A carbon emission reduction scheme recommendation evaluation method and device, equipment and storage medium

Abstract

The application discloses a carbon emission reduction scheme recommendation evaluation method and device, equipment and a storage medium, relates to the technical field of carbon emission reduction management, and the method comprises the following steps: establishing a carbon emission reduction scheme recommendation evaluation environment state according to carbon emission reduction scheme historical selection data of a plurality of enterprises and enterprise social learning information; constructing a state-action value function based on the carbon emission reduction scheme recommendation evaluation environment state and a carbon emission reduction scheme recommended to the enterprise; and calculating the best carbon emission reduction scheme recommended to the enterprise through the state-action value function. The application can more accurately grasp the preferences and demands of enterprises by comprehensively considering the carbon emission reduction scheme historical selection data of enterprises and enterprise social learning information, can adapt to multi-dimensional scheme characteristics and a dynamic market environment, fully gives play to the experience sharing advantages between enterprises, and thus more effectively recommends suitable carbon emission reduction schemes for enterprises.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of carbon emission reduction management, and more particularly to a carbon emission reduction scheme recommendation evaluation method, device, equipment and storage medium. BACKGROUND

[0002] Under the background of global climate change and environmental protection, carbon emission reduction has become the focus of attention of governments and enterprises around the world. The importance of carbon emission reduction scheme recommendation is increasingly prominent. By recommending appropriate carbon emission reduction schemes to enterprises, carbon emissions can be more effectively reduced, energy use efficiency can be improved, and the goal of "carbon peak and carbon neutrality" can be achieved. For enterprises, choosing an efficient carbon emission reduction scheme not only reduces operating costs, but also can generate more income in the carbon trading market. Therefore, providing accurate carbon emission reduction scheme recommendations is crucial to promoting the carbon emission reduction process of the whole society.

[0003] However, current carbon emission reduction scheme recommendations face many challenges. First, the needs and preferences of enterprises for carbon emission reduction schemes vary greatly, and different enterprises have different focuses on energy saving effects, implementation costs, technology maturity, etc., which makes the personalization of recommended schemes particularly complex. Second, the selection of carbon emission reduction schemes not only involves technical characteristics, but also is influenced by market dynamics, policies and regulations, and social cognition. Therefore, how to integrate multi-dimensional information and provide accurate scheme recommendations is an important problem faced by carbon emission reduction scheme recommendations. In addition, when choosing a scheme, enterprises often refer to the evaluation and experience of other enterprises, but the current system does not fully utilize this social learning process, making it difficult for the recommended results to meet actual needs.

[0004] The current carbon emission reduction scheme recommendation system still has some deficiencies in solving the above problems. Traditional recommendation algorithms often cannot adapt to complex multi-dimensional scheme characteristics and dynamic market environments, and lack flexibility when dealing with changes in enterprise preferences. In addition, existing recommendation systems often ignore information exchange and social influence between enterprises, making the recommended schemes limited in actual effect and difficult to fully utilize the advantages of experience sharing between enterprises. Therefore, the existing technology urgently needs a more intelligent and more adaptable recommendation method to improve the accuracy and applicability of the recommendations. SUMMARY

[0005] In view of at least one defect or improvement demand of the prior art, the present application provides a carbon emission reduction scheme recommendation evaluation method, device, equipment and storage medium, which is used to solve the problems that the recommendation algorithm in the prior art cannot adapt to multi-dimensional scheme characteristics and dynamic market environments, lacks flexibility when dealing with changes in enterprise preferences, and ignores information exchange and social influence between enterprises, making it difficult to fully utilize the advantages of experience sharing between enterprises.

[0006] To achieve the above objectives, according to a first aspect of the present invention, a method for recommending and evaluating carbon emission reduction schemes is provided, comprising:

[0007] Based on historical selection data of carbon reduction schemes from multiple enterprises and corporate social learning information, a carbon reduction scheme recommendation assessment of environmental status was established.

[0008] Based on the assessment of environmental status and the construction of a state-action value function for carbon emission reduction scheme recommendations to enterprises;

[0009] The optimal carbon reduction plan is recommended to enterprises by calculating the state-action value function.

