Method and device for identifying different carbon emission reduction scenes in expressway and medium

Abstract

The invention provides a method and equipment for identifying different carbon emission reduction scenes in an expressway and a medium, typical carbon emission reduction scenes in various stages of expressway construction, operation, maintenance and the like can be systematically sorted out through known information (such as field investigation, literature research, expert conversation, questionnaire survey and the like) and a trained AI model, and the expressway carbon emission reduction scene identification method and device can be used for identifying different carbon emission reduction scenes in various stages of expressway construction, operation, maintenance and the like. For example, low-carbon material application, renewable energy source development scenes, intelligent service system operation scenes and the like.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and medium for identifying different carbon emission reduction scenarios in a highway. Background Art

[0002] With the continuous increase of global climate change and greenhouse gas emissions, environmental protection and carbon reduction have become urgent global issues. In order to achieve the goal of sustainable development, governments, enterprises and organizations are actively seeking effective carbon reduction technologies and methods. With the rapid development of AI technology, especially the widespread application of deep learning, natural language processing (NLP) and other technologies, new ideas and methods are provided for the identification of carbon reduction scenarios. Through data analysis, pattern recognition and other technical means, AI models can track and analyze the carbon footprint of cities or enterprises in real time, identify the main emission sources, and play an important role in identifying carbon reduction scenarios. The existing methods for identifying carbon emission reduction include direct measurement and indirect measurement. For example, satellite remote sensing technology is used to monitor the carbon dioxide concentration on the earth's surface and identify carbon reduction based on carbon dioxide concentration. These methods can meet the needs to a certain extent, but they have limitations such as low data quality, limited coverage and high cost. Different AI models are not used based on different data characteristics to obtain the greenhouse gas carbon emissions corresponding to the vehicle, which reduces the accuracy of identifying carbon reduction scenarios. Summary of the invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is: a method for identifying different carbon emission reduction scenarios in a highway, comprising the following steps:

[0004] S100, obtain the initial area ID list A = {A1, ..., A i , ..., A n}, A i is the i-th initial area ID, i=1...n, n is the number of initial area IDs, wherein the initial area ID is a unique identifier that characterizes the initial area, and the initial area is an area in the target highway divided based on the installation location of the camera.

[0005] S200, according to A, obtain the first target priority list E corresponding to A = {E1, ..., E i ,……,E n}, E i A i The corresponding first target priority, wherein the first target priority is the maximum greenhouse gas carbon content that can be absorbed by plants in the initial area corresponding to the initial area ID.

[0006] S300, according to A, obtain the second target priority list F corresponding to A = {F1, ..., Fi , ..., F n}, F i A i The corresponding second target priority, wherein F is obtained in S300 by the following steps i :

[0007] S301, obtain A i Corresponding target vehicle ID list U i = {U i1 , ..., U ij , ..., U im(i)},U ij A i The corresponding j-th target vehicle ID, j = 1...m(i), m(i) is A i The number of target vehicle IDs in the corresponding target vehicle ID list, wherein the target vehicle ID is a unique identifier that characterizes the target vehicle, and the target vehicle is i The corresponding vehicle in the initial area.

[0008] S302, obtaining U through the first AI model i Corresponding target speed list B i = {B i1 , ..., B ij , ..., B im(i)}, B ij For U ij The corresponding target speed, wherein the target speed is the speed of the target vehicle obtained by inputting the characteristic information corresponding to the target vehicle into the first AI model.

[0009] S303, B i Input into the second AI model to obtain F i , where F i Meet the following conditions:

[0010] F i =∑ m(i) j＝1 H ij , H ij For B ij The corresponding key priority is the greenhouse gas carbon content released by the target vehicle obtained by inputting the target speed into the second AI model.

[0011] S400, when E i >F i When , the initial area is predicted to be a scenario where carbon emission reduction is not required.

[0012] S500, when E i ≤F iWhen , the initial area is predicted to be a scenario where carbon emission reduction is required.

[0013] The present invention protects an electronic device, including a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the above-mentioned method for different carbon emission reduction scenarios of highways.

[0014] The present invention protects a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned method for different carbon emission reduction scenarios of highways.

