Intelligent cold chain management method and system based on Internet and multi-dimensional analysis

Abstract

The invention relates to the technical field of cold chain logistics management, in particular to an intelligent cold chain management method and system based on the Internet and multi-dimensional analysis, and the method comprises the following steps: S1, collecting multi-dimensional data in a cold chain transportation process in real time, including temperature data, humidity data, vibration data, position data and state data of a transportation vehicle; s2, preprocessing the collected multi-dimensional data; s3, abnormal conditions in the cold chain transportation process are analyzed, and an abnormal analysis report is generated; s4, judging whether abnormal conditions such as temperature exceeding, humidity abnormity or excessive vibration occur in the cold chain transportation process or not, and recording specific information of occurrence of the abnormal conditions; and S5, sending the corresponding abnormal information to terminal equipment of related management personnel. According to the invention, through combination of multi-dimensional data acquisition and a big data analysis technology, comprehensive real-time monitoring and automatic abnormity early warning of the cold chain transportation process are realized, and the management efficiency is significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cold chain logistics management, and in particular to an intelligent cold chain management method and system based on the Internet and multi-dimensional analysis. Background Art

[0002] With the rapid development of global trade and logistics, cold chain transportation plays a vital role in many industries, especially in the transportation of food, medicine and biological products. The core of cold chain transportation is to ensure that environmental factors such as temperature and humidity are maintained within the set standard range during transportation to avoid the degradation or failure of commodity quality due to environmental changes. At present, data monitoring in cold chain transportation mainly relies on traditional temperature and humidity recording instruments. These devices usually require manual recording and manual inspection. Once an abnormal situation occurs, it is difficult for managers to be informed and respond in time. In addition, traditional cold chain management methods have great limitations in data processing and analysis, and often cannot achieve real-time data collection, processing and decision-making, resulting in low management efficiency and even failure to identify and prevent potential risks in time.

[0003] Most of the existing cold chain management systems are single data monitoring platforms, which cannot realize the comprehensive collection and analysis of multi-dimensional data; traditional cold chain management usually relies on limited sensor equipment to record temperature and humidity, and lacks real-time monitoring of multi-dimensional data such as vibration, location, and transportation vehicle status; in addition, the existing system usually cannot effectively use advanced data analysis technology to conduct in-depth mining of collected data, resulting in the failure to timely warn of abnormal situations during transportation, increasing the risks and losses in cold chain transportation. Therefore, there is an urgent need for an intelligent cold chain management method and system based on the Internet and multi-dimensional data analysis to solve the above problems. Summary of the invention

[0004] Based on the above objectives, the present invention provides an intelligent cold chain management method and system based on the Internet and multi-dimensional analysis.

[0005] An intelligent cold chain management method based on the Internet and multi-dimensional analysis includes the following steps: S1: Connect multiple sensor devices through the Internet to collect multi-dimensional data in the cold chain transportation process in real time, including temperature data, humidity data, vibration data, location data and status data of transportation vehicles, and transmit the multi-dimensional data to the cloud data storage platform through wireless network; S2: In the cloud data storage platform, the collected multi-dimensional data is pre-processed, including removing invalid data, filling missing data and data standardization; S3: Based on the cloud data storage platform, use big data analysis technology to perform real-time analysis on pre-processed multi-dimensional data, extract the correlation between the data, analyze the abnormal conditions in the cold chain transportation process, and generate an abnormal analysis report; S4: According to the abnormal analysis report, set multiple abnormal judgment thresholds to determine whether abnormal conditions such as excessive temperature, abnormal humidity or excessive vibration occur during cold chain transportation, and record specific information on the occurrence of abnormal conditions; S5: If an abnormal situation is determined in S4, the corresponding abnormal information is immediately sent to the terminal device of the relevant manager through the cloud data storage platform so that the manager can take management measures according to the specific abnormal information.

[0006] Optionally, the S1 specifically includes: S11: Connect multiple sensor devices to the Internet via wireless communication protocols, including Wi-Fi, 4G LTE, or 5G, to ensure real-time data transmission capabilities; S12: The multiple sensor devices include a temperature sensor, a humidity sensor, an acceleration sensor, a GPS positioning module and a transport vehicle status monitoring device, wherein: the temperature sensor is used to monitor the temperature data in the cold chain environment in real time; the humidity sensor is used to monitor the environmental humidity data in real time; the acceleration sensor is used to detect vibration data during transportation; the GPS positioning module is used to obtain the real-time location information of the transport vehicle; the transport vehicle status monitoring device is used to collect the vehicle's operating status data, including speed, fuel consumption and engine status; S13: The multi-dimensional data is transmitted to the cloud data storage platform in an encrypted manner through the wireless communication protocol. The encryption method adopts the transport layer security protocol to ensure the security and integrity of the data transmission process.