[0010] In one possible implementation approach, the carbon reduction scheme recommended for assessment of the environmental status is... for:

[0011] ;

[0012] in, Indicates enterprise eigenvectors, Indicates carbon emission reduction plan , where the scheme number is a feature vector. Provided by a carbon reduction program management company. The scheme is represented in the first place. Feature parameters on each feature This represents the number of features in the scheme, i.e., the number of dimensions of the multidimensional vector. Indicates enterprise In time The social learning information for each scheme is obtained based on the social learning model.

[0013] In one possible implementation, social learning information for:

[0014] ;

[0015] in, Indicates enterprise In time Time for decision Prior trust level, This represents the enterprise's perceived probability of the current solution, calculated from the solution characteristics and the perception model.

[0016] In one possible implementation, the state-action value function The update formula is:

[0017] ;

[0018] Among them, actions represents the enterprise recommends a certain solution , represents the learning rate, represents the discount factor, represents the reward function, represents the optimal action corresponding to the state at time is the network parameter of the DQN model.

[0019] In one possible implementation, the reward function is:

[0020] ;

[0021] wherein, represents the immediate reward value.

[0022] In one possible implementation, when considering the satisfaction of the enterprise to the carbon reduction recommendation solution, the reward function is updated as:

[0023] ;

[0024] wherein, represents the satisfaction adjustment value.

[0025] In one possible implementation, the optimal carbon reduction solution is determined by training based on the update formula of the state-action value function :

[0026]

[0027] wherein, is a random number sampled from a uniform distribution between [0, 1], represents the exploration probability, represents the optional action space, containing all the carbon reduction solutions that can be recommended.

[0028] According to a second aspect of the present application, there is also provided a carbon reduction solution recommendation evaluation device, comprising:

[0029] An environment state establishing module configured to establish a carbon reduction solution recommendation evaluation environment state according to carbon reduction solution historical selection data of a plurality of enterprises and enterprise social learning information;

[0030] A function constructing module configured to construct a state-action value function based on the carbon reduction solution recommendation evaluation environment state and the carbon reduction solution recommended to the enterprise;

[0031] a recommendation calculation module configured to recommend an optimal carbon reduction scheme to the enterprise by state-action value function calculation.

[0032] According to a third aspect of the present application, there is also provided a carbon reduction scheme recommendation evaluation device comprising at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program which, when executed by the processing unit, causes the processing unit to perform the steps of any of the above-mentioned carbon reduction scheme recommendation evaluation methods.

[0033] According to a fourth aspect of the present application, there is also provided a storage medium storing a computer program executable by an access authentication device, which, when running on the access authentication device, causes the access authentication device to perform the steps of any of the above-mentioned carbon reduction scheme recommendation evaluation methods.

[0034] Overall, compared with the prior art, the above technical solutions conceived by the present application can achieve the following beneficial effects:

[0035] The carbon reduction scheme recommendation evaluation method provided by the present application can more accurately grasp the preferences and needs of enterprises by comprehensively considering the historical selection data of carbon reduction schemes of enterprises and enterprise social learning information, can adapt to multi-dimensional scheme characteristics and dynamic market environment, and takes into account the information exchange and social influence between enterprises, fully utilizes the experience sharing advantage between enterprises, and helps to improve the acceptance of recommended schemes by enterprises, thereby more effectively recommending suitable carbon reduction schemes for enterprises. The state-action value function is used to calculate the optimal carbon reduction scheme, which is a scientific decision-making method based on data and algorithms, can comprehensively consider the effects of different carbon reduction schemes under different environmental states, and helps to maximize the carbon reduction effect under limited resource conditions and improve resource utilization efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0037] Figure 1 a flowchart of an embodiment of the carbon reduction scheme recommendation evaluation method provided by the present application;

[0038] Figure 2 a structural schematic diagram of an embodiment of the carbon reduction scheme recommendation evaluation device provided by the present application;

[0039] Figure 3A structural schematic diagram of a carbon emission reduction scheme recommendation evaluation device provided by an embodiment of the present application is provided. DETAILED DESCRIPTION

[0040] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. In addition, the technical features involved in the various embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0041] The terms "first", "second", "third" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0042] The present application provides a carbon emission reduction scheme recommendation evaluation method, device, equipment and storage medium, which are described below respectively.

