Enterprise carbon portrait generation method and system based on multi-source data fusion, and medium

Abstract

The invention discloses an enterprise carbon portrait generation method and system based on multi-source data fusion and a medium, mainly relates to the technical field of multi-source data fusion, and is used for solving the problems that an existing scheme lacks a standardized interface between internal and external data sources in the data level, and a traditional method depends on a statistical model in the technology level, so that the generation efficiency is low. And a complex non-linear relationship between carbon emission and multiple factors is difficult to capture due to linear assumption. Comprising the following steps: preprocessing correspondingly uploaded data through an edge computing gateway, and obtaining structured carbon portrait feature data from initial enterprise carbon data; obtaining a preset compatible access protocol and configuring a preset standardized interface, and obtaining carbon portrait feature data transmitted by the edge computing gateway; based on the weight, the specific numerical value of each carbon portrait feature data in the feature vector is updated; and obtaining carbon portrait feature data in real time, and further obtaining current carbon emission data by using the trained carbon portrait generation model.

Description

Technical Field

[0001] The present application relates to the technical field of multi-source data fusion, and in particular to a method, system and medium for generating an enterprise carbon portrait based on multi-source data fusion. Background Art

[0002] Currently, mainstream approaches to corporate carbon emissions assessment rely heavily on single-source modeling and analysis. For example, real-time data from energy consumption devices like electricity and gas meters is collected to construct linear regression models to estimate carbon emissions. While these approaches were initially favored due to their readily available data and simple computational complexity, their limitations are becoming increasingly apparent in real-world scenarios. First, the single data source makes assessment results highly dependent on the completeness of energy bills or production reports, neglecting indirect carbon emissions upstream and downstream of the supply chain (such as raw material transportation and waste disposal). Second, existing technologies often use static models that are unable to dynamically respond to operational changes. For example, when companies introduce energy-saving equipment or adjust production plans, traditional models require manual parameter recalibration, preventing real-time updates to carbon emissions forecasts and leading to delayed decision-making. Furthermore, existing research generally lacks the integration of external environmental data, such as regional carbon quota policies and the impact of extreme weather on energy consumption. This makes assessment results difficult to adapt to policy changes or unexpected events.

[0003] These limitations are due to several factors. First, at the data level, the lack of standardized interfaces between internal enterprise systems (such as ERP and MES) and external data sources makes it difficult to efficiently integrate heterogeneous data from multiple sources. Second, at the technical level, traditional methods rely heavily on statistical models (such as multivariate linear regression and time series analysis), whose linear assumptions make it difficult to capture the complex, nonlinear relationships between carbon emissions and multiple factors. Summary of the Invention

[0004] This application provides a method, system and medium for generating enterprise carbon portraits based on multi-source data fusion to solve the problem that existing solutions lack standardized interfaces between internal and external data sources at the data level. At the technical level, traditional methods mostly rely on statistical models, and their linear assumptions make it difficult to capture the complex nonlinear relationship between carbon emissions and multiple factors.

[0005] In a first aspect, the present application provides a method for generating an enterprise carbon profile based on multi-source data fusion, the method comprising: Using a pre-set collection platform, collect initial corporate carbon data; the types of initial corporate carbon data include: energy consumption data, production process data, supply chain data, unstructured data such as carbon policy texts, and energy market data; Based on the preset association between the preset collection platform and the edge computing gateway, the collected enterprise carbon data is transmitted to the corresponding edge computing gateway, and the edge computing gateway pre-processes the uploaded data and obtains structured carbon profile feature data from the initial enterprise carbon data; Obtain a preset compatible access protocol and configure a preset standardized interface, and then obtain the carbon profile feature data transmitted by the edge computing gateway through the preset standardized interface based on the preset compatible access protocol; Based on the type and collection time of the carbon portrait feature data, the carbon portrait feature data is combined into a feature vector in a preset type order; the weight of each type of carbon portrait feature data is obtained through a preset learnable weight matrix, and then the specific value of each carbon portrait feature data in the feature vector is updated based on the weight; The updated feature vector and the carbon emission data collected at the same time are input as training data into a preset carbon profile generation model to obtain a trained carbon profile generation model; the carbon profile feature data is obtained in real time, and then the current carbon emission data is obtained using the trained carbon profile generation model; Based on the carbon portrait characteristic data and carbon emission data, a carbon portrait with a preset display method is generated and displayed on the preset display interface.

