Carbon transaction question and answer method, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a carbon transaction question and answer method, electronic equipment and a storage medium. The method comprises the steps that under the condition that a carbon transaction association question associated with target energy storage is obtained, a trained question and answer model is obtained, and the question and answer model comprises a semantic analysis module and a factor determination module; inputting the carbon transaction associated question into the question and answer model, analyzing a carbon transaction associated intention of the carbon transaction associated question by using a semantic analysis module, determining an answer key factor according to the carbon transaction associated intention by using a factor determination module, and outputting according to the answer key factor; and determining a target answer, associated with the target energy storage, of the carbon transaction associated question according to a model output result output by the question and answer model. According to the technical scheme provided by the embodiment of the invention, the answer to the energy storage associated carbon transaction association problem can be efficiently and accurately determined.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of carbon emission, and particularly relate to a carbon trading question and answer method, an electronic device and a storage medium. BACKGROUND

[0002] Energy storage can replace high-emission units for peak shaving by charging at low carbon times and discharging at high carbon times, thereby generating tradable carbon emission reductions.

[0003] However, the carbon emission reduction trading (carbon trading) of energy storage involves strong professional information, analysis difficulty, policy sensitivity and cross-field relevance, thereby making it difficult to efficiently and accurately determine the answers to the carbon trading-related questions associated with energy storage, which needs to be solved urgently. SUMMARY

[0004] Embodiments of the present application provide a carbon trading question and answer method, an electronic device and a storage medium to efficiently and accurately determine the answers to the carbon trading-related questions associated with energy storage.

[0005] According to an aspect of the present application, a carbon trading question and answer method can include:

[0006] In a case where a carbon trading-related question associated with target energy storage is acquired, a trained question and answer model is acquired, wherein the question and answer model includes a semantic analysis module and a factor determination module;

[0007] The carbon trading-related question is input into the question and answer model to analyze the carbon trading-related intention of the carbon trading-related question by using the semantic analysis module, and to determine the answer key factor according to the carbon trading-related intention by using the factor determination module, so as to output according to the answer key factor;

[0008] According to the model output result output by the question and answer model, a target answer of the carbon trading-related question associated with the target energy storage is determined.

[0009] According to another aspect of the present application, an electronic device can include:

[0010] at least one processor; and

[0011] a memory in communication with the at least one processor; wherein

[0012] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to implement the carbon trading question and answer method provided by any embodiment of the present application when executed.

[0013] According to another aspect of the present application, there is provided a computer readable storage medium having stored thereon computer instructions for causing a processor to implement the carbon trading question and answer method provided by any of the embodiments of the present application when executed.

[0014] The technical solution of the embodiment of the present application, in the case of obtaining a carbon trading related question associated with a target energy storage, obtains a trained question and answer model, wherein the question and answer model comprises a semantic analysis module and a factor determination module; the carbon trading related question is input into the question and answer model to analyze the carbon trading related intention of the carbon trading related question by using the semantic analysis module, so that the question and answer model understands the intention expressed by the carbon trading related question, and determines the answer key factor according to the carbon trading related intention by using the factor determination module, so as to output according to the answer key factor; according to the model output result output by the question and answer model, the target answer of the carbon trading related question associated with the target energy storage is determined, so as to realize the determination of the answer of the carbon trading related question associated with the energy storage. The above technical solution automatically analyzes the carbon trading related intention by using the semantic analysis module in the language model, and automatically determines the answer key factor for the carbon trading related intention by using the factor determination module in the language model, without the need for inefficient manual searching and analysis of the answer of the carbon trading related question from the relevant information related to carbon trading. In addition, the influence of the accuracy of the determined answer caused by the lack of professional skills of manual work, the difficulty of manual analysis, the insensitivity of manual work to policies and the cross-domain of manual work can be avoided, so as to realize the efficient and accurate determination of the answer of the carbon trading related question associated with the energy storage.

[0015] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating any labor.

[0017] Figure 1 is a flowchart of a carbon trading question and answer method according to an embodiment of the present application;

[0018] Figure 2 is a flowchart of another carbon trading question and answer method according to an embodiment of the present application;

[0019] Figure 3 is a flowchart of another carbon trading question and answer method according to an embodiment of the present application;

[0020] Figure 4 is a structural block diagram of a carbon trading question and answer device according to an embodiment of the present application;

[0021] Figure 5 is a structural schematic diagram of an electronic device for implementing a carbon trading question and answer method according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the personnel in the technical field better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. The case of "target", "original" and the like is similar, and will not be described here. 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 does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] Before introducing the embodiments of the present application, the implementation process of the scheme currently used for carbon trading question and answer and the reason for the occurrence of the problem that it is difficult to efficiently and accurately determine the answer to the carbon trading associated problem associated with energy storage will be described exemplarily, so as to better understand the reason why the scheme proposed in the embodiments of the present application can efficiently and accurately determine the answer to the carbon trading associated problem associated with energy storage.

[0025] For example, currently, answers to carbon trading-related questions concerning energy storage are mostly determined manually. For instance, when a user raises a question about carbon trading, the user or staff need to manually search for the answer from a large amount of relevant information related to carbon trading involving energy storage, or manually analyze this large amount of information to determine the answer. However, manually searching for answers to carbon trading-related questions and manually analyzing large amounts of relevant information to determine the answer is inefficient. Furthermore, due to insufficient expertise of the user or staff, the difficulty of manually analyzing relevant information, lack of policy sensitivity, and cross-disciplinary issues, the accuracy of the answers is insufficient, making it difficult to efficiently and accurately determine the answers to the carbon trading-related questions concerning energy storage.

[0026] To address this, this invention employs a semantic parsing module within a language model to automatically parse the intent related to carbon trading, and a factor determination module within the language model to automatically determine the key factors for the answer to the intent related to carbon trading. This eliminates the need for inefficient manual searching and analysis of answers to carbon trading-related questions from relevant information, and avoids the impact on accuracy caused by insufficient human expertise, the difficulty of manual analysis, human insensitivity to policy, and human cross-disciplinary expertise. Thus, it achieves efficient and accurate determination of answers to carbon trading-related questions concerning energy storage. This will be elaborated upon in detail below.