[0043] Please refer to Figure 1 , Figure 1 An embodiment of a carbon emission reduction scheme recommendation evaluation method provided by the present application is provided, and in one specific embodiment of the present application, a carbon emission reduction scheme recommendation evaluation method is disclosed, which comprises:

[0044] S101, establishing a carbon emission reduction scheme recommendation evaluation environment state according to carbon emission reduction scheme history selection data of a plurality of enterprises and enterprise social learning information;

[0045] S102, constructing a state-action value function based on the carbon emission reduction scheme recommendation evaluation environment state and a carbon emission reduction scheme recommended to an enterprise;

[0046] S103, calculating the best carbon emission reduction scheme recommended to the enterprise through the state-action value function.

[0047] In the above embodiments, the historical selection data is the information of the recorded multiple enterprises selecting the carbon reduction scheme type, carbon reduction target, budget, preference for scheme characteristics, etc. in the past period of time, which helps to understand the preferences, behavior habits and reduction effectiveness of enterprises. The social learning information includes energy saving efficiency, carbon reduction amount, implementation cost, etc. By integrating these data, the enterprises are segmented, and a multi-dimensional carbon reduction scheme recommendation evaluation environment state is constructed. The carbon reduction scheme recommendation evaluation environment state not only reflects the individual characteristics of enterprises, but also integrates social environment and market dynamics, providing a solid foundation for subsequent recommendation calculation.

[0048] In the state-action value function, the state is defined as the quantitative representation of the carbon reduction scheme recommendation evaluation environment state, including the individual characteristics of enterprises, historical behavior, social learning information, etc. The action refers to the carbon reduction scheme recommended to the enterprise, which can be a specific reduction measure (such as using energy-saving lamps, buying electric vehicles, etc.), or a more macroscopic reduction strategy (such as reducing energy consumption, adopting renewable energy, etc.), and the action represents recommending a certain scheme to the enterprise .

[0049] A deep Q network (DQN) is used to estimate the state-action value function. The DQN model is a multi-layer neural network, whose input is the state vector and output is the expected return (i.e. Q value) corresponding to each action. The structure of the model can be adjusted according to the complexity of the problem, usually including input layer, hidden layer and output layer.

[0050] The constructed state-action value function is used to calculate the best carbon reduction scheme recommended to the enterprise. The current carbon reduction scheme recommendation environment state of the enterprise is input into the state-action value function. The function calculates and outputs the value of each carbon reduction scheme (i.e. expected return or effect) according to the input state. These values reflect the pros and cons of executing a specific action in a given state. According to the size of the output value, the carbon reduction scheme with the largest value is selected as the recommended result, which not only meets the individual characteristics and preferences of the enterprise, but also achieves the best reduction effect in the current environment state. In the recommendation process, some additional factors such as cost, feasibility, sustainability, etc. also need to be considered.

[0051] Compared with the prior art, the carbon emission reduction scheme recommendation evaluation method provided by the embodiment can more accurately grasp the preferences and needs of enterprises by comprehensively considering the historical selection data of the carbon emission reduction scheme of the enterprise and the enterprise social learning information, can adapt to multi-dimensional scheme characteristics and dynamic market environment, and simultaneously considers information exchange and social influence between enterprises, fully utilizes the experience sharing advantage between enterprises, and helps to improve the acceptance of the recommended scheme by the enterprise, so that the suitable carbon emission reduction scheme is more effectively recommended for the enterprise. The state-action value function is used to calculate the optimal carbon emission reduction scheme, which is a scientific decision-making method based on data and algorithm, can comprehensively consider the effect of different carbon emission reduction schemes under different environmental states, and is helpful to maximize the carbon emission reduction effect under the condition of limited resources and improve the resource utilization efficiency.

[0052] In some embodiments of the application, the carbon emission reduction scheme recommendation evaluation environment state is established for:

[0053]

[0054] Among them, represents the feature vector of the enterprise , represents the feature vector of the carbon emission reduction scheme , wherein the scheme number is provided by the carbon emission reduction scheme management company, represents the feature parameter of the scheme on the th feature, represents the number of scheme features, i.e. the dimension number of the multi-dimensional vector, represents the social learning information of the enterprise based on the social learning model at time .

