Cold-chain logistics big data intelligent monitoring method and system

Abstract

The invention relates to the technical field of big data monitoring control, in particular to a cold-chain logistics big data intelligent monitoring method and system. The method comprises the following steps: acquiring a cold-chain logistics original data set; performing data preprocessing on the cold-chain logistics original data set to obtain a standard cold-chain logistics data set; performing environmental information monitoring on the standard cold-chain logistics data set to obtain cold-chain logistics environmental data; performing parameter real-time sensing on the cold-chain logistics environment data to obtain environment parameter real-time data; and abnormal fluctuation identification is carried out on the environment parameter real-time data to generate real-time cold chain environment abnormal data. Therefore, through the Internet of Things technology, the multi-dimensional data analysis technology, the intelligent control technology and the visualization technology, multi-dimensional correlation analysis is carried out on the abnormal conditions of the cold-chain logistics so as to cope with different risks and abnormal conditions; and the cold-chain logistics process is intelligently monitored, regulated and controlled, so that real-time monitoring and accurate control of the cold-chain logistics are realized.

Description

Technical Field

[0001] The present invention relates to the field of big data monitoring and control technology, and in particular to a cold chain logistics big data intelligent monitoring method and system. Background Art

[0002] With the rapid development of global trade and logistics industry, cold chain logistics has become particularly important in ensuring the quality and safety of perishable foods, medicines and other temperature-controlled commodities. However, traditional cold chain logistics monitoring systems usually rely on manual monitoring or simple temperature and humidity sensor data collection, which cannot achieve comprehensive and real-time monitoring of multi-dimensional data such as temperature, humidity, equipment status, etc. in the entire logistics process. This method is not only difficult to meet the needs of modern cold chain logistics for efficiency, accuracy and real-time performance, but also easily leads to insufficient monitoring of potential risks, thereby affecting the quality of products in the logistics process. Based on the development of big data technology and intelligent monitoring systems, intelligent monitoring methods have gradually been introduced into the field of cold chain logistics. By combining technologies such as sensor networks, the Internet of Things, and cloud computing, intelligent and refined management of the entire process of cold chain logistics is achieved, thereby effectively improving the safety and efficiency of cold chain logistics. However, when dealing with abnormal situations, the existing cold chain logistics big data intelligent monitoring method technology often only performs single analysis of data, lacks multi-dimensional correlation analysis; and when dealing with different risks and abnormal situations, there is a lack of intelligent monitoring and control mechanisms, making it difficult to achieve accurate monitoring and control of cold chain logistics. Summary of the invention

[0003] Based on this, it is necessary to provide a cold chain logistics big data intelligent monitoring method and system to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a cold chain logistics big data intelligent monitoring method comprises the following steps:

[0005] Step S1: Acquire the original cold chain logistics data set; perform data preprocessing on the original cold chain logistics data set to obtain a standard cold chain logistics data set; perform environmental information monitoring on the standard cold chain logistics data set to obtain cold chain logistics environmental data;

[0006] Step S2: Real-time parameter perception of cold chain logistics environment data to obtain real-time environmental parameter data; abnormal fluctuation identification of real-time environmental parameter data to generate real-time cold chain environment abnormal data;

[0007] Step S3: Monitor the equipment operation information of the standard cold chain logistics data set to obtain equipment operation data; perform real-time performance analysis on the equipment operation data to obtain real-time operation performance data; perform anomaly detection on the equipment operation data according to the real-time operation performance data to generate real-time equipment operation anomaly data;

[0008] Step S4: Perform multi-dimensional correlation analysis on the real-time cold chain environment abnormal data through the real-time equipment operation abnormal data to obtain cold chain multi-dimensional correlation data; perform potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data; construct a cold chain logistics intelligent control model based on the real-time cold chain environment abnormal data and the real-time equipment operation abnormal data to obtain a cold chain logistics intelligent control model;

[0009] Step S5: Intelligently regulate the cold chain potential risk data through the cold chain logistics intelligent regulation model to obtain cold chain risk regulation data; monitor the standard cold chain logistics data set in real time through the cold chain risk regulation data to generate a real-time cold chain monitoring report; perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; extract risk regulation data from the cold chain risk regulation data to obtain risk regulation information;

[0010] Step S6: Build a monitoring cloud platform based on the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform; send abnormal warning information, normal cold chain logistics information and risk control information to the designated equipment of the production team based on the real-time cold chain monitoring cloud platform to perform cold chain logistics big data intelligent monitoring operations.