[0027] Figure 1 This is a flowchart of a carbon trading question-and-answer method provided in an embodiment of the present invention. This embodiment is applicable to question-and-answer situations related to carbon trading. The method can be executed by the carbon trading question-and-answer device provided in this embodiment of the present invention. This device can be implemented by software and / or hardware, and can be integrated into an electronic device, which can be various user terminals or servers.

[0028] See Figure 1 The method of this invention specifically includes the following steps:

[0029] S110. When a carbon trading related question is obtained that is associated with the target energy storage, a trained question-answering model is obtained, wherein the question-answering model includes a semantic parsing module and a factor determination module.

[0030] The target energy storage can be understood as energy storage that can be charged and discharged. It can generate tradable carbon emission reductions by charging the target energy storage during low-carbon periods and discharging it during high-carbon periods. It can be charged by clean energy sources such as photovoltaic and / or wind power.

[0031] Carbon trading-related questions can be understood as questions related to carbon emission reduction (carbon credits) trading of target energy storage. These questions can be expressed in natural language. For example, they can be at least one of the following: questions related to carbon emission reduction accounting, questions related to demand interpretation of carbon trading mechanisms, questions related to demand generation and filing paths, and questions related to demand interpretation of carbon credit duration rules. It should be noted that carbon trading-related questions may include not only the questions themselves related to carbon trading of target energy storage, but also at least one of the following: other data, energy storage-related data of target energy storage, and energy storage-related information, so as to conduct more accurate carbon trading Q&A through the above data.

[0032] A question-answering model can be understood as a model used to answer questions related to carbon trading. The question-answering model can be trained specifically for the carbon trading field. The question-answering model can be a quantized large language model (LLM). The question-answering model can run locally for local inference, and it can adopt a 7-billion parameter large language model (7 B LLM) with 4-bit integer quantization (INT4), and be stored locally with Advanced Encryption Standard (AES-256), without any data transmission to the cloud, thus facilitating privacy protection.

[0033] The semantic parsing module can be understood as a module used to parse carbon trading-related issues.

[0034] The Factor Determination module can be understood as a module used to determine the key factors of the answer.

[0035] In this embodiment of the invention, a question-and-answer model can be obtained when carbon trading-related questions are obtained.

[0036] S120. Input the carbon trading association question into the question-answering model, and use the semantic parsing module to analyze the carbon trading association intent of the carbon trading association question, and use the factor determination module to determine the key factors of the answer based on the carbon trading association intent, and output the answer based on the key factors of the answer.

[0037] Among them, carbon trading related intent can be understood as the intent associated with carbon trading as represented by the carbon trading related issues; carbon trading related intent may include at least one of the following: intent to determine carbon trading revenue, intent to determine the filing path, and intent to query carbon trading rules.

[0038] Key factors in the answer can be understood as the crucial factors needed to determine the target answer; key factors in the answer can be used as prompts to determine the target answer.

[0039] In this embodiment of the invention, carbon trading-related questions can be input into a question-and-answer model. The semantic parsing module can be used to parse the carbon trading-related intent, and the factor determination module can be used to determine the key factors of the answer based on the carbon trading-related intent.

[0040] In this embodiment of the invention, a semantic parsing module can be used to parse the entities related to carbon trading, and a factor determination module can be used to determine the key factors of the answer based on the carbon trading related intent and entities.

[0041] In this embodiment of the invention, the output can be based on the key factors of the answer. For example, based on the key factors of the answer, a Chinese paragraph at the Common European Framework of Reference for Languages ​​(CEFR) B1 level can be generated and output. For instance, the key factors of the answer include "daily net carbon emission reduction of 0.052t". The target carbon trading income is 3.1 yuan. The carbon trading registration path is resident registration -> street review -> city trading -> on-chain. Please explain today's income and steps in Chinese with no more than 120 characters. You can output "It is recommended to charge before 10 am today and discharge during the evening peak. It is expected to earn 3.1 yuan in carbon credits. The registration is submitted through the community's official WeChat account. After the street review, it will be automatically uploaded to the blockchain in 3 days."

[0042] S130. Based on the model output results of the question-and-answer model, determine the target answer for the carbon trading-related question that is related to the target energy storage.

[0043] The model output can be understood as the result of the question-answering model.

[0044] The target answer can be understood as the answer to the carbon trading-related question related to the target energy storage.

[0045] In this embodiment of the invention, the target answer can be determined based on the model output.

[0046] For example, if the carbon trading-related question is "How many carbon credits can I earn today? How do I register?", and the question-answering model outputs a confidence level of 0.88, which is greater than the confidence threshold of 0.8, then based on the model output, the target answer is determined to be "Expected carbon emission reduction of 0.052t". Carbon credits yield approximately 3.1 yuan. Registration process: 1) Submit data to the community platform; 2) Street office reviews within 3 days; 3) City trading center stores evidence on the blockchain. Operational suggestion: Charge to 95% SOC during off-peak hours in the morning, then discharge to 35% SOC between 6 PM and 10 PM. The SOC mentioned above refers to the State of Charge (SOC).

[0047] It should be noted that, based on the solutions of the embodiments of the present invention, a natural language carbon trading assistance platform can be built, thereby providing users with carbon trading Q&A services through the platform.

[0048] The solution of this invention can provide users with semantic Q&A for carbon trading under scenario-based guidance through a question-and-answer model. Users do not need to be professionals in the field of carbon emissions, nor do they need to have certain professionalism, analytical ability, or policy sensitivity to determine the questions related to carbon trading. It is also easy to use. In particular, the advantages of the solution of this invention are more prominent for small and medium-sized enterprises and household users who do not have the above-mentioned capabilities.

