A remote monitoring and early warning device for electronic scale cheating behavior
Through the coordinated work of the remote monitoring and early warning device, the real-time and accuracy of cheating behavior monitoring of electronic scales is solved, efficient identification and early warning processing of diverse cheating methods is achieved, and the fairness and accuracy of electronic scales are improved. sex.
Patent Information
- Application Number
- CN202411127654.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-16
AI Technical Summary
The prior art is difficult to effectively monitor and prevent electronic scale cheating, especially in the diverse cheating methods and complex working environments, which affect the real-time and accuracy of monitoring.
A remote monitoring and early warning device was designed, including a monitoring sensor network deployment module, a real-time status monitoring module, an abnormal feature recognition module and a cheating behavior analysis and early warning module. By obtaining the specification attributes and placement area information of the electronic scale, the monitoring sensor network is deployed. , collect and encrypt upload data in real time, build multi-channel data exception handling, identify abnormal characteristics and trigger early warning responses.
The real-time and accuracy of electronic scale cheating behavior monitoring is improved. Through multi-sensor fusion monitoring and multi-channel abnormal feature recognition, timely identification and early warning processing of diverse cheating methods are achieved.
Smart Images

Figure CN118670498B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of electronic scales, and in particular to a remote monitoring and early warning device for cheating behavior in electronic scales. Background Art
[0002] Electronic scales are widely used in commercial, industrial and scientific fields to accurately measure the weight of items. However, with the development of technology, the cheating methods of electronic scales have become more and more complicated, which poses a severe challenge to market fairness and consumer rights protection. In order to effectively monitor and prevent these cheating behaviors, advanced technical means and systematic monitoring solutions are needed.
[0003] However, there are many ways to cheat on electronic scales, including hardware changes, software tampering, and even environmental interference. Different cheating methods require different detection methods, which increases the complexity of monitoring. In addition, the working environment of electronic scales is diverse, and the sensor must be able to work stably under various environmental conditions and quickly and accurately capture any abnormal changes. Summary of the invention
[0004] The present application provides a remote monitoring and early warning device for cheating behavior on an electronic scale, which is used to solve the technical problem in the prior art that the real-time and accuracy of cheating behavior monitoring are affected due to the diversity of cheating methods on electronic scales and the complexity of the working environment.
[0005] The present application provides a remote monitoring and early warning device for cheating behavior of an electronic scale, the device comprising: a monitoring sensor network deployment module, the monitoring sensor network deployment module is used to obtain specification attribute information and placement area information of a target electronic scale, perform monitoring demand analysis on the target electronic scale based on the specification attribute information and placement area information, and deploy and obtain an electronic scale monitoring sensor network; a real-time status monitoring module, the real-time status monitoring module is used to perform real-time monitoring of the target electronic scale based on the electronic scale monitoring sensor network, collect and obtain electronic scale application environment information and electronic scale working status information, and encrypt the electronic scale application environment information and the electronic scale working status information The electronic scale is uploaded to the cloud processing center; an abnormal feature recognition module is used to construct a multi-source data abnormality processing multi-channel through the cloud processing center, and perform abnormal recognition processing on the electronic scale application environment information and the electronic scale working status information based on the multi-source data abnormality processing multi-channel to obtain an abnormal feature data set of the electronic scale; a cheating behavior analysis and early warning module is used to perform cheating behavior analysis based on the electronic scale abnormal feature data set to obtain cheating behavior parameters of the electronic scale, trigger an early warning response mechanism according to the electronic scale cheating behavior parameters, and perform early warning verification processing on the target electronic scale through the early warning response mechanism.
[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0007] The present application provides a remote monitoring and early warning device for cheating behavior on an electronic scale, which relates to the technical field of electronic scales. By analyzing monitoring needs, an electronic scale monitoring sensor network is deployed to monitor a target electronic scale in real time, collect and obtain information about the application environment of the electronic scale and the working status of the electronic scale, and perform abnormal identification processing and cheating behavior analysis. An early warning response mechanism is triggered according to the cheating behavior parameters of the electronic scale and an early warning verification process is performed. The technical problem in the prior art that the real-time and accuracy of cheating behavior monitoring are affected by the diversity of cheating methods of electronic scales and the complexity of the working environment is solved, and the technical effect of improving the real-time and accuracy of cheating behavior monitoring on electronic scales is achieved through multi-sensor fusion monitoring and multi-channel abnormal feature recognition. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.
