Method and equipment for carbon income path planning based on carbon emission reduction asset time sequence, and medium

Abstract

The invention discloses a method and equipment for carbon income path planning based on a carbon emission reduction asset time sequence and a medium, and the method comprises the steps: analyzing the time sequence of carbon emission reduction assets (i.e., a carbon emission reduction amount time sequence) and a carbon emission reduction policy time sequence of a target department under the drive of natural low carbon income in a carbon emission reduction scene; according to the method, evaluation of a carbon emission reduction scene and future capability prediction analysis are realized, a carbon emission reduction income path is planned, high dependence of current carbon emission comprehensive management and control on carbon quotas and carbon transactions is effectively solved, carbon emission management and control in a larger area and a larger time span can be realized through accurate and reliable prediction of the carbon emission reduction, and the carbon emission management and control efficiency is improved. Reliable data support and guarantee are provided for realizing the zero-carbon expressway, and a feasible scheme is provided for constructing a marketized and diversified ecological compensation mechanism and a realization mechanism in the traffic field.

Description

Technical Field

[0001] The present disclosure generally relates to the field of carbon revenue path technology, and specifically relates to a method, device and medium for carbon revenue path planning based on a carbon emission reduction asset time series. Background Art

[0002] Smart highways refer to the integration of new generation information technologies such as artificial intelligence, cloud computing, 5G, and big data on the basis of traditional highways, and ultimately form a new type of highway with intelligent decision-making, intelligent perception, and intelligent control capabilities. Compared with traditional highways, smart highways are more complete and advanced in terms of highway network perception system, highway infrastructure monitoring system, real-time traffic warning system, and road safety emergency response system.

[0003] In order to achieve the "zero carbon" goal, relevant technical departments have fully integrated photovoltaic technology, forestry carbon sink technology, and comprehensive carbon emission control technology in order to achieve overall sustainable zero-carbon operation. However, the "zero carbon" achieved by relevant technologies depends on the subsequent calculation and trading of carbon emission reductions, which makes it difficult to achieve the "zero carbon" goal within a larger range and a wider time span of the highway life cycle. Therefore, how to provide a method for carbon benefit path planning based on the time series of carbon emission reduction assets, that is, to provide a predictable carbon emission reduction forecasting method, and then in the carbon emission reduction scenario, by analyzing the time series of carbon emission reduction assets driven by natural low-carbon benefits (i.e., carbon emission reduction time series) and carbon emission reduction policy time series of the target department, to achieve the evaluation of carbon emission reduction scenarios and future capacity forecast analysis, and then plan the carbon emission reduction benefit path has become an urgent problem to be solved. Summary of the invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a method, device and medium for carbon benefit path planning based on the carbon emission reduction asset time series, which can accurately predict the carbon emission reduction of the target department and provide a reliable data basis for carbon emission reduction benefit path planning.

[0005] In a first aspect, an embodiment of the present application provides a method for carbon revenue path planning based on a carbon emission reduction asset time series, comprising:

[0006] Obtain the time series of carbon emission reductions corresponding to the target sector driven by natural low-carbon benefits;

[0007] Obtain carbon reduction policy time series;

[0008] Based on the carbon emission reduction time series and the carbon emission reduction policy time series, predict the future carbon emission reduction of the target sector to obtain the carbon emission reduction prediction result of the target sector under the influence of the carbon emission reduction policy;

[0009] Based on the carbon emission reduction forecast result of at least one of the target departments, a carbon emission reduction benefit path is planned.

[0010] In some embodiments, the forecasting of the future carbon emission reduction of the target sector based on the carbon emission reduction time series and the carbon emission reduction policy time series to obtain the forecast result of the carbon emission reduction of the target sector under the influence of the carbon emission reduction policy includes:

[0011] Performing block embedding and first variable embedding on the carbon emission reduction time series to obtain a plurality of time tokens and a first global variable token;

[0012] Performing second variable embedding on the carbon reduction policy time series to obtain a second global variable token;

[0013] Applying self-attention analysis to the time tokens to obtain a first dependency relationship between a plurality of the time tokens;

[0014] Performing cross attention analysis on the first global variable token and the second global variable token to obtain a second dependency relationship between the first global variable token and the second global variable token;

[0015] Based on the first dependency relationship and the second dependency relationship, the future carbon emission reduction of the target department is predicted to obtain the predicted result of the carbon emission reduction of the target department under the influence of the carbon emission reduction policy.

