissions of the park by improving the carbon emission sources and accurately determining the carbon emissions generated by dynamic user behavior, thereby improving the accuracy of recommending carbon emission management configuration parameters based on carbon emissions.

[0047] It is understandable that the operations implemented by the various modules of the recommendation system described below can be achieved by a single module, or by a combination of multiple sub-modules. Examples of the operations implemented by the recommendation system will be given below.

[0048] According to an embodiment of the present invention, determining a first trajectory from each residence to each park within a preset geographical area includes: determining a second trajectory between each residence and each park based on the mobile terminal trajectory represented by the signaling information of the mobile terminal; determining a geographically feasible trajectory from each residence to each park based on the location information of each residence and each park; and selecting the first trajectory from multiple geographically feasible trajectories based on the similarity between the second trajectory and the geographically feasible trajectory.

[0049] Signaling information from mobile terminals can be collected from various signal base stations within a preset geographical area. For example, each signal base station may include fields such as base station number, geographical location (e.g., latitude and longitude coordinates), base station range, and base station type. Each signaling message contains user identifier, timestamp, base station sequence number, and event type (e.g., calling, called, SMS, location update). After obtaining the above signaling information, data cleaning operations can be performed, such as deleting data containing missing fields and deleting duplicate or redundant data; alternatively, data cleaning tasks such as drift data processing, ping-pong data processing, and sparse data processing can also be performed.

[0050] It should be noted that the geographical area covered by each signal base station is different. To clearly determine the trajectory of a mobile terminal from a residence to a park based on signaling information, it is necessary to analyze the geographical location of the signal base stations. For example, each signal base station can be loaded into a Geographic Information System (GIS) based on its geographical location, and the coverage area of ​​all signal base stations can be divided using the Thiessen polygon algorithm. Furthermore, each residence and park can also be loaded into the GIS based on their respective location information. The matching relationship between residences, parks, and signal base stations can be determined based on the relationship between each residence / park and its respective coverage area.

[0051] For signaling information, multiple signaling messages from the same mobile terminal can be arranged in order of reception time at the signal base stations. Then, based on the signal base station and reception time of each signaling message, the trajectory of the same mobile terminal is determined. For each signal base station in the aforementioned trajectory, if the duration of the signaling information at that base station is greater than a duration threshold, then that base station is the stopping point of the signaling information; otherwise, it is the moving point. Subsequently, if the mobile terminal trajectory has stopping points that match both a residence and a park, and the trajectory indicates movement from the residence to the park with the destination being a stopping point that matches the park, then that trajectory is designated as the second trajectory.

[0052] In one example, the duration threshold can be dynamically set according to the length of the trip. For example, if the mobile terminal trajectory does not exceed 200km, the duration threshold for the mobile terminal trajectory is 30min; if the mobile terminal trajectory exceeds 200km, the duration threshold for the mobile terminal trajectory is 60min.

[0053] According to an embodiment of the present invention, the signal base station covers a large area, and the second trajectory formed by using the signal base station as a moving point and a stopping point may not be feasible in actual travel (e.g., a trajectory that directly crosses a river is not feasible). Therefore, a geographically feasible trajectory from each residence to each park can be determined based on the location information of each residence and each park. The location information may include geographical location (e.g., latitude and longitude coordinates).

[0054] For example, a navigation application's API can be invoked to determine multiple geographically feasible routes from each residence to each park, based on the location information of each residence and each park. Then, for each of the multiple geographically feasible routes from residence i to park j, the similarity between a second route and the existing geographically feasible routes is calculated. This second route is then filtered to obtain the first route from residence i to park j, which is considered the valid route and can be used by the user. A corresponding park travel database can be created for each first route from each residence to each park. It can be understood that any route between a pair of residences and parks obtained through the navigation application's API is considered a geographically feasible route.

[0055] In the embodiments of the present invention, by using the signaling information of the mobile terminal, the location information of the residence and the park, multiple forms of actual travel trajectories can be determined using multi-source data. By calculating the similarity between the two trajectories, it can be ensured that the first trajectory finally selected is the actual trajectory between the residence and the park. Compared with the method of using the straight-line distance between two points as the trajectory in related technologies, the actual trajectory can improve the accuracy of carbon emission information of traffic outside the park.

[0056] Figure 2 A data flow diagram for determining a first trajectory according to an embodiment of the present invention is shown. Figure 2 As shown, by analyzing signaling information, the mobile terminal trajectories of each mobile terminal can be obtained, and a second trajectory with the park as the destination can be determined based on these trajectories. On the other hand, a geographically feasible trajectory from the residence to the park can be determined using the location information of the residence and the park. By comparing the similarity between the second trajectory and the geographically feasible trajectory, an accurate and practically feasible first trajectory is determined.

[0057] In one specific embodiment, only the shape of the second trajectory or the geographically feasible trajectory can be considered, without considering the time point, to calculate the Frechet distance between the two trajectories, and this Frechet distance can be used as the similarity score. If the similarity score is higher than a threshold, the two trajectories are considered similar; otherwise, they are not similar. Alternatively, the geographically feasible trajectory can be divided into multiple trajectory segments with a progression order. The nearest signal base station to each trajectory segment can be identified, and the multiple signal base stations can be arranged according to the progression order. It can be determined whether the trend is the same as the change order of signal base stations in the second trajectory. If they are the same, the current geographically feasible trajectory is similar to the second trajectory; otherwise, they are not similar.

[0058] According to embodiments of the present invention, for each residence and each park, the geographic information system can load all their respective information. For example, it can load information such as the park's name, address, latitude and longitude coordinates, park attribute information, and management method within a preset geographic area. For residences, it can load their name, address, latitude and longitude coordinates, population information, etc. In the geographic information system, each residence and park can be represented by vector points, and the above information can serve as Point of Interest (POI) data for each vector point. The data on residences and parks can be combined with a road network dataset within the preset geographic area to construct a geospatial database for the preset geographic area.

