Fair scale monitoring method and system based on internet-of-things consensus discrimination

Abstract

The present invention relates to the technical field of fair scale monitoring, and particularly to a fair scale monitoring method and system based on Internet-of-Things consensus discrimination. The method comprises the following steps: data parameter collection, involving: collecting sensor data, timestamps and environment parameters; data preprocessing, involving: data cleaning and data conversion; consensus discrimination, involving: the establishment of a benchmark, comparative analysis, and consensus determination; evaluation of the accuracy of an electronic scale; result output and feedback, involving: result display and anomaly feedback; and continuous optimization and improvement, involving: model updating and device maintenance. The beneficial effects lie in: the fair scale monitoring method and system based on Internet-of-Things consensus discrimination provided in the present invention realize continuous and automatic monitoring of an electronic scale and greatly improve the monitoring efficiency by means of collecting data in real time using an Internet-of-Things sensor and by using automated data processing and analysis technology.

Description

A fair scale monitoring method and system based on Internet of Things consensus judgment Technical Field

[0001] The present invention relates to the technical field of fair scale monitoring, and in particular to a fair scale monitoring method and system based on Internet of Things consensus judgment. Background Art

[0002] With the rapid development of the Internet of Things (IoT), various smart devices have been widely used in daily life and commercial activities. As a key measurement tool in commercial transactions, the accuracy and fairness of electronic scales are directly related to the rights and interests of consumers and the reputation of merchants.

[0003] However, traditional electronic scale monitoring methods often rely on manual inspection and regular calibration, which is not only inefficient but also difficult to ensure long-term stability and accuracy.

[0004] In recent years, electronic scale monitoring methods based on the Internet of Things (IoT) have gained increasing attention. These methods collect real-time data from electronic scales through IoT sensors and utilize advanced data analysis techniques to process and analyze the data, enabling automated monitoring and evaluation of electronic scales. However, existing IoT electronic scale monitoring methods still face challenges, such as data processing complexity, accuracy of monitoring results, and system scalability. Summary of the Invention

[0005] The purpose of the present invention is to provide a fair scale monitoring method and system based on Internet of Things consensus judgment to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a fair scale monitoring method based on Internet of Things consensus judgment, the method comprising the following steps:

[0007] Data parameter collection, including collecting sensor data, timestamps, and environmental parameters;

[0008] Data preprocessing, including data cleaning and data conversion;

[0009] consensus judgment, including benchmarking, comparative analysis, and consensus judgment;

[0010] Evaluate the accuracy of electronic scales;

[0011] Result output and feedback, including result display and exception feedback;

[0012] Continuous optimization and improvement, including model updates and equipment maintenance.

[0013] Preferably, the specific operations of collecting the data parameters include:

[0014] Sensor data: The IoT weighing sensor collects weight data from the electronic scale in real time. The weight data is represented by a digital signal. Sensor ID: Each sensor has a unique identifier that is used to distinguish different sensors.

[0015] Timestamp, which records the exact time when each weight data point was collected, expressed in UNIX timestamp, in seconds or milliseconds;

[0016] Environmental parameters: collect the temperature data of the environment where the electronic scale is located, in degrees Celsius or Fahrenheit; collect the environmental humidity data, expressed as a percentage.

[0017] Preferably, the specific operations of the data preprocessing include:

[0018] Data cleaning, removal of outliers, and removal of abnormal data based on preset rules that exceed the normal weight range;

[0019] Data conversion and format conversion ensure that all data is converted into a unified format, such as CSV or JSON, to facilitate subsequent data processing and analysis.

[0020] Preferably, the specific operations of the consensus determination include:

[0021] Establishing a benchmark: Using calibration equipment to collect a series of weight data of known accuracy to serve as a benchmark.

[0022] Comparative analysis and difference value calculation: compare the monitored electronic scale data with the benchmark data point by point and calculate the difference between the two;

[0023] Consensus judgment, threshold setting: set a threshold range of difference value ±0.05 kg; judgment logic: if the difference value is within the threshold range, the data of this point is judged as "consensus".

[0024] Preferably, the specific operations of evaluating the accuracy of the electronic scale include:

[0025] Mass calculation: Mass (m) equals force (F) divided by gravitational acceleration (g), where (m) is the mass, (F) is the force measured by the sensor, and (g) is the gravitational acceleration (approximately 9.8 m / s²).

[0026] Mean absolute error, the mean absolute error (MAE) is equal to the average of the absolute values ​​of the differences between the true value and the predicted value of each measurement point;

[0027] Root Mean Square Error, The root mean square error (RMSE) is equal to the square root of the average of the squares of the differences between the true value and the predicted value at each measurement point.

