Intelligent weight checking system and intelligent weight checking method

Abstract

The invention provides an intelligent weight detection system and an intelligent weight detection method, and relates to the technical field of intelligent monitoring systems.The intelligent weight detection system comprises a weight detection equipment unit used for obtaining basic data of a to-be-detected vehicle, and the basic data comprise current load data and image data; the data processing unit is used for identifying the image data based on a deep learning model to obtain an image identification result, and dividing the load data according to the image identification result and a preset target to obtain temporary category data; and the data analysis unit is used for comprehensively analyzing the temporary category data and the image recognition result to obtain a final analysis result. According to the invention, the automatic data processing and analysis process is realized, so that the manual operation is reduced, and the overall working efficiency is improved. And the accuracy of the data can be ensured through high-precision weighing equipment and a deep learning model.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring systems, and in particular to an intelligent weighing system and an intelligent weighing method. Background Art

[0002] With the rapid development of the transportation industry, the problem of vehicle overloading has become increasingly prominent, which not only damages road infrastructure, but also seriously threatens road traffic safety. In order to effectively monitor and manage vehicle loads, intelligent weighing systems have emerged. Intelligent weighing systems use automation technology to improve weighing efficiency and accuracy.

[0003] Traditional intelligent weighing systems use manual operation combined with basic automation equipment, such as floor scales and basic weighing sensors. These systems have certain capabilities in data processing and analysis, but are generally average in terms of accuracy and real-time performance, which is insufficient under the high standards of modern logistics and traffic management. With the development of technology, the demand for higher accuracy and real-time performance is growing, and traditional weighing systems have certain limitations in the refined management of vehicle loads. Summary of the invention

[0004] The problem solved by the present invention is one or more of the above-mentioned problems in the prior art.

[0005] In order to solve the above problems, the present invention provides an intelligent weighing system and an intelligent weighing method.

[0006] In a first aspect, the present invention provides an intelligent weight checking system, comprising:

[0007] A weighing device unit, used to obtain basic data of the vehicle to be tested, wherein the basic data includes current load data and image data;

[0008] A data processing unit, configured to recognize the image data based on a deep learning model to obtain an image recognition result, and to classify the load data according to the image recognition result and a preset target to obtain temporary category data;

[0009] The data analysis unit is used to comprehensively analyze the temporary category data and the image recognition result to obtain a final analysis result.

[0010] Optionally, the weight checking device unit includes a weighing device and an image acquisition device;

[0011] The weighing device is used to obtain the current load data of the vehicle to be tested;

[0012] The image acquisition device is used to acquire image data of the vehicle to be tested, and the image data includes license plate data and driver face image data.

[0013] Optionally, the deep learning model includes a multi-scale convolution module, a depth separable convolution module and a multi-task output module, and the image data is recognized based on the deep learning model to obtain an image recognition result, including:

[0014] Preprocessing the image data to obtain temporary image data;

[0015] Extracting features from the temporary image data through the multi-scale convolution module to obtain multi-scale feature data;

[0016] Processing the multi-scale feature data through a depth-wise separable convolution module to obtain temporary feature data;

[0017] The temporary feature data is identified by the multi-task output module to obtain the image recognition result, which includes vehicle code data, vehicle type data, license plate data and cargo type data.

[0018] Optionally, the classifying the load data according to the image recognition result and a preset target to obtain temporary category data includes:

[0019] Associating the image recognition result with the load data, and classifying the associated data based on the preset target to obtain the temporary category data;

[0020] Among them, the preset targets include overweight thresholds and safety standards.

[0021] Optionally, the performing a comprehensive analysis on the temporary category data and the image recognition result to obtain a final analysis result includes:

[0022] Fusing the temporary category data and the image recognition result to obtain fused data;

[0023] The historical data of the vehicle to be tested is obtained, and the historical data and the fused data are comprehensively analyzed to obtain the final analysis result.

[0024] Optionally, the performing comprehensive analysis on the historical data and the fused data to obtain the final analysis result includes:

[0025] Get preset analysis indicators;

[0026] Based on the preset analysis index, the historical data and the fused data are analyzed to obtain the final analysis result.