[0016] In some embodiments, the step of embedding the carbon emission reduction time series into blocks to obtain a plurality of time tokens includes:

[0017] Dividing the carbon emission reduction time series into a plurality of non-overlapping regions;

[0018] Each of the non-overlapping regions is projected as one of the time tokens.

[0019] In some embodiments, the following formula is used for self-attention analysis:

[0020]

[0021] in, is the output of the self-attention layer, is the time token for each time zone, is the first global variable token, l∈{0,…,N-1} represents the lth time zone, and N is the number of time tokens corresponding to the carbon emission reduction time series.

[0022] In some embodiments, the following formula is used for cross-attention analysis:

[0023]

[0024] in, is the output of the cross attention layer, i.e., the input of the next self-attention layer, is the first global variable token, Y ex Is the second global variable token.

[0025] In some embodiments, the planning of the carbon emission reduction benefit path based on the carbon emission reduction prediction result of at least one of the target departments includes:

[0026] For each future time step, obtaining a carbon emission reduction evaluation index corresponding to at least one of the target sectors in the future time step;

[0027] The future time step with the highest carbon emission reduction evaluation index is used as the current carbon benefit path planning.

[0028] In a second aspect, an embodiment of the present application provides a device for planning a carbon revenue path based on a carbon emission reduction asset time series, including:

[0029] The first acquisition module is used to obtain the time series of carbon emission reduction corresponding to the target sector driven by natural low-carbon benefits;

[0030] The second acquisition module is used to obtain the carbon reduction policy time series;

[0031] A prediction module, used to predict the future carbon emission reduction of the target sector based on the carbon emission reduction time series and the carbon emission reduction policy time series, and obtain the carbon emission reduction prediction result of the target sector under the influence of the carbon emission reduction policy;

[0032] A planning module is used to plan a carbon emission reduction benefit path based on the carbon emission reduction forecast result of at least one of the target departments.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the embodiment of the present application when executing the program.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the embodiment of the present application.

[0035] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, it implements the method described in the embodiment of the present application.

[0036] The method, device and medium for carbon revenue path planning based on the carbon emission reduction asset time series provided in the embodiments of the present application predict the carbon emission reduction of the target department under the influence of the carbon emission reduction policy by analyzing the temporal dependency between the carbon emission reduction time series corresponding to the target department driven by natural low-carbon benefits and the carbon emission reduction policy time series, effectively solving the current high reliance on carbon quotas and carbon trading for comprehensive carbon emission management and control. Through accurate and reliable prediction of carbon emission reductions, carbon emission management and control can be achieved in larger areas and longer time spans, providing reliable data support and guarantee for the realization of zero-carbon highways.

[0037] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0039] Figure 1 A flow chart of a method for carbon revenue path planning based on a carbon emission reduction asset time series provided in an embodiment of the present application is shown;

[0040] Figure 2 A schematic diagram of the structure of a device for performing carbon revenue path planning based on a carbon emission reduction asset time series provided in another embodiment of the present application is shown;

[0041] Figure 3 A schematic diagram of the structure of a computer system of an electronic device or server suitable for implementing an embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0043] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0044] In order to further illustrate the technical solution provided by the embodiment of the present application, this is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiment of the present application provides the method operation instruction steps shown in the following embodiments or drawings, more or less operation instruction steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiment of the present application. The method may be executed in the order of the method shown in the embodiment or drawings or in parallel during the actual processing process or when the device is executed.

[0045] Please refer to Figure 1 , Figure 1 The flowchart of the method for carbon revenue path planning based on carbon emission reduction asset time series provided by an embodiment of the present application is shown. Figure 1 As shown, the method includes:

[0046] Step 101, obtaining the time series of carbon emission reduction corresponding to the target sector driven by natural low-carbon benefits.

[0047] It should be noted that the target department can be a department under the highway operation system, including but not limited to the transportation department, power supply department, power grid department, load department and energy storage department, which are managed through the comprehensive carbon emission control system to achieve refined energy control. The time series of carbon emission reduction corresponding to the target department driven by natural low-carbon benefits is the time series of carbon emission reduction production implemented by the target department under its own endogenous motivation such as cost traction and low-carbon benefits.