[0007] Optionally, the S2 specifically includes: S21: Screening the collected multi-dimensional data to identify and remove invalid data points caused by sensor equipment failure or signal interference, wherein the invalid data includes sensor readings exceeding a reasonable range, duplicate recorded data, and data that does not conform to time series logic; S22: using an interpolation algorithm to fill in missing values ​​in the multi-dimensional data, where the interpolation algorithm includes linear interpolation and polynomial interpolation; S23: Standardize the multi-dimensional data by using the Z-score standardization method to convert all types of data into a standard normal distribution with a mean of 0 and a standard deviation of 1, so as to eliminate the dimensional differences between different data dimensions; S24: converting the preprocessed multi-dimensional data into a unified storage format, including JSON or XML format; S25: Classify the multi-dimensional data according to the data type and add corresponding labels. The specific classifications include temperature data, humidity data, vibration data, location data and transport vehicle status data.

[0008] Optionally, the S3 specifically includes: S31: Analyze the preprocessed multi-dimensional data using the FP-Growth algorithm to identify and extract the correlation between the data dimensions, wherein the FP-Growth algorithm is used to mine frequent item sets and association rules to determine the relationship between temperature data, humidity data, vibration data, location data, and transport vehicle status data; S32: Based on machine learning technology, a random forest algorithm is used to train and classify the extracted correlation data to identify abnormal patterns in the cold chain transportation process, including abnormal temperature fluctuations, humidity deviations from the standard range, and abnormal increases in vibration of the transportation vehicle; S33: By deploying the Apache Kafka real-time data stream processing framework, we continuously monitor the multi-dimensional data transmitted in real time to detect and mark real-time data points that match the identified abnormal patterns, ensuring that abnormal situations can be captured immediately; S34: After an abnormal situation is detected, an abnormal analysis report is automatically generated, wherein the abnormal analysis report includes the abnormal type, occurrence time and occurrence location, and the data is graphically displayed using Tableau.

[0009] Optionally, the S31 specifically includes: S311: converting the preprocessed multi-dimensional data according to the format of a transaction set, where each transaction in the transaction set corresponds to a cold chain transportation event, including specific values ​​of temperature data, humidity data, vibration data, location data, and status data of the transportation vehicle; S312: Use the FP-Growth algorithm to mine frequent itemsets for the transaction set and set a minimum support threshold , use the FP-Growth algorithm to identify all Frequent itemsets of ; S313: Generate association rules based on the frequent item sets and set a minimum confidence threshold , by calculating the confidence of each frequent item set, filter out those that meet the confidence threshold Association rules of S314: performing correlation analysis on the association rules generated in S313 to identify the association relationship among the temperature data, humidity data, vibration data, location data and transport vehicle status data; S315: Storing the generated association rules and their support and confidence indicators in an association rule database of a cloud data storage platform.

[0010] Optionally, the S32 specifically includes: S321: sorting the correlation data extracted in step S31 to construct a data set containing multiple features and labels; each sample data includes multiple input feature values ​​and corresponding labels, and the label indicates whether the status during the cold chain transportation process is abnormal; S322: Standardize the features in the data set, and use the Z-score standardization method to normalize each feature to eliminate the scale differences between different feature dimensions; S323: Use the random forest algorithm to train the preprocessed data set and build a classification model; the random forest performs classification by building multiple decision trees and combining their voting results; S324: Use the trained classification model to classify the new cold chain transportation data and output the predicted label for each data point; if the predicted label of a data point is abnormal, it means that the point belongs to an abnormal temperature, humidity or vibration mode.

[0011] Optionally, the S33 specifically includes: S331: Receives real-time multi-dimensional data streams transmitted from S31 by deploying the Apache Kafka real-time data stream processing framework; S332: Utilize the consumer component of Apache Kafka to continuously monitor the real-time multi-dimensional data stream. The monitoring process includes parsing and preprocessing the received data to ensure the consistency and real-time nature of the data format. The preprocessing step includes timestamp correction and data synchronization processing. S333: Based on the classification model trained in S32, classify and predict the multi-dimensional data transmitted in real time to obtain the predicted label , indicating normal or abnormal; S334: Predict labels For abnormal real-time data points, the data points are automatically marked in the data stream and their information is recorded, including the type of abnormality, the time of occurrence, and the location of occurrence.