[0028] Preferably, the specific operations of the result output and feedback include:

[0029] Result display and data visualization: the monitoring results are displayed in the form of charts, such as line charts, scatter charts, etc., so that users can intuitively understand the accuracy of the electronic scale;

[0030] Abnormal feedback and alarm system: when abnormal data is detected, the alarm system will be triggered to promptly notify relevant personnel for processing.

[0031] The specific operations of continuous optimization and improvement include:

[0032] Model updates and threshold adjustments: Based on long-term monitoring data and user feedback, the threshold range for consensus judgment will be adjusted in a timely manner;

[0033] Equipment maintenance, regular calibration, regular calibration of electronic scales to ensure their long-term stability.

[0034] A system for monitoring a fair scale based on consensus judgment of the Internet of Things, the system comprising a data collection module, a data preprocessing module, a judgment module, an evaluation module, an output module, and an optimization module;

[0035] Data collection module, used for data parameter collection, including collecting sensor data, timestamps and environmental parameters;

[0036] Data preprocessing module, used for data preprocessing, including data cleaning and data conversion;

[0037] The discrimination module is used for consensus discrimination, including benchmark establishment, comparative analysis, and consensus determination;

[0038] Evaluation module, used to evaluate the accuracy of electronic scales;

[0039] Output module, used for result output and feedback, including result display and exception feedback;

[0040] Optimization module for continuous optimization and improvement, including model updates and equipment maintenance

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The proposed fair scale monitoring method and system based on IoT consensus recognition collects data in real time through IoT sensors and utilizes automated data processing and analysis techniques to achieve continuous and automatic monitoring of electronic scales, significantly improving monitoring efficiency. Consensus recognition technology combines baseline data with actual monitoring data to accurately assess the accuracy of electronic scales. Furthermore, metrics such as mean absolute error (MAE) and root mean square error (RMSE) are used to quantitatively analyze monitoring results and ensure their accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] FIG1 is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0044] In order to clearly and completely describe the objectives and technical solutions of the present invention and make the advantages more clearly understood, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are part of the embodiments of the present invention, not all of them, and are only used to explain the embodiments of the present invention, not to limit the embodiments of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention. Example 1

[0045] Referring to FIG1 , the present invention provides a technical solution: a fair scale monitoring method based on Internet of Things consensus judgment, the method comprising the following steps:

[0046] Data parameter collection, including collecting sensor data, timestamps, and environmental parameters;

[0047] Sensor data: The IoT weighing sensor collects weight data from the electronic scale in real time. The weight data is represented by a digital signal. Sensor ID: Each sensor has a unique identifier that is used to distinguish different sensors.

[0048] Timestamp, which records the exact time when each weight data point was collected, expressed in UNIX timestamp, in seconds or milliseconds;

[0049] Environmental parameters: collect the temperature data of the environment where the electronic scale is located, in degrees Celsius or Fahrenheit; collect the environmental humidity data, expressed as a percentage.

[0050] Data preprocessing, including data cleaning and data conversion;

[0051] Data cleaning, removal of outliers, and removal of abnormal data based on preset rules that exceed the normal weight range;

[0052] Data conversion and format conversion ensure that all data is converted into a unified format, such as CSV or JSON, to facilitate subsequent data processing and analysis.

[0053] consensus judgment, including benchmarking, comparative analysis, and consensus judgment;

[0054] Establishing a benchmark: Using calibration equipment to collect a series of weight data of known accuracy to serve as a benchmark.

[0055] Comparative analysis and difference value calculation: compare the monitored electronic scale data with the benchmark data point by point and calculate the difference between the two;

[0056] Consensus judgment, threshold setting: set a threshold range of difference value ±0.05 kg; judgment logic: if the difference value is within the threshold range, the data of this point is judged as "consensus".

[0057] Evaluate the accuracy of electronic scales; mass calculation: mass (m) equals force (F) divided by acceleration due to gravity (g), where (m) is mass, (F) is the force measured by the sensor, and (g) is the acceleration due to gravity (approximately 9.8 m / s²).

[0058] Mean absolute error, the mean absolute error (MAE) is equal to the average of the absolute values ​​of the differences between the true value and the predicted value of each measurement point;

[0059] Root Mean Square Error, The root mean square error (RMSE) is equal to the square root of the average of the squares of the differences between the true value and the predicted value at each measurement point.

[0060] Result output and feedback, including result display and exception feedback;

[0061] Result display and data visualization: the monitoring results are displayed in the form of charts, such as line charts, scatter charts, etc., so that users can intuitively understand the accuracy of the electronic scale;

[0062] Abnormal feedback and alarm system: when abnormal data is detected, the alarm system will be triggered to promptly notify relevant personnel for processing.