[0049] The technical solution of this invention, upon obtaining a carbon trading-related question associated with a target energy storage, acquires a trained question-and-answer model. This model includes a semantic parsing module and a factor determination module. The carbon trading-related question is input into the question-and-answer model. The semantic parsing module analyzes the carbon trading-related intent of the question, enabling the model to understand the intent expressed by the question. The factor determination module then determines the key factors of the answer based on the carbon trading-related intent, and outputs the answer based on these key factors. Based on the model output, the target answer for the carbon trading-related question associated with the target energy storage is determined, thereby achieving the determination of the answer to the carbon trading-related question associated with energy storage. The above technical solution uses the semantic parsing module in the language model to automatically parse the carbon trading-related intent, and the factor determination module in the language model to automatically determine the key factors of the answer to the carbon trading-related intent. This eliminates the need for inefficient manual searching and analysis of answers to carbon trading-related questions from relevant information. It also avoids the impact on the accuracy of the answers caused by insufficient human expertise, high difficulty of manual analysis, lack of sensitivity to policies, and cross-disciplinary expertise. Thus, it achieves efficient and accurate determination of answers to carbon trading-related questions related to energy storage.

[0050] An optional technical solution involves determining key factors for the answer based on the carbon trading association intent, including: obtaining energy storage association information of the target energy storage when the carbon trading association intent includes the intent to determine the filing path; determining the carbon trading filing path for the target energy storage based on the energy storage association information; and using the carbon trading filing path as a key factor for the answer.

[0051] The intention to determine the filing path can be understood as the intention to determine the path for filing carbon trading for the target energy storage.

[0052] Energy storage association information can be understood as information associated with the target energy storage; energy storage association information may include at least one of the following: energy storage location information, energy storage type, and energy storage size.

[0053] In this embodiment of the invention, when the carbon trading association intent includes determining the filing path intent, energy storage association information can be obtained. This energy storage association information can be obtained through connection or communication with the target energy storage, or it can be obtained from entities obtained by entity parsing the carbon trading association issue, etc.

[0054] The carbon trading registration path can be understood as the path for registering carbon trading for target energy storage.

[0055] In this embodiment of the invention, the carbon trading registration path can be determined based on energy storage association information, and the carbon trading registration path can be used as a key factor in the answer.

[0056] The technical solution of this invention, by obtaining the energy storage association information of the target energy storage when the intention of carbon trading association includes the intention of determining the filing path, determining the carbon trading filing path for carbon trading of the target energy storage based on the energy storage association information, and using the carbon trading filing path as a key factor in the answer, can achieve the answer to the carbon trading association question when the intention of the carbon trading association question is to determine the filing path.

[0057] Based on the above scheme, another optional technical solution is to use energy storage-related information, including energy storage location information; and to determine the carbon trading registration path for the target energy storage based on the energy storage-related information, including: obtaining a knowledge graph of registration regulations corresponding to the energy storage location information; and determining the carbon trading registration path for the target energy storage based on the knowledge graph of registration regulations.

[0058] Among them, energy storage location information can be understood as information related to the location of the target energy storage; energy storage location information may include, for example, the city, street and / or coordinates in the world coordinate system where the target energy storage is located.

[0059] The filing regulations knowledge graph can be understood as a knowledge graph corresponding to the regulations for filing carbon trading for target energy storage.

[0060] In this embodiment of the invention, a knowledge graph of filing regulations can be obtained. For example, a knowledge graph of filing regulations corresponding to the city and / or street where the energy storage location information is located can be obtained.

[0061] In this embodiment of the invention, it is also possible to obtain a general knowledge graph of filing regulations directly, without needing to obtain the knowledge graph of filing regulations through energy storage location information.

[0062] In this embodiment of the invention, the carbon trading registration path can be determined based on a knowledge graph of registration regulations. For example, the shortest compliance process can be searched on the knowledge graph of registration regulations K=(V,E), and the carbon trading registration path can be determined based on the shortest compliance process.

[0063] In this embodiment of the invention, the carbon trading registration path can also be determined based on at least one of the user type and energy storage location information of the user corresponding to the target energy storage, as well as the registration regulation knowledge graph. For example, the registration regulation knowledge graph K=(V,E) includes nodes such as "user type", "street review", and "city trading center". Based on the energy storage location information, at least one of the street where the target energy storage is located and the city trading center in the area where the target energy storage is located is determined. Based on at least one of the user type, street, and city trading center, the shortest path from the source node (such as "resident user type") to the target node ("complete on-chain") in each node of the registration regulation knowledge graph is found using the Dijkstra algorithm. Its time complexity is .

[0064] The technical solution of this invention obtains a knowledge graph of filing regulations corresponding to energy storage location information, and then determines the carbon trading filing path for carbon trading filing of the target energy storage based on the knowledge graph of filing regulations, thereby determining a more accurate carbon trading filing path.

[0065] Figure 2 This is a flowchart of another carbon trading question-and-answer method provided in this embodiment of the invention. This embodiment is an optimization based on the above-described technical solutions. In this embodiment, optionally, determining key factors of the answer according to the carbon trading association intent includes: when the carbon trading association intent includes the intent to determine carbon trading revenue, obtaining the objective function for determining carbon trading revenue and energy storage association data for the target energy storage; determining the target carbon trading revenue under the condition of using target energy storage based on the energy storage association data and the objective function, and using the target carbon trading revenue as the key factor of the answer. The explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.

[0066] See Figure 2 The method in this embodiment may specifically include the following steps:

[0067] S210. When a carbon trading-related question related to the target energy storage is obtained, a pre-trained question-answering model is obtained, wherein the question-answering model includes a semantic parsing module and a factor determination module.

[0068] S220. Input the carbon trading-related questions into the question-and-answer model, and then execute steps S230-S260 through the question-and-answer model.

[0069] S230. Using the semantic parsing module, analyze the carbon trading association intent of the carbon trading association problem.

[0070] S240. Using the factor determination module, when the carbon trading association intention includes the intention to determine carbon trading revenue, obtain the objective function for determining carbon trading revenue and the energy storage association data for the target energy storage.

[0071] In this context, determining the intention to generate carbon trading revenue can be understood as the intention to determine the revenue obtained from trading tradable carbon emission reductions generated by target energy storage.

[0072] The objective function can be understood as a function used to determine carbon trading revenue. That is, the objective function can include at least carbon trading revenue parameters, and can also include correlation parameters corresponding to energy storage data, so that the energy storage correlation data can be substituted into the objective function.

