An AI vision-based highway and waterway construction carbon emission accounting method and system

Abstract

This invention relates to the field of carbon emission accounting technology, and in particular to a method and system for carbon emission accounting in highway and waterway construction based on AI vision. The method includes: acquiring images of the dials of water meters, electricity meters, and fuel meters during the project construction phase and binding the dial images to virtual instrument files; controlling an AI vision acquisition terminal to upload the dial image data to an AI recognition cloud platform according to a preset acquisition strategy; recognizing the dial images to generate structured energy consumption data; calculating the actual energy consumption of water, electricity, and fuel under different meters, construction areas, and time granularities through cumulative calculation of adjacent energy consumption readings; and calculating the carbon emissions for the corresponding construction area and time granularity by combining a pre-set carbon emission factor database. This invention effectively solves the problem of insufficient accuracy in existing emission accounting methods due to the difficulty in obtaining continuous and accurate energy consumption data, and achieves accurate carbon emission accounting during the construction phase of highway and waterway projects.

Description

Technical Field

[0001] This invention relates to the field of carbon emission accounting technology, and in particular to a method and system for carbon emission accounting in highway and waterway construction based on AI vision. Background Technology

[0002] During the construction phase of highway and waterway projects, energy sources such as water, electricity, and fuel oil are widely used in construction and supporting facilities. Their energy consumption levels directly determine the carbon emissions during this phase. Therefore, carbon emission accounting based on actual energy consumption during construction is a crucial foundation for achieving refined carbon emission management in engineering construction.

[0003] However, existing technologies for carbon emission accounting during the construction phase generally suffer from the difficulty of accurately obtaining continuous energy consumption data that reflects actual energy consumption changes. Current methods typically rely on manual recording of meter readings or statistical analysis based on billing data. The resulting energy consumption data is mostly discrete, single-point data, lacking continuity and time-series characteristics. Under these circumstances, it is difficult to accurately calculate the actual energy consumption at different time granularities during the construction phase based on energy consumption changes at adjacent moments. Because of the inability to accurately obtain actual energy consumption, existing technologies often resort to estimation methods based on total energy consumption over a statistical period when conducting carbon emission accounting. This leads to discrepancies between the carbon emission accounting results and the actual energy consumption levels during construction, making it difficult to reflect the differences in carbon emissions across different construction areas and time periods. This accounting method not only affects the accuracy of carbon emission results but also limits the precision of carbon emission management during the construction phase. Summary of the Invention

[0004] This invention provides a method for carbon emission accounting in highway and waterway construction based on AI vision, which can effectively solve the problems in the background technology.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for carbon emission accounting in highway and waterway construction based on AI vision, the method comprising: Using AI vision, images of the dials of water meters, electricity meters, and fuel meters during the construction phase of highway and waterway projects are captured and bound to virtual instrument files; Based on the completed binding of the watch face image, the AI ​​vision acquisition terminal is controlled to upload the watch face image data to the AI ​​recognition cloud platform according to the preset acquisition strategy; In the AI ​​recognition cloud platform, the dial image is recognized to generate structured energy consumption data; Based on the structured energy consumption data, the actual energy consumption of water, electricity and fuel under different instruments, construction areas and time granularities is obtained by accumulating adjacent energy consumption readings. Based on the actual energy consumption, and combined with a pre-set carbon emission factor database, the carbon emissions for the corresponding construction area and time granularity are calculated.

[0006] Furthermore, the construction company's green construction management platform obtains the structured energy consumption data through a standardized data query interface, including: Call the project query interface to obtain a list of projects within the authorized scope and their corresponding project keys; Based on the project key, the instrument query interface is called to retrieve the instrument information of the instruments bound to the project in pages; Based on business needs, the meter reading data query interface is periodically called, and the project key, time range and meter identification filtering conditions are passed in to obtain the structured energy consumption data that is recognized by AI within the specified time period or the latest time.

[0007] Furthermore, the interface call process includes at least one of the following: querying during busy data upload times, setting a delay time for fetching data, and employing a retransmission mechanism.

[0008] Furthermore, the structured energy consumption data returned by the data query interface provided by the AI ​​recognition cloud platform includes: extended fields for data credibility and status judgment.