[0055] In the above embodiment, when constructing the deep Q network (DQN), these state information will be used as input features, processed by the neural network to estimate the expected return (i.e. Q value) of each action under different states. The action can represent the selection of different carbon emission reduction schemes, and the goal of DQN is to learn a strategy so that the action with the maximum Q value (i.e. the optimal emission reduction scheme) is selected under a given state.

[0056] In order to train DQN, a large amount of state-action-reward pairs need to be collected as training data. These data can be obtained through a simulation environment (such as a simulator based on enterprise characteristics and emission reduction scheme characteristics) or an actual running system (such as collecting data in an actual carbon emission reduction recommendation system). During the training process, DQN will continuously adjust its weights to minimize the difference between the predicted Q value and the actual Q value, so as to gradually optimize its decision-making ability. ​​

[0057] In some embodiments of the present application, the social learning information is:

[0058]

[0059] wherein, represents the prior trust of the enterprise in time on the decision , represents the perceived probability of the enterprise on the current scheme, which is calculated by the scheme characteristics and the perception model.

[0060] In the above embodiments, in the process of constructing the carbon emission reduction scheme recommendation evaluation system, the social learning information can be used as an important input feature to estimate the expected return (i.e. Q value) of each action in different states. By combining the individual characteristics of the enterprise, the characteristics of the carbon emission reduction scheme, and the social learning information, the system can more accurately recommend the emission reduction scheme that meets the needs and preferences of the enterprise.

[0061] Based on the information obtained from other enterprises, the enterprise updates its perceived probability of each scheme :

[0062]

[0063] wherein, represents the social distance weight between the enterprise and , reflecting the trust between enterprises. The smaller the distance, the higher the trust.

[0064] In some embodiments of the present application, the update formula of the state-action value function is:

[0065]

[0066] wherein, action represents recommending a certain scheme to the enterprise , represents the learning rate, represents the discount factor, represents the reward function, represents the state-action value function corresponding to the optimal action in state , is the network parameter of the DQN model.

[0067] In the above embodiments, the DQN is used to estimate the state-action value function ​​​i.e., in state selecting an action with an expected reward. Learning rate controls the update step size, discount factor controls the importance of future rewards, immediate reward obtained after performing an action in state , network parameters mainly weights and biases, are used for training and prediction of deep neural networks.

[0068] In some embodiments of the present application, the reward function is:

[0069] ;

[0070] wherein, represents the immediate reward value.

[0071] In the above embodiment, the immediate reward value g is a positive number, which is used to reward the enterprise for accepting the recommended solution, and correspondingly, if the enterprise rejects the recommended solution, a negative reward − g is given. This design encourages the system to recommend more solutions that are accepted by the enterprise.

[0072] In some embodiments of the present application, when considering the satisfaction of the enterprise to the carbon emission reduction recommended solution, the reward function is updated as:

[0073] ;

[0074] wherein, represents the satisfaction adjustment value.

[0075] In the above embodiment, in practical applications, only considering whether the enterprise accepts the recommended solution may not be sufficient to fully reflect the satisfaction of the enterprise and the performance of the system. Therefore, in the subsequent embodiment, the reward function can consider the satisfaction of the enterprise to the carbon emission reduction recommended solution for updating.

[0076] The satisfaction adjustment value y is a positive number, which is used to reward the enterprise for accepting and being satisfied with the recommended solution, if the enterprise accepts the recommended solution but is not satisfied, no reward is given (i.e., the reward is 0), and if the enterprise rejects the recommended solution, a negative reward − y is given. This design not only considers the acceptance behavior of the enterprise, but also considers the satisfaction of the enterprise to the solution, thereby more comprehensively reflecting the performance of the system.

[0077] In practical applications, the determination g andy The specific values may need to be adjusted based on the actual situation of the system and feedback from the enterprises. In addition, in order to accurately evaluate the satisfaction of the enterprises with the recommended solutions, the system may need to collect feedback data such as ratings, comments, etc. of the enterprises, which can be used to update the satisfaction model of the enterprises and further optimize the reward function and recommendation strategy.

[0078] In some embodiments of the present application, the state-action value function is trained based on the update formula to determine the optimal carbon reduction solution:

[0079]

[0080] wherein, is a random number uniformly distributed between [0, 1], represents the exploration probability, represents the optional action space, which contains all the carbon reduction solutions that can be recommended.