[0006] In one implementation of this application, initial enterprise carbon data is collected using a preset collection platform, specifically including: Utilize pre-set energy consumption monitoring and metering equipment to collect energy usage in each production link of the enterprise in real time, obtain energy consumption data, and present the energy consumption data in a time series numerical format; wherein, the pre-set energy consumption monitoring and metering equipment includes at least: smart electricity meters, gas meters and fuel sensors; Extracting production process data from the manufacturing execution system; wherein the production process data includes at least: equipment operating parameters, raw material input, and waste output; Obtain supply chain data through the logistics management system; the supply chain data includes at least: transportation routes, vehicle types, and supplier carbon emission coefficients; Extract unstructured carbon policy text data related to corporate carbon profiling through a pre-set policy disclosure platform; Energy market data is collected through the electricity trading platform; the energy market data includes at least: real-time electricity prices and carbon emission intensity index.

[0007] In one implementation of the present application, before transmitting the collected enterprise carbon data to the corresponding edge computing gateway based on the preset association relationship between the preset collection platform and the edge computing gateway, the method further includes: Obtain the preset association relationship between the preset collection platform and the edge computing gateway through the preset interface.

[0008] In one implementation of the present application, the edge computing gateway pre-processes the uploaded data and obtains structured carbon profile feature data from the initial enterprise carbon data, specifically including: Remove abnormal initial corporate carbon data that is not within the preset reasonable range; The sliding window mean filling method is used to fill in the deleted initial enterprise carbon data; When the abnormal initial enterprise carbon data is at the beginning of the data sequence and the forward part of the window is less than the preset window value, the mean of the beginning part is used for filling; when it is at the end and the backward part of the window is less than the preset window value, the mean of the end part is used for filling; Extract structured feature data from processed data through keyword extraction technology; The characteristic data is normalized to obtain carbon image characteristic data.

[0009] In one implementation of the present application, a learnable weight matrix is ​​preset to obtain the weights of each type of carbon image feature data, and then based on the weights, the specific values ​​of each carbon image feature data in the feature vector are updated, specifically including: The weight matrix can be learned by presetting: , calculate the weight of each type of carbon portrait feature data; Where i represents the i-th type, b is the preset bias term, W represents the first preset weight matrix, h represents the second preset weight matrix, represents the carbon image feature data of the i-th type; and =1, where n represents the total number of types; Each carbon image feature data is added to the corresponding weight to obtain the specific value of the updated carbon image feature data.

[0010] In one implementation of the present application, the updated feature vector and the carbon emission data collected at the same time are input as training data into a preset carbon profile generation model to obtain a trained carbon profile generation model, specifically including: During the model training process, adversarial network technology is used to generate adversarial samples, which are then input into the carbon portrait generation model; In terms of loss function construction, the weight values ​​of mean square error and cross entropy are obtained, and the loss function is calculated using a weighted combination of mean square error and cross entropy; The parameters of the carbon portrait generation model are updated at preset time intervals through online learning technology until the parameters remain unchanged or the preset time length is reached.

[0011] In one implementation of the present application, a carbon portrait in a preset display mode is generated based on the carbon portrait feature data and the carbon emission data, and displayed on a preset display interface, specifically including: Get the carbon portrait template; Based on a preset update time interval, the carbon portrait feature data and carbon emission data are input into the carbon portrait template to update the carbon portrait.

[0012] In a second aspect, the present application provides a system for generating enterprise carbon profiles based on multi-source data fusion, the system comprising: The collection module is used to collect initial enterprise carbon data using a preset collection platform. The types of initial enterprise carbon data include: energy consumption data, production process data, supply chain data, unstructured data such as carbon policy texts, and energy market data. An acquisition module is used to transmit the collected enterprise carbon data to the corresponding edge computing gateway based on the preset association relationship between the preset collection platform and the edge computing gateway, pre-process the uploaded data through the edge computing gateway, and obtain structured carbon profile feature data from the initial enterprise carbon data; The transmission module is used to obtain a preset compatible access protocol and configure a preset standardized interface, and then obtain the carbon profile feature data transmitted by the edge computing gateway through the preset standardized interface based on the preset compatible access protocol; An update module is used to combine the carbon portrait feature data into a feature vector in a preset type order based on the type and collection time of the carbon portrait feature data; obtain the weight of each type of carbon portrait feature data through a preset learnable weight matrix, and then update the specific value of each carbon portrait feature data in the feature vector based on the weight; The display module is used to input the updated feature vector and the carbon emission data at the same collection time as training data into the preset carbon portrait generation model to obtain a trained carbon portrait generation model; obtain carbon portrait feature data in real time, and then use the trained carbon portrait generation model to obtain current carbon emission data; generate a carbon portrait with a preset display method based on the carbon portrait feature data and carbon emission data, and display it on a preset display interface.