[0048] It should be understood that when there is no exogenous driving force from government policies, each department, such as each enterprise, will also form its own carbon emission reduction time series due to its own costs, benefits, etc. For example, lower low-carbon innovation costs will cause enterprises to invest more resources in technology research and development upgrades, which can drive enterprises to achieve a transformation in production methods, thereby obtaining a carbon emission reduction time series with gradually increasing and converging carbon emission reductions. However, excessive pooling layer capital pressure will dampen the enthusiasm of enterprises for low-carbon technology innovation. At this time, the higher risk of R&D investment makes it worthwhile for enterprises to continue to adopt traditional production methods, thereby obtaining a carbon emission reduction time series with decreasing and converging carbon emission reductions.

[0049] That is to say, the time series of carbon emission reduction corresponding to the target department driven by natural low-carbon benefits is the time series corresponding to the endogenous variable of the target department, which is used to reflect the impact of the target department's own situation on the change of carbon emission reduction. In the embodiment of the present application, the time series of carbon emission reduction corresponding to the target department driven by natural low-carbon benefits will tend to converge when there is no exogenous driving force, that is, the carbon emission reduction of the target department will eventually become a fixed value.

[0050] Step 102: Obtain the carbon emission reduction policy time series.

[0051] It should be noted that carbon emission reduction policies include but are not limited to subsidy mechanisms and penalty mechanisms. The carbon emission reduction policy time series is used to characterize the intensity and duration of carbon emission reduction policies provided by government departments.

[0052] It should also be noted that evolutionary game research between the government and enterprises found that exogenous drivers (subsidy mechanisms and punishment mechanisms) within a certain range can effectively encourage enterprises to choose low-carbon innovation, while excessive exogenous drivers (excessive government low-carbon innovation subsidies and fines) cannot stimulate corporate enthusiasm for low-carbon innovation. At this time, the role of exogenous motivation is no longer significant.

[0053] Step 103, based on the carbon emission reduction time series and the carbon emission reduction policy time series, predict the future carbon emission reduction of the target department to obtain the carbon emission reduction prediction result of the target department under the influence of the carbon emission reduction policy.

[0054] It should be noted that although the relevant technologies analyze the carbon emission reductions of enterprises under the influence of endogenous and exogenous forces respectively, such analysis can neither well explain the development trend of carbon emission reduction of enterprises under the influence of both, nor predict the carbon emission reduction results of enterprises under the influence of dynamically changing policies. Therefore, it is impossible for government departments to better allocate and plan the carbon benefits of enterprises in the region.

[0055] Based on this, this application proposes to predict the future carbon emission reduction of the target sector based on the carbon emission reduction time series driven by the endogenous driving force of the enterprise and the carbon emission reduction policy time series driven by exogenous driving force.

[0056] In a feasible embodiment, the present application uses a forecasting model that can capture time dependency and multivariate correlation to predict future carbon emission reductions in a target sector.

[0057] Specifically, the carbon emission reduction time series is subjected to block embedding and first variable embedding to obtain multiple time tokens and a first global variable token, the carbon emission reduction policy time series is subjected to second variable embedding to obtain a second global variable token, self-attention analysis is applied to the time token to obtain the first dependency relationship between the multiple time tokens, cross-attention analysis is performed on the first global variable token and the second global variable token to obtain the second dependency relationship between the first global variable token and the second global variable token, and based on the first dependency relationship and the second dependency relationship, the future carbon emission reduction of the target sector is predicted to obtain the carbon emission reduction prediction result of the target sector under the influence of the carbon emission reduction policy.

[0058] In a specific embodiment, the carbon emission reduction time series can be expressed as The carbon reduction policy time series can be expressed as Among them, L is the length of the lookback window of the carbon emission reduction time series, x i represents the value at the i-th time point, L ′ is the length of the lookback window of the carbon reduction policy time series, C is the number of carbon reduction policy types, is the jth carbon emission reduction policy.

[0059] The prediction model is based on the carbon emission reduction time series and carbon emission reduction policy time series, and predicts the carbon emission reduction of the target sector in the next s time steps. The prediction result of carbon emission reduction of the target department under the influence of carbon emission reduction policy can be expressed as:

[0060]

[0061] It should be noted that in the embodiment of the present application, in order to avoid the computational complexity caused by using too fine-grained variable representation of the carbon emission reduction policy time series, as well as unnecessary noise introduced by time dislocation and other reasons, the global representation of the carbon emission reduction time series and the carbon emission reduction policy time series is used to model the interaction between different variables. Specifically, the following formula is used to obtain the first global variable token and the second global variable token:

[0062] Y en =EnVariateEmbed(x)

[0063] Y ex,j =ExVariateEmbed(z (j) ), j∈{1,…,C}

[0064]

[0065] Among them, Y en is the first global variable token, Y ex,j is the second global variable token corresponding to the carbon reduction policy, Y ex A collection of representations of various carbon reduction policies.