[0081] In the above embodiments, is used to determine whether to explore or exploit. When , the system randomly selects an action to explore new recommended solutions, which can help the system avoid local optimal solutions. When , the system selects the action with the maximum value in the current state, i.e. makes recommendations according to the optimal strategy learned so far. controls the balance between exploration and exploitation. Initially is larger, the system tends to explore more to obtain more information. During the training process, gradually reduce , so that the system shifts from exploration to exploitation, i.e. more inclined to use the optimal strategy learned.

[0082] By setting the maximum number of iterations, the state-action value function is iteratively trained, and the optimal action is calculated, and the carbon reduction solution recommended to the enterprise is .

[0083] After receiving the recommended solution, the enterprise adjusts the perception probability based on the social learning model and makes a decision based on its own preferences. The purchase probability is expressed as:

[0084] ;

[0085] wherein, represents the enterprise's perception of the recommended solution, which follows a normal distribution. indicates the perceived volatility.

[0086] The feedback data of each enterprise is recorded for further training and optimization of the model, and through multiple rounds of interaction and feedback, the DQN model is continuously updated to make the recommended strategy closer to the actual preference of the enterprise.

[0087] The network parameters of the DQN model are optimized using the gradient descent method

[0088]

[0089] wherein, is the learning rate.

[0090] In order to better implement the carbon emission reduction scheme recommendation evaluation method in the embodiment of the application, on the basis of the carbon emission reduction scheme recommendation evaluation method, please refer to Figure 2 , Figure 2 The structure diagram of an embodiment of the carbon emission reduction scheme recommendation evaluation device provided by the application is shown in the figure. The embodiment of the application provides a carbon emission reduction scheme recommendation evaluation device 200, which comprises:

[0091] An environment state establishing module 210 is configured to establish a carbon emission reduction scheme recommendation evaluation environment state according to carbon emission reduction scheme historical selection data of multiple enterprises and enterprise social learning information;

[0092] A function constructing module 220 is configured to construct a state-action value function based on the carbon emission reduction scheme recommendation evaluation environment state and the carbon emission reduction scheme recommended to the enterprise;

[0093] A recommendation calculating module 230 is configured to calculate the best carbon emission reduction scheme recommended to the enterprise through the state-action value function.

[0094] It should be noted that the device 200 provided by the above embodiment can realize the technical solutions described in the above method embodiments, and the principles of the specific implementation of the above modules or units can be referred to the corresponding content in the above method embodiments, which will not be described here.

[0095] Please refer to Figure 3 , Figure 3 The structure diagram of the carbon emission reduction scheme recommendation evaluation equipment provided by the embodiment of the application is shown in the figure. Based on the above carbon emission reduction scheme recommendation evaluation method, the application further correspondingly provides a carbon emission reduction scheme recommendation evaluation equipment. The carbon emission reduction scheme recommendation evaluation equipment can be a mobile terminal, a desktop computer, a notebook computer, a palm computer and a server, etc. The carbon emission reduction scheme recommendation evaluation equipment 300 comprises a processor 310, a memory 320 and a display 330. Figure 3 ​​Only portions of the components of the battery highly real-time measurement synchronous tracking flight welding device are shown, but it should be understood that all of the components shown are not required, and more or fewer components can be substituted.

[0096] The memory 320 can be an internal storage unit of the carbon emission reduction scheme recommendation evaluation device 300 in some embodiments, such as a hard disk or a memory of the carbon emission reduction scheme recommendation evaluation device 300. The memory 320 can also be an external storage device of the carbon emission reduction scheme recommendation evaluation device 300 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like equipped on the carbon emission reduction scheme recommendation evaluation device 300. Further, the memory 320 can include both an internal storage unit and an external storage device of the carbon emission reduction scheme recommendation evaluation device 300. The memory 320 is used to store application software installed on the carbon emission reduction scheme recommendation evaluation device 300 and various types of data, such as program codes installed on the carbon emission reduction scheme recommendation evaluation device 300. The memory 320 can also be used to temporarily store data that has been output or will be output. In an embodiment, the carbon emission reduction scheme recommendation evaluation program 340 is stored on the memory 320, and the carbon emission reduction scheme recommendation evaluation program 340 can be executed by the processor 310 to implement the carbon emission reduction scheme recommendation evaluation method of the embodiments.