[0011] The present invention obtains a standard cold chain logistics data set by acquiring and preprocessing the original cold chain logistics data set, and further monitors the environmental information of the standard cold chain logistics data set to generate cold chain logistics environmental data, ensuring the accuracy and completeness of the data, and providing a reliable basis for subsequent analysis. Real-time parameter perception and abnormal fluctuation identification of environmental data are performed, and real-time cold chain environmental abnormal data are generated in time, so as to effectively monitor and respond to changes in environmental conditions; by monitoring equipment operation information and performing real-time performance analysis, equipment failure or performance degradation can be discovered in time, so that measures can be taken in advance to reduce the impact of equipment failure on cold chain logistics, and improve the equipment operation and maintenance efficiency and the reliability of cold chain logistics; multi-dimensional correlation analysis of real-time equipment operation abnormal data and real-time cold chain environmental abnormal data can reveal potential cold chain risks, and by generating cold chain potential risk data and constructing an intelligent control model, the monitoring and intelligent control of the cold chain environment and equipment status are ensured. The cold chain potential risk data is regulated by the intelligent control model to generate cold chain risk control data, and the standard cold chain logistics data set is monitored in real time to generate a real-time cold chain monitoring report. Through early warning analysis of reports, abnormal warning information is issued in time, and normal cold chain logistics information and risk control information are extracted, so as to realize comprehensive monitoring of cold chain logistics, ensure timely discovery and response to potential problems, and reduce risks in the cold chain logistics process. Through the construction of a real-time cold chain monitoring cloud platform, the automatic transmission and processing of abnormal warning information, normal cold chain logistics information and risk control information are realized, thereby improving the efficiency and accuracy of information transmission, enabling the production team to respond to the actual needs of cold chain logistics in a timely manner, and optimizing the execution efficiency of cold chain logistics big data intelligent monitoring operations. Therefore, the present invention realizes multi-dimensional correlation analysis of abnormal situations in cold chain logistics through Internet of Things technology, multi-dimensional data analysis technology, intelligent control technology and visualization technology to deal with different risks and abnormal situations; and intelligent monitoring and regulation of the cold chain logistics process are carried out to realize real-time monitoring and precise control of cold chain logistics.

[0012] Preferably, step S2 comprises the following steps:

[0013] Step S21: extracting the characteristic type of the cold chain logistics environment data to obtain the cold chain environment characteristic type data; constructing a characteristic matrix for the cold chain environment characteristic type data to obtain the cold chain environment characteristic matrix;

[0014] Step S22: performing environmental parameter numerical identification on the cold chain environment characteristic matrix to generate environmental parameter numerical data; performing time series analysis on the cold chain environment characteristic matrix according to the environmental parameter numerical data to obtain cold chain environment time series data;

[0015] Step S23: Record the real-time parameter changes of the cold chain environment time series data to obtain real-time environmental parameter data;

[0016] Step S24: Calculate the change rate of the real-time data of the environmental parameters to obtain environmental change rate data; monitor the fluctuation duration of the real-time data of the environmental parameters through the environmental change rate data to generate parameter fluctuation time data;

[0017] Step S25: Identify the fluctuation frequency of the cold chain environment time series data according to the parameter fluctuation time data to generate fluctuation frequency data;

[0018] Step S26: Perform abnormal environment analysis on the cold chain environment feature matrix based on the fluctuation frequency data to generate real-time cold chain environment abnormal data.

[0019] The present invention can effectively organize and represent the environmental characteristic data in the cold chain logistics by extracting the characteristic types of the cold chain logistics environment data and constructing the cold chain environment characteristic matrix; the cold chain environment characteristic matrix is ​​numerically identified to generate environmental parameter numerical data, and the cold chain environment time series data is obtained in combination with time series analysis, so as to accurately grasp the time dynamic changes of the cold chain environment characteristics and provide data support for real-time monitoring; the cold chain environment time series data is recorded in real time to obtain the real-time data of the environmental parameters, thereby realizing the real-time tracking of the cold chain environment state. The real-time data of the environmental parameters is monitored for the duration of fluctuations, and the parameter fluctuation time data is generated to accurately determine the rate and duration of the environmental parameter changes; the cold chain environment time series data is identified for the fluctuation frequency based on the parameter fluctuation time data to generate the fluctuation frequency data, further revealing the frequent fluctuation characteristics in the cold chain environment; the cold chain environment characteristic matrix is ​​analyzed for abnormal environment through the fluctuation frequency data to generate the real-time abnormal cold chain environment data, so as to timely discover the abnormal environment in the cold chain logistics and ensure the stability and safety of the cold chain logistics.

[0020] Preferably, step S3 comprises the following steps:

[0021] Step S31: extracting equipment information by stage from the standard cold chain logistics data set using sensors to obtain equipment information by stage;

[0022] Step S32: monitor the operation information of the equipment in different stages to obtain the equipment operation data;

[0023] Step S33: performing load bearing test on the equipment phase information according to the equipment operation data to generate operation phase load data; performing collaborative load processing on the operation phase load data to obtain operation phase collaborative load data;

[0024] Step S34: Perform distributed real-time performance analysis on the equipment operation data based on the collaborative load data in the operation phase to obtain real-time operation performance data;

[0025] Step S35: Record the performance degradation trend of the equipment stage information through the real-time operation performance data to generate operation performance degradation data; perform abnormal pattern recognition on the operation performance degradation data to obtain operation abnormality data;

[0026] Step S36: Perform equipment abnormality detection on the equipment operation data according to the abnormal operation data to obtain real-time abnormal operation data of the equipment.