[0009] Figure 1 A schematic diagram of the structure of a remote monitoring and early warning device for cheating behavior on an electronic scale provided in an embodiment of the present application;
[0010] Figure 2 A schematic diagram of a process for constructing a multi-channel multi-source data anomaly processing in a remote monitoring and early warning device for electronic scale cheating provided in an embodiment of the present application;
[0011] Figure 3 A schematic diagram of a process for obtaining an abnormal feature data set of an electronic scale in a remote monitoring and early warning device for electronic scale cheating provided in an embodiment of the present application.
[0012] Explanation of the reference numerals: monitoring sensor network deployment module 11, real-time status monitoring module 12, abnormal feature recognition module 13, cheating behavior analysis and early warning module 14. DETAILED DESCRIPTION
[0013] The present application provides a remote monitoring and early warning device for cheating behavior on an electronic scale, which is used to solve the technical problem in the prior art that the real-time and accuracy of cheating behavior monitoring are affected due to the diversity of cheating methods on electronic scales and the complexity of the working environment.
[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.
[0016] Embodiment 1
[0017] like Figure 1 As shown, the present application provides a remote monitoring and early warning device for electronic scale cheating behavior, the device comprising:
[0018] The monitoring sensor network deployment module 11 is used to obtain the specification attribute information and placement area information of the target electronic scale, perform monitoring demand analysis on the target electronic scale based on the specification attribute information and placement area information, and deploy an electronic scale monitoring sensor network.
[0019] Furthermore, the monitoring sensor network deployment module 11 is also used to perform the following steps:
[0020] P11: Obtain the electronic scale sensor monitoring type, the electronic scale sensor monitoring type includes electromagnetic field sensor, vibration sensor, visual sensor, temperature and humidity sensor and anti-dismantling device; P12: Based on the specification attribute information, perform monitoring demand analysis on the electronic scale sensor monitoring type, and obtain the specification parameters of the monitoring sensor; P13: Perform layout optimization analysis on the electronic scale sensor monitoring type and the monitoring sensor specification parameters according to the placement area information, and determine the monitoring sensor layout parameters; P14: Based on the electronic scale sensor monitoring type, the monitoring sensor specification parameters and the monitoring sensor layout parameters, perform monitoring network deployment on the target electronic scale, and obtain the electronic scale monitoring sensor network.
[0021] It should be understood that the monitoring sensor network deployment module 11 of the present application is mainly responsible for obtaining the specification attribute information of the target electronic scale, including but not limited to the model, accuracy, range and other key parameters of the electronic scale. These characteristics directly determine the basic performance and working range of the electronic scale. At the same time, the placement area information of the electronic scale is obtained. This information covers the ambient temperature, humidity, electromagnetic environment and potential vibration sources, etc., which have a significant impact on the measurement accuracy and stability of the electronic scale. Furthermore, based on the specification attribute information and placement area information, the monitoring needs analysis of the target electronic scale is performed, and then the corresponding electronic scale monitoring sensor network is deployed according to the monitoring needs analysis results.
[0022] Furthermore, the specific process of deploying the electronic scale monitoring sensor network may be to first identify and determine the electronic scale sensor monitoring type suitable for the target electronic scale, wherein the electronic scale sensor monitoring type mainly includes an electromagnetic field sensor (used to detect electromagnetic interference in the surrounding environment), a vibration sensor (monitoring abnormal vibrations that may be caused by cheating), a visual sensor (used to capture images of the scale surface and the surrounding environment for subsequent analysis), a temperature and humidity sensor (monitoring the impact of environmental temperature and humidity changes on the performance of the electronic scale), and an anti-disassembly device, wherein the anti-disassembly device is a micro switch, which is a conventional anti-disassembly and anti-theft switch. Before the cover is removed, the micro switch is in a conductive state when the cover is abutted. Once the cover is removed, the micro switch is in a non-conductive state. Its main function is to provide a physical or electronic protection mechanism to prevent the device (such as an electronic scale) from being disassembled, tampered with, or destroyed without authorization. These sensor types together constitute the basis of the electronic scale monitoring sensor network.
[0023] Furthermore, the specification attribute information of the electronic scale, such as accuracy requirements, measuring range, etc., is used to conduct an in-depth monitoring demand analysis of the selected sensor type. In this process, the module will evaluate the applicability and necessity of each sensor under specific specification attributes, so as to determine the specific specification parameters of the required sensor, such as sensitivity, resolution, measurement range, etc. Then, after obtaining the sensor monitoring type and specification parameters, the module combines the placement area information to optimize the sensor's layout position, quantity, angle, etc., to ensure that the sensor network can fully and accurately cover the target electronic scale and its surrounding environment, while avoiding unnecessary redundancy and blind spots. For example, through layout optimization analysis, the optimal monitoring sensor layout parameters are determined, including the installation location, quantity, and layout method of the sensor, etc., to provide guidance for the subsequent monitoring network deployment.