[0027] Optionally, the preset analysis indicators include a compliance indicator, an overload rate indicator, and a behavior recognition indicator. Based on the preset analysis indicators, the historical data and the fusion data are analyzed to obtain the final analysis result, including:

[0028] When the preset analysis indicator is the compliance indicator, calculating the change data of the fusion data and the historical data, and judging the compliance risk of the vehicle to be tested based on the change data;

[0029] When the preset analysis index is the overload rate index, the overload rate of the vehicle to be tested is calculated according to the historical data, and compared with the fused data to determine the change trend of the vehicle to be tested;

[0030] When the preset analysis indicator is the behavior recognition indicator, the historical data is divided according to the set time interval to obtain time series data, a specific overload pattern is determined based on the time series data, and the fused data is analyzed according to the specific overload pattern to obtain the specific overload pattern currently corresponding to the vehicle under test.

[0031] Optionally, the intelligent weighing system further includes an encryption unit, a display unit and a storage unit;

[0032] The encryption unit is used to encrypt the data in the process;

[0033] The display unit is used for visual display to the user;

[0034] The storage unit is used to store the historical data of the intelligent weighing system.

[0035] Optionally, the intelligent weighing system further comprises an alarm unit for issuing an alarm message and notifying management personnel when an abnormal situation occurs in the vehicle to be tested.

[0036] In a second aspect, the present invention provides an intelligent weighing method, which is applied to the intelligent weighing system, and the intelligent weighing method comprises:

[0037] Obtaining basic data of the vehicle to be tested, wherein the basic data includes current load data and image data;

[0038] Recognize the image data based on the deep learning model to obtain an image recognition result, and classify the load data according to the image recognition result and a preset target to obtain temporary category data;

[0039] The temporary category data and the image recognition result are comprehensively analyzed to obtain a final analysis result.

[0040] The intelligent weighing system and intelligent weighing method of the present invention have the beneficial effect that the intelligent weighing system realizes the automated and intelligent management of vehicle load by combining advanced weighing technology and deep learning algorithms.

[0041] The weighing equipment unit can use high-precision weighing sensors that can measure the real-time load data of the vehicle and have fast response capabilities to meet the needs of dynamic weighing. Then, for example, high-resolution cameras are used to capture images of the vehicle. These image data are crucial for subsequent deep learning recognition. Accurate vehicle load data helps to ensure the accuracy and reliability of the weighing process, and image data collection provides a rich source of information for the deep learning model, laying the foundation for subsequent automated processing and analysis.

[0042] The data processing unit uses the trained deep learning model to process the image data, identify key information such as vehicle code, type, license plate number and cargo type, and divide the load data into different categories based on the image recognition results and preset goals (such as overweight threshold and safety standards), forming temporary category data. The introduction of the deep learning model has greatly improved the accuracy of image recognition, reduced manual intervention, and increased processing speed. And by setting preset goals, the system can automatically classify vehicles to provide support for subsequent data analysis and decision-making.

[0043] Finally, the data analysis unit analyzes the temporary category data and image recognition results. For example, the historical data of the vehicle to be tested can be obtained and compared with the temporary category data and image recognition to obtain the final analysis results. Through the comparative analysis of historical data, the system can identify potential problems and risks and provide data support for management decisions.

[0044] Therefore, the present invention realizes an automated data processing and analysis process to reduce manual operations and improve overall work efficiency. The accuracy of the data can be ensured through high-precision weighing equipment and deep learning models. During system operation, through real-time monitoring and analysis, the system can promptly detect safety hazards such as overloading and take measures to prevent accidents. And through comprehensive analysis results, it can provide strong decision-making support for management, which helps to optimize logistics and traffic management strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is one of the structural schematic diagrams of an intelligent weighing system according to an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of deep learning model data processing according to an embodiment of the present invention;

[0047] Figure 3This is a second structural diagram of an intelligent weighing system according to an embodiment of the present invention.

[0048] Figure 4 The figure is a flow chart of an intelligent weighing method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be interpreted as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0050] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0051] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to"; the term "based on" means "based at least in part on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0052] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0053] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0054] like Figure 1 As shown, an intelligent weight checking system provided by an embodiment of the present invention includes:

[0055] The weighing device unit is used to obtain basic data of the vehicle to be tested, and the basic data includes current load data and image data.