[0009] Furthermore, the formula for calculating the carbon emissions is as follows: ; in, Total carbon emissions; This refers to the consumption of water, electricity, and oil. The carbon emission factors are for water, electricity, and oil.

[0010] Furthermore, the method also includes: The structured energy consumption data and the calculated carbon emissions are then visualized in a multi-dimensional manner. The construction company's green construction management platform uses data analysis models to automatically identify and issue early warnings for abnormal water, electricity, and oil consumption behaviors, as well as situations where carbon emission intensity exceeds standards.

[0011] A carbon emission accounting system for highway and waterway construction based on AI vision, comprising: The on-site perception module is used to collect images of the dials of water meters, electricity meters, and fuel meters during the construction phase of highway and waterway construction projects using AI vision, and to obtain the corresponding dial image data. The network transmission module is used to upload the dial image data to the cloud; The platform service module includes an AI recognition cloud platform, a green construction management platform, and an application display platform. The AI ​​recognition cloud platform is used to recognize and process the received dial image data to generate structured energy consumption data. The green construction management platform is used to calculate the corresponding carbon emissions based on the structured energy consumption data. The application display platform is used to display the carbon emissions.

[0012] Furthermore, the data interaction between the AI ​​recognition cloud platform and the green construction management platform adopts secure communication based on the HTTPS protocol, and performs dual authentication and data isolation through customer keys and project keys.

[0013] Furthermore, the system adopts an edge computing deployment approach, setting up localized edge computing nodes within the highway and waterway construction area; The dial image data collected by the field perception module is sent to the edge computing node through the local network; The edge computing node performs recognition processing on the dial image data, generates structured energy consumption data, and sends the structured energy consumption data to the platform service module.

[0014] The present invention also includes a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described above.

[0015] The technical solution of this invention can achieve the following technical effects: Compared with existing technologies, the AI-based vision-based carbon emission accounting method for highway and waterway construction provided by this invention can acquire continuous energy consumption readings during the construction phase and calculate the actual energy consumption based on the cumulative calculation of adjacent energy consumption readings. This avoids the accounting bias caused by relying solely on discrete single-point data or statistical bills for estimation. By using actual energy consumption as the basis for carbon emission accounting, this invention can more accurately reflect the real energy consumption levels in different construction areas and at different times during highway and waterway construction, ensuring that the carbon emission accounting results are consistent with the actual energy use during construction, effectively improving the accuracy and reliability of carbon emission accounting during the construction phase.

[0016] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating the carbon emission accounting method for highway and waterway construction based on AI vision; Figure 2 This is a flowchart illustrating the process by which the construction company's green construction management platform obtains structured energy consumption data through a standardized data query interface. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0021] Example 1: like Figure 1 As shown, this application provides a method for carbon emission accounting in highway and waterway construction based on AI vision. The method includes: S1: Using AI vision, images of the dials of water meters, electricity meters, and fuel meters during the construction phase of highway and waterway projects are captured and bound to virtual instrument files; Specifically, during the construction phase of highway and waterway projects, to achieve real-time and continuous perception of energy consumption information at the construction site, images of existing water meters, electricity meters, and fuel meters are acquired using an AI vision-based method in construction-related areas such as living quarters, office areas, prefabrication yards, mixing plants, and steel processing yards. Without disassembling, replacing, or modifying the original metering instruments, a vision acquisition terminal is non-intrusively installed on the outside of the water meter, electricity meter, and fuel meter dial. This allows the vision acquisition terminal to stably acquire dial images under predetermined installation angles and viewing distances, ensuring that the acquired dial images clearly reflect the current energy consumption readings. As one of the key inventive aspects of this invention, after acquiring the dial images, they are bound to a pre-established virtual instrument file within the system. The virtual instrument file is used to digitally map physical instruments at the system level and at least to distinguish between different construction areas, different energy consumption types, and different physical instruments. By using the above binding method, each acquired dial image can be associated with a unique physical instrument within the system, thus avoiding the problem of image source confusion when there are many similar instruments on the construction site. For example, in a highway and waterway construction project, a corresponding virtual instrument file can be created for the fuel meters set up in the mixing plant area, and the dial images acquired by the fuel meters can be bound to their virtual instrument files. This ensures that subsequent energy consumption statistics for the fuel meters always correspond to the same construction area and the same energy user, laying the foundation for continuous acquisition and standardized management of energy consumption data during the construction phase.