[0024] Finally, based on the electronic scale sensor monitoring type, monitoring sensor specification parameters, and monitoring sensor layout parameters, a detailed monitoring network deployment is performed on the target electronic scale. During this process, the module will guide the installer to accurately install various sensors in the specified location according to the predetermined layout plan, and connect the sensors to the cloud processing center via wired or wireless means. After the deployment is completed, the electronic scale monitoring sensor network will be able to collect and transmit the electronic scale application environment information and working status information in real time, providing a solid data foundation for subsequent abnormal identification and cheating behavior analysis.
[0025] Furthermore, step P13 of the embodiment of the present application also includes:
[0026] P13-1: Divide the placement area information into applicable areas according to the electronic scale sensor monitoring type to obtain a sensor type applicable area set; P13-2: Perform coverage analysis on the sensor type applicable area set based on the monitoring sensor specification parameters to obtain multiple sensor layout plans, and the multiple sensor layout plans include sensor layout quantity and sensor layout position; P13-3: Perform layout simulation on the target electronic scale according to the multiple sensor layout plans to obtain multiple sensor layout monitoring effects; P13-4: Compare and optimize the multiple sensor layout plans based on the multiple sensor layout monitoring effects to determine the monitoring sensor layout parameters.
[0027] Specifically, the specific process of determining the monitoring sensor layout parameters through layout optimization analysis can be: first, according to the characteristics of the electronic scale sensor monitoring type (such as the sensitivity of the electromagnetic field sensor to the electromagnetic environment, the response of the vibration sensor to the vibration source, etc.), the placement area information is divided into detailed applicability areas, such as electromagnetic field sensors and vibration sensors are suitable for the center point or fulcrum area of the scale platform, stable and stable areas, etc. The placement area is divided into multiple sub-areas, each of which is marked as applicable or possibly restricted according to the type of sensor, thereby forming a sensor type applicable area set, providing preliminary spatial layout guidance for subsequent sensor layout.
[0028] Furthermore, based on the monitoring sensor specifications (such as measurement range, sensitivity, etc.), an in-depth coverage analysis is conducted on the applicable area set of sensor types. Through coverage analysis, the monitoring capabilities of different sensors at different locations are evaluated, and how they work together to achieve comprehensive coverage of the target electronic scale and its surrounding environment. For example, by calculating how many vibration sensors are needed in a certain area and their specific placement points, multiple sensor layout plans are generated, each of which details the number, location, and possible combinations of sensor layouts.
[0029] Furthermore, in order to verify the actual effects of the multiple sensor deployment schemes, the target electronic scale was simulated using three-dimensional simulation technology. In the simulation environment, different working scenarios and potential cheating behaviors were simulated to evaluate the performance of each sensor deployment scheme in terms of data collection, anomaly detection, etc. Through simulation, the monitoring effects of multiple sensor deployments were obtained, and these effects demonstrated the advantages and disadvantages of different schemes in a quantitative form (such as monitoring accuracy, response time, etc.).
[0030] Finally, based on the monitoring effects of multiple sensor deployments, a comprehensive comparison and optimization analysis of different deployment schemes was conducted. Taking into account multiple factors such as monitoring effect, cost-effectiveness, and installation difficulty, the schemes were screened and optimized through intelligent algorithms (such as genetic algorithms, particle swarm optimization algorithms, etc.) to determine the optimal monitoring sensor deployment parameters. These parameters not only ensure the comprehensiveness and accuracy of the monitoring network, but also take into account economy and feasibility. This laid a solid foundation for subsequent real-time status monitoring and cheating behavior analysis.
[0031] The real-time status monitoring module 12 is used to perform real-time monitoring of the target electronic scale based on the electronic scale monitoring sensor network, collect and obtain the electronic scale application environment information and the electronic scale working status information, and encrypt and upload the electronic scale application environment information and the electronic scale working status information to the cloud processing center.
[0032] Furthermore, the real-time status monitoring module 12 is also used to perform the following steps:
[0033] P21: Perform sensitive data identification on the electronic scale application environment information and the electronic scale working status information to obtain the electronic scale sensitive data information; P22: Rate the sensitivity of the electronic scale sensitive data information according to the electronic scale data security standard to determine the electronic scale sensitive data level; P23: Determine the data encryption transmission coefficient based on the electronic scale sensitive data level; P24: Encrypt the electronic scale application environment information and the electronic scale working status information based on the data encryption transmission coefficient and upload them to the cloud processing center.