[0056] Specifically, the weight checking equipment unit may include a weighing device, such as a high-precision weighing sensor and a matching weighing meter, which can accurately measure the weight of the vehicle. It may also include image acquisition equipment, such as a high-definition camera, and may also include auxiliary equipment such as fill lights and protective covers. Through high-precision weighing sensors, the system can obtain accurate vehicle load data, thereby improving the accuracy of the weighing process. The acquisition of image data provides the system with rich information, allowing the system to perform more comprehensive data analysis and vehicle identification.

[0057] A data processing unit is used to identify the image data based on a deep learning model to obtain an image recognition result, and to classify the load data according to the image recognition result and a preset target to obtain temporary category data.

[0058] Specifically, the image data is first preprocessed, such as denoising: using filtering technology to remove noise from the image and improve image quality. Enhancement: adjusting the contrast, brightness and color of the image to make the characteristics of the vehicle more obvious. Standardization: standardizing the image size and pixel value to meet the input requirements of the deep learning model. The deep learning model is then used to identify the image data to obtain image recognition results, such as vehicle code, type, license plate number and cargo type. Finally, according to the preset target settings, such as overweight threshold, safety standards, etc., the load data is divided into different categories according to the image recognition results and preset targets to obtain temporary category data, such as compliance, overload, special cargo, etc.

[0059] By using deep learning models, the characteristics of vehicles can be accurately identified, improving the accuracy of data processing. At the same time, automated image recognition and load data division reduce manual intervention and improve the automation level of the entire weighing process.

[0060] The data analysis unit is used to comprehensively analyze the temporary category data and the image recognition result to obtain a final analysis result.

[0061] Specifically, the data analysis unit plays the role of converting the initially processed data into useful information and decision support in the intelligent weighing system. The comprehensive analysis process includes statistical analysis of temporary category data, such as calculating average load, frequency distribution, overload rate, etc. It is also possible to analyze the change trend of load data over time through historical data, identify any abnormal patterns or potential risks, and obtain the final analysis results, which help managers make more informed decisions.

[0062] Through comprehensive analysis, the system can provide a more comprehensive perspective and help managers make more accurate business decisions. At the same time, the system's real-time monitoring and analysis capabilities enable the system to promptly detect potential risks, such as overloaded vehicles, so that preventive measures can be taken, thereby ensuring that all vehicles comply with legal and regulatory requirements and reduce violations. The results of data analysis help optimize logistics and transportation processes and improve overall operational efficiency.

[0063] Suppose a company needs to ensure that its transport vehicles are not overloaded to avoid fines and ensure driver safety. When the vehicle passes through the weighing station, the system collects load data and vehicle images. The deep learning model is used to identify the vehicle type, license plate number, and cargo type. The system fuses the recognition results with the load data to form temporary category data. The data analysis unit performs statistical and trend analysis on the fused data to identify overloaded vehicles. Finally, the system generates a report showing the overload rate, compliance assessment, and safety risk assessment. Finally, the company adjusts the transportation plan based on the report to ensure that the vehicle is not overloaded and improve transportation safety. Through this intelligent weighing system, real-time monitoring and management of vehicle loads can be achieved to ensure the compliance and safety of the transportation process, while improving operational efficiency.

[0064] In this embodiment, the intelligent weighing system realizes the automated and intelligent management of vehicle load by combining advanced weighing technology and deep learning algorithms.

[0065] The weighing equipment unit can use high-precision weighing sensors that can measure the real-time load data of the vehicle and have fast response capabilities to meet the needs of dynamic weighing. Then, for example, high-resolution cameras are used to capture images of the vehicle. These image data are crucial for subsequent deep learning recognition. Accurate vehicle load data helps to ensure the accuracy and reliability of the weighing process, and image data collection provides a rich source of information for the deep learning model, laying the foundation for subsequent automated processing and analysis.

[0066] The data processing unit uses the trained deep learning model to process the image data, identify key information such as vehicle code, type, license plate number and cargo type, and divide the load data into different categories based on the image recognition results and preset goals (such as overweight threshold and safety standards), forming temporary category data. The introduction of the deep learning model has greatly improved the accuracy of image recognition, reduced manual intervention, and increased processing speed. And by setting preset goals, the system can automatically classify vehicles to provide support for subsequent data analysis and decision-making.