[0013] In one implementation of the present application, the acquisition module includes an acquisition unit, Used to collect energy usage in each production link of an enterprise in real time using preset energy consumption monitoring and metering equipment, and obtain energy consumption data, and the energy consumption data is presented in a time series numerical format; wherein the preset energy consumption monitoring and metering equipment includes at least: smart electricity meters, gas meters and fuel sensors; Extracting production process data from the manufacturing execution system; wherein the production process data includes at least: equipment operating parameters, raw material input, and waste output; Obtain supply chain data through the logistics management system; the supply chain data includes at least: transportation routes, vehicle types, and supplier carbon emission coefficients; Extract unstructured carbon policy text data related to corporate carbon profiling through a pre-set policy disclosure platform; Energy market data is collected through the electricity trading platform; the energy market data includes at least: real-time electricity prices and carbon emission intensity index.

[0014] In a third aspect, the present application provides a non-volatile computer storage medium on which computer instructions are stored. When the computer instructions are executed, they implement a method for generating an enterprise carbon portrait based on multi-source data fusion as described above.

[0015] It can be seen from the above technical solutions that this application has the following advantages: ‌Solved the problem of data layer interface standardization‌: By obtaining a pre-set compatible access protocol and configuring a pre-set standardized interface, this application addresses the existing problem of a lack of standardized interfaces between internal and external data sources at the data level. This ensures smooth and accurate data transmission and interaction between different data sources, improving the efficiency and accuracy of data processing.

[0016] Capable of capturing complex nonlinear relationships: The method used in this application does not rely on traditional statistical models. Instead, it uses a pre-set learnable weight matrix and a pre-set carbon profile generation model to capture the complex nonlinear relationship between carbon emissions and multiple factors. This overcomes the limitations of traditional methods' linear assumptions, enabling the generated carbon profile to more accurately and comprehensively reflect a company's carbon emissions.

[0017] Achieved multi-source data fusion and efficient processing: This application can collect various types of initial enterprise carbon data, including energy consumption data, production process data, supply chain data, unstructured data such as carbon policy texts, and energy market data. Through preprocessing and structured extraction by the edge computing gateway, and subsequent feature vector combination and weight update, it achieves efficient fusion and processing of multi-source data, providing a rich and accurate data foundation for the generation of carbon portraits.

[0018] Furthermore, this application can acquire carbon profile feature data in real time and utilize a trained carbon profile generation model to obtain current carbon emissions data. This makes the generated carbon profile real-time and dynamic, reflecting the latest status of a company's carbon emissions and providing timely and effective support for carbon emission management and decision-making.

[0019] Furthermore, this application can generate a carbon profile in a preset display format based on carbon profile feature data and carbon emissions data, and display it on a preset display interface. This intuitive display method allows users to clearly understand the company's carbon emissions, facilitating carbon emissions analysis and decision-making. Furthermore, the preset display interface provides convenient interactive functions for user operation and query convenience. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a flow chart of a method for generating an enterprise carbon portrait based on multi-source data fusion provided in an embodiment of the present application.

[0022] Figure 2 This is a schematic diagram of the internal structure of an enterprise carbon portrait generation system based on multi-source data fusion provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0024] It should be understood by those skilled in the art that the embodiments described below are merely preferred embodiments of the present disclosure and do not imply that the present disclosure can only be implemented through these preferred embodiments. These preferred embodiments are merely intended to explain the technical principles of the present disclosure and are not intended to limit the scope of protection of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of the present disclosure.

[0025] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0026] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0027] The embodiment provides a method for generating an enterprise carbon profile based on multi-source data fusion, such as Figure 1 As shown, the method provided in the embodiment of the present application mainly includes the following steps: Step 110: Use the preset collection platform to collect initial enterprise carbon data.

[0028] The types of initial enterprise carbon data include: energy consumption data, production process data, supply chain data, carbon policy text-based unstructured data, and energy market data; In some embodiments, energy consumption data collection involves real-time collection of energy usage across all production processes using energy consumption monitoring and metering devices such as smart electricity meters, gas meters, and fuel sensors. This data is presented in a time series format, detailing the specific energy consumption at each point in time, providing fundamental and critical data support for subsequent analysis. This data covers various energy sources used in daily production operations, including electricity, water, gas, and coal.