[0034] Optionally, the real-time status monitoring module 12 of the present application is responsible for continuously monitoring the working status of the target electronic scale and its surrounding environment, obtaining the electronic scale application environment information and the electronic scale working status information, and ensuring the real-time and accuracy of the data. In the process of collecting and processing these data, the module also incorporates a data security protection mechanism to ensure that sensitive information is not leaked.
[0035] Specifically, the real-time status monitoring module 12 first performs a comprehensive scan on the collected electronic scale application environment information and electronic scale working status information, and uses a preset sensitive data identification algorithm or rule, such as keyword matching, pattern recognition, etc., to identify the part that may contain sensitive information, such as user privacy data, commercial secrets, etc. These identified data are sensitive data information of the electronic scale. This step is the first step to protect data security, which helps to process the data more targetedly later.
[0036] Furthermore, after sensitive data is identified, the sensitive data information is rated in detail according to the electronic scale data security standards (these standards may be formulated by industry specifications, laws and regulations, or internal corporate regulations). The rating process will consider multiple factors such as the nature of the data, the scope of impact, and the possible consequences of leakage, and perform numerical quantification and weighted comprehensive calculation of the factors to ultimately determine the level of each sensitive data item. This step provides an important basis for data encryption transmission and ensures that the encryption measures match the data sensitivity.
[0037] Furthermore, based on the sensitive data level, the corresponding data encryption transmission coefficient is determined. This coefficient determines the strength and complexity of data encryption, usually including the selection of encryption algorithm, key length and management method, etc. For example, for data with high sensitivity level, the module will select a more powerful encryption algorithm and a longer key to ensure the security of the data during transmission, while data with low sensitivity level can adopt relatively simple encryption measures.
[0038] Finally, according to the determined data encryption transmission coefficient, the electronic scale application environment information and electronic scale working status information are encrypted. The encryption process follows industry standards and practices to ensure that the data cannot be easily decrypted even if it is intercepted during transmission. The encrypted data is then securely uploaded to the cloud processing center for subsequent analysis and early warning. This step ensures that the data is not stolen or tampered with during transmission, ensures the security and integrity of the data, and provides a solid technical guarantee for the reliable operation of the electronic scale and the monitoring of cheating behavior.
[0039] The abnormal feature identification module 13 is used to construct a multi-source data abnormality processing multi-channel through the cloud processing center, perform abnormality identification processing on the electronic scale application environment information and the electronic scale working status information based on the multi-source data abnormality processing multi-channel, and obtain an electronic scale abnormal feature data set.
[0040] Further, such as Figure 2 As shown, the abnormal feature recognition module 13 is also used to perform the following steps:
[0041] P31: Construct a multi-source data processing channel architecture through the cloud processing center according to the electronic scale sensor monitoring type; P32: Perform pre-processing program analysis on the electronic scale monitoring data set based on the electronic scale sensor monitoring type to obtain a multi-source monitoring data pre-processing program set; P33: Perform anomaly recognition network training on the electronic scale monitoring data set according to the electronic scale sensor monitoring type to obtain a multi-source data anomaly feature recognition network set; P34: Based on the multi-source monitoring data pre-processing program set and the multi-source data anomaly feature recognition network set, perform processor configuration on the multi-source data processing channel architecture to construct the multi-source data anomaly processing multi-channel.
[0042] It should be understood that the abnormal feature identification module 13 of the present application is responsible for building an efficient multi-source data abnormality processing multi-channel in the cloud processing center to accurately identify the abnormal features of the electronic scale application environment and working status.
[0043] Among them, the construction process of the multi-source data exception processing multi-channel can be, first, in the cloud processing center, according to the diversity of electronic scale sensor monitoring types (such as electromagnetic field sensors, vibration sensors, visual sensors, temperature and humidity sensors, anti-dismantling devices, etc.), a corresponding multi-source data processing channel architecture is constructed. These channel architectures are used to process data sources from different sensors, such as electromagnetic field sensors, vibration sensors, visual sensors, and temperature and humidity sensors. Ensure that each type of data can be specially processed and analyzed, provide independent channels for different types of data streams, and ensure that they can be processed in parallel and efficiently.
[0044] Furthermore, a special preprocessing program is performed for the electronic scale monitoring data set of each sensor monitoring type. Remove noise from the data, fill in missing values, standardize data formats, etc. to improve the accuracy of subsequent anomaly identification. The preprocessing steps of data from different sensor sources are different. For example, the data from the vibration sensor may require noise reduction, while the data from the visual sensor may require image enhancement and edge detection. Subsequently, according to the monitoring type of the electronic scale sensor, the electronic scale monitoring data set is trained with anomaly recognition networks to obtain a multi-source data anomaly feature recognition network set. The anomaly recognition network uses machine learning and deep learning algorithms to train models to identify abnormal features in various types of data. The anomaly feature recognition models of data from different sensor sources are different. For example, a convolutional neural network (CNN) can be used to process visual sensor data, and a long short-term memory network (LSTM) can be used to process time series data.