[0073] Energy storage associated data can be understood as data associated with the target energy storage; energy storage associated data may include at least one of the following: energy storage round-trip efficiency, energy storage rated charging power, energy storage rated discharging power, energy storage maximum charging power, and energy storage maximum discharging power.

[0074] In this embodiment of the invention, a factor determination module can be used to obtain the objective function and energy storage related data when the carbon trading association intention includes determining the carbon trading revenue intention.

[0075] S250. Using the factor determination module, based on energy storage correlation data and objective function, determine the target carbon trading revenue under the condition of using target energy storage, and use the target carbon trading revenue as the key factor of the answer.

[0076] Among them, the target carbon revenue data can be understood as the revenue obtained by trading the tradable carbon emission reductions generated by the target energy storage when the target energy storage is used.

[0077] In this embodiment of the invention, the target carbon trading revenue can be determined based on energy storage correlation data and objective function, and the target carbon trading revenue can be used as a key factor in the answer.

[0078] In this embodiment of the invention, other data, including at least one of carbon price, time-of-use electricity price data, marginal emission factor (MEF) in time series form, and time period length, can also be obtained. The factor determination module is used to determine the target carbon trading revenue under the condition of using target energy storage based on the other data, energy storage related data, and objective function.

[0079] It is important to note that the aforementioned energy storage-related data and / or other data can be obtained based on energy storage location information, can be directly obtained from preset data, can be obtained through connection or communication with the target energy storage, or can be obtained from entities obtained by entity parsing of carbon trading-related issues. For example, entities in the carbon trading-related issues can be parsed, and energy storage-related data and / or other data can be determined based on the parsed entities. If the entities corresponding to the energy storage-related data and / or other data cannot be parsed from the carbon trading-related issues, preset energy storage-related data and / or other data can be obtained. This allows the use of the parsed related data and / or other data when the carbon trading-related issues include related data and / or other data, and the direct acquisition of preset related data and / or other data when the related data and / or other data cannot be parsed from the carbon trading-related issues.

[0080] S260. Output based on the key factors of the answer.

[0081] S270. Based on the model output results of the question-and-answer model, determine the target answer for the carbon trading-related question that is related to the target energy storage.

[0082] The technical solution of this invention, when the intent of carbon trading is to determine the intention of carbon trading revenue, involves acquiring an objective function for determining carbon trading revenue and energy storage-related data for the target energy storage; based on the energy storage-related data and the objective function, determining the target carbon trading revenue when using the target energy storage, and using the target carbon trading revenue as a key factor in the answer. This technical solution enables the answering of carbon trading-related questions when the intent is to determine carbon trading revenue.

[0083] Figure 3This is a flowchart of another carbon trading question-and-answer method provided in this embodiment of the invention. This embodiment is based on and optimized from the above-mentioned technical solutions. In this embodiment, optionally, the objective function includes at least a carbon trading revenue parameter, an energy storage power parameter, and a correlation parameter corresponding to the energy storage-related data; determining the target carbon trading revenue under the condition of using target energy storage based on the energy storage-related data and the objective function includes: substituting the energy storage-related data into the correlation parameter, and obtaining the optimal solution of the energy storage power parameter with the goal of maximizing the carbon trading revenue parameter; determining the target carbon trading revenue under the condition of using target energy storage based on the first parameter value of the carbon trading revenue parameter under the optimal solution. The explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.

[0084] See Figure 3 The method in this embodiment may specifically include the following steps:

[0085] S310. When a carbon trading related question is obtained that is associated with the target energy storage, a trained question-answering model is obtained, wherein the question-answering model includes a semantic parsing module and a factor determination module.

[0086] S320. Input the carbon trading-related questions into the question-and-answer model, and then execute steps S330-S380 through the question-and-answer model.

[0087] S330. Using the semantic parsing module, analyze the carbon trading association intent of the carbon trading association problem.

[0088] S340. Using the factor determination module, when the carbon trading association intention includes the intention to determine carbon trading revenue, obtain the objective function for determining carbon trading revenue and the energy storage association data for the target energy storage. The objective function includes at least carbon trading revenue parameters, energy storage power parameters, and association parameters corresponding to the energy storage association data.

[0089] Among them, the carbon trading revenue parameter can be understood as the parameter corresponding to the revenue obtained by trading the tradable carbon emission reductions generated by the target energy storage.

[0090] Energy storage power parameters can be understood as parameters that characterize the power of the target energy storage.

[0091] The associated parameters can be understood as parameters corresponding to the energy storage associated data, that is, the energy storage associated data can be substituted into the associated parameters.

[0092] S350: Using the factor determination module, the energy storage correlation data is substituted into the correlation parameters, and the optimal solution of the energy storage power parameters is obtained with the goal of maximizing the carbon trading revenue parameters.

[0093] The optimal solution can be understood as the solution that maximizes the value of the carbon trading revenue parameter after substituting the energy storage power parameters. It should be noted that the optimal solution may not be a numerical solution; it may be the power curve of the target energy storage (which may include the charging power curve of the target energy storage at different times of the day and the discharging power curve of the target energy storage at different times of the day).

[0094] In this embodiment of the invention, the factor determination module can be used to substitute the energy storage related data into the related parameters, and the optimal solution can be obtained with the goal of maximizing the carbon trading revenue parameters.

[0095] In this embodiment of the invention, when the energy storage correlation data includes not only data such as energy storage power that can be substituted into the correlation parameters, but also at least one of the following constraint data: rated energy storage charging power, rated energy storage discharging power, maximum energy storage charging power, and maximum energy storage discharging power, the constraint conditions can be determined based on the constraint data, and then, under the constraint conditions, the optimal solution can be obtained with the goal of maximizing the carbon trading revenue parameters.

[0096] S360. Using the factor determination module, determine the target carbon trading revenue under the condition of using target energy storage based on the first parameter value of the carbon trading revenue parameter under the optimal solution.

[0097] The first parameter value can be understood as the parameter value of the carbon trading revenue parameter under the optimal solution.