[0059] According to embodiments of the present invention, the probability of a user traveling to each park differs for each residence, thus the external traffic carbon emission information generated by the first trajectory from each residence to each park differs. Through big data analysis, user travel preferences are related to park attractiveness and the time-distance cost coefficient of the first trajectory. For the same residence, users tend to choose parks with lower time-distance cost coefficients and stronger park attractiveness. Therefore, embodiments of the present invention comprehensively calculate the park travel probability from two variables: park attractiveness and the time-distance cost coefficient of the first trajectory. In the following text, park attractiveness is quantified by travel recommendation information determined using park attribute information and pedestrian flow information within the park, and the time-distance cost coefficient is quantified by distance recommendation information of the first trajectory.

[0060] According to an embodiment of the present invention, travel recommendation information is determined based on park attribute information and pedestrian flow information within the park, including: using the entropy weight method to determine the information weight of each park attribute information based on multiple park attribute information of each park; the park attribute information includes: the number of surrounding transportation facilities and shopping facilities within a preset distance, the park area, the park level, and the park type; determining static recommendation information for each park based on each park attribute information and the information weight of each park attribute information; determining dynamic recommendation information related to congestion based on pedestrian flow information and park capacity information; and correcting the static recommendation information using the dynamic recommendation information to obtain travel recommendation information.

[0061] According to embodiments of the present invention, the static attractiveness of a park can be quantified using information inherent to the park itself, such as the number of surrounding transportation and shopping facilities within a preset distance, the park's area, park rating, and park type; and the dynamic attractiveness of a park can be quantified using pedestrian flow information. For example, park attribute information is inherent to each park, and parks with different attributes have different impacts on user travel preferences. Different pedestrian flow information also has different impacts on user travel preferences. For instance, big data analysis can determine that users tend to choose parks with lower pedestrian flow and less congestion.

[0062] Park attribute information can include internal and external attributes. Internal attributes include the park area, park level, and park type mentioned above. External attributes include the number of transportation and shopping facilities around the park within a preset distance (e.g., 1km). The park level can be determined through publicly available data, and the park type can be determined through the number of functions it undertakes (e.g., scenic sightseeing, comprehensive, etc.). Pedestrian traffic information can be determined through the number of online park entry applications and / or traffic collection devices installed at the entrance, such as the number of users entering the park.

[0063] The information weight of each park attribute in the park attribute information can be determined by formulas (1) to (4):

[0064] (1);

[0065] (2);

[0066] (3);

[0067] (4);

[0068] Where, x' jh x' represents the attribute information of the h-th park in the j-th park. jhmax and x' jhmin This represents the maximum and minimum values ​​among the n h-th park attribute information items, where n represents the number of parks in the preset geographical area, i.e., j = {1, 2, ..., n}, x jh This represents the standard value of the attribute information of the h-th park in the j-th park, where m is the total number of residential areas. The weight of the h-th park attribute information of the j-th park is determined by the ratio of the h-th park attribute information of the j-th park to the sum of the h-th park attribute information of the n parks. E h The information entropy of the h-th park attribute information is... Let h be the information weight of the h-th park attribute information, and g be the total number of park attribute information, i.e., h = {1, 2, ..., g}.

[0069] The static recommendation information for the park can be determined using formula (5):

[0070] (5);

[0071] The park attribute information consists of 5 items. The 5 park attribute information for the j-th park are: the number of surrounding transportation facilities within a preset distance x j1 Number of shopping facilities around the park within a preset distance x j2 Park area x j3 Park level x j4 and park type x j5 , This represents the static recommendation information for the j-th park; other parameters can be found above.

[0072] As stated above, park attractiveness is also affected by pedestrian traffic information, and dynamic recommendation information and travel recommendation information can be determined by the following formulas (6) to (8):

[0073] (6);

[0074] (7);

[0075] (8);

[0076] in, Let Y be the number of users in the j-th park at time t. j For the park capacity information of the j-th park, F j The dynamic recommendation information related to congestion for the j-th park can be determined by the ratio of the number of users to the park's capacity information. This is the crowding attenuation factor. The congestion sensitivity coefficient can range from 1.5 to 3.0. The congestion attenuation factor is a function that is segmented and related to the dynamic recommendation information. By multiplying the congestion attenuation factor by the static recommendation information, the travel recommendation information after correcting the static recommendation information is obtained. .

[0077] In embodiments of the present invention, during the determination of off-park traffic carbon emission information, based on user travel preferences and in addition to determining the static attractiveness of parks using park attribute information, a dynamic congestion attenuation factor related to pedestrian flow information is introduced. Thus, in determining off-park traffic carbon emission information, dynamic attractiveness is added to the traditional static attractiveness, enabling travel recommendation information to more realistically simulate users' park selection behavior and improve the accuracy of off-park traffic carbon emission information. Furthermore, since pedestrian flow information is collected in real time, embodiments of the present invention can also integrate dynamic detection methods with emission factor methods and the full life cycle method, overcoming the limitations of single methods.

[0078] According to an embodiment of the present invention, determining the probability of reaching a park via each mode of transportation along the first trajectory based on the distance of the first trajectory, the speed information of each of the multiple modes of transportation, and travel recommendation information includes: determining the travel time to reach the park via each mode of transportation based on the distance of the first trajectory and the speed information of each of the multiple modes of transportation; determining distance recommendation information for the first trajectory based on the distance of the first trajectory and the travel time to reach the park via each mode of transportation; and determining the probability of reaching the park via each mode of transportation along the first trajectory based on the distance recommendation information of the residence for the first trajectory, the distance recommendation information of the residence to each park corresponding to the first trajectory, and travel recommendation information.