[0029] Production process data collection: Accurately extract structured data such as equipment operating parameters, raw material input, and waste output from the Manufacturing Execution System (MES). The MES system comprehensively records various information throughout the company's production process. Equipment operating parameters, including operating time, power, and speed, reflect the equipment's working status; raw material input clearly defines the specific quantity and type of raw materials used in each production batch; and waste output provides a visual representation of waste generation during the production process. This data is crucial for analyzing the sources of carbon emissions within a company's production process and the relationship between production efficiency and carbon emissions.

[0030] Supply Chain Data Collection: Information such as transportation routes, vehicle types, and supplier carbon emission coefficients is collected through the Logistics Management System (TMS). This data is transmitted via APIs for rapid and stable acquisition. Transportation routes detail the entire logistical trajectory of products from supplier to enterprise and then on to customer delivery. Vehicle types identify the means of transport used, with carbon emission characteristics varying significantly across different vehicles. Supplier carbon emission coefficients reflect the carbon emissions levels of suppliers in the production of raw materials and other processes. API integration between the TMS and the enterprise's carbon profiling system enables real-time and accurate access to this critical supply chain data.

[0031] Unstructured data collection related to policy texts: We collect extensive unstructured data on policy texts, such as regional carbon quotas and carbon tax rates, from platforms where relevant policies are publicly available. Government departments and related institutions publicly disclose various carbon emission-related policy information on official websites and specific policy release platforms. Using web crawlers or specialized data collection software, we collect policy texts from these platforms. We then conduct in-depth processing and analysis of these unstructured texts to extract key information valuable for building corporate carbon profiles.

[0032] Energy market data collection: Real-time electricity prices and carbon intensity indices are collected from power trading platforms. Power trading platforms provide real-time updates on electricity market transaction prices, which are closely related to companies' electricity procurement costs and energy usage decisions. The carbon intensity index reflects the carbon intensity trend of the entire energy market. By connecting to the power trading platform's data interface, this data can be obtained periodically or in real time, providing companies with market dynamics for energy selection and carbon emission assessment.

[0033] Step 120: Based on the preset association relationship between the preset collection platform and the edge computing gateway, the collected enterprise carbon data is transmitted to the corresponding edge computing gateway, the edge computing gateway pre-processes the corresponding uploaded data, and obtains structured carbon portrait feature data from the initial enterprise carbon data.

[0034] It should be noted that edge computing gateways are deployed for preliminary data aggregation and encrypted transmission locally. Located close to data sources, edge computing gateways can quickly collect data generated by peripheral devices and perform preliminary organization and aggregation, reducing data transmission volume. Furthermore, encryption technology is used to encrypt data to ensure data security during transmission. Regarding data storage, a distributed storage cluster is used to efficiently store massive amounts of data. This distributed storage cluster consists of multiple storage nodes, which use distributed storage algorithms to disperse data across each node. This not only increases storage capacity, but also improves data read and write speeds and reliability, meeting the needs of enterprises for storing large amounts of historical data and real-time data during carbon profile generation.

[0035] Before transmitting the collected enterprise carbon data to the corresponding edge computing gateway based on the preset association relationship between the preset collection platform and the edge computing gateway, the method further includes: Obtain the preset association relationship between the preset collection platform and the edge computing gateway through the preset interface.

[0036] Among them, the edge computing gateway pre-processes the uploaded data and obtains structured carbon portrait feature data from the initial enterprise carbon data, specifically: Remove abnormal initial corporate carbon data that is not within the preset reasonable range; The sliding window mean filling method is used to fill in the deleted initial enterprise carbon data; When the abnormal initial enterprise carbon data is at the beginning of the data sequence and the forward part of the window is less than the preset window value, the mean of the beginning part is used for filling; when it is at the end and the backward part of the window is less than the preset window value, the mean of the end part is used for filling; Extract structured feature data from processed data through keyword extraction technology; The characteristic data is normalized to obtain carbon image characteristic data.

[0037] For example, for a device that collects data every 10 minutes, if the current data point at the 50th minute is used as the target point, the window can be set to 5 data points before and after (i.e., 40-60 minutes of data).