[0066] It should be noted that there are two variable embedding layers EnVariateEmbed: and ExVariateEmbed: It is instantiated as a trainable linear projector. The trained projector mapping can make the global variable token contain the information of the entire time series.

[0067] Furthermore, in an embodiment of the present application, the carbon emission reduction time series is embedded in blocks to obtain multiple time tokens, including: dividing the carbon emission reduction time series into multiple non-overlapping areas, and then projecting each non-overlapping area into a time token.

[0068] That is to say, since the temporal causal relationship is crucial to the prediction of carbon emission reduction, the carbon emission reduction time series is segmented and expressed in fine time tokens, which can be specifically expressed as:

[0069] {s1,s2,…,s N}=Patchify(x)

[0070] K en =PatchEmbed(s1,s2,…,s N )

[0071] Among them, the time length corresponding to each time token is P, is the number of time tokens corresponding to the carbon emission reduction time series, s i is the i-th time token in the time token sequence. PatchEmbed() maps each time series of length P to D dimensions, which can be obtained through training. Therefore, the carbon emission reduction time series The time token map contains N D-dimensional time tokens.

[0072] During the self-attention analysis, the embedding vector corresponding to the carbon emission reduction time series includes multiple time-by-time tokens. and a first global variable token Among them, the first global variable token As the global token of the entire carbon emission reduction time series, it integrates the information of other time tokens, provides a comprehensive understanding of the internal time dependency of the carbon emission reduction time series, and can better interact with the carbon emission reduction policy time series. The process can be formalized as:

[0073]

[0074] in, is the output of the self-attention layer, is the time token for each time zone, is the first global variable token, l∈{0,…,N-1} represents the lth time zone, and N is the number of time tokens corresponding to the carbon emission reduction time series.

[0075] Furthermore, [·,·] represents the concatenation of the time token of the carbon emission reduction time series and the first global variable token along the sequence dimension. Self-Attn(.) represents the multi-head self-attention to the time token, and LN(·) represents layer normalization.

[0076] It should be noted that cross attention between variables is widely used in multimodal learning to extract the dependency between two different embedding vectors. In the embodiment of the present application, the cross attention layer uses the first global variable token as the query and the second global variable token as the key and value to establish a connection between the two global variable tokens. The output of the cross attention layer is then connected to the time token of other carbon emission reduction time series. The above process can be formalized as:

[0077]

[0078] in, is the input of the next self-attention layer, is the first global variable token from layer l, Y ex Is the second global variable token.

[0079] Furthermore, Cross-Attn(.) is the multi-head cross attention of the carbon emission reduction time series and the carbon emission reduction policy time series, where the query is the first global variable token from layer l. The output of the crisscross attention layer It will become the input of the next self-attention layer. In this way, the first global variable token of the carbon emission reduction time series can learn multivariate correlation and further diffuse to the time token of the carbon emission reduction time series, realizing the information transfer between the first global variable token of the carbon emission reduction policy time series and the carbon emission reduction time token.

[0080] Furthermore, the L2 loss function is selected to measure the difference between the predicted value and the true value.

[0081]

[0082] Where L is the number of time zones, x i and The actual value and the predicted carbon emission reduction results.

[0083] Step 104: planning a carbon emission reduction benefit path based on the carbon emission reduction forecast result of at least one target department.

[0084] In a feasible embodiment, for each future time step, a carbon emission reduction evaluation index corresponding to at least one target sector in the future time step is obtained, and the future time step with the highest carbon emission reduction evaluation index is used as the current carbon benefit path planning.

[0085] Optionally, the carbon emission reduction evaluation index is calculated using the following formula:

[0086] P=ΠT m

[0087] Among them, P is the carbon emission reduction evaluation index corresponding to the future time step, T m The carbon emission reduction forecast result obtained by predicting the mth target sector in the future time step.

[0088] Therefore, the method for carbon benefit path planning based on carbon emission reduction asset time series provided in the embodiment of the present application predicts the carbon emission reduction of the target department under the influence of carbon emission reduction policy by analyzing the temporal dependency between the carbon emission reduction time series corresponding to the target department driven by natural low-carbon benefits and the carbon emission reduction policy time series. This effectively solves the current high reliance of comprehensive carbon emission management on carbon quotas and carbon trading, and through accurate and reliable prediction of carbon emission reductions, can achieve carbon emission control over larger areas and longer time spans, providing reliable data support and guarantee for the realization of zero-carbon highways.