[0079] For each first trajectory, the distance of the first trajectory can be directly determined, and the travel time to the park for each mode of transportation can be determined based on the ratio of the distance of the first trajectory to the speed information of the transportation mode.

[0080] In one embodiment, the distance of the first trajectory and the travel time to the park via each mode of transportation can be weighted and summed to determine the distance recommendation information for the first trajectory.

[0081] Table 1 shows the applicable speed information and distance for various modes of transportation.

[0082] Table 1

[0083]

[0084] For example, the distance recommendation information for the first trajectory is determined based on the distance of the first trajectory and the travel time to the park via each mode of transportation. This includes: determining the time distance cost coefficient for each mode of transportation to reach the park based on the distance of the first trajectory and the travel time to the park via each mode of transportation; determining the distance sensitive parameter that matches the comparison results between the time distance cost coefficient and multiple preset cost intervals; and determining the distance recommendation information for the first trajectory based on the product of the time distance cost coefficient and the distance sensitive parameter.

[0085] The time-distance cost coefficient for reaching the park via each mode of transportation can be determined by formula (9):

[0086] (9);

[0087] in, D represents the time-distance cost coefficient for traveling from the i-th residence to the j-th park via the k-th mode of transportation. ij t represents the distance of the first trajectory from the i-th residence to the j-th park. k，ij This represents the travel time to reach the park using the k-th mode of transportation along the first trajectory. and These represent the weights of travel time and distance, respectively. and The sum is 1. It can be between 0.3 and 0.5; It can be between 0.5 and 0.7. It should be noted that users' travel preferences typically lean towards parks that are closer and have shorter travel times. Therefore, the time-distance cost coefficient obtained by adding the parameters of different dimensions in the above formula (9) is... This aligns with the trend of how time and distance influence user travel preferences. (Time and distance cost coefficient) It is primarily used as a coefficient in subsequent solutions and is a dimensionless coefficient. Alternatively, in other embodiments, the travel time of various modes of transportation between the i-th residence and the j-th park can be used to evaluate t. k，ij Normalize to eliminate dimensions; similarly, use the distances of multiple first trajectories from the i-th residence to all parks to normalize D. ij Normalization is performed to eliminate dimensions. Then, the two dimensionless parameters are substituted into formula (9) to obtain the time-distance cost coefficient. .

[0088] However, through big data analysis, some parks have strong inherent appeal, and even with a large time-distance cost coefficient, there are still people traveling to them. That is, the actual time-distance cost coefficient of parks has a clear inflection point. Therefore, this embodiment of the invention corrects the time-distance cost coefficient by using a piecewise negative exponential decay function.

[0089] For example, the distance recommendation information of the first trajectory and the time distance cost coefficient form a negative exponential decay function relationship.

[0090] Distance recommendation information can be determined using formula (10):

[0091] (10);

[0092] in, , These are the constant parameters for the k-th mode of transportation. , , These are three distance-sensitive parameters for the k-th mode of transportation. This embodiment of the invention includes three preset cost intervals, such as (0, ..., ...). ]、( , ]、( [+∞], Based on the comparison results between the time distance cost coefficient and multiple preset cost intervals, a distance-sensitive parameter matching the comparison results is determined, and then distance recommendation information is determined based on the product of the time distance cost coefficient and the distance-sensitive parameter. .

[0093] In this embodiment of the invention, a larger distance-sensitive parameter indicates that the distance recommendation information is more sensitive to distance. In one embodiment, a data-driven maximum likelihood estimation (MLE) model can be used to solve for the distance-sensitive parameter by maximizing the probability of observed selection behavior.

[0094] For example, for distance-sensitive parameters Construct the log-likelihood function as shown in formula (11) :

[0095] (11);

[0096] Among them, y ij 0 or 1 indicates whether the first trajectory from the i-th residence to the j-th park is selected. For the first trajectory whose time-distance cost coefficient is within the first preset cost interval, y ij The value is 1; other parameters are described above.

[0097] Maximize using iterative optimization algorithms (such as gradient descent). This allows us to find the solution that maximizes the probability of the observed data. . and The solution and Similarly, this will not be repeated here. Furthermore, the R-value of McFadden is calculated using formula (12). 2 Indicators determine the model's goodness of fit and ensure the parameters are reasonable.

[0098] (12);

[0099] Where, lnL(0) is the likelihood value containing only constant terms. express , and Any one of them. Usually R 2 A distance-sensitive parameter ≥0.2 is considered acceptable, R 2 A distance sensitivity parameter ≥0.4 is considered good. If... , and R 2 If the value is ≥0.4, then the distance-sensitive parameter can be used as the parameter obtained by formula (10).

[0100] According to an embodiment of the present invention, the distance recommendation information for the first trajectory corresponding to each residence to each park (n in total) under each mode of transportation can be determined in accordance with the above formula (10).

[0101] For example, information can be recommended based on the distance of the first trajectory from the i-th residence to the j-th park using formula (13). Time distance cost coefficient Travel recommendation information for each park (including travel recommendation information when j is 1~n) Determine the probability of arriving at the park via each mode of transportation k following the first trajectory:

[0102] (13);

[0103] Among them, P k，ij This represents the probability of traveling from residence i to park j via the kth mode of transportation. Other parameters are described above.