[0038] More specifically, abnormal initial corporate carbon data that is not within the preset reasonable range is removed: For example, suppose we collect energy consumption data and find that power consumption on a particular day suddenly surges to several times the normal value. This is clearly an outlier. We can identify and remove this outlier based on a pre-defined reasonable range (for example, a power consumption upper and lower limit based on historical data or industry standards).

[0039] ‌The sliding window mean filling method is used to fill the deleted initial corporate carbon data‌: Assume that in the energy consumption data, due to equipment failure, the data of some days is missing. We can use the sliding window mean filling method to fill the data.

[0040] Set a preset window value, such as 5 days. For missing data points, we calculate the average power consumption of the 5 days before and after (if data exists) and use this average to fill the missing data points.

[0041] ‌Special case mean filling‌: When the abnormal initial corporate carbon data is at the beginning of the data sequence and the forward part of the window is less than the preset window value (for example, the data for the first three days is missing, but the preset window value is 5 days), we use the mean of the starting part (that is, the existing data points) for filling.

[0042] Similarly, when the abnormal data is at the end and the backward part of the window is less than the preset window value, we use the mean of the end part for filling.

[0043] ‌Use keyword extraction technology to extract structured feature data from the processed data‌: For unstructured carbon policy text data, we can use keyword extraction technology to extract key information related to carbon emissions.

[0044] For example, through natural language processing technology, we can identify keywords such as "emission reduction target", "carbon tax", "green energy" in the text, and extract these keywords and their related contextual information as structured feature data.

[0045] Normalize the feature data to obtain carbon image feature data: Assume that the feature data we extract include electricity consumption in different time periods, carbon emission intensity in the production process, etc. The dimensions and ranges of these data may be different.

[0046] To facilitate subsequent analysis and modeling, we need to normalize these feature data. For example, we can use the min-max normalization method to scale the data to the range of [0, 1] to obtain standardized carbon profile feature data.

[0047] Step 130: Obtain a preset compatible access protocol and configure a preset standardized interface, and then obtain the carbon portrait feature data transmitted by the edge computing gateway through the preset standardized interface based on the preset compatible access protocol.

[0048] It should be noted that based on the various types of collected data, standardized interfaces are built and unified data access protocols (such as RESTful API) are designed to support HTTP / HTTPS communication and be compatible with multiple formats such as JSON and CSV to ensure the compatibility of multi-source heterogeneous data.

[0049] Step 140: Based on the type and collection time of the carbon portrait feature data, the carbon portrait feature data are combined into a feature vector in a preset type order; the weight of each type of carbon portrait feature data is obtained through a preset learnable weight matrix, and then the specific value of each carbon portrait feature data in the feature vector is updated based on the weight.

[0050] In some embodiments, a learnable weight matrix is ​​preset to obtain weights for each type of carbon image feature data, and then based on the weights, specific values ​​of each carbon image feature data in the feature vector are updated, specifically including: The learnable weight matrix can be preset: , calculate the weight of each type of carbon portrait feature data; Where i represents the i-th type, b is the preset bias term, W represents the first preset weight matrix, h represents the second preset weight matrix, represents the carbon image feature data of the i-th type; and =1, where n represents the total number of types; Each carbon image feature data is added to the corresponding weight to obtain the specific value of the updated carbon image feature data.

[0051] It should be noted that feature vector combination involves combining the carbon profile feature data into a feature vector in a pre-set order based on its type and collection time. This step ensures the orderliness and structure of the feature data, facilitating subsequent processing and analysis.

[0052] Application of a Preset Learnable Weight Matrix: A pre-set learnable weight matrix is ​​used to calculate the weights for each type of carbon profile feature data. This matrix allows the model to automatically adjust the weights during learning to better capture the relationship between feature data and carbon emissions.

[0053] Those skilled in the art will appreciate that the weights calculated using the above formula reflect the relative importance of each feature in carbon emissions prediction or analysis. These weights are dynamically learned, meaning they adjust based on changes in the training data to optimize the model's predictive performance.

[0054] Multiplying each carbon profile feature by its corresponding weight is a comprehensive result that takes into account all feature data and their weights, reflecting each feature's impact on the final output. From a straightforward operational perspective, this can be described as "adjusting" each feature data according to its weight (reflected in the overall calculation as its contribution to the final sum). Ultimately, the weighted sum of all feature data forms the updated feature vector. The "addition" here actually refers to the application of softmax normalized weights, where each feature data is multiplied by its weight and then added as part of the overall sum to form the new feature representation.