[0015] The present invention has at least the following beneficial effects: a method for identifying different carbon emission reduction scenarios in a highway, comprising the following steps: obtaining an initial area ID list, obtaining a first target priority list corresponding to the initial area ID list based on the initial area ID list, obtaining a second target priority list corresponding to the initial area ID list based on the initial area ID list, wherein a target vehicle ID list corresponding to the initial area ID is obtained, a target speed list corresponding to the target vehicle ID list is obtained through a first AI model, the target speed list is input into a second AI model, and a second target priority is obtained. When the first target priority is greater than the second target priority, the initial area is predicted to be a scenario where carbon emission reduction is not required, and when the first target priority is not greater than the second target priority, the initial area is predicted to be a scenario where carbon emission reduction is required. The present invention reduces the cost of identifying carbon emission reduction scenarios, expands the coverage of identifying carbon emission reduction scenarios, and uses different AI models based on different characteristics of the data to obtain the greenhouse gas carbon emissions corresponding to the vehicle. Different target models are used to obtain different types of objective functions to obtain the corresponding greenhouse gas carbon emissions, thereby improving the accuracy of identifying carbon emission reduction scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 A flowchart of a method for identifying different carbon emission reduction scenarios on a highway provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] Example

[0020] A method for identifying different carbon emission reduction scenarios in a highway, the method comprising the following steps: Figure 1 As shown:

[0021] S100, obtain the initial area ID list A = {A1, ..., A i , ..., A n}, A i is the i-th initial area ID, i=1...n, n is the number of initial area IDs, wherein the initial area ID is a unique identifier that characterizes the initial area, and the initial area is an area in the target highway divided based on the installation location of the camera.

[0022] Specifically, those skilled in the art know that any method for determining an identifier in the prior art falls within the protection scope of the present invention and will not be described in detail herein.

[0023] Specifically, the target expressway is an expressway for which a carbon emission reduction scenario is to be identified.

[0024] S200, according to A, obtain the first target priority list E corresponding to A = {E1, ..., E i ,……,E n}, E i A i The corresponding first target priority, wherein the first target priority is the maximum greenhouse gas carbon content that can be absorbed by plants in the initial area corresponding to the initial area ID.

[0025] S300, according to A, obtain the second target priority list F corresponding to A = {F1, ..., F i , ..., F n}, F i A i The corresponding second target priority, wherein F is obtained in S300 by the following steps i :

[0026] S301, obtain A i Corresponding target vehicle ID list U i = {U i1 , ..., U ij , ..., Uim(i)},U ij A i The corresponding j-th target vehicle ID, j = 1...m(i), m(i) is A i The number of target vehicle IDs in the corresponding target vehicle ID list, wherein the target vehicle ID is a unique identifier that characterizes the target vehicle, and the target vehicle is i The corresponding vehicle in the initial area.

[0027] Specifically, those skilled in the art know that any method for determining a vehicle identification in the prior art falls within the protection scope of the present invention and will not be described in detail herein, for example: a vehicle identification such as a license plate number.

[0028] S302, obtaining U through the first AI model i Corresponding target speed list B i = {B i1 , ..., B ij , ..., B im(i)}, B ij For U ij The corresponding target speed, wherein the target speed is the speed of the target vehicle obtained by inputting the characteristic information corresponding to the target vehicle into the first AI model.

[0029] Specifically, in S302, the following steps are performed to obtain B ij :

[0030] S3021, obtain the sample feature vector list G corresponding to the sample vehicle ID list = {G1, ..., G e , ..., G f}, G e = {G e1 , ..., G ei , ..., G en}, G ei is the i-th sample feature vector corresponding to the e-th sample vehicle ID, e = 1...f, f is the number of sample vehicle IDs in the sample vehicle ID list, where G ei The method of obtaining is to convert the i-th sample feature information Q corresponding to the e-th sample vehicle ID ei The vector obtained by inputting into the natural language processing model, Q ei = {Q 1 ei , Q 2 ei , Q 3 ei , Q 4 ei , Q 5 ei}, Q1 ei The starting position of the initial area corresponding to A1 corresponding to the e-th sample vehicle ID and A i The distance between the corresponding initial region and the final position, Q 2 ei The starting position of the initial area corresponding to A1 and A i The number of vehicles that have traveled between the corresponding initial area and the end position within the first preset time period, Q 3 ei The starting position of the sample vehicle corresponding to the e-th sample vehicle ID in the initial area corresponding to A1 and A i The average vehicle speed between the terminal positions of the corresponding initial area, Q 4 ei The starting position of the initial area corresponding to A1 and A i The average value of the average vehicle speeds corresponding to the sample vehicle IDs other than the e-th sample vehicle ID between the end positions of the corresponding initial area, Q 5 ei is the e-th sample vehicle ID in A i The starting position of the corresponding initial area is i+1 The error value between the first speed and the second speed corresponding to the starting position of the corresponding initial area, A i+1 is the i+1th initial region ID.