[0012] Optionally, the S4 specifically includes: S41: Based on the abnormal analysis report generated by S3, analyze the historical temperature data and the current transportation environment, and set the temperature abnormality judgment threshold and ,in, The maximum temperature threshold allowed during cold chain transportation; The minimum temperature threshold allowed during cold chain transportation; S42: According to the abnormal analysis report, set the humidity abnormality judgment threshold and ;in, It is the maximum humidity threshold allowed during cold chain transportation; It is the minimum humidity threshold allowed during cold chain transportation; S43: According to the analysis of the vibration data in the transportation process in the abnormal analysis report, set the vibration abnormality judgment threshold ,in The maximum vibration amplitude allowed during cold chain transportation. If the threshold is exceeded, it is considered as vibration abnormality. S44: Based on the thresholds set in S41, S42 and S43, the temperature data, humidity data and vibration data collected during the cold chain transportation are monitored in real time, and whether an abnormal situation occurs is determined by the following formula: ; in, Temperature data for real-time monitoring; For real-time monitoring of humidity data, It is the vibration amplitude data monitored in real time; S45: When S44 determines an abnormal situation, it will automatically record the specific information of the abnormal event, including the abnormal type, occurrence time, occurrence location and related data indicators.

[0013] Optionally, the S5 specifically includes: S51: Encapsulate the abnormal information of the abnormal situation determined in S4 into a structured data packet, where the data packet adopts a data format of JSON or XML; S52: Encrypt the encapsulated abnormal information data using the AES-256 encryption algorithm or the TLS protocol; S53: Sending the encrypted abnormal information data packet to the cloud data storage platform through a security protocol; S54: After receiving the abnormal information, the cloud data storage platform pushes it to the terminal device of the relevant manager so that the manager can take timely response measures.

[0014] An intelligent cold chain management system based on the Internet and multi-dimensional analysis is used to implement the above-mentioned intelligent cold chain management method based on the Internet and multi-dimensional analysis, including the following modules: Sensor data acquisition module: used to connect multiple sensor devices through the Internet to collect multi-dimensional data in the cold chain transportation process in real time, including temperature data, humidity data, vibration data, location data and status data of transportation vehicles; Cloud data storage module: used to receive data from the sensor data acquisition module, and perform data standardization processing on it, remove invalid data and fill in missing data; Data analysis anomaly detection module: used to analyze the pre-processed data in real time through big data analysis technology, extract the correlation between the data, and use machine learning-based algorithms to identify anomalies in the cold chain transportation process and generate anomaly analysis reports; Abnormal judgment and threshold setting module: used to set multiple abnormal judgment thresholds according to the abnormal analysis report generated by the data analysis abnormal detection module, and compare the real-time data with the preset thresholds to determine whether abnormal conditions such as excessive temperature, abnormal humidity or excessive vibration have occurred, and record the specific information of the abnormal conditions; Abnormal information transmission and notification module: When the abnormal judgment and threshold setting module judges an abnormal situation, the corresponding abnormal information is immediately sent to the terminal device of the relevant manager, so that the manager can take timely response measures.

[0015] Beneficial effects of the present invention: The present invention, by utilizing Internet technology and multi-dimensional data collection methods, can monitor various environmental parameters in the cold chain transportation process in real time, including temperature, humidity, vibration, location, and transportation vehicle status; the comprehensive collection of such multi-dimensional data provides a more accurate and comprehensive information basis for cold chain management, effectively avoiding the limitations of traditional cold chain management systems that only rely on temperature and humidity data; in addition, real-time data transmission and cloud storage technology ensure the timeliness and accessibility of data, allowing managers to grasp the transportation status at any time.

[0016] The present invention, by combining big data analysis technology and machine learning algorithms, can conduct in-depth analysis of real-time collected data, automatically identify and predict abnormal situations in cold chain transportation; for example, it can determine in real time whether temperature exceeds the standard, humidity is abnormal, or vibration is excessive during transportation, and promptly issue an alarm to management personnel; this automated abnormality detection and early warning function greatly improves the risk management efficiency in the cold chain transportation process and reduces the need for human intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic diagram of a smart cold chain management method according to an embodiment of the present invention; Figure 2 Schematic diagram of a smart cold chain management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0020] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0021] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0022] like Figure 1 As shown, a smart cold chain management method and system based on the Internet and multi-dimensional analysis includes the following steps: S1: Connect multiple sensor devices through the Internet to collect multi-dimensional data in the cold chain transportation process in real time, including temperature data, humidity data, vibration data, location data and status data of transportation vehicles, and transmit the multi-dimensional data to the cloud data storage platform through wireless network; S2: In the cloud data storage platform, the collected multi-dimensional data is pre-processed, including removing invalid data, filling missing data and data standardization, to provide an accurate data basis for subsequent analysis; S3: Based on the cloud data storage platform, use big data analysis technology to perform real-time analysis on pre-processed multi-dimensional data, extract the correlation between the data, analyze the abnormal conditions in the cold chain transportation process, and generate an abnormal analysis report; S4: According to the abnormal analysis report, set multiple abnormal judgment thresholds to determine whether abnormal conditions such as excessive temperature, abnormal humidity or excessive vibration occur during cold chain transportation, and record specific information on the occurrence of abnormal conditions; S5: If an abnormal situation is determined in S4, the corresponding abnormal information is immediately sent to the terminal device of the relevant manager through the cloud data storage platform so that the manager can take management measures according to the specific abnormal information.