[0104] In embodiments of the present invention, during the determination of carbon emission information for transportation outside the park, a time-distance cost coefficient (combining the distance of the first trajectory and the travel time of the transportation mode) is used instead of a single distance factor. This improves the accuracy of carbon emission information for each transportation mode, thereby enhancing the overall accuracy of carbon emission information for transportation outside the park. Furthermore, based on user travel behavior characteristics, a segmented preset cost interval allows the distance recommendation information to be repeatedly corrected in segments while adhering to negative exponential decay, better reflecting real user travel preferences. Compared to traditional models that do not consider decay, the overall accuracy of carbon emission information for transportation outside the park is higher and more realistic.

[0105] Figure 3 A data flow diagram for determining travel probabilities according to an embodiment of the present invention is shown. For example... Figure 3As shown, for each first trajectory, the distance of the first trajectory and the travel time along the first trajectory according to multiple modes of transportation can be determined. A time-distance cost coefficient is obtained by weighted summation of distance and travel time. By comparing the time-distance cost coefficient with multiple preset cost intervals, the distance-sensitive parameter that best matches each first trajectory is determined. Then, distance recommendation information is determined based on the distance-sensitive parameter and the time-distance cost coefficient. The travel probability of each first trajectory can be determined based on the distance recommendation information of multiple first trajectories.

[0106] According to embodiments of the present invention, the travel probability based on the first trajectory is determined from two aspects: the first trajectory and park attribute information. However, for each first trajectory, in actual travel behavior, multiple users at a residence can choose to travel according to the first trajectory, the same user can choose to travel multiple times according to the first trajectory within a certain time period, and a user can choose multiple modes of transportation to travel according to the first trajectory. Therefore, in addition to analyzing from the perspective of the first trajectory, it is also necessary to integrate and analyze the attribute information of the starting point (residence) and the carbon emissions generated by the transportation mode itself to improve the accuracy of determining the carbon emissions generated by the first trajectory.

[0107] According to an embodiment of the present invention, the second processing module 130 is configured to determine the off-park transportation carbon emission information of multiple residences to the park based on the travel probability, carbon emission information of each mode of transportation, travel selection probability of each mode of transportation, population information of the residence, park travel frequency, and distance of each first trajectory. In one embodiment, the off-park transportation carbon emission information can be determined as follows: intermediate carbon emission information of each mode of transportation is determined based on the product of the travel selection probability, carbon emission information, and distance of the first trajectory; for each first trajectory, the intermediate carbon emission information of each mode of transportation, the travel probability, the population information of the residence corresponding to the first trajectory, and the park travel frequency are multiplied together, and the results of multiplying each mode of transportation are summed to obtain the off-park transportation carbon emission information of each residence corresponding to the first trajectory to the park; the off-park transportation carbon emission information of each residence corresponding to the first trajectory to the park is summed to obtain the off-park transportation carbon emission information of multiple residences to the park.

[0108] The probability P of the first trajectory from residence i to park j via the k-th mode of transportation has been determined above. k,ij This will not be elaborated upon here.

[0109] The probability of choosing a mode of transportation refers to the probability that a user will choose a particular mode of transportation for each first trajectory; carbon emission information can be the carbon emission factor of that mode of transportation. Carbon emission information for each mode of transportation can be found in Table 2 below:

[0110] Table 2

[0111]

[0112] Table 2 uses various modes of transportation, including walking, cycling, electric bicycles, buses, subways, and cars, as examples. The carbon emission factor for each mode of transportation in Table 2 represents the carbon emissions generated per person traveling 1 km using that mode of transportation. The unit of the carbon emission factor is kgCO2 / (person). -1 ·km -1 ).

[0113] According to embodiments of the present invention, user behavior preferences tend to select different modes of transportation based on different distances. Therefore, the transportation selection probability is determined based on the distribution characteristics of the applicable distances for each mode of transportation. This distribution characteristic (distance and the amount of data used for each mode of transportation) can be determined through big data analysis. For example, if the distance of the first trajectory is 7km, the data volume of each mode of transportation at 7km is standardized (e.g., the ratio of the data volume of each mode of transportation to the sum of the data volume of all modes of transportation) to obtain the transportation selection probability.

[0114] Intermediate carbon emissions for each mode of transportation can be determined using the following formula (14):

[0115] (14);

[0116] Among them, T k,ij B represents the intermediate carbon emission information of the first trajectory of the k-th mode of transportation from the i-th residence to the j-th park. k and C k Let D represent the probability of choosing the k-th mode of transportation and the carbon emission factor, respectively. ij Let k represent the distance of the first trajectory from the i-th residence to the j-th park, and k represent the mode of transportation, k=1,...,6, where 1 is walking, 2 is bicycle, 3 is electric bicycle, 4 is bus, 5 is subway, and 6 is car.

[0117] Starting from the residence of the first trajectory, the population information of the corresponding residence can be the population size, which can be determined through public channels. For example, it can be obtained through... Determine the population information M of residential areas or apartment types. i1 ,pass Determine the population information M of the hotel-type residence. i2 ,in, z represents the average number of people per household in each residential area or park type. i1 Indicates the number of households in a residential area. This indicates the population of each residence of the hotel type.

[0118] Carbon emission information for off-site transportation from each residence to the park for each first trajectory can be determined using formula (15):

[0119] (15);

[0120] Among them, CE ij This provides information on off-park transportation carbon emissions for the first trajectory from the i-th residence to the j-th park. For population information of the i-th settlement, M can be determined based on the type of settlement. i =M i1 Or M i =M i2 , The frequency of park visits is given, and other parameters are explained in formulas (13), (14), and (15) above.

[0121] From the perspective of the park, the carbon emission information of off-site transportation from multiple residential points to park j can be determined by formula (16):

[0122] (16);

[0123] CE 外部 This can refer to the total carbon emissions from multiple residential locations to park j, with other parameters explained above.