[0022] S2: Based on the completed watch face image, control the AI ​​vision acquisition terminal to upload the watch face image data to the AI ​​recognition cloud platform according to the preset acquisition strategy; Specifically, after binding the dial images with virtual instrument files, the AI ​​vision acquisition terminal is controlled to automatically acquire dial images of various energy consumption instruments at the construction site according to a pre-set acquisition strategy, and the acquired dial image data is uploaded to the AI ​​recognition cloud platform. The acquisition strategy is configured according to the management needs of the construction phase to determine the acquisition frequency, acquisition time period, and terminal wake-up method of the dial images, enabling the AI ​​vision acquisition terminal to complete the dial image acquisition task periodically according to predetermined rules without manual intervention. As a preferred implementation of the invention, the AI ​​vision acquisition terminal adopts a low-power operating mode, entering a sleep state during non-acquisition periods and automatically waking up when preset acquisition conditions are met, thus adapting to the application environment of dispersed locations and complex power supply conditions at highway and waterway construction sites. After completing the dial image acquisition, the AI ​​vision acquisition terminal sends the dial image data to the AI ​​recognition cloud platform via wireless communication, realizing centralized reception and unified management of the dial image data. For example, in a highway and waterway construction project, the meter image acquisition strategy in the mixing plant area can be set to automatic acquisition on an hourly basis. The AI ​​vision acquisition terminal will automatically wake up and complete the image upload in each acquisition cycle, so that construction management personnel can obtain continuous meter image data without on-site meter reading, providing a stable data source for subsequent energy consumption information processing.

[0023] S3: In the AI ​​recognition cloud platform, the dial image is recognized to generate structured energy consumption data; Specifically, when the AI ​​recognition cloud platform receives the dial image uploaded by the on-site acquisition terminal, it automatically processes the image in the cloud environment to transform the raw image information into structured energy consumption data that can be used for subsequent energy consumption calculations. Specifically, the AI ​​recognition cloud platform first preprocesses the received dial image to reduce the impact of shooting angle deviations, lighting changes, and on-site background factors on the recognition results, making the dial area clearer and more stable. Then, based on a pre-trained dial image recognition model, the AI ​​recognition cloud platform locates the dial area in the image and identifies and analyzes the reading information on the dial to obtain the corresponding energy consumption reading. The identified energy consumption reading is correlated with the corresponding instrument identification information and the image acquisition time during the generation process, forming structured energy consumption data with time-series characteristics, enabling accurate calculation of actual energy consumption based on continuous reading changes.

[0024] S4: Based on structured energy consumption data, the actual energy consumption of water, electricity and fuel is obtained by accumulating adjacent energy consumption readings; Specifically, for structured energy consumption data generated by the same energy consumption meter at different time points, the energy consumption readings at adjacent times are compared in chronological order. By accumulating the differences between adjacent readings, the actual energy consumption within the corresponding time interval is obtained. This cumulative calculation method based on changes in adjacent readings effectively avoids statistical biases caused by single readings or periodic summaries, ensuring that the calculation results accurately reflect the actual changes in energy use during the construction phase. During the calculation process, the consumption corresponding to each energy consumption meter is associated with its respective construction area, thereby enabling the separate acquisition of water, electricity, and fuel consumption in different construction areas. Statistical analysis of energy consumption is supported at different time granularities, such as minutes, hours, and days. For example, in a highway and waterway construction project, by accumulating the changes in meter readings at adjacent collection times within the mixing plant area, the actual electricity consumption of that area within a specified time period can be obtained, providing an accurate data foundation for subsequent construction energy consumption analysis.

[0025] S5: Based on actual energy consumption and combined with a pre-set carbon emission factor database, calculate the carbon emissions for the corresponding construction area and time granularity.