[0067] Finally, the data analysis unit analyzes the temporary category data and image recognition results. For example, the historical data of the vehicle to be tested can be obtained and compared with the temporary category data and image recognition to obtain the final analysis results. Through the comparative analysis of historical data, the system can identify potential problems and risks and provide data support for management decisions.

[0068] Therefore, the present invention realizes an automated data processing and analysis process to reduce manual operations and improve overall work efficiency. The accuracy of the data can be ensured through high-precision weighing equipment and deep learning models. During system operation, through real-time monitoring and analysis, the system can promptly detect safety hazards such as overloading and take measures to prevent accidents. And through comprehensive analysis results, it can provide strong decision-making support for management, which helps to optimize logistics and traffic management strategies.

[0069] Optionally, the weight checking device unit includes a weighing device and an image acquisition device;

[0070] The weighing device is used to obtain the current load data of the vehicle to be tested;

[0071] The image acquisition device is used to acquire image data of the vehicle to be tested, and the image data includes license plate data and driver face image data.

[0072] Alternatively, if Figure 2 As shown, the deep learning model includes a multi-scale convolution module, a deep separable convolution module and a multi-task output module. The image data is recognized based on the deep learning model to obtain an image recognition result, including:

[0073] Preprocessing the image data to obtain temporary image data;

[0074] Extracting features from the temporary image data through the multi-scale convolution module to obtain multi-scale feature data;

[0075] Processing the multi-scale feature data through a depth-wise separable convolution module to obtain temporary feature data;

[0076] The temporary feature data is identified by the multi-task output module to obtain the image recognition result, which includes vehicle code data, vehicle type data, license plate data and cargo type data.

[0077] Specifically, in the intelligent weight inspection system, the application of deep learning models has significantly improved the accuracy and efficiency of image data recognition. First, the image data is preprocessed to improve the quality of the image data and make it more suitable for processing by the deep learning model. Preprocessing often includes adjusting the brightness and contrast of the image, cropping unnecessary edges, scaling the image to a uniform size, and normalizing pixel values ​​to obtain temporary image data, which is ready to be input into the deep learning model.

[0078] The deep learning model includes a multi-scale convolution module, a depth-separable convolution module, and a multi-task output module. The multi-scale convolution module is used to extract features of images at different scales to capture information from local to global. Usually, convolution operations are performed on temporary image data through convolution kernels of different sizes to generate multi-scale feature maps and obtain multi-scale feature data, which contain feature representations of images at different levels.

[0079] The depthwise separable convolution module further processes multi-scale feature data to reduce the computational complexity of the model. Multi-scale feature data can be processed using depthwise separable convolution (such as that used in MobileNet) to achieve dimensionality reduction and abstraction of features to obtain temporary feature data, which is more compact and rich in information.

[0080] Finally, through the multi-task output module: realize multi-task recognition of image data, including vehicle code, type, license plate and cargo type. Multiple output branches can be designed, each branch is responsible for different recognition tasks, sharing the underlying feature extraction network, and obtaining image recognition results, including vehicle code data, vehicle type data, license plate data and cargo type data.

[0081] Multi-scale convolution can capture local and global features of the image and improve recognition accuracy. Depth-wise separable convolution reduces the computational complexity of the model, making it more efficient. Multi-task learning enables the model to handle multiple tasks at the same time, improving the generalization ability of the model. At the same time, the pre-processing and optimized feature extraction process speeds up the processing of image data.

[0082] Optionally, the classifying the load data according to the image recognition result and a preset target to obtain temporary category data includes:

[0083] Associating the image recognition result with the load data, and classifying the associated data based on the preset target to obtain the temporary category data;

[0084] Among them, the preset targets include overweight thresholds and safety standards.

[0085] Specifically, in the intelligent weighing system, the division of load data according to image recognition results and preset targets is a key step, which allows the system to classify and manage different types of vehicle loads. The image recognition results are associated with the load data to form a set of comprehensive data containing vehicle identity information and load information. According to the setting of preset targets, such as laws and regulations, safety standards and business needs, overweight thresholds and safety standards are set. These preset targets are used to evaluate whether the vehicle's load is compliant.