[0124] In the embodiments of the present invention, taking into account the carbon emissions caused by user travel behavior, the analysis is carried out from multiple dimensions such as the first travel trajectory, the mode of transportation along the first trajectory, the travel situation of the residence, and the attractiveness of the park itself. The carbon emission calculation process of each of the above dimensions takes into account dynamic factors. The accuracy of the carbon emission information of external transportation from multiple residences to the same park is improved from each dimension, thereby improving the accuracy of the subsequent recommendation of carbon emission management configuration parameters based on comprehensive carbon emission information.

[0125] According to an embodiment of the present invention, the frequency of park visits can be determined as follows: based on the signaling information of the mobile terminal, multiple third trajectories with different destinations in a preset geographical area during the same period are determined; based on the ratio of the second trajectory with the destination of the park to the multiple third trajectories during the same period, the park visit ratio is determined; and based on the park visit ratio and the average annual frequency of users' park visits in the preset geographical area, the park visit frequency is determined.

[0126] For example, given the multiple mobile terminal trajectories determined by signaling information from mobile terminals as described above, multiple third trajectories for different destinations within a preset geographical area during the same time period can be obtained from these trajectories. The ratio of the second trajectory with the park as the destination to the multiple third trajectories within the same time period is used as the park travel ratio. The park trip frequency is then calculated by multiplying the park trip ratio by the average annual frequency of park trips within the preset geographical area. .

[0127] For example, the frequency of park visits can be determined using the following formula (17):

[0128] (17);

[0129] in, To increase the frequency of park visits, and This includes the proportion of park visits and the average annual frequency of park visits by users within a preset geographical area. For example, the ratio of the number of second trajectories to the number of mobile terminals within a preset geographical area can be used as a metric. .

[0130] According to embodiments of the present invention, the process of determining the aforementioned carbon emission information from external traffic involves time-sensitive data such as signaling information, big data, and real-time pedestrian flow information. Compared with data obtained through traditional channels such as questionnaires and literature databases, the data accuracy is higher. Furthermore, by combining the carbon emission information from external traffic with GIS, abstract carbon emission information can be mapped to specific geographical locations, thus improving the precision. In particular, carbon emissions generated by user activity are dynamic and mobile. GIS can not only store spatial locations but also associate all attribute information of those locations. Its powerful spatial analysis capabilities make carbon emission accounting dynamic and highly visible.

[0131] According to an embodiment of the present invention, the comprehensive carbon emission information of each park can be obtained by summing the carbon emission information of external traffic, the carbon emission information of internal traffic, and the carbon emission information of visits and operations generated by visits and operations within the park.

[0132] Carbon emissions from in-park transportation, and carbon emissions from in-park visits and operations, can be determined as follows: In-park transportation carbon emissions generated by visiting the park using multiple modes of transportation are determined based on the passenger capacity, annual mileage, and carbon emissions of each mode of transportation within the park; in-park visit carbon emissions are determined based on carbon emissions from the consumption of goods consumed during visits, carbon emissions from the recycling of waste generated, and carbon emissions from the use of equipment within the park; and operational carbon emissions are determined based on the first operational carbon emissions sub-information generated by landscape maintenance activities and the second operational carbon emissions sub-information generated by garden maintenance activities.

[0133] The various modes of transportation within the park can include walking, bicycles, electric sightseeing vehicles, fuel-powered sightseeing vehicles, fuel-powered sightseeing boats, and electric sightseeing boats. Similar to the carbon emission information for each mode of transportation outside the park mentioned above, the carbon emission information for each mode of transportation within the park is also presented as a carbon emission factor, as shown in Table 3.

[0134] Table 3

[0135]

[0136] Table 3 shows the carbon emission factor for each mode of transportation within the park, representing the carbon emissions generated per person traveling 1 km using that mode of transportation. The unit of the carbon emission factor is kgCO2 / (person). -1 ·km -1 ).

[0137] The product of passenger capacity, annual mileage, and carbon emissions for each mode of transportation can be calculated, and the carbon emissions information for transportation within the park can be obtained by summing all products. For example, the carbon emissions information for transportation within the park can be determined using formula (18):

[0138] (18);

[0139] in, , , Let represent the annual mileage, carbon emission factor, and passenger capacity of the k'-th mode of transportation within the park, respectively. This indicates carbon emission information related to transportation within the park.

[0140] Information on carbon emissions generated by activities within the park can be obtained by summing the carbon emissions from the consumption of goods consumed during the visit, the carbon emissions from the recycling of waste generated during the visit, and the carbon emissions from the use of equipment within the park.

[0141] Carbon emission information for consumer goods consumed during park visits can be categorized into carbon emissions generated at each stage, including raw material acquisition, processing and manufacturing, packaging, transportation, sales, and waste recycling. Waste recycling of consumer goods is combined with all waste disposal within the park.

[0142] For example, a list of consumer goods that the park can provide can be obtained, and information such as the types and quantities of raw materials for each consumer good in the list can be determined (which can be obtained from the manufacturer's invention text). For example, carbon emissions during the deforestation process can be considered for timber-related items.

[0143] Carbon emission information for the raw material acquisition stage can be determined using the following formula (19):

[0144] (19);

[0145] Among them, CE 原材料 This indicates carbon emission information during the raw material acquisition phase, specifically the amount of carbon emissions during that phase. Let l represent the amount of the l-th raw material obtained. Let be the carbon emission factor required to obtain the l-th raw material, 'a' be the type of raw material used in the y-th consumer good, and 'b' be the number of types of consumer goods in the park. Let y be the annual sales volume of the yth type of consumer good.