[0055] Step 150: Input the updated feature vector and the carbon emission data at the same collection time as training data into a preset carbon portrait generation model to obtain a trained carbon portrait generation model; obtain the carbon portrait feature data in real time, and then use the trained carbon portrait generation model to obtain the current carbon emission data; generate a carbon portrait in a preset display method based on the carbon portrait feature data and carbon emission data, and display it on a preset display interface.

[0056] It should be noted that the process of obtaining carbon portrait feature data in real time and then using the trained carbon portrait generation model to obtain the current carbon emission data requires "based on the type and collection time of the carbon portrait feature data, combining the carbon portrait feature data into a feature vector in a preset type order; obtaining the weights of each type of carbon portrait feature data through a preset learnable weight matrix, and then updating the specific values ​​of each carbon portrait feature data in the feature vector based on the weights" to obtain the specific values ​​of the real-time data, and then using the model to obtain the current carbon emission data.

[0057] The updated feature vector and the carbon emission data at the same collection time are used as training data to input into a preset carbon portrait generation model to obtain a trained carbon portrait generation model, which can be specifically: During the model training process, adversarial network technology is used to generate adversarial samples, which are then input into the carbon portrait generation model; In terms of loss function construction, the weight values ​​of mean square error and cross entropy are obtained, and the loss function is calculated using a weighted combination of mean square error and cross entropy; The parameters of the carbon portrait generation model are updated at preset time intervals through online learning technology until the parameters remain unchanged or the preset time length is reached.

[0058] Among them, based on the carbon portrait feature data and carbon emission data, a carbon portrait with a preset display method is generated and displayed on a preset display interface, which can be specifically: Get the carbon portrait template; Based on a preset update time interval, the carbon portrait feature data and carbon emission data are input into the carbon portrait template to update the carbon portrait.

[0059] In addition, this application can carry out dynamic updates and visual displays of carbon portraits, mainly including the following: Monitor real-time data sources through message queues (such as RabbitMQ), trigger model recalculation, and implement data stream monitoring. Use Git-like mechanism to manage model versions, supporting historical status backtracking and comparative analysis; Design a display interface covering heat maps, carbon emission trend forecasts, emission reduction suggestions, etc., specifically including: A heat map showing the carbon emission intensity distribution of each factory area of ​​the enterprise based on the geographic information system; Combined with the ARIMA model to predict the carbon emission trend in the next 7 days, the carbon emission trend prediction curve with a confidence interval of 95%; Generate priority recommendations based on model output (such as "replace high-energy-consuming equipment" and "optimize logistics routes") to provide companies with carbon emission reduction advice; Supports providing RESTful interfaces for enterprise ERP systems to call, realizing the coordinated linkage between carbon data and production plans.

[0060] In addition, this application Figure 2 The embodiment of this application provides a system for generating corporate carbon profiles based on multi-source data fusion. Figure 2 As shown, the system provided in the embodiment of the present application mainly includes: The collection module 210 is used to collect initial enterprise carbon data using a preset collection platform; the types of initial enterprise carbon data include: energy consumption data, production process data, supply chain data, carbon policy text-type unstructured data, and energy market data.

[0061] The acquisition module 210 includes an acquisition unit, Used to collect energy usage in each production link of an enterprise in real time using preset energy consumption monitoring and metering equipment, and obtain energy consumption data, and the energy consumption data is presented in a time series numerical format; wherein the preset energy consumption monitoring and metering equipment includes at least: smart electricity meters, gas meters and fuel sensors; Extracting production process data from the manufacturing execution system; wherein the production process data includes at least: equipment operating parameters, raw material input, and waste output; Obtain supply chain data through the logistics management system; the supply chain data includes at least: transportation routes, vehicle types, and supplier carbon emission coefficients; Extract unstructured carbon policy text data related to corporate carbon profiling through a pre-set policy disclosure platform; Energy market data is collected through the electricity trading platform; the energy market data includes at least: real-time electricity prices and carbon emission intensity index.

[0062] The acquisition module 220 is used to transmit the collected enterprise carbon data to the corresponding edge computing gateway based on the preset association relationship between the preset collection platform and the edge computing gateway, pre-process the uploaded data through the edge computing gateway, and obtain structured carbon portrait feature data from the initial enterprise carbon data.