[0098] In this embodiment of the invention, a factor determination module can be used to determine the target carbon trading revenue based on a first parameter value. For example, the first parameter value can be used as the target carbon trading revenue.

[0099] S370: Take the target carbon trading revenue as a key factor in the answer.

[0100] S380. Output based on the key factors of the answer.

[0101] S390. Based on the model output results of the question-and-answer model, determine the target answer for the carbon trading-related question that is related to the target energy storage.

[0102] The technical solution of this invention includes at least a carbon trading revenue parameter, an energy storage power parameter, and a correlation parameter corresponding to energy storage-related data in the objective function. The energy storage-related data is substituted into the correlation parameters, and the optimal solution for the energy storage power parameter is obtained by maximizing the carbon trading revenue parameter. Based on the first parameter value of the carbon trading revenue parameter under the optimal solution, the target carbon trading revenue under the condition of using the target energy storage is determined. The above technical solution can obtain the maximum achievable target carbon trading revenue.

[0103] An optional technical solution uses the target carbon trading revenue as a key factor in the answer, including: using the target carbon trading revenue and the optimal solution as key factors in the answer; outputting based on the key factors in the answer, including: determining the carbon trading revenue answer based on the target carbon trading revenue, and determining operational recommendations for operating the target energy storage based on the optimal solution; and outputting the carbon trading revenue answer and operational recommendations.

[0104] In this embodiment of the invention, the target carbon trading revenue and the optimal solution can be used as key factors in the answer.

[0105] The answer to carbon trading revenue can be understood as the revenue obtained from trading the tradable carbon emission reductions generated by the target energy storage.

[0106] Operational suggestions can be understood as recommendations on the actions required to realize the benefits of carbon trading.

[0107] It is understood that the target carbon trading revenue is the maximum revenue obtained from trading the tradable carbon emission reductions generated by the target energy storage. Therefore, if arbitrary operations are performed on the target energy storage, the actual revenue may not reach the target carbon trading revenue. Thus, in this embodiment of the invention, the carbon trading revenue answer can be determined based on the target carbon trading revenue, and operation suggestions can be made based on the optimal solution to prompt the user to perform the operations required to achieve the target carbon trading revenue.

[0108] The technical solution of this invention uses the target carbon trading revenue and the optimal solution as key factors in the answer. Based on the target carbon trading revenue, it determines the carbon trading revenue answer, and based on the optimal solution, it determines the operational suggestions for operating the target energy storage. Then, it outputs the carbon trading revenue answer and the operational suggestions, which can help users understand the operations required to achieve the target carbon trading revenue, thereby helping to realize the target carbon trading revenue corresponding to the carbon trading revenue answer.

[0109] Another optional technical solution includes an objective function comprising a first function for determining time-period carbon emission reduction, a second function for determining daily carbon emission reduction, and a third function for determining carbon trading revenue. The first function includes energy storage power parameters and time-period emission reduction parameters; the second function includes time-period emission reduction parameters and daily carbon emission reduction parameters; and the third function includes daily carbon emission reduction parameters and carbon trading revenue parameters. Based on the first parameter value of the carbon trading revenue parameter in the optimal solution, the target carbon trading revenue under the use of target energy storage is determined, including: determining a range fluctuation value based on the second parameter value of the time-period emission reduction parameter in the optimal solution; and determining the carbon trading revenue range under the use of target energy storage based on the first parameter value and the range fluctuation value of the carbon trading revenue parameter in the optimal solution, and using the carbon trading revenue range as the target carbon trading revenue under the use of target energy storage.

[0110] The first function can be understood as a function used to determine carbon emission reduction for a given period.

[0111] The second function can be understood as a function used to determine daily carbon emission reductions.

[0112] The third function can be understood as a function used to determine the revenue from carbon trading.

[0113] The time-period emission reduction parameter can be understood as a parameter that characterizes the amount of tradable carbon emission reduction that the target energy storage can generate in the corresponding time period.

[0114] The daily carbon emission reduction parameter can be understood as a parameter that characterizes the amount of tradable carbon emission reduction that the target energy storage can generate each day.

[0115] It is understandable that the first function includes energy storage power parameters and time-period emission reduction parameters, the second function includes time-period emission reduction parameters and daily carbon emission reduction parameters, and the third function includes daily carbon emission reduction parameters and carbon trading revenue parameters. Therefore, time-period carbon emission reduction can be calculated using the first function, daily carbon emission reduction can be calculated using the second function based on the calculated time-period carbon emission reduction, and carbon trading revenue can be calculated using the third function based on the calculated daily carbon emission reduction. In other words, carbon trading revenue can be calculated progressively using energy storage power and energy storage-related data through the first, second, and third functions. Therefore, the objective function can include the first, second, and third functions.

[0116] For example, the first function could be a time-period carbon reduction function. , This refers to the carbon emission reduction parameter for a specific time period (specifically, it can refer to the carbon emission reduction for the time period corresponding to time t, which can be, for example, a time period with time t as the starting point, midpoint, or end point). It is the marginal emission factor parameter (which can be substituted with the unit t). / MWh boundary emission factor). This is the length parameter for each time period (which can be replaced with a time period length of 0.25 hours). The energy storage power parameters include the energy storage charging power parameters (which can specifically refer to the energy storage charging power at time t, in MW). The energy storage power parameters include the energy storage discharge power parameters (specifically, the energy storage discharge power at time t, expressed in MW), and η is the energy storage round-trip efficiency parameter (specifically, the round-trip efficiency of the target energy storage, which can be substituted into 0-1). It's important to note that t mentioned above is a time index, which can correspond to one t every 15 minutes (0.25 hours) per day. This means that the carbon emission reduction value calculated by the first function for a given period is not limited to a single value, but can have up to 96 values, to facilitate the calculation of daily net carbon emission reduction using the second function. The second function could be, for example, a daily net carbon emission reduction function. , This refers to the daily carbon emission reduction parameter (which can be specifically represented by the unit t). (The target energy storage's daily net carbon emission reduction); it should be noted that when the daily net carbon emission reduction under the optimal solution is greater than 0, carbon revenue can be claimed for the target energy storage in terms of carbon reduction. Alternatively, the carbon gain from reducing the carbon dimension can be used as the target carbon trading gain. The third function could be, for example, a carbon trading gain function. , The carbon price parameter (which can be substituted into units of yuan) (The carbon price on a certain day). This refers to the carbon trading revenue parameter (specifically, it can refer to the carbon trading revenue in yuan on a certain day corresponding to the carbon price mentioned above).