[0146] For example, carbon emission information in the processing and manufacturing stage mainly refers to energy consumption during the processing and manufacturing process. Carbon emission information for the processing and manufacturing stage can be determined using the following formula (20):

[0147] (20);

[0148] Among them, CE 加工 This indicates carbon emission information during the processing and manufacturing stage, specifically the amount of carbon emissions during that stage. Let L be the amount of raw material L consumed during the processing and manufacturing stage of the y-th consumer good. The amount of energy consumed by type r in processing type l raw material for type y consumer goods (such as the electricity consumption of factory equipment). Let be the carbon emission factor of the r-th energy source, and c be the total number of energy types consumed in processing and manufacturing.

[0149] For example, carbon emission information during the packaging stage mainly refers to the carbon emissions generated by the use of packaging materials. Carbon emission information for the packaging stage can be determined using the following formula (21):

[0150] (twenty one);

[0151] Among them, CE包装 This indicates carbon emission information during the packaging stage, specifically the amount of carbon emissions during the packaging phase. The amount of packaging material used is f. Let f be the carbon emission factor of the f-th type of packaging material, and d be the total number of types of packaging materials.

[0152] For example, carbon emission information during the transportation phase mainly refers to the carbon emissions generated from transporting consumer goods from the production site to the park. The distance between the two locations can be determined based on the location information of the production site and the park, solely for determining the carbon emission information during the transportation phase. In one specific embodiment, considering the transportation mode and the entire transportation transit process, the carbon emission information during the transportation phase can be determined using the following formula (22):

[0153] (twenty two);

[0154] Among them, CE 运输 This indicates carbon emission information during the transportation phase, specifically the amount of carbon emissions during the transportation phase, D. s Let C be the distance of the s-th segment of transportation. sk’’ Let Q be the carbon emission factor of the k''th mode of transport in segment s. s Let be the quantity of consumables transported in segment s, where the k''th transport method in segment s can be determined from a public source (usually a fixed transport method, so there is no need to sum k''), and e is the total number of segments into which the transport trajectory of consumable y is divided.

[0155] For example, carbon emissions during the sales phase mainly refer to the carbon emissions generated by the sales points of consumer goods within the park, such as the energy consumed (e.g., electricity, gas) for lighting, air conditioning, and refrigeration equipment at these sales points. Carbon emissions during the sales phase can be determined using the following formula (23):

[0156] (twenty three);

[0157] Among them, CE 销售 This indicates carbon emission information during the sales phase, specifically the amount of carbon emissions during the sales phase. Let be the amount of the r-th type of energy consumed during the sales phase, and v be the v-th sales point in the park, with a total of w sales points. Information on carbon emissions generated at each point of sale.

[0158] By summing the above formulas (19) to (23), we can obtain the carbon emission information (CE) of the goods consumed during the visit to the park. 消费 For example, in formula (24):

[0159] (twenty four);

[0160] Among them, carbon emission information during the production stage (CE) 生产 It is obtained by summing formulas (19) to (22).

[0161] Information on carbon emissions from waste generated mainly includes the packaging and waste generated from consumer goods purchased by visitors within the park and from outside purchases, as well as the treatment processes such as landfill, incineration, and recycling.

[0162] The carbon emission information for the recycling of generated waste can be determined using formula (25):

[0163] (25);

[0164] Among them, CE 废弃物 This indicates the carbon emission information related to the recycling of generated waste, specifically the amount of carbon emissions from the recycling of generated waste. Let p be the annual processing volume of the p-th type of waste. Let be the carbon emission factor for the treatment method corresponding to the p-th type of waste. Let p be the annual recycling volume of the p-th type of waste. Let be the carbon emission factor for the p-th type of waste, and there are a total of q types of waste.

[0165] The carbon emission information for using equipment within the park mainly refers to the carbon emissions generated from activities within the park and the carbon emissions generated from using various recreational facilities within the park.

[0166] For example, the carbon emission information of equipment within the park can be determined using formula (26):

[0167] (26);

[0168] Among them, CE 活动 This indicates the carbon emission information of the equipment within the park. The annual consumption of the r-th type of energy used by amusement facilities for users' activities within the park.

[0169] Visit carbon emissions information CE 活动 It can be obtained by summing formulas (24) to (26), such as by calculating according to formula (27):

[0170] (27);

[0171] Among them, CE 活动 This indicates information about carbon emissions during the visit.

[0172] The first operational carbon emission sub-information for landscape maintenance activities mainly refers to the energy consumption of buildings other than sales points and amusement facilities, such as building operation and maintenance, lighting, and water purification. For example, the first operational carbon emission sub-information can be determined by formula (28):

[0173] (28);

[0174] Among them, CE 景观 This indicates the first operational carbon emissions information. This represents the annual consumption of the r-th energy source by landscape maintenance activities.

[0175] The second operational carbon emission sub-information for garden maintenance activities includes four stages: irrigation, fertilization, pesticide application, and pruning. The second operational carbon emission sub-information can be obtained by summing the carbon emissions of each of the four stages.

[0176] For example, the carbon emissions from irrigation, fertilization, pesticide application, and pruning can be determined using formulas (29), (30), (31), and (32), respectively:

[0177] (29);

[0178] (30);

[0179] (31);

[0180] (32);

[0181] Among them, CE 灌溉 CE 施肥 CE 施药 CE 修剪 These represent the carbon emissions during the irrigation process. , , These represent the irrigated area, fertilized area, and pesticide-applied area, respectively. , , The carbon emission factors for irrigation, fertilization, and pesticide application are respectively represented. N represents the water quota, with the unit being 2L / m2 * day, and day represents the number of irrigation days. and These represent the amount of base fertilizer and the amount of topdressing, respectively. , , These represent the number of times base fertilizer is applied, the number of times topdressing is applied, and the number of times pesticides are applied, respectively. H represents the amount of pesticide used. The carbon emissions from pruning are mainly generated by the use of pruning machinery, and can be indirectly determined by the energy consumption of the pruning machinery. This refers to the total number of machines used in the pruning process within the park. The first step in garden pruning The annual consumption of the rth type of energy in a machine.