[0045] Furthermore, based on the set of multi-source monitoring data preprocessors and the set of multi-source data abnormal feature recognition networks, the multi-source data processing channel architecture is configured with processors. This step seamlessly integrates the preprocessors and abnormal recognition networks into each processing channel to form a complete multi-source data abnormality processing multi-channel. These processing channels can efficiently process and analyze data from different sensors, identify abnormal features, and generate electronic scale abnormal feature data sets. For example, by integrating preprocessors and abnormal recognition networks, the system can detect abnormal use of electronic scales in real time, such as abnormal vibrations or environmental electromagnetic interference. It can provide strong support for subsequent cheating behavior warnings.
[0046] Further, such as Figure 3 As shown, the abnormal feature recognition module 13 is also used to perform the following steps:
[0047] P35: Map the electronic scale application environment information and the electronic scale working status information with the multi-source data exception processing multi-channel to obtain the electronic scale matching channel data set; P36: Perform exception recognition processing on the electronic scale matching channel data set based on the multi-source data exception processing multi-channel to obtain a multi-channel exception feature data set; P37: Integrate the multi-channel exception feature data set in time sequence to obtain a multi-channel exception feature sequence data set; P38: Perform interactive verification based on the multi-channel exception feature sequence data set to obtain the electronic scale exception feature data set.
[0048] In a possible embodiment of the present application, the specific process of obtaining an abnormal feature data set of an electronic scale through abnormal identification processing may be to first perform shunt mapping on the received electronic scale application environment information and electronic scale working status information and the pre-built multi-source data abnormality processing multi-channel. The purpose of shunt mapping is to guide different types of data to corresponding processing channels respectively. For example, the data of the electromagnetic field sensor will be mapped to the channel for processing electromagnetic interference, and the data of the vibration sensor will be mapped to the channel for processing physical vibration. Through this shunt mapping, it can be ensured that each type of data can be processed in the most suitable channel, thereby improving the accuracy and efficiency of data processing.
[0049] Furthermore, based on the multi-source data anomaly processing multi-channel, the electronic scale matching channel data set is processed for anomaly recognition. The anomaly recognition network in each channel will perform feature extraction and anomaly detection on the incoming data according to its trained model. These networks can automatically identify abnormal patterns in the data, such as abnormal fluctuations, mutation points, etc., and record these abnormal features. For example, the data of the visual sensor can identify abnormal image patterns through image processing algorithms, while the data of the vibration sensor can detect abnormal vibrations through spectrum analysis. After this step, the module will obtain a multi-channel abnormal feature data set, each of which contains the abnormal features detected by the corresponding channel.
[0050] Furthermore, in order to more comprehensively understand the abnormal behavior of the electronic scale, the module arranges and integrates the multi-channel abnormal feature data sets in time series. The purpose of time series arrangement and integration is to synchronize the abnormal feature data of different channels according to the time axis for subsequent comprehensive analysis. Through time series arrangement and integration, the module obtains a multi-channel abnormal feature sequence data set, which clearly shows the changes in the abnormal features of the electronic scale in different time periods. This step ensures that all abnormal features can be compared and analyzed within a unified time frame, thereby improving the accuracy and comprehensiveness of abnormal identification.
[0051] Finally, based on the multi-channel abnormal feature sequence data set, interactive verification is performed to obtain the electronic scale abnormal feature data set. Interactive verification will interactively verify the abnormal features of the same sequence and different channels. Through data comparison and correlation analysis between different channels, the mutual influence and constraint relationship between different channels, as well as the continuity and consistency of abnormal features in time, further confirm and screen the abnormal features of the electronic scale, remove false alarms and noise interference, and obtain a more accurate and reliable electronic scale abnormal feature data set. For example, if the electromagnetic field sensor and the vibration sensor detect anomalies at the same time, the system can determine whether these anomalies are related through interactive verification, thereby improving the reliability and accuracy of anomaly detection.
[0052] Furthermore, step P38 of the embodiment of the present application also includes:
[0053] P38-1: According to the multi-channel abnormal feature sequence data set, determine the abnormal visual feature timing data set and the abnormal feature timing data set of the remaining channels; P38-2: Use the abnormal visual feature data set as the first priority verification feature, and sort the credibility of the abnormal feature timing data sets of the remaining channels to obtain the verification priority of the remaining channels; P38-3: Interactively verify the abnormal feature timing data sets of the remaining channels according to the verification priority of the remaining channels to obtain the abnormal feature data sets of the remaining channels of the electronic scale; P38-4: Verify and supplement the abnormal feature data sets of the remaining channels of the electronic scale based on the first priority verification feature to obtain the abnormal feature data set of the electronic scale.