[0089] It should be noted that although the operations of the method of the present invention are described in a particular order in the drawings, this does not require or imply that the operations must be performed in this particular order or that all illustrated operations must be performed to achieve desired results.

[0090] Figure 2 A schematic diagram of the structure of a device for performing carbon revenue path planning based on a carbon emission reduction asset time series provided in another embodiment of the present application is shown.

[0091] like Figure 2 As shown, the device 10 for planning a carbon revenue path based on a carbon emission reduction asset time series includes:

[0092] The first acquisition module 11 is used to obtain the corresponding carbon emission reduction time series of the target sector driven by natural low-carbon benefits;

[0093] The second acquisition module 12 is used to obtain the carbon emission reduction policy time series;

[0094] A prediction module 13 is used to predict the future carbon emission reduction of the target sector based on the carbon emission reduction time series and the carbon emission reduction policy time series, and obtain the carbon emission reduction prediction result of the target sector under the influence of the carbon emission reduction policy;

[0095] The planning module 14 is used to plan the carbon emission reduction benefit path based on the carbon emission reduction prediction result of at least one of the target departments.

[0096] In some embodiments, the prediction module 13 is further configured to:

[0097] Performing block embedding and first variable embedding on the carbon emission reduction time series to obtain a plurality of time tokens and a first global variable token;

[0098] Performing second variable embedding on the carbon reduction policy time series to obtain a second global variable token;

[0099] Applying self-attention analysis to the time tokens to obtain a first dependency relationship between a plurality of the time tokens;

[0100] Performing cross attention analysis on the first global variable token and the second global variable token to obtain a second dependency relationship between the first global variable token and the second global variable token;

[0101] Based on the first dependency relationship and the second dependency relationship, the future carbon emission reduction of the target department is predicted to obtain the predicted result of the carbon emission reduction of the target department under the influence of the carbon emission reduction policy.

[0102] In some embodiments, the carbon emission reduction time series is divided into a plurality of non-overlapping regions;

[0103] Each of the non-overlapping regions is projected as one of the time tokens.

[0104] In some embodiments, the following formula is used for self-attention analysis:

[0105]

[0106] in, is the output of the self-attention layer, is the time token for each time zone, is the first global variable token, l∈{0,…,N-1} represents the lth time zone, and N is the number of time tokens corresponding to the carbon emission reduction time series.

[0107] In some embodiments, the following formula is used for cross-attention analysis:

[0108]

[0109] in, is the input of the next self-attention layer, is the first global variable token, Y ex Is the second global variable token.

[0110] In some embodiments, the planning module 14 is further configured to:

[0111] For each future time step, obtaining a carbon emission reduction evaluation index corresponding to at least one of the target sectors in the future time step;

[0112] The future time step with the highest carbon emission reduction evaluation index is used as the current carbon benefit path planning.

[0113] It should be understood that the units or modules described in the device 10 for carbon benefit path planning based on carbon emission reduction asset time series are similar to those described in the reference Figure 1 The various steps in the described method correspond to each other. Therefore, the operations and features described above for the method are also applicable to the device 10 for carbon revenue path planning based on the carbon emission reduction asset time series and the modules contained therein, which will not be repeated here. The device 10 for carbon revenue path planning based on the carbon emission reduction asset time series can be pre-implemented in a browser or other security application of an electronic device, or loaded into the browser or its security application of an electronic device by downloading or the like. The corresponding units in the device 10 for carbon revenue path planning based on the carbon emission reduction asset time series can cooperate with the units in the electronic device to implement the solution of the embodiment of the present application.

[0114] For the several modules or units mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0115] Reference below Figure 3 , Figure 3 A schematic diagram of the structure of a computer system of an electronic device or server suitable for implementing an embodiment of the present application is shown.

[0116] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation instructions of the system are also stored. The CPU 301, the ROM 302 and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0117] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, a mouse, etc.; an output section 307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0118] In particular, according to an embodiment of the present application, the above reference flow chart Figure 2 The described process can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program includes a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, the above-mentioned functions defined in the system of the present application are executed.