[0031] Specifically, the sample vehicle ID is a unique identifier that characterizes a sample vehicle, wherein the sample vehicle is a vehicle that has traveled through a target highway.

[0032] Furthermore, the method for acquiring the sample vehicle ID is consistent with the method for acquiring the target vehicle ID.

[0033] Specifically, those skilled in the art know that any method in the prior art that uses a natural language processing model to convert a numerical value into a vector falls within the scope of protection of the present invention and will not be described in detail herein, for example: natural language processing models such as the Bert model and the Word2vec model, for example, a method of converting each numerical value into a vector for vector addition or vector concatenation.

[0034] Specifically, the time span of the first preset time period ranges from 3 days to 7 days, wherein the end time of the first preset time period is earlier than the current time. Those skilled in the art know that the first preset time period can be selected according to actual needs, which falls within the protection scope of the present invention and will not be repeated here.

[0035] Specifically, the first speed is a predicted vehicle speed, wherein those skilled in the art know that any method for predicting vehicle speed in the prior art falls within the protection scope of the present invention and will not be described herein in detail. It can be understood that: the first vehicle speed is the speed corresponding to the sample vehicle ID at the relevant position obtained by any method for predicting vehicle speed in the prior art, such as a method for predicting vehicle speed by predicting latitude and longitude and weather conditions.

[0036] Specifically, the second speed is the actual vehicle speed.

[0037] Specifically, those skilled in the art know that any method for obtaining an error in the prior art falls within the protection scope of the present invention and will not be described in detail herein.

[0038] S3022: Input the sample speed list corresponding to G and G into the initial neural network model for training to obtain a first AI model, wherein the first AI model is a trained neural network model.

[0039] Specifically, the sample speed list includes a plurality of sample speeds, wherein each sample speed corresponds to a sample feature vector, and the sample speed is the actual speed of the target vehicle ID corresponding to the sample feature vector at the corresponding position.

[0040] Specifically, those skilled in the art know that any method for training a neural network model in the prior art falls within the protection scope of the present invention and will not be described in detail herein.

[0041] S3023, Get U ij The corresponding target feature vector is the target feature vector of U ij Corresponding target feature information W ij The vector obtained by inputting into the natural language processing model, where W ij = {W 1 ij , W 2 ij , W 3 ij , W 4 ij , W 5 ij},W 1 ij For U ij The starting position of the initial area corresponding to the target vehicle corresponding to A1 is the same as A i The distance between the corresponding initial regions and their end positions, W 2 ij The starting position of the initial area corresponding to A1 and A iThe number of vehicles that have traveled between the corresponding end positions of the initial area within the second preset time period, W 3 ij For U ij The starting position of the corresponding target vehicle in the initial area corresponding to A1 is i The average vehicle speed between the corresponding initial area and the terminal position, W 4 ij The starting position of the initial area corresponding to A1 and A i The corresponding initial region's end position is between U ij The average value of the average speeds of target vehicles other than the corresponding target vehicle, W 5 ij For U ij The corresponding target vehicle is in A i The starting position of the corresponding initial area is i+1 The error value between the first speed and the second speed corresponding to the starting position of the corresponding initial area.

[0042] Specifically, the end time of the second preset time period is the current moment, wherein the time span of the second preset time period is consistent with the time span of the first preset time period.

[0043] S3024, input the target feature vector into the first AI model to obtain U ij The corresponding target speed B ij .

[0044] S303, B i Input into the second AI model to obtain F i , where F i Meet the following conditions:

[0045] F i =∑ m(i) j＝1 H ij , H ij For B ij The corresponding key priority is the greenhouse gas carbon content released by the target vehicle obtained by inputting the target speed into the second AI model.

[0046] Specifically, S303 also includes the following steps:

[0047] S3031, obtain the objective function list L = {L1, ..., L r , ..., L s}, L ris the objective function corresponding to the rth target vehicle type, r=1…s, s is the number of objective functions, wherein the objective function is a function obtained by inputting data associated with the target vehicle type into the target model.

[0048] Specifically, the data associated with the target vehicle type includes the vehicle speed of the same target vehicle type and the greenhouse gas carbon emissions corresponding to the vehicle speed.