[0063] The transmission module 230 is used to obtain a preset compatible access protocol and configure a preset standardized interface, and then obtain the carbon portrait feature data transmitted by the edge computing gateway through the preset standardized interface based on the preset compatible access protocol.

[0064] Update module 240 is used to combine the carbon portrait feature data into a feature vector in a preset type order based on the type and collection time of the carbon portrait feature data; obtain the weight of each type of carbon portrait feature data through a preset learnable weight matrix, and then update the specific value of each carbon portrait feature data in the feature vector based on the weight.

[0065] The display module 250 is used to input the updated feature vector and the carbon emission data at the same collection time as training data into a preset carbon portrait generation model to obtain a trained carbon portrait generation model; obtain carbon portrait feature data in real time, and then use the trained carbon portrait generation model to obtain current carbon emission data; generate a carbon portrait in a preset display method based on the carbon portrait feature data and carbon emission data, and display it on a preset display interface.

[0066] In addition, an embodiment of the present application also provides a non-volatile computer storage medium on which executable instructions are stored. When the executable instructions are executed, a method for generating an enterprise carbon portrait based on multi-source data fusion as described above is implemented.

[0067] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for generating an enterprise carbon profile based on multi-source data fusion, characterized in that: The method comprises: Using a pre-set collection platform, collect initial corporate carbon data; the types of initial corporate carbon data include: energy consumption data, production process data, supply chain data, unstructured data such as carbon policy texts, and energy market data; Based on the preset association between the preset collection platform and the edge computing gateway, the collected enterprise carbon data is transmitted to the corresponding edge computing gateway, and the edge computing gateway pre-processes the uploaded data and obtains structured carbon profile feature data from the initial enterprise carbon data; Obtain a preset compatible access protocol and configure a preset standardized interface, and then obtain the carbon profile feature data transmitted by the edge computing gateway through the preset standardized interface based on the preset compatible access protocol; Based on the type and collection time of the carbon portrait feature data, the carbon portrait feature data is combined into a feature vector in a preset type order; the weight of each type of carbon portrait feature data is obtained through a preset learnable weight matrix, and then the specific value of each carbon portrait feature data in the feature vector is updated based on the weight; The updated feature vector and the carbon emission data collected at the same time are input as training data into a preset carbon profile generation model to obtain a trained carbon profile generation model; the carbon profile feature data is obtained in real time, and then the current carbon emission data is obtained using the trained carbon profile generation model; Based on the carbon portrait characteristic data and carbon emission data, a carbon portrait with a preset display method is generated and displayed on the preset display interface.

2. The method for generating an enterprise carbon profile based on multi-source data fusion according to claim 1 is characterized in that: Use the pre-set collection platform to collect initial corporate carbon data, including: Utilize pre-set energy consumption monitoring and metering equipment to collect energy usage in each production link of the enterprise in real time, obtain energy consumption data, and present the energy consumption data in a time series numerical format; wherein, the pre-set energy consumption monitoring and metering equipment includes at least: smart electricity meters, gas meters and fuel sensors; Extracting production process data from the manufacturing execution system; wherein the production process data includes at least: equipment operating parameters, raw material input, and waste output; Obtain supply chain data through the logistics management system; the supply chain data includes at least: transportation routes, vehicle types, and supplier carbon emission coefficients; Extract unstructured carbon policy text data related to corporate carbon profiling through a pre-set policy disclosure platform; Energy market data is collected through the electricity trading platform; the energy market data includes at least: real-time electricity prices and carbon emission intensity index.

3. The method for generating an enterprise carbon profile based on multi-source data fusion according to claim 1 is characterized in that: Before transmitting the collected enterprise carbon data to the corresponding edge computing gateway based on the preset association relationship between the preset collection platform and the edge computing gateway, the method further includes: Obtain the preset association relationship between the preset collection platform and the edge computing gateway through the preset interface.

4. The method for generating an enterprise carbon profile based on multi-source data fusion according to claim 1 is characterized in that: The edge computing gateway pre-processes the uploaded data and obtains structured carbon profile feature data from the initial enterprise carbon data, including: Remove abnormal initial corporate carbon data that is not within the preset reasonable range; The sliding window mean filling method is used to fill in the deleted initial enterprise carbon data; When the abnormal initial enterprise carbon data is at the beginning of the data sequence and the forward part of the window is less than the preset window value, the mean of the beginning part is used for filling; when it is at the end and the backward part of the window is less than the preset window value, the mean of the end part is used for filling; Extract structured feature data from processed data through keyword extraction technology; The characteristic data is normalized to obtain carbon image characteristic data.