[0023] S1 specifically includes: S11: Connect multiple sensor devices to the Internet through wireless communication protocols, including Wi-Fi, 4G LTE or 5G, to ensure real-time data transmission capabilities; wireless communication protocol selection is based on transmission distance, bandwidth requirements and network coverage to optimize data transmission efficiency and stability; S12: Multiple sensor devices include temperature sensors, humidity sensors, acceleration sensors, GPS positioning modules and transport vehicle status monitoring equipment, wherein: the temperature sensor is used to monitor the temperature data in the cold chain environment in real time to ensure that the temperature is always kept within the set range during transportation; the humidity sensor is used to monitor the environmental humidity data in real time to prevent product quality problems caused by abnormal humidity; the acceleration sensor is used to detect vibration data during transportation to prevent damage to goods caused by excessive vibration; the GPS positioning module is used to obtain the real-time location information of the transport vehicle to realize dynamic monitoring of the transport route; the transport vehicle status monitoring equipment is used to collect the vehicle's operating status data, including speed, fuel consumption and engine status, to ensure the normal operation of the transport vehicle; S13: The multi-dimensional data is transmitted to the cloud data storage platform in an encrypted manner through the wireless communication protocol. The encryption method adopts the Transport Layer Security Protocol (TLS) to ensure the security and integrity of the data transmission process. Through the above technical steps, the efficient, reliable and secure collection and transmission of multi-dimensional data is achieved, ensuring the real-time monitoring of key parameters and data integrity during the cold chain transportation process, providing a solid foundation for subsequent data analysis and anomaly detection.

[0024] S2 specifically includes: S21: Screening the collected multi-dimensional data to identify and remove invalid data points caused by sensor equipment failure or signal interference. Invalid data includes sensor readings that exceed a reasonable range, duplicate recorded data, and data that does not conform to time series logic; S22: Interpolation algorithms are used to fill missing values ​​in multi-dimensional data. Interpolation algorithms include linear interpolation and polynomial interpolation to ensure the integrity and continuity of the data set and provide seamless data support for subsequent analysis; S23: Standardize multi-dimensional data and use the Z-score standardization method to convert various data into a standard normal distribution with a mean of 0 and a standard deviation of 1, so as to eliminate the dimensional differences between different data dimensions and improve the accuracy and consistency of data analysis; S24: converting the pre-processed multi-dimensional data into a unified storage format, including JSON or XML format, to ensure the compatibility and scalability of the data in the cloud data storage platform, and facilitate subsequent data query and analysis operations; S25: Classify the multi-dimensional data according to the data type and add corresponding labels. The specific classifications include temperature data, humidity data, vibration data, location data and transport vehicle status data. Labeling processing facilitates rapid retrieval and targeted analysis. Through the above steps, the preprocessing method ensures the quality and consistency of the collected multi-dimensional data, providing a reliable data foundation for subsequent real-time analysis and anomaly detection.

[0025] S3 specifically includes: S31: Analyze the preprocessed multi-dimensional data using the FP-Growth algorithm to identify and extract the correlation between the data dimensions. The FP-Growth algorithm is used to mine frequent item sets and association rules to determine the relationship between temperature data, humidity data, vibration data, location data, and transport vehicle status data; S32: Based on machine learning technology, the random forest algorithm is used to train and classify the extracted correlation data to identify abnormal patterns in the cold chain transportation process, including abnormal temperature fluctuations, humidity deviations from the standard range, and abnormal increases in vibration of transportation vehicles; S33: By deploying the Apache Kafka real-time data stream processing framework, we continuously monitor the multi-dimensional data transmitted in real time to detect and mark real-time data points that match the identified abnormal patterns, ensuring that abnormal situations can be captured immediately; S34: After an abnormal situation is detected, an abnormal analysis report is automatically generated. The abnormal analysis report includes the abnormality type, time and location of occurrence, and uses Tableau to display the data graphically so that managers can quickly understand and evaluate the abnormal situation. Through the above technical steps, in-depth analysis of multi-dimensional data and real-time anomaly detection are achieved, ensuring data accuracy and timely identification of abnormal situations during cold chain transportation, providing solid technical support for smart cold chain management.