[0063] Continuous optimization and improvement, including model updates and equipment maintenance;

[0064] Model updates and threshold adjustments: Based on long-term monitoring data and user feedback, the threshold range for consensus judgment will be adjusted in a timely manner;

[0065] Equipment maintenance, regular calibration, regular calibration of electronic scales to ensure their long-term stability. Example 2

[0066] Based on the first embodiment, the new equipment deployment and initial calibration are proposed

[0067] background:

[0068] A supermarket purchased a batch of new electronic scales before opening and planned to use a fair scale monitoring method based on IoT consensus judgment to ensure the accuracy of the electronic scales.

[0069] operate:

[0070] Use the Data Collection Module to connect to the sensors of all new scales and collect sensor data, timestamps, and environmental parameters.

[0071] In the data preprocessing module, the newly collected data is cleaned and converted to ensure that the data format is unified and outliers are removed.

[0072] In the discrimination module, calibration equipment is used to establish baseline data for the new electronic scale and set the initial consensus discrimination threshold.

[0073] The evaluation module uses the initial data to calculate the mean absolute error (MAE) and root mean square error (RMSE) of the electronic scale to evaluate the initial accuracy of the electronic scale.

[0074] The evaluation results are displayed to supermarket managers through the output module, and the alarm system is triggered when anomalies are detected.

[0075] During the continuous optimization and improvement phase, supermarket managers decide whether additional calibration or adjustments are needed based on the initial assessment results. Example 3

[0076] Based on the first embodiment, daily monitoring and exception handling are proposed

[0077] background:

[0078] A farmers' market has been using a fair scale monitoring system based on IoT consensus for some time and wants to continue using the system to ensure the daily accuracy of electronic scales.

[0079] operate:

[0080] The data collection module continuously collects sensor data, timestamps, and environmental parameters.

[0081] The data preprocessing module automatically cleans and transforms newly collected data.

[0082] The discrimination module regularly compares and analyzes the collected data with the benchmark data and determines whether the data reaches a consensus.

[0083] The evaluation module periodically calculates the MAE and RMSE of the scale to assess its daily accuracy.

[0084] If the output module detects abnormal data, it triggers the alarm system and notifies market management personnel for processing.

[0085] Market managers perform necessary equipment maintenance or calibration based on the alarm information. Example 4

[0086] Based on the first embodiment, the model update and threshold adjustment are proposed.

[0087] background:

[0088] After a period of use, the fair scale monitoring system based on IoT consensus judgment has accumulated a large amount of data, and managers hope to update the model and adjust the threshold based on this data.

[0089] operate:

[0090] Managers analyze long-term monitoring data to understand the accuracy and stability of electronic scales.

[0091] According to the analysis results, the threshold range of consensus judgment is adjusted in the optimization module to better adapt to the current usage environment.

[0092] If necessary, managers can also update the benchmark data in the discrimination module to reflect the latest calibration results.

[0093] The updated models and thresholds are applied to the system to further improve the accuracy and efficiency of monitoring. Example 5

[0094] Based on the first embodiment, multi-site deployment and centralized management are proposed

[0095] background:

[0096] A supermarket chain plans to deploy a fair scale monitoring system based on IoT consensus judgment in multiple branches and hopes to achieve centralized management.

[0097] operate:

[0098] Install data collection modules in each branch and connect all modules to the central server.

[0099] The central server is responsible for collecting data from all branches and performing unified data preprocessing, consensus judgment, evaluation and output.

[0100] Managers can view the electronic scale monitoring results of all branches in real time through the central server and conduct centralized management.

[0101] If an electronic scale in a branch malfunctions, the central server will trigger the alarm system and notify the branch's manager to handle the situation.

[0102] Managers can uniformly optimize and improve the electronic scales of all branches based on the data analysis results of the central server. Example 6

[0103] Based on the first embodiment, a system for monitoring a fair scale based on consensus judgment of the Internet of Things is proposed. The system consists of a data collection module, a data preprocessing module, a judgment module, an evaluation module, an output module and an optimization module.

[0104] Data collection module, used for data parameter collection, including collecting sensor data, timestamps and environmental parameters;

[0105] Data preprocessing module, used for data preprocessing, including data cleaning and data conversion;

[0106] The discrimination module is used for consensus discrimination, including benchmark establishment, comparative analysis, and consensus determination;

[0107] Evaluation module, used to evaluate the accuracy of electronic scales;

[0108] Output module, used for result output and feedback, including result display and exception feedback;

[0109] Optimization module for continuous optimization and improvement, including model updates and equipment maintenance.

[0110] The first to sixth embodiments achieve the following effects:

[0111] Improve monitoring efficiency: Through real-time data collection through IoT sensors and the use of automated data processing and analysis technology, continuous and automatic monitoring of electronic scales can be achieved, greatly improving monitoring efficiency.

[0112] Guaranteed monitoring accuracy: Consensus-based discrimination technology combines benchmark data with actual monitoring data to accurately assess the accuracy of electronic scales. Furthermore, metrics such as mean absolute error (MAE) and root mean square error (RMSE) are used to quantitatively analyze monitoring results to ensure their accuracy.