[0086] Based on the preset goals, the associated data is divided and the vehicle load data is classified into different temporary categories, such as "compliant", "overloaded", "special cargo", etc. Finally, the load data of each category is further analyzed, such as calculating the average load, detecting overload, and statistical frequency.

[0087] The system can ensure that the loads of all vehicles comply with laws, regulations and safety standards, reducing violations. And by promptly identifying overloaded vehicles, the system helps reduce the risk of traffic accidents and improve road safety.

[0088] In some embodiments, when a vehicle enters a weighing station, a high-definition camera captures an image of the vehicle and a weighing device measures the vehicle's load. The deep learning model identifies the vehicle type as a "truck," the license plate number as "ABC1234," and the cargo type as "fragile." The system associates the recognition result with the load data and obtains the vehicle's load as "10 tons." The system evaluates the vehicle's load based on a preset overweight threshold (such as "8 tons") and safety standards, and classifies the vehicle into an "overloaded" category because the load exceeds the preset overweight threshold. The system notifies the manager and requires the vehicle to unload the excess cargo and to perform special treatment on "fragile goods."

[0089] Optionally, the performing a comprehensive analysis on the temporary category data and the image recognition result to obtain a final analysis result includes:

[0090] Fusing the temporary category data and the image recognition result to obtain fused data;

[0091] The historical data of the vehicle to be tested is obtained, and the historical data and the fused data are comprehensively analyzed to obtain the final analysis result.

[0092] Optionally, the performing comprehensive analysis on the historical data and the fused data to obtain the final analysis result includes:

[0093] Get preset analysis indicators;

[0094] Based on the preset analysis index, the historical data and the fused data are analyzed to obtain the final analysis result.

[0095] Optionally, the preset analysis indicators include a compliance indicator, an overload rate indicator, and a behavior recognition indicator. Based on the preset analysis indicators, the historical data and the fusion data are analyzed to obtain the final analysis result, including:

[0096] When the preset analysis indicator is the compliance indicator, calculating the change data of the fusion data and the historical data, and judging the compliance risk of the vehicle to be tested based on the change data;

[0097] When the preset analysis index is the overload rate index, the overload rate of the vehicle to be tested is calculated according to the historical data, and compared with the fused data to determine the change trend of the vehicle to be tested;

[0098] When the preset analysis indicator is the behavior recognition indicator, the historical data is divided according to the set time interval to obtain time series data, a specific overload pattern is determined based on the time series data, and the fused data is analyzed according to the specific overload pattern to obtain the specific overload pattern currently corresponding to the vehicle under test.

[0099] Specifically, first, the temporary category data and image recognition results need to be integrated. The goal of this process is to form a unified data set that contains information about the vehicle to be tested, such as vehicle type, gross weight, and compliance status. Such fusion can provide basic data for subsequent analysis.

[0100] The historical data of the vehicle to be tested is then extracted from the database. This data usually includes the vehicle's past compliance records and load information. This historical data will be used to compare and analyze with the newly acquired fused data to understand the changing trends of vehicle behavior.

[0101] In the final comprehensive analysis phase, it is very important to set some preset analysis indicators. These indicators usually include compliance indicators, overload rate indicators, and behavior recognition indicators. Through these indicators, the safety and compliance of the vehicle can be comprehensively evaluated.

[0102] Analysis based on preset analysis indicators:

[0103] Compliance indicator analysis, by comparing the newly integrated data with historical data, can calculate the compliance changes of the vehicle. If the current status is "compliant" and the historical status is "overloaded", it means that the vehicle has improved and the compliance risk has decreased.

[0104] Overload rate indicator analysis: The overload rate of a vehicle can be calculated from historical data. For example, if the vehicle has been overloaded many times in the past period of time, its overload rate can be obtained. If the current fused data shows an improving trend, it can be judged that the risk of the vehicle has been reduced.

[0105] Behavior recognition indicator analysis divides historical data according to set time intervals (such as daily or weekly) to form time series data. By analyzing this data, specific overloading patterns can be identified. For example, it is found that overloading is more frequent in certain time periods. By comparing the current fused data with these patterns, it can be determined whether the vehicle meets the specific overloading pattern.