[0026] Specifically, the carbon emission factor database pre-sets carbon emission factors corresponding to different energy types such as water, electricity, and fuel oil. These factors can be configured based on project location, energy supply method, or industry standards, ensuring they reflect the carbon emission levels associated with different energy sources. During carbon emission calculations, the actual energy consumption obtained in the previous stage is matched with the corresponding energy type's carbon emission factor, and the corresponding carbon emissions are calculated accordingly. This ensures the carbon emission calculation results are directly based on actual energy consumption. By linking the calculated carbon emissions with construction area and time information, carbon emissions at different time granularities in different construction areas can be obtained, achieving refined accounting of carbon emissions during the construction phase. For example, in a highway and waterway construction project, the actual electricity consumption of the mixing plant area within a specified time period, combined with the corresponding electricity carbon emission factor, can be used to calculate the carbon emissions generated in that area during that time period, thus accurately reflecting the impact of construction activities on carbon emissions.

[0027] This invention effectively solves the problem of insufficient accuracy in existing emission accounting due to the difficulty in obtaining continuous and accurate energy consumption data, and realizes accurate carbon emission accounting during the construction phase of highway and waterway transportation.

[0028] As a preferred embodiment of the above, such as Figure 2 As shown, the construction company's green construction management platform obtains structured energy consumption data through a standardized data query interface, including: A10: Call the project query interface to obtain a list of projects within the authorized scope and the corresponding project keys; A20: Call the meter query interface based on the project key to retrieve meter information of the meter bound to the project in pages; A30: Based on business needs, periodically call the meter reading data query interface, pass in the project key, time range and meter identifier filtering conditions, and obtain the latest structured energy consumption data recognized by AI within the specified time period.

[0029] Specifically, the construction company's green construction management platform utilizes a standardized data query interface provided by the AI ​​recognition cloud platform to achieve unified acquisition and management of structured energy consumption data. During data interaction, the green construction management platform first obtains a list of construction projects within the currently authorized scope through the project query interface, and simultaneously acquires the unique key corresponding to each construction project, serving as the basis for subsequent data access and permission verification. After completing project-level identity verification, the green construction management platform uses the project's unique key to call the meter query interface, retrieving meter information such as water meters, electricity meters, and fuel meters that have been bound to the construction project in a paginated manner, thereby establishing the correspondence between the construction project and each energy consumption meter. Based on this, the green construction management platform periodically calls the meter reading data query interface according to actual business needs. During the interface call process, the project's unique key, time range, and meter identification filtering conditions are passed in to actively pull or receive pushed meter reading data to obtain structured energy consumption data that has been processed by AI within a specified time period or the latest generation. Through the above interface call process, the construction party can achieve continuous acquisition and centralized management of energy consumption data during the construction phase without directly participating in on-site data collection and image recognition, providing a stable and reliable data foundation for subsequent energy consumption statistics and carbon emission accounting.

[0030] As a preferred embodiment of the above, the interface call process includes at least one of the following: querying during busy data upload times, setting a delay time for fetching data, and employing a retransmission mechanism.

[0031] Specifically, during the API call process, data queries can be performed outside peak periods of concentrated image uploads or recognition processing, based on the AI ​​recognition cloud platform's operational status and data upload load, thereby reducing the impact of API congestion on data acquisition. Simultaneously, instead of immediately fetching data after generation, a delay is set to allow structured energy consumption data to be aggregated and cached on the cloud platform before retrieval, improving the completeness and consistency of returned data. Furthermore, in the event of network fluctuations or communication anomalies, a retransmission mechanism is introduced to re-request unsuccessfully acquired or incompletely transmitted data, preventing data loss due to single communication failures. Through at least one of these API call optimization strategies, the construction party's green construction management platform can continuously and reliably acquire structured energy consumption data during the construction phase, even in complex network environments and high-concurrency scenarios, providing stable data support for subsequent energy consumption statistics and carbon emission accounting.

[0032] As a preferred embodiment of the above, the structured energy consumption data returned by the data query interface provided by the AI ​​recognition cloud platform includes: extended fields for data credibility and status judgment.