[0026] S31 specifically includes: S311: convert the preprocessed multi-dimensional data according to the format of the transaction set, where each transaction in the transaction set corresponds to a cold chain transportation event, including specific values ​​of temperature data, humidity data, vibration data, location data, and status data of the transportation vehicle; specifically, establish a data table containing all transportation events, where each row represents a transportation event, and each column represents a specific value of a data dimension; S312: Use the FP-Growth algorithm to mine frequent itemsets for the transaction set and set the minimum support threshold , use the FP-Growth algorithm to identify all Frequent itemsets of ; The FP-Growth algorithm includes the process of constructing an FP tree and mining frequent item sets from the FP tree. The specific steps are as follows: Construct FP tree: scan the transaction set, count the frequency of each item, and delete items below the support threshold. , and arrange the remaining items in descending order of frequency; construct an FP tree based on the arranged items to record the path of frequent items in each transaction; Mining frequent item sets: Starting from the conditional pattern base of the FP tree, recursively mine all frequent item sets; S313: Generate association rules based on frequent item sets and set minimum confidence threshold , by calculating the confidence of each frequent item set, filter out those that meet the confidence threshold Association rules of The steps for generating association rules include: Generate candidate rules: For each frequent item set, generate all possible item pair combinations to form candidate association rules A→B; Calculate confidence: For each candidate association rule A→B, calculate its confidence: Confidence(A→B) = Support(A ∪ B) / Support(A); Screening rules: retain all association rules with a confidence level not less than γ; S314: performing correlation analysis on the association rules generated in S313 to identify the association relationship among the temperature data, humidity data, vibration data, location data and transport vehicle status data; The specific steps include: Support calculation: Calculate the support of each association rule Support(A→B) = (number of transactions with A and B) / (total number of transactions); Confidence calculation: Calculate the confidence of each association rule: Confidence(A→B) = Support(A ∪ B) / Support(A); Determine the correlation relationship: Determine the strong correlation between the data dimensions based on the calculation results of support and confidence; S315: The generated association rules and their support and confidence indicators are stored in the association rule database of the cloud data storage platform. The association rule database is used to store and manage all identified association rules to support subsequent abnormal pattern recognition and analysis. Through the above technical steps, the FP-Growth algorithm is used to efficiently mine frequent item sets in multi-dimensional data, thereby identifying and extracting key association relationships between data dimensions. This method not only improves the efficiency of data analysis, but also provides accurate rules and patterns for anomaly detection in cold chain transportation.

[0027] S32 specifically includes: S321: The correlation data extracted in step S31 are sorted to construct a data set containing multiple features (such as temperature, humidity, vibration, etc.) and labels (such as normal, abnormal); each sample data includes multiple input feature values ​​and corresponding labels, and the label indicates whether the status during the cold chain transportation process is abnormal; S322: Standardize the features in the data set, use the Z-score standardization method to normalize each feature, eliminate the scale differences between different feature dimensions, and make the training process more stable and efficient; S323: Use the random forest algorithm to train the preprocessed data set and build a classification model; the random forest algorithm performs classification by building multiple decision trees and combining their voting results; the training process of each tree ensures the independence of each decision tree by randomly sampling the feature space; The specific steps to build a classification model using the random forest algorithm are as follows: Select training set and test set: Divide the preprocessed data set into training set and test set according to a certain ratio, such as 70% for training and 30% for testing; Construct a decision tree: For each sample in the training set, select the optimal feature through the splitting node of the decision tree; for each tree, select the optimal splitting feature through the following information gain calculation formula: ,in, Features For the dataset The gain, For the dataset The entropy of represents the uncertainty of the data set. Features The value set of For the characteristics The value is A subset of For the dataset The number of samples in For subset The number of samples in ; Randomization during training: When building each tree, features are randomly selected from the training data (feature randomization) and samples are randomly drawn from the dataset (sample randomization), which helps improve the generalization ability of the model and reduce overfitting; Voting mechanism: The random forest model performs classification through ensemble learning. After completing the training of all decision trees, for each sample in the test set, the random forest determines the final classification result by voting on the prediction results of all decision trees.

[0028] S324: Use the trained classification model to classify new cold chain transportation data and output the predicted label for each data point; if the predicted label of a data point is abnormal, it means that the point belongs to an abnormal temperature, humidity or vibration mode; by using the random forest algorithm to train and classify multi-dimensional data, abnormal patterns in cold chain transportation can be accurately identified; the random forest algorithm integrates multiple decision trees to effectively avoid the overfitting problem of a single decision tree and improve the accuracy and stability of anomaly detection.

[0029] S33 specifically includes: S331: Receives real-time multi-dimensional data streams transmitted from S31 by deploying the Apache Kafka real-time data stream processing framework; S332: Use the Apache Kafka consumer component to continuously monitor real-time multi-dimensional data streams. The monitoring process includes parsing and preprocessing the received data to ensure the consistency and real-time nature of the data format. The preprocessing steps include timestamp correction and data synchronization. The specific formula is as follows: ,in, is the corrected timestamp, is the original timestamp received, is the time synchronization deviation; S333: Based on the classification model trained in S32, classify and predict the multi-dimensional data transmitted in real time to obtain the predicted label , indicating normal or abnormal; S334: Predict labels For abnormal real-time data points, the data points are automatically marked in the data stream and their information is recorded, including the type of abnormality, time of occurrence, and location of occurrence; by deploying the Apache Kafka real-time data stream processing framework, it can efficiently receive and monitor real-time multi-dimensional data streams in the cold chain transportation process, ensuring the accuracy and real-time performance of data processing, and improving the intelligence and automation level of the smart cold chain management system.