[0049] Furthermore, the target vehicle type is a type of vehicle classified based on the fuel consumption of the vehicle, such as a small gasoline vehicle, a medium-sized gasoline vehicle, a medium-sized diesel vehicle, a large diesel vehicle, and other target vehicle types.

[0050] Specifically, the target model is a polynomial regression model, wherein those skilled in the art know that the regression model can be selected according to actual needs, all of which fall within the protection scope of the present invention and will not be described in detail here.

[0051] S3032, when U ij The corresponding vehicle type and L r When the corresponding target vehicle type is the same, ij Input to L r To obtain H ij .

[0052] Specifically, the second AI model is a model for constructing a generated objective function to obtain key priorities.

[0053] Specifically, those skilled in the art know that any method for identifying vehicle types in the prior art falls within the protection scope of the present invention and will not be described in detail herein, for example: a method for identifying vehicle types based on license plate numbers and the length and width of the vehicle.

[0054] S400, when E i >F i When , the initial area is predicted to be a scenario where carbon emission reduction is not required.

[0055] S500, when E i ≤F i When , the initial area is predicted to be a scenario where carbon emission reduction is required.

[0056] An embodiment of the present invention provides a method for identifying different carbon emission reduction scenarios in a highway, comprising the following steps: obtaining an initial area ID list, obtaining a first target priority list corresponding to the initial area ID list based on the initial area ID list, and obtaining a second target priority list corresponding to the initial area ID list based on the initial area ID list, wherein a target vehicle ID list corresponding to the initial area ID is obtained, and a target speed list corresponding to the target vehicle ID list is obtained through a first AI model, and the target speed list is input into a second AI model to obtain a second target priority. When the first target priority is greater than the second target priority, the initial area is predicted to be a scenario where carbon emission reduction is not required, and when the first target priority is not greater than the second target priority, the initial area is predicted to be a scenario where carbon emission reduction is required. The present invention reduces the cost of identifying carbon emission reduction scenarios, expands the coverage of identifying carbon emission reduction scenarios, and uses different AI models based on different characteristics of the data to obtain the greenhouse gas carbon emissions corresponding to the vehicle, wherein different target models are used to obtain different types of objective functions to obtain the corresponding greenhouse gas carbon emissions, thereby improving the accuracy of identifying carbon emission reduction scenarios.

[0057] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0058] An embodiment of the present invention further provides an electronic device, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0059] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for identifying different carbon emission reduction scenarios in a highway, characterized in that: The method comprises the following steps: S100, obtain the initial area ID list A = {A1, ..., A i , ..., A n }, A i is the i-th initial area ID, i=1...n, n is the number of initial area IDs, wherein the initial area ID is a unique identifier representing the initial area, and the initial area is an area in the target highway divided based on the installation location of the camera; S200, according to A, obtain the first target priority list E corresponding to A = {E1, ..., E i ,……,E n }, E i A i The first target priority corresponding to the initial region ID is the maximum greenhouse gas carbon content that can be absorbed by plants in the initial region corresponding to the initial region ID; S300, according to A, obtain the second target priority list F corresponding to A = {F1, ..., F i , ..., F n }, F i A i The corresponding second target priority, wherein F is obtained in S300 by the following steps i : S301, obtain A i Corresponding target vehicle ID list U i = {U i1 , ..., U ij , ..., U im(i) },U ij A i The corresponding j-th target vehicle ID, j = 1...m(i), m(i) is A i The number of target vehicle IDs in the corresponding target vehicle ID list, wherein the target vehicle ID is a unique identifier that characterizes the target vehicle, and the target vehicle is i The vehicles in the corresponding initial area; S302, obtaining U through the first AI model i Corresponding target speed list B i = {B i1 , ..., B ij , ..., B im(i) }, B ij For U ij A corresponding target speed, wherein the target speed is the speed of the target vehicle obtained by inputting the characteristic information corresponding to the target vehicle into the first AI model; S303, B i Input into the second AI model to obtain F i , where F i Meet the following conditions: F i =∑ m(i) j＝1 H ij , H ij For B ij A corresponding key priority, wherein the key priority is the greenhouse gas carbon content released by the target vehicle obtained by inputting the target speed into the second AI model; S400, when E i >F i When , the initial area is predicted to be a scenario where carbon emission reduction is not required; S500, when E i ≤F i When , the initial area is predicted to be a scenario where carbon emission reduction is required.