[0033] Specifically, the AI ​​recognition cloud platform, while returning structured energy consumption data through its data query interface, also returns extended fields reflecting data reliability and operational status. This allows data users to assess the validity of the acquired energy consumption data. The extended fields indicate the status of the dial image during the recognition process, including image quality, whether there are any anomalies in the recognition process, and the operational status of the acquisition terminal. This helps determine whether the returned energy consumption data is suitable for subsequent processing. In practical applications, when the dial image is blurry, obstructed, or has abnormal lighting, the extended fields can indicate uncertainty in the recognition results, enabling data users to identify and distinguish between normal and abnormal data. When the acquisition terminal is in a low-battery, offline, or communication abnormal state, the extended fields also reflect the corresponding status information, preventing incomplete or unreliable data from being directly used for subsequent energy consumption statistics. By introducing these extended fields into the structured energy consumption data, the data acquisition process not only returns the energy consumption reading itself but also simultaneously provides information related to data quality and device status, providing a more reliable data foundation for subsequent energy consumption data processing.

[0034] As a preferred embodiment of the above, the formula for calculating carbon emissions is: ; in, Total carbon emissions; This refers to the consumption of water, electricity, and oil. The carbon emission factors are for water, electricity, and oil.

[0035] Specifically, carbon emissions generated during the construction phase are calculated based on the actual energy consumption obtained in the previous phase, which corresponds to the water, electricity, and fuel consumption during construction. In the carbon emission calculation process, carbon emission factors corresponding to water, electricity, and fuel are pre-configured in the system for different energy types to characterize the carbon emission level generated per unit of energy consumption. During the calculation, the actual energy consumption of a construction area at a specified time granularity is matched with the corresponding energy type's carbon emission factor, and the carbon emissions corresponding to that energy consumption are calculated accordingly. Subsequently, the carbon emissions generated by different energy types in the same construction area at the same time granularity are summarized to obtain the total carbon emissions of the construction area within that time range. This calculation method ensures that the carbon emission results are directly based on actual energy consumption and simultaneously reflect the comprehensive impact of multiple energy sources, such as water, electricity, and fuel, on carbon emissions during the construction phase. For example, in a highway and waterway construction project, the total carbon emissions generated in the area during that time period can be calculated based on the actual electricity, water and fuel consumption of the mixing plant area in a day, combined with the corresponding carbon emission factors. The calculation results of each energy type are then summed up.

[0036] As a preferred embodiment of the above, the method further includes: The structured energy consumption data and the calculated carbon emissions are visualized in a multi-dimensional way. The construction company's green construction management platform uses data analysis models to automatically identify and issue early warnings for abnormal water, electricity, and oil consumption behaviors, as well as situations where carbon emission intensity exceeds standards.

[0037] Specifically, after obtaining structured energy consumption data and calculating carbon emissions, the construction company's green construction management platform aggregates and processes the energy consumption and carbon emission data in a unified manner. This data is then displayed in a multi-dimensional way through visualization, focusing on dimensions such as construction area, energy type, and time granularity. A dashboard-style display visually presents water, electricity, and fuel consumption in different areas and time periods, along with corresponding carbon emission levels, enabling managers to quickly grasp the overall energy consumption and carbon emission status during the construction phase. Based on this, the platform's built-in data analysis model analyzes and processes the continuously acquired energy consumption and carbon emission data to identify abnormal water, electricity, or fuel consumption during construction, as well as situations where the carbon emission intensity per unit of construction exceeds a preset threshold. When such abnormalities or exceedances are detected, the platform generates corresponding warning information and pushes the warning results to the manager's mobile terminal or management interface. This assists construction managers in promptly identifying problems in energy consumption and carbon emission management during the construction phase, achieving dynamic monitoring and management of carbon emissions during construction.

[0038] Example 2: Based on the same inventive concept as the AI ​​vision-based carbon emission accounting method for highway and waterway construction in the foregoing embodiments, this invention also provides an AI vision-based carbon emission accounting system for highway and waterway construction, comprising: The on-site perception module is used to collect images of the dials of water meters, electricity meters, and fuel meters during the construction phase of highway and waterway construction projects using AI vision, and to obtain the corresponding dial image data. The network transmission module is used to upload the dial image data to the cloud; The platform service module includes an AI recognition cloud platform, a green construction management platform, and an application display platform. The AI ​​recognition cloud platform is used to recognize and process the received dial image data to generate structured energy consumption data; the green construction management platform is used to calculate the corresponding carbon emissions based on the structured energy consumption data; and the application display platform is used to display the carbon emissions.