[0054] Specifically, the specific process of obtaining the electronic scale abnormal feature data set through interactive verification may be, first, according to the characteristics of the multi-channel abnormal feature sequence data set, subdividing it into an abnormal visual feature time series data set and abnormal feature time series data sets of other channels. The abnormal visual feature time series data set usually contains abnormal changes in the image or video data captured by the visual sensor, such as visual anomalies caused by cheating. The remaining channels may include other types of sensor data such as electromagnetic field, vibration, temperature, etc.
[0055] Furthermore, because visual anomalies are often more intuitive and easy to verify, the abnormal visual feature data set is regarded as the first priority verification feature. At the same time, the credibility of the remaining channel abnormal feature time series data sets is sorted to determine their verification priority. This sorting process can sort the electromagnetic field abnormal feature data, vibration sensor abnormal feature data, and temperature and humidity abnormal feature data according to data accuracy, sensitivity, etc., and then verify and determine the abnormal features in order from high to low, aiming to improve verification efficiency and accuracy.
[0056] Furthermore, according to the verification priority of the remaining channels, the abnormal feature time series data sets of the remaining channels are cross-verified. In this process, the module will consider the data correlation and mutual influence between different channels, and confirm or exclude potential abnormal features through cross-comparison and comprehensive analysis. Interactive verification techniques include data fusion, association rule mining, etc., which help the module to extract more reliable and consistent abnormal information from multi-source data. For example, if both the vibration sensor and the electromagnetic field sensor detect an abnormality, but the temperature and humidity sensor does not detect a change, the verification priority can be used to determine whether these anomalies have a common cause, thereby improving the accuracy of detection. Then, the abnormal feature data sets of the remaining channels of the electronic scale are obtained, which have been preliminarily screened and verified.
[0057] Finally, based on the first-priority visual features, the abnormal feature data sets of the remaining channels are verified and supplemented to obtain the abnormal feature data set of the electronic scale. The monitoring data of other sensors may be interfered with by cheating, but the monitoring data of visual sensors is more intuitive and relatively less interfered with. Therefore, when other monitoring abnormal features are interfered with, the visual abnormal feature data can be used for verification and supplementation. The visual features can be used as the first-priority verification features to provide an important reference for the data of other channels. For example, if the visual features show obvious abnormal changes, and the feature data of other channels also have abnormalities, but the degree is unclear, the authenticity and severity of these abnormalities can be more accurately confirmed through the supplementary verification of visual features, providing a solid data foundation for subsequent cheating behavior analysis and early warning.
[0058] The cheating behavior analysis and early warning module 14 is used to perform cheating behavior analysis based on the electronic scale abnormal feature data set to obtain electronic scale cheating behavior parameters, trigger an early warning response mechanism according to the electronic scale cheating behavior parameters, and perform early warning verification processing on the target electronic scale through the early warning response mechanism.
[0059] Furthermore, the cheating behavior analysis and early warning module 14 is also used to perform the following steps:
[0060] P41: Constructing an electronic scale cheating behavior analysis network, the electronic scale cheating behavior analysis network includes a cheating behavior type analysis subnetwork and a cheating behavior degree analysis subnetwork; P42: Based on the electronic scale cheating behavior analysis network, performing cheating behavior analysis on the electronic scale abnormal feature data set to obtain cheating behavior type parameters and cheating behavior degree parameters; P43: Obtaining the electronic scale cheating behavior parameters based on the cheating behavior type parameters and cheating behavior degree parameters.
[0061] Optionally, the cheating behavior analysis and early warning module 14 of the present application is responsible for deeply mining the potential cheating behaviors in the abnormal feature data set of the electronic scale, and triggering the corresponding early warning response mechanism accordingly. Specifically, firstly, based on artificial intelligence algorithms such as deep learning and machine learning, the characteristic patterns of cheating behaviors are automatically learned and extracted from a large amount of data, and an electronic scale cheating behavior analysis network is constructed. The network consists of two core sub-networks: a cheating behavior type analysis sub-network and a cheating behavior degree analysis sub-network. The cheating behavior type analysis sub-network is used to identify the types of cheating behaviors of electronic scales, such as increasing weight, reducing weight, tampering with data, etc., and the cheating behavior degree analysis sub-network is used to evaluate the severity of cheating behaviors, such as cheating frequency, cheating amplitude, etc.