2. The method for different carbon emission reduction scenarios of highways according to claim 1 is characterized in that: In S302, B is obtained by the following steps: ij : S3021, obtain the sample feature vector list G corresponding to the sample vehicle ID list = {G1, ..., G e , ..., G f }, G e = {G e1 , ..., G ei , ..., G en }, G ei is the i-th sample feature vector corresponding to the e-th sample vehicle ID, e = 1...f, f is the number of sample vehicle IDs in the sample vehicle ID list, where G ei The method of obtaining is to convert the i-th sample feature information Q corresponding to the e-th sample vehicle ID ei The vector obtained by inputting into the natural language processing model, Q ei = {Q 1 ei , Q 2 ei , Q 3 ei , Q 4 ei , Q 5 ei }, Q 1 ei The starting position of the initial area corresponding to A1 corresponding to the e-th sample vehicle ID and A i The distance between the corresponding initial region and the final position, Q 2 ei The starting position of the initial area corresponding to A1 and A i The number of vehicles that have traveled between the corresponding initial area and the end position within the first preset time period, Q 3 ei The starting position of the sample vehicle corresponding to the e-th sample vehicle ID in the initial area corresponding to A1 and A i The average vehicle speed between the terminal positions of the corresponding initial area, Q 4 ei The starting position of the initial area corresponding to A1 and A i The average value of the average vehicle speeds corresponding to the sample vehicle IDs other than the e-th sample vehicle ID between the end positions of the corresponding initial area, Q 5 ei is the e-th sample vehicle ID in A i The starting position of the corresponding initial area is i+1 The error value between the first speed and the second speed corresponding to the starting position of the corresponding initial area, A i+1 is the i+1th initial area ID; S3022, inputting the sample speed list corresponding to G and G into the initial neural network model for training, and obtaining a first AI model, wherein the sample speed list includes a plurality of sample speeds, and the sample speed is the actual speed of the target vehicle ID corresponding to the sample feature vector at the corresponding position, and the first AI model is the trained neural network model; S3023, Get U ij The corresponding target feature vector is the target feature vector of U ij Corresponding target feature information W ij The vector obtained by inputting into the natural language processing model, where W ij = {W 1 ij , W 2 ij , W 3 ij , W 4 ij , W 5 ij },W 1 ij For U ij The starting position of the initial area corresponding to the target vehicle corresponding to A1 is the same as A i The distance between the corresponding initial regions and their end positions, W 2 ij The starting position of the initial area corresponding to A1 and A i The number of vehicles that have traveled between the corresponding end positions of the initial area within the second preset time period, W 3 ij For U ij The starting position of the corresponding target vehicle in the initial area corresponding to A1 is i The average vehicle speed between the corresponding initial area and the terminal position, W 4 ij The starting position of the initial area corresponding to A1 and A i The corresponding initial region ends at the position between U ij The average value of the average speeds of target vehicles other than the corresponding target vehicle, W 5 ij For U ij The corresponding target vehicle is in A i The starting position of the corresponding initial area is i+1 an error value between a first speed and a second speed corresponding to the starting positions of the corresponding initial areas, wherein the first speed is a predicted vehicle speed and the second speed is an actual vehicle speed; S3024, input the target feature vector into the first AI model to obtain U ij The corresponding target speed B ij .

3. The method for different carbon emission reduction scenarios of highways according to claim 2 is characterized in that: The time span of the first preset time period ranges from 3 days to 7 days, wherein the end time of the first preset time period is earlier than the current time.

4. The method for different highway carbon emission reduction scenarios according to claim 2 is characterized in that: The end time of the second preset time period is the current time, wherein the time span of the second preset time period is consistent with the time span of the first preset time period.

5. The method for different carbon emission reduction scenarios of highways according to claim 1 is characterized in that: S303 also includes the following steps: S3031, obtain the objective function list L = {L1, ..., L r , ..., L s }, L r is the objective function corresponding to the rth target vehicle type, r=1…s, s is the number of objective functions, wherein the objective function is a function obtained by inputting data associated with the target vehicle type into the target model; S3032, when U ij The corresponding vehicle type and L r When the corresponding target vehicle type is the same, ij Input to L r To obtain H ij .

6. The method for different carbon emission reduction scenarios of highways according to claim 5 is characterized in that: The target vehicle type is a type of vehicle classified based on fuel consumption of the vehicle.

7. The method for different carbon emission reduction scenarios of highways according to claim 5 is characterized in that: The target model is a polynomial regression model.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method according to any one of claims 1 to 7.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method according to any one of claims 1 to 7.

Images