[0039] Specifically, the AI ​​vision-based carbon emission accounting system for highway and waterway construction comprises a field perception module, a network transmission module, and a platform service module. The field perception module is deployed at the construction site of the highway and waterway project to collect images of water, electricity, and fuel meters using AI vision during the construction phase, generating meter image data reflecting the current energy consumption status. The network transmission module establishes a data communication channel between the field perception module and the cloud, enabling the collected meter image data to be uploaded to the cloud wirelessly, achieving centralized transmission and aggregation processing of the meter image data. The platform service module runs in a cloud environment and includes an AI recognition cloud platform, a green construction management platform, and an application demonstration platform. The cloud platform identifies and processes the received dial image data, converting the image information into structured energy consumption data. The green construction management platform, after acquiring the structured energy consumption data, processes the energy consumption information across different meters, construction areas, and time granularities, and calculates carbon emissions accordingly. The application display platform then presents the calculated carbon emissions, enabling construction managers to intuitively understand the energy consumption levels and carbon emissions during the construction phase. This modular system architecture achieves a complete closed loop from on-site energy consumption perception and data transmission to carbon emission accounting and result display.

[0040] As a preferred embodiment of the above, the data interaction between the AI ​​recognition cloud platform and the green construction management platform adopts secure communication based on the HTTPS protocol, and performs dual authentication and data isolation through customer keys and project keys.

[0041] Specifically, to enhance the security and controllability of data interaction between the AI ​​recognition cloud platform and the green construction management platform, both parties adopt a secure transmission method based on the HTTPS protocol. Data requests and responses are transmitted through encrypted channels, reducing the risk of data theft, tampering, or replay during network transmission. When making interface calls, the green construction management platform includes a customer key and a project key in each data access request. The customer key identifies the data access subject and completes customer-level identity verification, while the project key limits the data access scope and completes project-level permission verification. This allows the platform to further differentiate data access permissions for different construction projects under the same customer. Upon receiving a data request, the AI ​​recognition cloud platform verifies the customer key and project key, returning structured energy consumption data matching the corresponding project only if authentication is successful. Furthermore, data is isolated based on the project dimension during data organization and return, preventing cross-use of data between different customers or different projects of the same customer. Through this dual authentication and data isolation mechanism, structured energy consumption data has clear access boundaries and permission control capabilities during cross-platform interaction, thus ensuring data security and compliance management for carbon emission accounting during the construction phase.

[0042] As a preferred embodiment of the above, the system adopts an edge computing deployment method, setting up local edge computing nodes in the construction area of ​​highway and waterway construction. The dial image data collected by the field perception module is sent to the edge computing node via the local network; Edge computing nodes process and identify the dial image data to generate structured energy consumption data, which is then sent to the platform service module.

[0043] Specifically, to adapt to the application scenarios of dispersed construction sites, complex network conditions, and high data security requirements in highway and waterway construction, the system adopts an edge computing deployment approach. Localized edge computing nodes are set up within the construction area to process data collected on-site locally. After acquiring the dial image, the on-site sensing module sends the dial image data to the corresponding edge computing node through the local network deployed within the construction area, allowing the image data to enter the recognition and processing flow without being directly uploaded to the cloud. Upon receiving the dial image data, the edge computing node performs recognition processing on the dial image in its local environment, converting the raw image information into structured energy consumption data, thereby reducing bandwidth consumption and latency caused by cross-network transmission of image data. After completing the recognition processing, the edge computing node sends the generated structured energy consumption data to the platform service module for subsequent energy consumption statistics and carbon emission accounting. By moving the image recognition processing to the local construction area, the system ensures the continuity of energy consumption data acquisition, improves the real-time performance of data processing, and enhances the security of energy consumption data during transmission and processing during the construction phase.