[0062] Furthermore, based on the electronic scale cheating behavior analysis network, a detailed cheating behavior analysis is performed on the electronic scale abnormal feature data set. Through the cheating behavior type analysis subnetwork, the cheating behavior type in the abnormal feature data is identified and classified to obtain the cheating behavior type parameter. Through the cheating behavior degree analysis subnetwork, the severity of each cheating behavior is evaluated to obtain the cheating behavior degree parameter. For example, the frequency of data falsification and the numerical deviation of each falsification, as well as the specific magnitude of weight tampering and the impact on the overall weighing result are analyzed.
[0063] Finally, based on the cheating behavior type parameters and cheating behavior degree parameters, the final electronic scale cheating behavior parameters are obtained through comprehensive analysis. These parameters specifically describe the cheating behavior of the target electronic scale, including cheating type, behavior pattern, severity, etc. For example, if a certain electronic scale frequently tampered with the weight and the value deviation was large, its cheating behavior parameters would be displayed as a high-risk type. Through this step, the module can accurately grasp the cheating situation of the electronic scale and provide accurate data support for the subsequent early warning response mechanism.
[0064] After obtaining the cheating behavior parameters of the electronic scale, the early warning response mechanism will trigger corresponding early warning measures based on these parameters. For example, for high-risk cheating behaviors, the system can immediately notify relevant managers to conduct on-site verification or automatically record and store relevant data for subsequent investigation. In this way, cheating behaviors can be discovered and analyzed in a timely manner, and quickly responded and handled to ensure the fairness and accuracy of the use of electronic scales.
[0065] In summary, the embodiments of the present application have at least the following technical effects:
[0066] The monitoring demand analysis module of this application obtains the specification attributes and placement area information of the target electronic scale, deploys a suitable monitoring sensor network, and ensures that all working conditions and environmental information of the electronic scale can be fully covered. The real-time status monitoring module can collect the application environment information and working status information of the electronic scale in real time, and encrypt the data and upload it to the cloud processing center to ensure the security of the data during transmission. The abnormal feature recognition module builds a multi-source data abnormality processing multi-channel through the cloud processing center, which can efficiently process and analyze various types of data and accurately identify abnormal features. The cheating behavior analysis and early warning module obtains detailed cheating behavior parameters by analyzing the abnormal feature data set of the electronic scale, and triggers the early warning response mechanism based on these parameters to ensure that the early warning verification and processing can be carried out in a timely and accurate manner. The technical effect of improving the real-time and accuracy of electronic scale cheating behavior monitoring through multi-sensor fusion monitoring and multi-channel abnormal feature recognition has been achieved.
[0067] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0068] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
[0069] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.
Claims
1. A remote monitoring and early warning device for electronic scale cheating, characterized in that: The device comprises: A monitoring sensor network deployment module, the monitoring sensor network deployment module is used to obtain specification attribute information and placement area information of the target electronic scale, perform monitoring demand analysis on the target electronic scale based on the specification attribute information and placement area information, and deploy an electronic scale monitoring sensor network; A real-time status monitoring module, which is used to perform real-time monitoring of the target electronic scale based on the electronic scale monitoring sensor network, collect and obtain the electronic scale application environment information and the electronic scale working status information, and encrypt and upload the electronic scale application environment information and the electronic scale working status information to a cloud processing center; An abnormal feature recognition module, wherein the abnormal feature recognition module is used to construct a multi-source data abnormality processing multi-channel through the cloud processing center, perform abnormality recognition processing on the electronic scale application environment information and the electronic scale working status information based on the multi-source data abnormality processing multi-channel, and obtain an abnormal feature data set of the electronic scale; A cheating behavior analysis and early warning module, the cheating behavior analysis and early warning module is used to perform cheating behavior analysis based on the electronic scale abnormal feature data set to obtain electronic scale cheating behavior parameters, trigger an early warning response mechanism according to the electronic scale cheating behavior parameters, and perform early warning verification processing on the target electronic scale through the early warning response mechanism; The deployment obtains an electronic scale monitoring sensor network, including: Obtaining electronic scale sensor monitoring types, wherein the electronic scale sensor monitoring types include electromagnetic field sensors, vibration sensors, visual sensors, temperature and humidity sensors, and anti-disassembly devices; Based on the specification attribute information, a monitoring demand analysis is performed on the electronic scale sensor monitoring type to obtain the monitoring sensor specification parameters; Performing a layout optimization analysis on the monitoring type of the electronic scale sensor and the specification parameters of the monitoring sensor according to the placement area information to determine the monitoring sensor layout parameters; Based on the electronic scale sensor monitoring type, the monitoring sensor specification parameters and the monitoring sensor deployment parameters, a monitoring network is deployed for the target electronic scale to obtain the electronic scale monitoring sensor network; The construction of multi-source data exception processing multi-channel includes: Constructing a multi-source data processing channel architecture through the cloud processing center according to the electronic scale sensor monitoring type; Based on the electronic scale sensor monitoring type, the electronic scale monitoring data set is respectively subjected to preprocessing program analysis to obtain a multi-source monitoring data preprocessing program set; According to the electronic scale sensor monitoring type, the electronic scale monitoring data set is respectively trained with anomaly recognition networks to obtain a multi-source data anomaly feature recognition network set; Based on the multi-source monitoring data pre-processing program set and the multi-source data anomaly feature recognition network set, the multi-source data processing channel architecture is configured with a processing program to construct the multi-source data anomaly processing multi-channel.