[0182] The second operational carbon emission sub-information can be obtained by summing (29) to (32). The combined operational carbon emission information of the first and second operational carbon emission sub-information is shown in formula (33):

[0183] (33);

[0184] Among them, CE 公园 This indicates information about the carbon emissions from operations.

[0185] The comprehensive carbon emission information sources and their definitions for each park are shown in Table 4.

[0186] Table 4

[0187]

[0188] In summary, by combining the park's own operational carbon emission information, user behavior-related external traffic carbon emission information, internal traffic carbon emission information, and visitor carbon emission information, we can obtain the comprehensive carbon emission information for each park.

[0189] Comprehensive carbon emission information can be determined according to formula (34):

[0190] (34);

[0191] Among them, CE 运营 Indicates comprehensive carbon emission information, CE 用户 Information indicating carbon emissions generated by user behavior, CE 用户 =CE 外部 + CE 内部 + CE 游览 .

[0192] According to embodiments of the present invention, from the perspective of user carbon footprint, it includes multiple carbon emission sources such as carbon emissions generated by user visits and carbon emissions generated by the park's own operation, such as transportation, waste disposal, building operation and maintenance, public facility operation, and garden maintenance. The overall carbon emission sources are rich, comprehensive, and clear.

[0193] Figure 4A scenario diagram of a system for recommending configuration parameters for park carbon emission management according to an embodiment of the present invention is shown. Figure 4 As shown, the carbon emission information generated by user behavior includes carbon emission information from external transportation, internal transportation, consumption, waste recycling, and equipment. The consumption, waste recycling, and equipment carbon emission information are combined to form the visit carbon emission information. For external transportation carbon emission information, the carbon emissions to and from the park are measured from three dimensions: transportation mode, first trajectory, and residence, based on the probability of choosing each mode of transportation under the first trajectory, the probability of travel on each first trajectory, and the frequency of park visits. Consumption carbon emission information includes carbon emissions from production, transportation, and sales stages. For park operation carbon emission information, there are two sub-information: first operation carbon emission information generated by landscape maintenance activities and second operation carbon emission information generated by garden maintenance activities. The second operation carbon emission information generated by garden maintenance activities includes four stages: irrigation, fertilization, pesticide application, and pruning. Based on carbon emission information generated by user behavior and carbon emission information from park operations, comprehensive carbon emission information for each park can be obtained. Then, based on the comprehensive carbon emission information for each park, carbon emission management configuration parameters for each park can be determined.

[0194] Based on the comprehensive carbon emission information of each park, output the carbon emission management configuration parameters for each park, including: determining the carbon emission management configuration parameters that match the comprehensive carbon emission information from the database, and outputting the carbon emission management configuration parameters for each park.

[0195] In embodiments of the present invention, carbon emission management configuration parameters matching each comprehensive carbon emission information are pre-built in the database. For example, each range of comprehensive carbon emission information is uniquely mapped to a carbon emission management configuration parameter and stored in the database.

[0196] Therefore, after determining the comprehensive carbon emission information for each park, the recommendation system can use this comprehensive carbon emission information as matching input. By matching the comprehensive carbon emission information with multiple value ranges, and if a target value range is matched, the database returns the carbon emission management configuration parameters corresponding to that target value range. These carbon emission management configuration parameters are then presented to the user as the output of the entire recommendation system. This allows the recommendation system to provide users with more accurate carbon emission management configuration parameters.

[0197] Figure 5 A block diagram of an electronic device suitable for implementing a recommendation system for park carbon emission management configuration parameters according to an embodiment of the present invention is shown. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0198] like Figure 5 As shown, the electronic device 500 according to an embodiment of the present invention includes a processor 501, which can be configured according to data stored in a read-only memory (ROM), such as... Figure 5 The program in ROM 502 or loaded from storage section 508 into random access memory (RAM) is as follows: Figure 5 The processor 501 executes various appropriate actions and processes by storing programs in RAM 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the recommended system according to embodiments of the present invention.

[0199] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 executes various operations of the recommendation system according to embodiments of the present invention by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also execute various operations of the recommendation system according to embodiments of the present invention by executing programs stored in said one or more memories.

[0200] According to an embodiment of the present invention, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0201] According to embodiments of the present invention, the recommendation system according to embodiments of the present invention can be implemented as a computer software program. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for executing the recommendation system shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of the embodiments of the present invention. According to embodiments of the present invention, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0202] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the recommendation system according to embodiments of the present invention.

[0203] According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0204] For example, according to embodiments of the present invention, a computer-readable storage medium may include the ROM 502 and / or RAM 503 described above and / or one or more memories other than ROM 502 and RAM 503.

[0205] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for executing the recommendation system provided in the embodiments of the present invention. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the recommendation system provided in the embodiments of the present invention.

[0206] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this embodiment of the invention. According to embodiments of the invention, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0207] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0208] According to embodiments of the present invention, program code for executing the computer programs provided in the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0209] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, the features described in the various embodiments of the present invention can be combined and / or combined in various ways without departing from the spirit and teachings of the present invention. All such combinations and / or pairings fall within the scope of this invention.

[0210] The embodiments of the present invention have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of the invention. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of the invention, and all such substitutions and modifications should fall within the scope of the invention.