[0106] After the above steps, the final analysis report generated will include information such as compliance assessment, overload rate trend and behavior pattern recognition. This information provides managers with a comprehensive perspective to help them make more informed decisions.

[0107] Through such comprehensive analysis, the compliance of vehicles can be improved, and problems can be discovered and solved in a timely manner. Potential overloading risks can be warned, thereby reducing the possibility of accidents. At the same time, data support can be provided for management decisions to help optimize transportation policies and management methods. That is, this analysis process can more comprehensively understand the changes in vehicle behavior through the comprehensive use of temporary category data, image recognition results and historical data, thereby ensuring traffic safety and compliance with regulations. This data-driven analysis method effectively improves the accuracy and efficiency of transportation safety management.

[0108] Alternatively, if Figure 3 As shown, the intelligent weighing system further includes an encryption unit, a display unit and a storage unit;

[0109] The encryption unit is used to encrypt the data in the process;

[0110] The display unit is used for visual display to the user;

[0111] The storage unit is used to store the historical data of the intelligent weighing system.

[0112] Optionally, the intelligent weighing system further comprises an alarm unit for issuing an alarm message and notifying management personnel when an abnormal situation occurs in the vehicle to be tested.

[0113] Specifically, the design of the intelligent weight inspection system can effectively improve the monitoring and management capabilities of the vehicles to be tested. The encryption unit is responsible for encrypting all data in the processing process to ensure the security of the data during transmission and storage. This can prevent unauthorized access and data leakage, and protect user privacy and business secrets. For example, when the system collects the weight, vehicle type and other sensitive information of the vehicle, these data are stored in the system in encrypted form after passing through the encryption unit.

[0114] The display unit provides users with a visual display of data, including real-time data, historical records, abnormal alarms, etc. Through an intuitive graphical interface, users can quickly understand the status of the vehicle and related information. For example, the display unit can use touch screen technology, and users can view the weight of the vehicle to be tested, compliance status, and received alarm messages such as "overload alarm" in real time.

[0115] The storage unit is used to store the historical data of the intelligent weighing system, including the vehicle's past weight records, compliance records and alarm history. These data are not only used for subsequent analysis, but also provide decision support for managers.

[0116] The alarm unit is responsible for monitoring the status of the vehicle under test and issuing an alarm message to promptly notify the management personnel when any abnormal situation (such as overloading, illegal driving, etc.) is found. For example, when the system detects that the load of a vehicle exceeds the set compliance range, the alarm unit will trigger an alarm and notify relevant personnel via SMS or email.

[0117] In some embodiments, the system workflow can be summarized as follows: 1. Data collection: collect relevant information such as the weight and type of the vehicle to be tested through sensors. 2. Data encryption: The collected data is encrypted by the encryption unit to ensure data security. 3. Data storage: The encrypted data is stored in the storage unit for subsequent reference and analysis. 4. Visual display: Real-time data and historical records are displayed to the user through the display unit to facilitate user monitoring and judgment. 5. Abnormal monitoring: The system continuously monitors the status of the vehicle to be tested, and immediately issues an alarm through the alarm unit when an abnormal situation occurs, and notifies relevant management personnel.

[0118] Through the design of the above units, that is, through encryption processing, sensitive data is protected and the security of the system is enhanced. At the same time, the display unit provides real-time data display, allowing users to respond quickly and effectively reduce the occurrence of violations such as overloading. And the historical data saved by the storage unit provides a basis for future trend analysis and decision support, helping managers optimize transportation plans. Finally, the alarm unit ensures that quick action can be taken in abnormal situations to reduce safety hazards and ensure transportation safety.

[0119] like Figure 4As shown, an intelligent weight detection method provided by an embodiment of the present invention includes:

[0120] Obtaining basic data of the vehicle to be tested, wherein the basic data includes current load data and image data;

[0121] Recognize the image data based on the deep learning model to obtain an image recognition result, and classify the load data according to the image recognition result and a preset target to obtain temporary category data;

[0122] The temporary category data and the image recognition result are comprehensively analyzed to obtain a final analysis result.