5. The method for generating an enterprise carbon profile based on multi-source data fusion according to claim 1 is characterized in that: By presetting a learnable weight matrix, the weights of each type of carbon profile feature data are obtained, and then based on the weights, the specific values ​​of each carbon profile feature data in the feature vector are updated, including: The weight matrix can be learned by presetting: , calculate the weight of each type of carbon portrait feature data; Where i represents the i-th type, b is the preset bias term, W represents the first preset weight matrix, h represents the second preset weight matrix, represents the carbon image feature data of the i-th type; and =1, where n represents the total number of types; Each carbon image feature data is added to the corresponding weight to obtain the specific value of the updated carbon image feature data.

6. The method for generating an enterprise carbon profile based on multi-source data fusion according to claim 1 is characterized in that: The updated feature vector and the carbon emission data collected at the same time are used as training data to input into the preset carbon profile generation model to obtain a trained carbon profile generation model, specifically including: During the model training process, adversarial network technology is used to generate adversarial samples, which are then input into the carbon portrait generation model; In terms of loss function construction, the weight values ​​of mean square error and cross entropy are obtained, and the loss function is calculated using a weighted combination of mean square error and cross entropy; The parameters of the carbon portrait generation model are updated at preset time intervals through online learning technology until the parameters remain unchanged or the preset time length is reached.

7. The method for generating an enterprise carbon profile based on multi-source data fusion according to claim 1 is characterized in that: Based on the carbon profile feature data and carbon emission data, a carbon profile with a preset display method is generated and displayed on the preset display interface, specifically including: Get the carbon portrait template; Based on a preset update time interval, the carbon portrait feature data and carbon emission data are input into the carbon portrait template to update the carbon portrait.

8. A system for generating enterprise carbon profiles based on multi-source data fusion, characterized in that: The system comprises: The collection module is used to collect initial enterprise carbon data using a preset collection platform. The types of initial enterprise carbon data include: energy consumption data, production process data, supply chain data, unstructured data such as carbon policy texts, and energy market data. An acquisition module is used to transmit the collected enterprise carbon data to the corresponding edge computing gateway based on the preset association relationship between the preset collection platform and the edge computing gateway, pre-process the uploaded data through the edge computing gateway, and obtain structured carbon profile feature data from the initial enterprise carbon data; The transmission module is used to obtain a preset compatible access protocol and configure a preset standardized interface, and then obtain the carbon profile feature data transmitted by the edge computing gateway through the preset standardized interface based on the preset compatible access protocol; An update module is used to combine the carbon portrait feature data into a feature vector in a preset type order based on the type and collection time of the carbon portrait feature data; obtain the weight of each type of carbon portrait feature data through a preset learnable weight matrix, and then update the specific value of each carbon portrait feature data in the feature vector based on the weight; The display module is used to input the updated feature vector and the carbon emission data at the same collection time as training data into the preset carbon portrait generation model to obtain a trained carbon portrait generation model; obtain carbon portrait feature data in real time, and then use the trained carbon portrait generation model to obtain current carbon emission data; generate a carbon portrait with a preset display method based on the carbon portrait feature data and carbon emission data, and display it on a preset display interface.

9. The enterprise carbon profile generation system based on multi-source data fusion according to claim 8 is characterized in that: The acquisition module includes an acquisition unit, Used to collect energy usage in each production link of an enterprise in real time using preset energy consumption monitoring and metering equipment, and obtain energy consumption data, and the energy consumption data is presented in a time series numerical format; wherein the preset energy consumption monitoring and metering equipment includes at least: smart electricity meters, gas meters and fuel sensors; Extracting production process data from the manufacturing execution system; wherein the production process data includes at least: equipment operating parameters, raw material input, and waste output; Obtain supply chain data through the logistics management system; the supply chain data includes at least: transportation routes, vehicle types, and supplier carbon emission coefficients; Extract unstructured carbon policy text data related to corporate carbon profiling through a pre-set policy disclosure platform; Energy market data is collected through the electricity trading platform; the energy market data includes at least: real-time electricity prices and carbon emission intensity index.

10. A non-volatile computer storage medium, characterized in that Computer instructions are stored thereon, and when the computer instructions are executed, they implement a method for generating an enterprise carbon portrait based on multi-source data fusion as described in any one of claims 1 to 7.

Images