[0097] The processor 310 can be a central processing unit (CPU), a microprocessor, or other data processing chip in some embodiments, and is used to run program codes or process data stored in the memory 320, such as to execute the carbon emission reduction scheme recommendation evaluation method.

[0098] The display 330 can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, and the like in some embodiments. The display 330 is used to display information of the carbon emission reduction scheme recommendation evaluation device 300 and to display a visualized user interface. The components 310-330 of the carbon emission reduction scheme recommendation evaluation device 300 communicate with each other through a system bus.

[0099] In an embodiment, the steps in the carbon emission reduction scheme recommendation evaluation method described above are implemented when the processor 310 executes the carbon emission reduction scheme recommendation evaluation program 340 in the memory 320.

[0100] The embodiment also provides a computer readable storage medium, which stores a carbon emission reduction scheme recommendation evaluation program, and the carbon emission reduction scheme recommendation evaluation program realizes the following steps when executed by a processor:

[0101] establishing a carbon emission reduction scheme recommendation evaluation environment state according to carbon emission reduction scheme historical selection data of a plurality of enterprises and enterprise social learning information;

[0102] constructing a state-action value function based on the carbon emission reduction scheme recommendation evaluation environment state and a carbon emission reduction scheme recommended to the enterprise;

[0103] calculating the optimal carbon emission reduction scheme recommended to the enterprise through the state-action value function.

[0104] In summary, the carbon emission reduction scheme recommendation evaluation method provided by the application can more accurately grasp the preferences and needs of enterprises by comprehensively considering the carbon emission reduction scheme historical selection data of enterprises and enterprise social learning information, can adapt to multi-dimensional scheme characteristics and dynamic market environment, and considers information exchange and social influence between enterprises, fully utilizes the experience sharing advantage between enterprises, and helps to improve the acceptance of enterprises to the recommended scheme, thereby more effectively recommending suitable carbon emission reduction schemes for enterprises. The state-action value function is used to calculate the optimal carbon emission reduction scheme, which is a scientific decision-making method based on data and algorithms, can comprehensively consider the effects of different carbon emission reduction schemes under different environment states, and helps to maximize the carbon emission reduction effect under limited resource conditions and improve resource utilization efficiency.

[0105] The application also provides a computer readable storage medium, which stores a computer program, and the program realizes the steps of the above method when executed by a processor. The computer readable storage medium can include but is not limited to any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, micro-drives, and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0106] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the application is not limited by the action sequence described, because according to the application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the application.

[0107] In the above embodiments, the description of each embodiment focuses on different aspects, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0108] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the described apparatus embodiments are merely schematic. Taking the division of the units as an example, the division can be changed in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0109] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0110] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of a software functional unit.

[0111] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that makes a contribution to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various program codes that can be stored in the medium.

[0112] Those skilled in the art can understand that all or part of the steps of various methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer readable memory, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0113] The above merely describes exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. Any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. Those skilled in the art will easily derive other embodiments of the present disclosure after considering the specification and practicing the disclosure herein. The present application is intended to cover any variations, uses, or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not described in the present disclosure. The specification and examples are merely considered as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

[0114] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not contradict, they should be considered within the scope of the present disclosure.