[0123] The advantages of the intelligent weighing method of this embodiment over the prior art are the same as the advantages of the above-mentioned intelligent weighing system over the prior art, which will not be repeated here.

[0124] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. An intelligent weight checking system, characterized in that: include: A weighing device unit, used to obtain basic data of the vehicle to be tested, wherein the basic data includes current load data and image data; A data processing unit, configured to recognize the image data based on a deep learning model to obtain an image recognition result, and to classify the load data according to the image recognition result and a preset target to obtain temporary category data; The data analysis unit is used to comprehensively analyze the temporary category data and the image recognition result to obtain a final analysis result.

2. The intelligent weighing system according to claim 1, characterized in that: The weighing equipment unit includes a weighing device and an image acquisition device; The weighing device is used to obtain the current load data of the vehicle to be tested; The image acquisition device is used to acquire image data of the vehicle to be tested, and the image data includes license plate data and driver face image data.

3. The intelligent weighing system according to claim 2 is characterized in that: The deep learning model includes a multi-scale convolution module, a depth separable convolution module and a multi-task output module. The image data is recognized based on the deep learning model to obtain an image recognition result, including: Preprocessing the image data to obtain temporary image data; Extracting features from the temporary image data through the multi-scale convolution module to obtain multi-scale feature data; Processing the multi-scale feature data through a depth-wise separable convolution module to obtain temporary feature data; The temporary feature data is identified by the multi-task output module to obtain the image recognition result, which includes vehicle code data, vehicle type data, license plate data and cargo type data.

4. The intelligent weighing system according to claim 3 is characterized in that: The step of classifying the load data according to the image recognition result and the preset target to obtain temporary category data includes: Associating the image recognition result with the load data, and classifying the associated data based on the preset target to obtain the temporary category data; Among them, the preset targets include overweight thresholds and safety standards.

5. The intelligent weighing system according to claim 1, characterized in that: The comprehensive analysis of the temporary category data and the image recognition result to obtain the final analysis result includes: Fusing the temporary category data and the image recognition result to obtain fused data; The historical data of the vehicle to be tested is obtained, and the historical data and the fused data are comprehensively analyzed to obtain the final analysis result.

6. The intelligent weighing system according to claim 5, characterized in that: The comprehensive analysis of the historical data and the fused data to obtain the final analysis result includes: Get preset analysis indicators; Based on the preset analysis index, the historical data and the fused data are analyzed to obtain the final analysis result.

7. The intelligent weighing system according to claim 6, characterized in that: The preset analysis indicators include compliance indicators, overload rate indicators and behavior recognition indicators. Based on the preset analysis indicators, the historical data and the fusion data are analyzed to obtain the final analysis results, including: When the preset analysis indicator is the compliance indicator, calculating the change data of the fused data and the historical data, and judging the compliance risk of the vehicle to be tested based on the change data; When the preset analysis index is the overload rate index, the overload rate of the vehicle to be tested is calculated according to the historical data, and compared with the fused data to determine the change trend of the vehicle to be tested; When the preset analysis indicator is the behavior recognition indicator, the historical data is divided according to the set time interval to obtain time series data, a specific overload pattern is determined based on the time series data, and the fused data is analyzed according to the specific overload pattern to obtain the specific overload pattern currently corresponding to the vehicle under test.

8. The intelligent weighing system according to claim 1, characterized in that: It also includes an encryption unit, a display unit and a storage unit; The encryption unit is used to encrypt the data in the process; The display unit is used for visual display to the user; The storage unit is used to store the historical data of the intelligent weighing system.

9. The intelligent weighing system according to claim 1, characterized in that: It also includes an alarm unit for issuing an alarm message and notifying the management personnel when the vehicle to be tested has an abnormal situation.

10. An intelligent weighing method, characterized in that: Applied to the intelligent weighing system according to any one of claims 1 to 9, the intelligent weighing method comprises: Obtaining basic data of the vehicle to be tested, wherein the basic data includes current load data and image data; Recognize the image data based on the deep learning model to obtain an image recognition result, and classify the load data according to the image recognition result and a preset target to obtain temporary category data; The temporary category data and the image recognition result are comprehensively analyzed to obtain a final analysis result.

Images