[0117] The second parameter value can be understood as the parameter value of the time-period emission reduction parameter under the optimal solution; the second parameter value can include the time-period carbon emission reduction corresponding to each time period of the day.

[0118] The range of fluctuation values ​​can be understood as the numerical values ​​that the first parameter value can fluctuate up or down, and it can be used to determine the range of carbon trading profits.

[0119] In this embodiment of the invention, the range of floating values ​​can be determined based on the second parameter value. For example, the second parameter value can be substituted into the formula. During the period Calculate the range fluctuation value It should be noted that the second parameter value substituted here can be the second parameter value corresponding to each time period of the day.

[0120] The carbon trading revenue range can be understood as the range of revenue obtained by trading the tradable carbon emission reductions generated by the target energy storage when using target energy storage.

[0121] In this embodiment of the invention, the carbon trading revenue range can be determined based on a first parameter value and a range fluctuation value. For example, the carbon trading revenue range can be determined based on the first parameter value. and range fluctuation value Determine the range of carbon trading revenue. The carbon trading profit range can be a range with 95% confidence.

[0122] In this embodiment of the invention, the carbon trading revenue range can be used as the target carbon trading revenue.

[0123] The technical solution of this invention includes a first function for determining carbon emission reduction over a time period, a second function for determining daily carbon emission reduction, and a third function for determining carbon trading revenue. The first function includes energy storage power parameters and time period emission reduction parameters; the second function includes time period emission reduction parameters and daily carbon emission reduction parameters; and the third function includes daily carbon emission reduction parameters and carbon trading revenue parameters. Based on the second parameter value of the time period emission reduction parameters under the optimal solution, a range of fluctuation values ​​is determined. Then, based on the first parameter value of the carbon trading revenue parameters under the optimal solution and the range of fluctuation values, a carbon trading revenue range under the condition of using target energy storage is determined. This carbon trading revenue range is then used as the target carbon trading revenue under the condition of using target energy storage, thus obtaining the target carbon trading revenue expressed in range form.

[0124] Another optional technical solution, after obtaining the optimal solution for energy storage power parameters with the goal of maximizing carbon trading revenue parameters, the carbon trading question-answering method further includes: assessing the confidence level of key factors of the answer based on the optimal solution and outputting the confidence level; determining the target answer for the carbon trading-related question and its association with the target energy storage based on the model output results of the question-answering model, including: determining the target answer for the carbon trading-related question and its association with the target energy storage based on the model output results of the question-answering model when the confidence level is greater than a preset confidence level threshold.

[0125] Here, confidence level can be understood as the degree of confidence in the model's output results.

[0126] In this embodiment of the invention, the confidence level can be evaluated and output based on the optimal solution. For example, the confidence level can be calculated based on the optimal solution using the formula... The evaluation value is a confidence level (Conf) in the range of 0–1, and then the confidence level (Conf) is output. It is the normalized variance of each energy storage power (including energy storage charging power and energy storage discharging power) in the optimal solution. This represents the average token confidence score of the question-answering model's output.

[0127] The confidence threshold can be understood as the maximum confidence level of a pre-defined, uncertain target answer.

[0128] In this embodiment of the invention, when the confidence level is greater than a confidence threshold, the target answer is determined based on the model output. Conversely, when the confidence level is less than or equal to the confidence threshold, it indicates that the model output may be a misleading result generated by the model and is unreliable; therefore, the process of determining the target answer based on the model output is not performed.

[0129] The technical solution of this invention evaluates the confidence level of key factors of the answer based on the optimal solution and outputs the confidence level. Then, when the confidence level is greater than a preset confidence level threshold, the target answer related to the carbon trading issue and the target energy storage is determined based on the model output result of the question-and-answer model. This achieves confidence gating. In other words, by determining the target answer only when the confidence level is greater than the confidence level threshold, the determination of the illusory answer can be avoided, thereby improving the accuracy of the determined target answer.

[0130] To better understand the technical solutions of the above embodiments of the present invention, an optional example is provided here. For example, when a carbon trading-related question is obtained, a question-and-answer model is obtained. This model includes a semantic parsing module, a data access module, a factor determination module, an answer generator, and a confidence calculation module. The factor determination module includes a carbon emission reduction calculation submodule, a trading revenue determination submodule, and a registration path determination submodule. The carbon trading-related question is input into the question-and-answer model to use the semantic parsing module to parse the carbon trading-related intent and entity. The data access module is used to access and obtain data corresponding to the carbon trading-related intent and entity (i.e., data required to obtain key factors of the answer corresponding to the flawed carbon trading-related intent, such as energy storage-related data, other data, and a knowledge graph of registration regulations, etc.). If the carbon trading-related intent includes the intent to determine carbon trading revenue, the carbon emission reduction calculation submodule is used to calculate the daily net carbon emission reduction (e.g., through a first function and a second function to maximize the daily net carbon emission reduction). The algorithm takes carbon emission reduction parameters as the target and obtains the optimal solution for energy storage power parameters to achieve daily net carbon emission reduction. Using a trading revenue determination submodule, based on the daily net carbon emission reduction, it calculates the target carbon trading revenue and carbon trading revenue range using a third function, and uses these three factors as key answer elements. When the carbon trading-related intent includes determining the filing path, the filing path determination submodule searches for the shortest compliance process on the filing regulations knowledge graph and determines the carbon trading filing path based on this shortest process, using this path as a key answer element. An answer generator is used to generate Chinese paragraphs from the obtained key answer elements, and these Chinese paragraphs are output as model results. A confidence calculation module is used to calculate the confidence level, and the confidence level is output. If the confidence level is greater than the confidence threshold, the target answer is determined based on the model output.