[0030] S4 specifically includes: S41: Based on the abnormal analysis report generated by S3, analyze the historical temperature data and the current transportation environment, and set the temperature abnormality judgment threshold and ,in, The maximum temperature threshold allowed during cold chain transportation; The minimum temperature threshold allowed during cold chain transportation; S42: According to the abnormal analysis report and the product's sensitivity to humidity, set the humidity abnormality judgment threshold and ;in, It is the maximum humidity threshold allowed during cold chain transportation; It is the minimum humidity threshold allowed during cold chain transportation; S43: According to the analysis of the vibration data in the transportation process in the abnormal analysis report, set the vibration abnormality judgment threshold ,in The maximum vibration amplitude allowed during cold chain transportation. If the threshold is exceeded, it is considered as vibration abnormality. S44: Based on the thresholds set in S41, S42 and S43, the temperature data, humidity data and vibration data collected during the cold chain transportation are monitored in real time, and whether an abnormal situation occurs is determined by the following formula: ; in, is the real-time monitored temperature data (unit: °C); is the real-time monitored humidity data (unit: %), It is the vibration amplitude data monitored in real time (unit: m / s²); S45: When S44 determines an abnormal situation, it will automatically record the specific information of the abnormal event, including the type of abnormality, time of occurrence, location of occurrence and related data indicators; the type of abnormality is temperature exceeding the standard, temperature being too low, humidity abnormality or vibration abnormality; the time of occurrence is the specific time when the abnormal situation occurs; the location of occurrence is the real-time location of the transport vehicle; the related data indicators are the specific data values ​​of temperature, humidity and vibration amplitude; through the above steps, clear temperature, humidity and vibration abnormality judgment thresholds are set to ensure strict control of key environmental parameters during cold chain transportation; when the real-time monitoring data exceeds the preset threshold, the specific information of the abnormal situation can be identified and recorded in time; these technical measures improve the accuracy and response speed of abnormality detection, and ensure that the environmental conditions of cold chain transportation always meet product safety standards.

[0031] S5 specifically includes: S51: encapsulate the abnormal information (including the abnormal type, occurrence time and specific data) of the abnormal situation determined in S4 into a structured data packet, and the data format adopted by the data packet is JSON or XML; S52: Encrypt the encapsulated abnormal information data using the AES-256 encryption algorithm or the TLS protocol to ensure the security of data transmission; S53: Send the encrypted abnormal information data packet to the cloud data storage platform through a security protocol (such as HTTPS or MQTT) to ensure reliable data transmission; S54: After receiving the abnormal information, the cloud data storage platform pushes it to the terminal device of the relevant manager so that the manager can take timely response measures; the technical measures in the above steps jointly improve the security, real-time and reliability of the smart cold chain management system, effectively ensure the quality and transportation safety of goods in the cold chain transportation process, and reduce the economic losses and quality risks caused by abnormal situations.

[0032] like Figure 2 As shown, a smart cold chain management system based on the Internet and multi-dimensional analysis is used to implement the above-mentioned smart cold chain management method based on the Internet and multi-dimensional analysis, including the following modules: Sensor data acquisition module: used to connect multiple sensor devices through the Internet to collect multi-dimensional data in the cold chain transportation process in real time, including temperature data, humidity data, vibration data, location data and status data of transportation vehicles; Cloud data storage module: used to receive data from the sensor data acquisition module, perform data standardization, remove invalid data and fill in missing data, and provide an accurate data basis for subsequent data analysis; Data analysis anomaly detection module: used to analyze the pre-processed data in real time through big data analysis technology, extract the correlation between the data, and use machine learning-based algorithms (such as random forest algorithm) to identify abnormal situations in the cold chain transportation process and generate abnormal analysis reports; Abnormal judgment and threshold setting module: used to set multiple abnormal judgment thresholds according to the abnormal analysis report generated by the data analysis abnormal detection module, and compare the real-time data with the preset thresholds to determine whether abnormal conditions such as excessive temperature, abnormal humidity or excessive vibration have occurred, and record the specific information of the abnormal conditions; Abnormal information transmission and notification module: When the abnormal judgment and threshold setting module judges an abnormal situation, the corresponding abnormal information is immediately sent to the terminal device of the relevant manager, so that the manager can take timely response measures.