Claims

1. A system for recommending configuration parameters for park carbon emission management, characterized in that, Recommendation systems include: The data interface module is used to determine the first trajectory from each residence within a preset geographical area to each park; For each park: The first processing module is used to determine travel recommendation information based on park attribute information and pedestrian flow information within the park; for each first trajectory, it determines the probability of reaching the park by each mode of transportation according to the distance of the first trajectory, the speed information of each of the various modes of transportation, and the travel recommendation information. The second processing module is used to determine the off-park transportation carbon emission information of multiple residences to the park based on the travel probability, carbon emission information of each mode of transportation, transportation selection probability of each mode of transportation, population information of the residence, park travel frequency and distance of each first trajectory. The carbon emission comprehensive processing module is used to determine the comprehensive carbon emission information of each park based on the carbon emission information of traffic outside the park, the carbon emission information of traffic inside the park, and the carbon emission information of visitor behavior and operation behavior generated in the park. The recommendation module is used to output carbon emission management configuration parameters for each park based on the comprehensive carbon emission information of each park. The carbon emission management configuration parameters are used to uniquely determine a set of processing strategies for managing the carbon emissions of the park.

2. The recommendation system according to claim 1, characterized in that, Determine the primary trajectory from each residence within a predefined geographical area to each park, including: Based on the mobile terminal trajectory represented by the signaling information of the mobile terminal, a second trajectory between each residence and each park is determined. Based on the location information of each residence and each park, determine the geographically feasible route from each residence to each park; The first trajectory is obtained by filtering from multiple geographically feasible trajectories based on the similarity between the second trajectory and the geographically feasible trajectory.

3. The recommendation system according to claim 1, characterized in that, Based on park attribute information and pedestrian traffic information within the park, travel recommendations are determined, including: Using the entropy weight method, the information weight of each park attribute is determined based on the multiple park attribute information of each park. The park attribute information includes: the number of surrounding transportation facilities and shopping facilities within a preset distance, the park area, the park level, and the park type. Based on the attribute information of each park and the information weight of each park attribute information, the static recommendation information of the parks is determined; Based on pedestrian traffic information and park capacity information, dynamic recommendation information related to congestion level is determined; Dynamic recommendation information is used to correct static recommendation information to obtain travel recommendation information.

4. The recommendation system according to claim 1, characterized in that, Based on the distance of the first trajectory, the speed information of each mode of transportation, and travel recommendation information, the probability of reaching the park via each mode of transportation according to the first trajectory is determined, including: Based on the distance of the first trajectory and the speed information of each mode of transportation, determine the travel time to the park by each mode of transportation; Based on the distance of the first trajectory and the travel time to the park via each mode of transportation, distance recommendation information for the first trajectory is determined; Based on the distance recommendation information of the residence for the first trajectory, the distance recommendation information of the residence to each park corresponding to the first trajectory, and the travel recommendation information, the travel probability of reaching the park by each mode of transportation according to the first trajectory is determined.

5. The recommendation system according to claim 4, characterized in that, Based on the distance of the first trajectory and the travel time to the park via each mode of transportation, the recommended distance information for the first trajectory includes: Based on the distance of the first trajectory and the travel time to the park via each mode of transportation, determine the time-distance cost coefficient for reaching the park via each mode of transportation; Based on the comparison results between the time-distance cost coefficient and multiple preset cost intervals, a distance-sensitive parameter matching the comparison results is determined. A larger distance-sensitive parameter indicates that the distance-based recommendation information is more sensitive to distance. The distance recommendation information for the first trajectory is determined by multiplying the time distance cost coefficient and the distance sensitivity parameter.

6. The recommendation system according to claim 1, characterized in that, Based on travel probability, carbon emission information for each mode of transportation, travel choice probability for each mode of transportation, population information of the residential area, frequency of park visits, and distance of each first trajectory, the off-site transportation carbon emission information from multiple residential areas to the park is determined, including: The intermediate carbon emission information for each mode of transportation is determined by multiplying the transportation selection probability, carbon emission information, and distance of the first trajectory for each mode of transportation. For each first trajectory, the intermediate carbon emission information of each mode of transportation, the probability of travel, the population information of the residence corresponding to the first trajectory, and the frequency of park visits are multiplied together, and the results of multiplying each mode of transportation are summed to obtain the off-park transportation carbon emission information of the residence corresponding to the first trajectory to the park. The carbon emission information of off-site transportation from each residential point to the park is summed to obtain the carbon emission information of off-site transportation from multiple residential points to the park.

7. The recommendation system according to claim 1 or 6, characterized in that, Park visit frequency is determined as follows: Based on the signaling information of the mobile terminal, determine multiple third trajectories for different destinations in a preset geographical area during the same period; The proportion of trips to the park is determined by the ratio of the second trajectory with the park as the destination to multiple third trajectories within the same time period. as well as The frequency of park visits is determined based on the proportion of park visits and the average annual frequency of park visits by users within a preset geographical area.

8. The recommendation system according to claim 1, characterized in that, The recommendation system is also used for: Based on the passenger capacity, annual mileage, and carbon emission information of each mode of transportation within the park, determine the carbon emission information of in-park transportation generated by visiting the park through multiple modes of transportation; Based on carbon emission information of goods consumed during visits to the park, carbon emission information of waste generated during recycling, and carbon emission information of equipment used within the park, the carbon emission information of visits to the park is determined. Operational carbon emission information is determined based on the first operational carbon emission sub-information generated by landscape maintenance activities within the park and the second operational carbon emission sub-information generated by garden maintenance activities.

9. The recommendation system according to claim 1, characterized in that, Based on the comprehensive carbon emission information of each park, output the carbon emission management configuration parameters for each park, including: Determine carbon emission management configuration parameters from the database that match the comprehensive carbon emission information, and output the carbon emission management configuration parameters for each park.

10. An electronic device, comprising: One or more processors; Memory, used to store one or more programs. The feature is that, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the operations performed by the recommendation system according to any one of claims 1 to 9.

Images