[0113] Improve system scalability: This approach uses a modular design to facilitate system expansion and upgrades. New sensors and data processing modules can be easily added to meet monitoring needs in different scenarios.

[0114] Centralized management: Electronic scales at multiple branches are centrally managed through a central server, enabling unified data collection, processing, and display. Managers can view monitoring results from each branch in real time and conduct centralized management and optimization.

[0115] Timely detection and resolution of anomalies: When abnormal data is detected, the system automatically triggers an alarm system and promptly notifies relevant personnel to handle the situation. This helps to identify and resolve issues promptly, avoiding unnecessary losses to business transactions.

[0116] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A fair scale monitoring method based on Internet of Things consensus judgment, characterized by: The method comprises the following steps: Data parameter collection, including collecting sensor data, timestamps, and environmental parameters; Data preprocessing, including data cleaning and data conversion; Consensus determination, including benchmarking, comparative analysis, and consensus determination; Evaluate the accuracy of electronic scales; Result output and feedback, including result display and abnormal feedback; Continuous optimization and improvement, including model updates and equipment maintenance.

2. According to claim 1, a fair scale monitoring method based on Internet of Things consensus judgment is characterized by: The specific operations of data parameter collection include: Sensor data: The weight data on the electronic scale is collected in real time through the IoT weighing sensor. The weight data is represented in the form of a digital signal. Sensor ID: Each sensor has a unique identifier to distinguish different sensors. Timestamp, which records the exact time when each weight data point was collected, expressed in UNIX timestamp, in seconds or milliseconds; Environmental parameters: collect the temperature data of the environment where the electronic scale is located, in degrees Celsius or Fahrenheit; collect the environmental humidity data, expressed as a percentage.

3. According to claim 1, a fair scale monitoring method based on Internet of Things consensus judgment is characterized by: The specific operations of the data preprocessing include: Data cleaning, removal of outliers, and removal of abnormal data according to preset rules that exceed the normal weight range; Data conversion and format conversion ensure that all data is converted into a unified format, such as CSV or JSON, to facilitate subsequent data processing and analysis.

4. The fair scale monitoring method based on Internet of Things consensus judgment according to claim 1 is characterized by: The specific operations of the consensus determination include: Establishing a Benchmark, Benchmark Weight Data: Using calibration equipment to collect a series of weight data of known accuracy as a benchmark; Comparative analysis and difference value calculation: compare the monitored electronic scale data with the benchmark data point by point and calculate the difference between the two; Consensus judgment, threshold setting: set a threshold range of difference value ±0.05 kg; judgment logic: if the difference value is within the threshold range, the data at this point is judged as "consensus".

5. The fair scale monitoring method based on Internet of Things consensus judgment according to claim 1 is characterized by: The specific operations of evaluating the accuracy of the electronic scale include: Mass calculation, mass (m) equals force (F) divided by gravity acceleration (g), (m) is the mass, (F) is the force measured by the sensor, and (g) is the acceleration due to gravity (about 9.8 m / s²); Mean absolute error, the mean absolute error (MAE) is equal to the average of the absolute values ​​of the difference between the true value and the predicted value of each measurement point; Root Mean Square Error,The root mean square error (RMSE) is equal to the square root of the average of the squares of the differences between the true value and the predicted value at each measurement point.

6. The fair scale monitoring method based on Internet of Things consensus judgment according to claim 1 is characterized by: The specific operations of the result output and feedback include: Result display and data visualization: the monitoring results are displayed in the form of charts, such as line charts, scatter charts, etc., so that users can intuitively understand the accuracy of the electronic scale; Abnormal feedback, alarm system, when abnormal data is monitored, the alarm system is triggered to notify relevant personnel in time for processing.

7. The fair scale monitoring method based on Internet of Things consensus judgment according to claim 1 is characterized by: The specific operations of continuous optimization and improvement include: Model update, threshold adjustment, timely adjustment of consensus judgment threshold range based on long-term monitoring data and user feedback; Equipment maintenance, regular calibration, regular calibration of electronic scales to ensure its long-term stability.

8. A system for monitoring a fair scale based on consensus judgment of the Internet of Things according to any one of claims 1 to 7, characterized in that: The system consists of a data collection module, a data preprocessing module, a discrimination module, an evaluation module, an output module and an optimization module; Data collection module, used for data parameter collection, including collecting sensor data, timestamps and environmental parameters; Data preprocessing module, used for data preprocessing, including data cleaning and data conversion; The discrimination module is used for consensus discrimination, including benchmark establishment, comparative analysis, and consensus determination; Evaluation module, used to evaluate the accuracy of electronic scales; Output module, used for result output and feedback, including result display and abnormal feedback; Optimization module for continuous optimization and improvement, including model updates and equipment maintenance.

Images