[0033] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0034] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A smart cold chain management method based on the Internet and multi-dimensional analysis, characterized in that: The following steps are involved: S1: Connect multiple sensor devices through the Internet to collect multi-dimensional data in the cold chain transportation process in real time, including temperature data, humidity data, vibration data, location data and status data of transportation vehicles, and transmit the multi-dimensional data to the cloud data storage platform through wireless network; S2: In the cloud data storage platform, the collected multi-dimensional data is pre-processed, including removing invalid data, filling missing data and data standardization; S3: Based on the cloud data storage platform, use big data analysis technology to perform real-time analysis on pre-processed multi-dimensional data, extract the correlation between the data, analyze the abnormal conditions in the cold chain transportation process, and generate an abnormal analysis report; S4: According to the abnormal analysis report, set multiple abnormal judgment thresholds to determine whether abnormal conditions such as excessive temperature, abnormal humidity or excessive vibration occur during cold chain transportation, and record specific information on the occurrence of abnormal conditions; S5: If an abnormal situation is determined in S4, the corresponding abnormal information is immediately sent to the terminal device of the relevant manager through the cloud data storage platform so that the manager can take management measures according to the specific abnormal information.

2. According to claim 1, a smart cold chain management method based on the Internet and multi-dimensional analysis is characterized in that: The S1 specifically includes: S11: Connect multiple sensor devices to the Internet via wireless communication protocols, including Wi-Fi, 4G LTE, or 5G, to ensure real-time data transmission capabilities; S12: The multiple sensor devices include a temperature sensor, a humidity sensor, an acceleration sensor, a GPS positioning module and a transport vehicle status monitoring device, wherein: the temperature sensor is used to monitor the temperature data in the cold chain environment in real time; the humidity sensor is used to monitor the environmental humidity data in real time; the acceleration sensor is used to detect vibration data during transportation; the GPS positioning module is used to obtain the real-time location information of the transport vehicle; the transport vehicle status monitoring device is used to collect the vehicle's operating status data, including speed, fuel consumption and engine status; S13: The multi-dimensional data is transmitted to the cloud data storage platform in an encrypted manner through the wireless communication protocol. The encryption method adopts the transport layer security protocol to ensure the security and integrity of the data transmission process.

3. According to claim 1, a smart cold chain management method based on the Internet and multi-dimensional analysis is characterized in that: The S2 specifically includes: S21: Screening the collected multi-dimensional data to identify and remove invalid data points caused by sensor equipment failure or signal interference, wherein the invalid data includes sensor readings exceeding a reasonable range, duplicate recorded data, and data that does not conform to time series logic; S22: using an interpolation algorithm to fill in missing values ​​in the multi-dimensional data, where the interpolation algorithm includes linear interpolation and polynomial interpolation; S23: Standardize the multi-dimensional data by using the Z-score standardization method to convert all types of data into a standard normal distribution with a mean of 0 and a standard deviation of 1, so as to eliminate the dimensional differences between different data dimensions; S24: converting the preprocessed multi-dimensional data into a unified storage format, including JSON or XML format; S25: Classify the multi-dimensional data according to the data type and add corresponding labels. The specific classifications include temperature data, humidity data, vibration data, location data and transport vehicle status data.

4. According to claim 1, a smart cold chain management method based on the Internet and multi-dimensional analysis is characterized in that: The S3 specifically includes: S31: Analyze the preprocessed multi-dimensional data using the FP-Growth algorithm to identify and extract the correlation between the data dimensions, wherein the FP-Growth algorithm is used to mine frequent item sets and association rules to determine the relationship between temperature data, humidity data, vibration data, location data, and transport vehicle status data; S32: Based on machine learning technology, a random forest algorithm is used to train and classify the extracted correlation data to identify abnormal patterns in the cold chain transportation process, including abnormal temperature fluctuations, humidity deviations from the standard range, and abnormal increases in vibration of the transportation vehicle; S33: By deploying the Apache Kafka real-time data stream processing framework, we continuously monitor the multi-dimensional data transmitted in real time to detect and mark real-time data points that match the identified abnormal patterns, ensuring that abnormal situations can be captured immediately; S34: After an abnormal situation is detected, an abnormal analysis report is automatically generated, wherein the abnormal analysis report includes the abnormal type, occurrence time and occurrence location, and the data is graphically displayed using Tableau.

5. According to claim 4, a smart cold chain management method based on the Internet and multi-dimensional analysis is characterized in that: The S31 specifically includes: S311: converting the preprocessed multi-dimensional data according to the format of a transaction set, where each transaction in the transaction set corresponds to a cold chain transportation event, including specific values ​​of temperature data, humidity data, vibration data, location data, and status data of the transportation vehicle; S312: Use the FP-Growth algorithm to mine frequent itemsets for the transaction set and set a minimum support threshold , use the FP-Growth algorithm to identify all Frequent itemsets of ; S313: Generate association rules based on the frequent item sets and set a minimum confidence threshold , by calculating the confidence of each frequent item set, filter out those that meet the confidence threshold Association rules of S314: performing correlation analysis on the association rules generated in S313 to identify the association relationship among the temperature data, humidity data, vibration data, location data and transport vehicle status data; S315: Storing the generated association rules and their support and confidence indicators in an association rule database of a cloud data storage platform.