[0044] This application provides a computer device including a memory and a processor. The memory stores a computer program that can be executed by the processor. When the computer program is executed by the processor, it performs the method described above.

[0045] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of the application as defined herein, and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for carbon emission accounting in highway and waterway construction based on AI vision, characterized in that, The method includes: Using AI vision, images of the dials of water meters, electricity meters, and fuel meters during the construction phase of highway and waterway projects are captured and bound to virtual instrument files; Based on the completed binding of the watch face image, the AI ​​vision acquisition terminal is controlled to upload the watch face image data to the AI ​​recognition cloud platform according to the preset acquisition strategy; In the AI ​​recognition cloud platform, the dial image is recognized to generate structured energy consumption data; Based on the structured energy consumption data, the actual energy consumption of water, electricity and fuel under different instruments, construction areas and time granularities is obtained by accumulating adjacent energy consumption readings. Based on the actual energy consumption, and combined with a pre-set carbon emission factor database, the carbon emissions for the corresponding construction area and time granularity are calculated.

2. The method for carbon emission accounting of highway and waterway construction based on AI vision according to claim 1, characterized in that, The construction company's green construction management platform obtains the structured energy consumption data through a standardized data query interface, including: Call the project query interface to obtain a list of projects within the authorized scope and their corresponding project keys; Based on the project key, the instrument query interface is called to retrieve the instrument information of the instruments bound to the project in pages; Based on business needs, the meter reading data query interface is periodically called, and the project key, time range and meter identification filtering conditions are passed in to obtain the structured energy consumption data that is recognized by AI within the specified time period or the latest time.

3. The method for carbon emission accounting of highway and waterway construction based on AI vision according to claim 2, characterized in that, The interface call process includes at least one of the following: querying during busy data upload times, setting a delay time for fetching data, and using a retransmission mechanism.

4. The method for carbon emission accounting of highway and waterway construction based on AI vision according to claim 3, characterized in that, The structured energy consumption data returned by the data query interface provided by the AI ​​recognition cloud platform includes extended fields for data credibility and status judgment.

5. The method for carbon emission accounting of highway and waterway construction based on AI vision according to claim 1, characterized in that, The formula for calculating carbon emissions is as follows: ； in, Total carbon emissions; This refers to the consumption of water, electricity, and oil. The carbon emission factors are for water, electricity, and oil.

6. The method for carbon emission accounting of highway and waterway construction based on AI vision according to claim 1, characterized in that, The method further includes: The structured energy consumption data and the calculated carbon emissions are then visualized in a multi-dimensional manner. The construction company's green construction management platform uses data analysis models to automatically identify and issue early warnings for abnormal water, electricity, and oil consumption behaviors, as well as situations where carbon emission intensity exceeds standards.

7. A carbon emission accounting system for highway and waterway construction based on AI vision, employing the carbon emission accounting method for highway and waterway construction as described in any one of claims 1-6, characterized in that, include: The on-site perception module is used to collect images of the dials of water meters, electricity meters, and fuel meters during the construction phase of highway and waterway construction projects using AI vision, and to obtain the corresponding dial image data. The network transmission module is used to upload the dial image data to the cloud; The platform service module includes an AI recognition cloud platform, a green construction management platform, and an application display platform. The AI ​​recognition cloud platform is used to recognize and process the received dial image data to generate structured energy consumption data. The green construction management platform is used to calculate the corresponding carbon emissions based on the structured energy consumption data. The application display platform is used to display the carbon emissions.

8. The AI ​​vision-based carbon emission accounting system for highway and waterway construction according to claim 7, characterized in that, The data interaction between the AI ​​recognition cloud platform and the green construction management platform adopts secure communication based on the HTTPS protocol, and uses dual authentication and data isolation through customer keys and project keys.

9. The AI ​​vision-based carbon emission accounting system for highway and waterway construction according to claim 7, characterized in that, The system adopts an edge computing deployment approach, setting up localized edge computing nodes within the construction area of ​​highways and waterways; The dial image data collected by the field perception module is sent to the edge computing node through the local network; The edge computing node performs recognition processing on the dial image data, generates structured energy consumption data, and sends the structured energy consumption data to the platform service module.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-6.

Images