2. The remote monitoring and early warning device for electronic scale cheating behavior according to claim 1, characterized in that: The step of determining the monitoring sensor deployment parameters includes: Divide the placement area information into applicable areas according to the monitoring type of the electronic scale sensor to obtain a sensor type applicable area set; Performing a coverage analysis on the applicable area set of the sensor type based on the specification parameters of the monitoring sensor to obtain a plurality of sensor deployment schemes, wherein the plurality of sensor deployment schemes include the number of sensors deployed and the sensor deployment positions; Performing a layout simulation on the target electronic scale according to the multiple sensor layout schemes to obtain multiple sensor layout monitoring effects; Based on the monitoring effects of the multiple sensor deployments, the multiple sensor deployment schemes are compared and optimized to determine the monitoring sensor deployment parameters.
3. The remote monitoring and early warning device for electronic scale cheating behavior according to claim 1, characterized in that: The method of encrypting and uploading the electronic scale application environment information and the electronic scale working status information to a cloud processing center includes: Performing sensitive data identification on the electronic scale application environment information and the electronic scale working status information to obtain the electronic scale sensitive data information; Rating the sensitivity of the sensitive data information of the electronic scale according to the electronic scale data security standard to determine the sensitive data level of the electronic scale; Determining a data encryption transmission coefficient according to the sensitive data level of the electronic scale; Based on the data encryption transmission coefficient, the electronic scale application environment information and the electronic scale working status information are encrypted and uploaded to the cloud processing center.
4. The remote monitoring and early warning device for electronic scale cheating as claimed in claim 1, characterized in that: The step of obtaining an abnormal feature data set of an electronic scale includes: The electronic scale application environment information and the electronic scale working status information are shunted and mapped with the multi-source data exception processing multi-channel to obtain an electronic scale matching channel data set; Based on the multi-source data anomaly processing multi-channel, anomaly identification processing is performed on the electronic scale matching channel data set to obtain a multi-channel anomaly feature data set; Arranging and integrating the multi-channel abnormal feature data sets in time sequence to obtain a multi-channel abnormal feature sequence data set; Interactive verification is performed based on the multi-channel abnormal feature sequence data set to obtain the electronic scale abnormal feature data set.
5. The remote monitoring and early warning device for electronic scale cheating as claimed in claim 4, characterized in that: The step of obtaining the abnormal feature data set of the electronic scale comprises: Determine an abnormal visual feature time series data set and abnormal feature time series data sets of other channels according to the multi-channel abnormal feature sequence data set; The abnormal visual feature time series data set is used as the first priority verification feature, and the abnormal feature time series data sets of the remaining channels are sorted by credibility to obtain the verification priorities of the remaining channels; Interactively verify the abnormal feature time series data sets of the remaining channels according to the verification priorities of the remaining channels to obtain the abnormal feature data sets of the remaining channels of the electronic scale; The abnormal feature data sets of other channels of the electronic scale are verified and supplemented based on the first priority verification feature to obtain the abnormal feature data set of the electronic scale.
6. The remote monitoring and early warning device for electronic scale cheating behavior according to claim 1, characterized in that: The obtaining of the electronic scale cheating behavior parameters includes: Constructing an electronic scale cheating behavior analysis network, wherein the electronic scale cheating behavior analysis network includes a cheating behavior type analysis subnetwork and a cheating behavior degree analysis subnetwork; Based on the electronic scale cheating behavior analysis network, cheating behavior analysis is performed on the electronic scale abnormal feature data set to obtain cheating behavior type parameters and cheating behavior degree parameters; and according to the cheating behavior type parameters and cheating behavior degree parameters, the electronic scale cheating behavior parameters are obtained.