6. According to claim 5, a smart cold chain management method based on the Internet and multi-dimensional analysis is characterized in that: The S32 specifically includes: S321: sorting the correlation data extracted in step S31 to construct a data set containing multiple features and labels; each sample data includes multiple input feature values ​​and corresponding labels, and the label indicates whether the status during the cold chain transportation process is abnormal; S322: Standardize the features in the data set, and use the Z-score standardization method to normalize each feature to eliminate the scale differences between different feature dimensions; S323: Use the random forest algorithm to train the preprocessed data set and build a classification model; the random forest performs classification by building multiple decision trees and combining their voting results; S324: Use the trained classification model to classify the new cold chain transportation data and output the predicted label for each data point; if the predicted label of a data point is abnormal, it means that the point belongs to an abnormal temperature, humidity or vibration mode.

7. The intelligent cold chain management method based on the Internet and multi-dimensional analysis according to claim 6 is characterized in that: The S33 specifically includes: S331: Receives real-time multi-dimensional data streams transmitted from S31 by deploying the Apache Kafka real-time data stream processing framework; S332: Utilize the consumer component of Apache Kafka to continuously monitor the real-time multi-dimensional data stream. The monitoring process includes parsing and preprocessing the received data to ensure the consistency and real-time nature of the data format. The preprocessing step includes timestamp correction and data synchronization processing. S333: Based on the classification model trained in S32, classify and predict the multi-dimensional data transmitted in real time to obtain the predicted label , indicating normal or abnormal; S334: Prediction label For abnormal real-time data points, the data points are automatically marked in the data stream and their information is recorded, including the type of abnormality, the time of occurrence, and the location of occurrence.

8. The intelligent cold chain management method based on the Internet and multi-dimensional analysis according to claim 1 is characterized in that: The S4 specifically includes: S41: Based on the abnormal analysis report generated by S3, analyze the historical temperature data and the current transportation environment, and set the temperature abnormality judgment threshold and ,in, The maximum temperature threshold allowed during cold chain transportation; The minimum temperature threshold allowed during cold chain transportation; S42: According to the abnormal analysis report, set the humidity abnormality judgment threshold and ;in, It is the maximum humidity threshold allowed during cold chain transportation; It is the minimum humidity threshold allowed during cold chain transportation; S43: According to the analysis of the vibration data in the transportation process in the abnormal analysis report, set the vibration abnormality judgment threshold ,in The maximum vibration amplitude allowed during cold chain transportation. If the threshold is exceeded, it is considered as vibration abnormality. S44: Based on the thresholds set in S41, S42 and S43, the temperature data, humidity data and vibration data collected during the cold chain transportation are monitored in real time, and whether an abnormal situation occurs is determined by the following formula: ； in, Temperature data for real-time monitoring; For real-time monitoring of humidity data, It is the vibration amplitude data monitored in real time; S45: When S44 determines an abnormal situation, it will automatically record the specific information of the abnormal event, including the abnormal type, occurrence time, occurrence location and related data indicators.

9. The intelligent cold chain management method based on the Internet and multi-dimensional analysis according to claim 1 is characterized in that: The S5 specifically includes: S51: Encapsulate the abnormal information of the abnormal situation determined in S4 into a structured data packet, where the data packet adopts a data format of JSON or XML; S52: Encrypt the encapsulated abnormal information data using the AES-256 encryption algorithm or the TLS protocol; S53: Sending the encrypted abnormal information data packet to the cloud data storage platform through a security protocol; S54: After receiving the abnormal information, the cloud data storage platform pushes it to the terminal device of the relevant manager so that the manager can take timely response measures.

10. An intelligent cold chain management system based on the Internet and multi-dimensional analysis, used to implement an intelligent cold chain management method based on the Internet and multi-dimensional analysis as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Sensor data acquisition module: used to connect multiple sensor devices through the Internet to collect multi-dimensional data in the cold chain transportation process in real time, including temperature data, humidity data, vibration data, location data and status data of transportation vehicles; Cloud data storage module: used to receive data from the sensor data acquisition module, and perform data standardization processing on it, remove invalid data and fill in missing data; Data analysis anomaly detection module: used to analyze the pre-processed data in real time through big data analysis technology, extract the correlation between the data, and use machine learning-based algorithms to identify anomalies in the cold chain transportation process and generate anomaly analysis reports; Abnormal judgment and threshold setting module: used to set multiple abnormal judgment thresholds according to the abnormal analysis report generated by the data analysis abnormal detection module, and compare the real-time data with the preset thresholds to determine whether abnormal conditions such as excessive temperature, abnormal humidity or excessive vibration have occurred, and record the specific information of the abnormal conditions; Abnormal information transmission and notification module: When the abnormal judgment and threshold setting module judges an abnormal situation, the corresponding abnormal information is immediately sent to the terminal device of the relevant manager, so that the manager can take timely response measures.

Images