[0131] Based on 200 users, a 90-day carbon trading Q&A experiment was conducted using the above-mentioned technical solution and a manual solution. The experimental results are shown in Table 1 below.

[0132] Table 1 Experimental Results

[0133] Indicator The technical solution Artificial solution Accuracy of term explanation 96.8% — Revenue determination error (%) 4.2 12.5 Average response time 1.5 s 45 s User satisfaction 4.6 / 5 3.1 / 5

[0134] The aforementioned technical solution provides a carbon trading question-answering scheme that integrates local reasoning, formulaic calculation, and semantic interaction. Experimental results show that during the carbon trading question-answering process, the terminology interpretation accuracy of this technical solution is greater than or equal to 95%. For carbon trading correlation questions where the intent is to determine carbon trading returns, the 24-hour relative error of the determined target carbon trading returns is less than or equal to 5%. The end-to-end latency of a single round of question-answering interaction is less than or equal to 2 seconds (using a 10-watt Edge Graphics Processing Unit (Edge GPU 10W) ​​for computation). Large language model processing time Total time Furthermore, by using a local question-and-answer model for carbon trading, it is possible to conduct carbon trading Q&A without uploading the original data related to the target energy storage, thus achieving not only readable and accurate carbon trading Q&A but also meeting privacy compliance requirements.

[0135] Figure 4 This is a structural block diagram of a carbon trading question-and-answer device provided in an embodiment of the present invention. This device is used to execute the carbon trading question-and-answer method provided in any of the above embodiments. This device and the carbon trading question-and-answer methods of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the carbon trading question-and-answer device can be found in the embodiments of the carbon trading question-and-answer methods described above. See also... Figure 4 The device may specifically include: a question-and-answer model acquisition module 410, an answer key factor output module 420, and a target answer determination module 430.

[0136] The question-answering model acquisition module 410 is used to acquire a trained question-answering model when a carbon trading-related question related to the target energy storage is obtained. The question-answering model includes a semantic parsing module and a factor determination module.

[0137] The answer key factor output module 420 is used to input carbon trading related questions into the question answering model. The semantic parsing module is used to parse the carbon trading related intent of the carbon trading related questions, and the factor determination module is used to determine the answer key factors based on the carbon trading related intent, so as to output the answer key factors.

[0138] The target answer determination module 430 is used to determine the target answer related to the target energy storage for the carbon trading related questions based on the model output results output by the question-and-answer model.

[0139] The answer key factor output module 420 may include:

[0140] The energy storage association data acquisition submodule is used to acquire the objective function for determining carbon trading revenue and the target energy storage when the carbon trading association intention includes the intention to determine carbon trading revenue.

[0141] The first answer key factor is a sub-module used to determine the target carbon trading revenue under the condition of using target energy storage based on energy storage related data and objective function, and the target carbon trading revenue is used as the answer key factor.

[0142] Optionally, based on the above-mentioned device, the objective function includes at least carbon trading revenue parameters, energy storage power parameters, and related parameters corresponding to energy storage-related data;

[0143] The key factors for the first answer, as a sub-module, can include:

[0144] The optimal solution is obtained by substituting the energy storage correlation data into the correlation parameters and aiming to maximize the carbon trading revenue parameters to obtain the optimal solution of the energy storage power parameters.

[0145] The target carbon trading revenue determination unit is used to determine the target carbon trading revenue under the condition of using target energy storage, based on the first parameter value of the carbon trading revenue parameter under the optimal solution.

[0146] Optionally, based on the above-described apparatus, the key factor of the first answer, as a sub-module, may include:

[0147] The key factors of the answer are used as units to take the target carbon trading revenue and the optimal solution as the key factors of the answer;

[0148] The answer key factor output module 420 may include:

[0149] The Operation Recommendation Determination Submodule is used to determine the carbon trading revenue answer based on the target carbon trading revenue, and to determine the operation recommendations for the target energy storage based on the optimal solution;

[0150] The operation suggestion output submodule is used to output the answer to the carbon trading profit and operation suggestions.

[0151] Optionally, based on the above-mentioned device, the objective function includes a first function for determining carbon emission reduction over a period of time, a second function for determining carbon emission reduction over a day, and a third function for determining carbon trading revenue. The first function includes energy storage power parameters and period emission reduction parameters, the second function includes period emission reduction parameters and daily carbon emission reduction parameters, and the third function includes daily carbon emission reduction parameters and carbon trading revenue parameters.

[0152] The target carbon trading revenue determination unit may include:

[0153] The interval floating value determination sub-unit is used to determine the interval floating value based on the second parameter value of the emission reduction parameter for the time period under the optimal solution;

[0154] The target carbon trading revenue is used as a sub-unit to determine the carbon trading revenue range under the condition of using target energy storage, based on the first parameter value and the range fluctuation value of the carbon trading revenue parameter under the optimal solution, and the carbon trading revenue range is used as the target carbon trading revenue under the condition of using target energy storage.

[0155] Optionally, based on the above-described apparatus, the apparatus may further include:

[0156] The confidence output module is used to evaluate the confidence of key factors in the answer after obtaining the optimal solution for energy storage power parameters with the goal of maximizing carbon trading revenue parameters, and output the confidence score.

[0157] Target answer determination module 430 may include:

[0158] The target answer determination submodule is used to determine the target answer related to the carbon trading-related question and the target energy storage based on the model output results of the question-and-answer model, when the confidence level is greater than the preset confidence level threshold.

[0159] Optionally, the answer key factor output module 420 may include:

[0160] The energy storage association information acquisition submodule is used to acquire the energy storage association information of the target energy storage when the carbon trading association intent includes the intent to determine the filing path.

[0161] The second answer key factor is a sub-module used to determine the carbon trading registration path for the target energy storage based on energy storage-related information, and the carbon trading registration path is used as the answer key factor.

[0162] Optionally, based on the above-mentioned device, the energy storage association information includes energy storage location information;

[0163] The key factors for the second answer, as a sub-module, can include:

[0164] The filing regulations knowledge graph acquisition unit is used to acquire the filing regulations knowledge graph corresponding to the energy storage location information.