[0119] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium such as a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0120] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operating instructions of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the aforementioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, the boxes represented by two connections can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operating instruction, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] The units or modules involved in the embodiments described in the present application may be implemented by software or by hardware. The described units or modules may also be set in a processor. For example, they may be described as: a processor includes a first acquisition module, a second acquisition module, a prediction module, and a planning module. Among them, the names of these units or modules do not constitute a limitation on the units or modules themselves under certain circumstances. For example, the first acquisition module may also be described as "obtaining the time series of carbon emission reductions corresponding to the target department driven by natural low-carbon benefits."

[0122] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device. The above computer-readable storage medium stores one or more programs, and when the above programs are used by one or more processors to execute the method for carbon revenue path planning based on carbon emission reduction asset time series described in the present application.

[0123] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for carbon revenue path planning based on carbon emission reduction asset time series, characterized in that: include: Obtain the time series of carbon emission reductions corresponding to the target sector driven by natural low-carbon benefits; Obtain carbon reduction policy time series; Based on the carbon emission reduction time series and the carbon emission reduction policy time series, predict the future carbon emission reduction of the target sector to obtain the carbon emission reduction prediction result of the target sector under the influence of the carbon emission reduction policy; Based on the carbon emission reduction forecast result of at least one of the target departments, a carbon emission reduction benefit path is planned.

2. The method for carbon benefit path planning based on carbon emission reduction asset time series according to claim 1 is characterized in that: The predicting of the future carbon emission reduction of the target sector based on the carbon emission reduction time series and the carbon emission reduction policy time series to obtain the carbon emission reduction prediction result of the target sector under the influence of the carbon emission reduction policy includes: Performing block embedding and first variable embedding on the carbon emission reduction time series to obtain a plurality of time tokens and a first global variable token; Performing second variable embedding on the carbon reduction policy time series to obtain a second global variable token; Applying self-attention analysis to the time tokens to obtain a first dependency relationship between a plurality of the time tokens; Performing cross attention analysis on the first global variable token and the second global variable token to obtain a second dependency relationship between the first global variable token and the second global variable token; Based on the first dependency relationship and the second dependency relationship, the future carbon emission reduction of the target department is predicted to obtain the predicted result of the carbon emission reduction of the target department under the influence of the carbon emission reduction policy.

3. The method for carbon benefit path planning based on carbon emission reduction asset time series according to claim 2 is characterized in that: The step of embedding the carbon emission reduction time series into blocks to obtain a plurality of time tokens includes: Dividing the carbon emission reduction time series into a plurality of non-overlapping regions; Each of the non-overlapping regions is projected as one of the time tokens.

4. The method for carbon benefit path planning based on carbon emission reduction asset time series according to claim 2 is characterized in that: The following formula is used for self-attention analysis: in, is the output of the self-attention layer, is the time token for each time zone, is the first global variable token, l∈{0,…,N-1} represents the lth time zone, and N is the number of time tokens corresponding to the carbon emission reduction time series.

5. The method for carbon benefit path planning based on carbon emission reduction asset time series according to claim 2 is characterized in that: The following formula is used for cross attention analysis: in, is the input of the next self-attention layer, is the first global variable token, Y ex Is the second global variable token.

6. According to the method for carbon revenue path planning based on carbon emission reduction asset time series according to claim 2, it is characterized in that: The planning of the carbon emission reduction benefit path based on the carbon emission reduction prediction result of at least one of the target sectors comprises: For each future time step, obtaining a carbon emission reduction evaluation index corresponding to at least one of the target sectors in the future time step; The future time step with the highest carbon emission reduction evaluation index is used as the current carbon benefit path planning.

7. A device for carbon revenue path planning based on carbon emission reduction asset time series, characterized in that: include: The first acquisition module is used to obtain the time series of carbon emission reduction corresponding to the target sector driven by natural low-carbon benefits; The second acquisition module is used to obtain the carbon reduction policy time series; A prediction module, used to predict the future carbon emission reduction of the target sector based on the carbon emission reduction time series and the carbon emission reduction policy time series, and obtain the carbon emission reduction prediction result of the target sector under the influence of the carbon emission reduction policy; A planning module is used to plan a carbon emission reduction benefit path based on the carbon emission reduction forecast result of at least one of the target departments.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the method for carbon benefit path planning based on the carbon emission reduction asset time series as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for carbon benefit path planning based on the carbon emission reduction asset time series as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for carbon benefit path planning based on a carbon emission reduction asset time series described in any one of claims 1 to 6 is implemented.

Images