[0115] Those skilled in the art can easily understand that the above only describes preferred embodiments of the present application and is not intended to limit the present application. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for recommending and evaluating carbon emission reduction schemes, characterized in that, include: Based on historical selection data of carbon reduction schemes from multiple enterprises and corporate social learning information, a carbon reduction scheme recommendation assessment of environmental status was established. Based on the aforementioned carbon emission reduction scheme, an assessment of the environmental status is recommended, and a state-action value function is constructed for the carbon emission reduction scheme recommended to enterprises. The optimal carbon reduction plan recommended to enterprises is calculated using the state-action value function. The proposed carbon reduction scheme recommends an assessment of the environmental status. for: ； in, Indicates enterprise eigenvectors, Indicates carbon emission reduction plan , where the scheme number is a feature vector. Provided by a carbon reduction program management company. The scheme is represented in the first place. Feature parameters on each feature Indicates enterprise In time Social learning information for each scheme is obtained based on a social learning model. Among them, the social learning information for: ； in, Indicates enterprise In time Time for decision Prior trust level, This represents the enterprise's perceived probability of the current solution, calculated from the solution characteristics and the perception model; ； in, Indicates enterprise and The social distance weighting between companies reflects the level of trust between them; the smaller the distance, the higher the level of trust. Among them, based on the state-action value function The updated formula is used to train and determine the optimal carbon reduction scheme: ； in, These are random numbers sampled from a uniform distribution between [0,1]. Indicates the probability of exploration. This indicates the available action space, including all possible carbon reduction solutions; The optimal action is calculated by iteratively training the state-action value function by setting a maximum number of iterations. to enterprises Recommended carbon reduction schemes are ; After receiving the recommendation, the enterprise adjusts the perceived probability based on a social learning model. And make decisions based on personal preferences, probability of purchase Expressed as: ； in, This represents the enterprise's perception of the recommended solution, following a normal distribution. It indicates perceived volatility.

2. The carbon emission reduction scheme recommendation and evaluation method as described in claim 1, characterized in that, The state-action value function The update formula is: ； Among them, actions Indicates to enterprises Recommend a solution , Indicates the learning rate. Indicates the discount factor. Represents the reward function, Indicates the state The state-action value function corresponding to the optimal action at that time. These are the network parameters of the DQN model.

3. The carbon emission reduction scheme recommendation and evaluation method as described in claim 2, characterized in that, The reward function for: ； in, This indicates the instant reward value.

4. The carbon emission reduction scheme recommendation and evaluation method as described in claim 3, characterized in that, When considering the satisfaction of enterprises with the recommended carbon reduction plan, the reward function Updated to: ； in, This indicates the adjusted value for satisfaction.

5. A carbon emission reduction scheme recommendation and evaluation device, characterized in that, include: The environmental status establishment module is configured to establish carbon reduction scheme recommendations and assess environmental status based on historical selection data of carbon reduction schemes from multiple enterprises and corporate social learning information. The function construction module is configured to assess the environmental status based on the carbon reduction scheme recommendation and construct a state-action value function for the carbon reduction scheme recommended to enterprises; The recommendation calculation module is configured to calculate the best carbon reduction plan recommended to the enterprise through the state-action value function; The proposed carbon reduction scheme recommends an assessment of the environmental status. for: ； in, Indicates enterprise eigenvectors, Indicates carbon emission reduction plan , where the scheme number is a feature vector. Provided by a carbon reduction program management company. The scheme is represented in the first place. Feature parameters on each feature Indicates enterprise In time Social learning information for each scheme is obtained based on a social learning model. Among them, the social learning information for: ； in, Indicates enterprise In time Time for decision Prior trust level, This represents the enterprise's perceived probability of the current solution, calculated from the solution characteristics and the perception model; ； in, Indicates enterprise and The social distance weighting between companies reflects the level of trust between them; the smaller the distance, the higher the level of trust. Among them, based on the state-action value function The updated formula is used to train and determine the optimal carbon reduction scheme: ； in, These are random numbers sampled from a uniform distribution between [0,1]. Indicates the probability of exploration. This indicates the available action space, including all possible carbon reduction solutions; The optimal action is calculated by iteratively training the state-action value function by setting a maximum number of iterations. to enterprises Recommended carbon reduction schemes are ; After receiving the recommendation, the enterprise adjusts the perceived probability based on a social learning model. And make decisions based on personal preferences, probability of purchase Expressed as: ； in, This represents the enterprise's perception of the recommended solution, following a normal distribution. It indicates perceived volatility.

6. A carbon emission reduction scheme recommendation and evaluation device, characterized in that, It includes at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program that, when executed by the processing unit, causes the processing unit to perform the steps of the carbon emission reduction scheme recommendation evaluation method according to any one of claims 1 to 4.

7. A storage medium, characterized in that, It stores a computer program executable by an access authentication device, which, when run on the access authentication device, causes the access authentication device to perform the steps of the carbon reduction scheme recommendation evaluation method according to any one of claims 1 to 4.

Images