[0165] The carbon trading registration path determination unit is used to determine the carbon trading registration path for the target energy storage based on the registration regulation knowledge graph.

[0166] The carbon trading question-and-answer device provided in this embodiment of the invention acquires a pre-trained question-and-answer model when a carbon trading-related question associated with a target energy storage is obtained through a question-and-answer model acquisition module. The question-and-answer model includes a semantic parsing module and a factor determination module. The carbon trading-related question is input into the question-and-answer model through an answer key factor output module. The semantic parsing module analyzes the carbon trading-related intent of the question, enabling the question-and-answer model to understand the intent expressed by the question. The factor determination module determines the answer key factors based on the carbon trading-related intent and outputs the answer key factors accordingly. Finally, the target answer determination module determines the target answer for the carbon trading-related question associated with the target energy storage based on the model output results of the question-and-answer model, thereby determining the answer to the carbon trading-related question associated with energy storage. The aforementioned device automatically parses the carbon trading-related intent using the semantic parsing module in the language model, and automatically determines the key factors for the answer to the carbon trading-related intent using the factor determination module in the language model. This eliminates the need for inefficient manual searching and analysis of answers to carbon trading-related questions from relevant information. It also avoids the impact on the accuracy of the answers caused by insufficient human expertise, high difficulty of manual analysis, lack of policy sensitivity, and cross-disciplinary expertise, thus achieving efficient and accurate determination of answers to carbon trading-related questions related to energy storage.

[0167] The carbon trading Q&A device provided in this embodiment of the invention can execute the carbon trading Q&A method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0168] It is worth noting that in the embodiments of the carbon trading Q&A device described above, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0169] Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0170] likeFigure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0171] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0172] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as carbon trading question-and-answer methods.

[0173] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0174] In some embodiments, the carbon trading question-and-answer method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the carbon trading question-and-answer method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the carbon trading question-and-answer method by any other suitable means (e.g., by means of firmware).

[0175] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0176] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0177] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0178] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0179] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0180] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0181] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0182] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A carbon trading Q&A method, characterized by, The method comprises the following steps: In the case of obtaining a carbon trading related question associated with a target energy storage, a trained question and answer model is obtained, wherein the question and answer model comprises a semantic analysis module and a factor determination module; The carbon trading related question is input into the question and answer model to analyze the carbon trading related intention of the carbon trading related question by using the semantic analysis module, and to determine the answer key factor according to the carbon trading related intention by using the factor determination module, so as to output according to the answer key factor; According to the model output result output by the question and answer model, the target answer of the carbon trading related question associated with the target energy storage is determined.

2. The method of claim 1, wherein, The determination of the answer key factor according to the carbon trading related intention comprises: In the case that the carbon trading related intention includes the intention of determining the carbon trading revenue, a target function for determining the carbon trading revenue and energy storage related data of the target energy storage are obtained; According to the energy storage related data and the target function, the target carbon trading revenue in the case of using the target energy storage is determined, and the target carbon trading revenue is taken as the answer key factor.

3. The method of claim 2, wherein, The target function at least includes a carbon trading revenue parameter, a storage power parameter and an associated parameter corresponding to the energy storage related data; The determination of the target carbon trading revenue in the case of using the target energy storage according to the energy storage related data and the target function comprises: Substitute the energy storage related data into the associated parameter, and obtain the optimal solution of the storage power parameter by maximizing the carbon trading revenue parameter; According to the first parameter value of the carbon trading revenue parameter under the optimal solution, the target carbon trading revenue in the case of using the target energy storage is determined.

4. The method of claim 3, wherein, The target carbon trading revenue is taken as the answer key factor. The output according to the answer key factor comprises: According to the target carbon trading revenue, the carbon trading revenue answer is determined, and according to the optimal solution, the operation suggestion of operating the target energy storage is determined; The carbon trading revenue answer and the operation suggestion are output. The target function includes a first function for determining the period carbon emission reduction, a second function for determining the daily carbon emission reduction and a third function for determining the carbon trading revenue, the first function includes the storage power parameter and the period emission reduction parameter, the second function includes the period emission reduction parameter and the daily carbon emission reduction parameter, and the third function includes the daily carbon emission reduction parameter and the carbon trading revenue parameter; 5. The method of claim 3, wherein, The determination of the target carbon trading revenue in the case of using the target energy storage according to the energy storage related data and the target function comprises: According to the second parameter value of the period emission reduction parameter under the optimal solution, the interval floating value is determined; ​ determining a carbon trading revenue interval in the case of adopting the target energy storage according to the first parameter value of the carbon trading revenue parameter under the optimal solution and the interval floating value, and taking the carbon trading revenue interval as a target carbon trading revenue in the case of adopting the target energy storage.

6. The method of claim 3, wherein, After obtaining the optimal solution of the energy storage power parameter by taking maximizing the carbon trading revenue parameter as a target, the method further comprises: evaluating a confidence degree of the answer key factor according to the optimal solution, and outputting the confidence degree; determining a target answer of the carbon trading related question associated with the target energy storage according to the model output result output by the question and answer model, comprises: in the case that the confidence degree is greater than a preset confidence degree threshold, determining a target answer of the carbon trading related question associated with the target energy storage according to the model output result output by the question and answer model.

7. The method of claim 1, wherein, determining the answer key factor according to the carbon trading related intention, comprises: in the case that the carbon trading related intention comprises a determination of a record path intention, obtaining energy storage related information of the target energy storage; determining a carbon trading record path for recording the carbon trading of the target energy storage according to the energy storage related information, and taking the carbon trading record path as an answer key factor.

8. The method of claim 7, wherein, the energy storage related information comprises energy storage location information; determining the carbon trading record path for recording the carbon trading of the target energy storage according to the energy storage related information, comprises: obtaining a record regulation knowledge graph corresponding to the energy storage location information; determining the carbon trading record path for recording the carbon trading of the target energy storage according to the record regulation knowledge graph.

9. An electronic device, comprising: comprises: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to make the at least one processor execute the carbon trading question and answer method in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for making the processor execute when the carbon trading question and answer method in any one of claims 1-8 is implemented.

Images