[0027] The present invention uses sensors to extract equipment information from standard cold chain logistics data sets in stages to obtain equipment information in stages, which can achieve staged extraction of equipment information and provide staged data support for subsequent monitoring and analysis. The equipment stage information is monitored for operation information to obtain equipment operation data to ensure real-time grasp of the equipment's operating status; the operation stage collaborative load data is obtained through collaborative load processing to effectively monitor the load distribution of the equipment at each stage; distributed real-time performance analysis is performed on the equipment operation data based on the operation stage collaborative load data to obtain real-time operation performance data to ensure the real-time nature of the equipment's operating status and the accuracy of distributed analysis; abnormal operation data is obtained through abnormal pattern recognition to timely discover equipment performance degradation and operation anomalies, providing support for effective monitoring of the equipment's operating status; equipment abnormality detection is performed on the equipment operation data based on the abnormal operation data to obtain real-time equipment operation anomaly data to ensure rapid response when abnormalities occur in the equipment's operation.

[0028] Preferably, step S4 comprises the following steps:

[0029] Step S41: performing multi-dimensional separation on the real-time cold chain environment abnormal data according to the real-time equipment operation abnormal data to obtain cold chain multi-dimensional separation data; independently arranging the cold chain multi-dimensional separation data to obtain cold chain multi-dimensional arrangement data;

[0030] Step S42: extracting features of each dimension of the cold chain multi-dimensional arrangement data to obtain cold chain multi-dimensional feature data; constructing a cold chain multi-dimensional feature matrix for the cold chain multi-dimensional feature data to obtain a cold chain multi-dimensional feature matrix;

[0031] Step S43: performing associated node identification on the cold chain multi-dimensional feature matrix to generate cold chain multi-dimensional associated node data; performing strength measurement of each associated node on the cold chain multi-dimensional feature matrix through the cold chain multi-dimensional associated node data to obtain cold chain node strength data; performing dimensional correlation analysis on the cold chain multi-dimensional feature matrix based on the cold chain node strength data to obtain cold chain multi-dimensional associated data;

[0032] Step S44: performing potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data;

[0033] Step S45: constructing a cold chain logistics intelligent control model according to the real-time cold chain environment abnormality data and the real-time equipment operation abnormality data to obtain a cold chain logistics intelligent control pre-model, and training the cold chain logistics intelligent control pre-model using the real-time cold chain environment abnormality data and the equipment in real time to obtain a cold chain logistics intelligent control training model;

[0034] Step S46: Perform model cross-validation evaluation on the cold chain logistics intelligent control training model to obtain cold chain logistics intelligent control model evaluation data; adjust model parameters of the cold chain logistics intelligent control training model using the cold chain logistics intelligent control model evaluation data to obtain the cold chain logistics intelligent control model.

[0035] The present invention uses the real-time abnormal data of the equipment to perform multi-dimensional separation on the real-time abnormal data of the cold chain environment, obtains the multi-dimensional separation data of the cold chain, and arranges it independently to generate the multi-dimensional arrangement data of the cold chain, thereby ensuring the independence and controllability of the data in each dimension. The multi-dimensional feature matrix of the cold chain is constructed for the multi-dimensional feature data of the cold chain to obtain the multi-dimensional feature matrix of the cold chain, which effectively organizes the multi-dimensional feature data and fully demonstrates the correlation of the data of each dimension. The associated nodes of the cold chain multi-dimensional feature matrix are identified to generate the multi-dimensional associated node data of the cold chain, and the cold chain node strength data is obtained by measuring the node strength, and the dimensional correlation analysis of the multi-dimensional feature matrix of the cold chain is further performed to generate the multi-dimensional associated data of the cold chain, thereby ensuring the accuracy of the correlation between the dimensions; the potential risk analysis of the multi-dimensional associated data of the cold chain is performed to generate the potential risk data of the cold chain, thereby effectively identifying the potential risk points in the cold chain logistics. Based on the real-time abnormal cold chain environment data and the real-time abnormal equipment operation data, a cold chain logistics intelligent control pre-model is constructed, and the pre-model is trained to generate a cold chain logistics intelligent control training model, which improves the accuracy and adaptability of the intelligent control model; the cold chain logistics intelligent control training model is cross-validated and evaluated to generate cold chain logistics intelligent control model evaluation data, and the model parameters are adjusted through the evaluation data to finally generate a cold chain logistics intelligent control model. The efficiency and accuracy of the model are ensured, providing a guarantee for the practical application of cold chain logistics intelligent control.

[0036] Preferably, step S44 includes the following steps:

[0037] Step S441: monitoring high-frequency fluctuation points of cold chain multi-dimensional correlation data to generate multi-dimensional high-frequency fluctuation point data;

[0038] According to the multi-dimensional high-frequency fluctuation point data, the impact segment analysis of the cold chain multi-dimensional correlation data is carried out to obtain the high-frequency fluctuation impact segment data;

[0039] Step S442: Identify the risk factors of the high-frequency fluctuation affected segment data to obtain segment risk factor data;

[0040] According to the segment risk factor data, the potential risk type characteristics of the cold chain multi-dimensional correlation data are analyzed to obtain the potential risk type characteristic data;

[0041] Step S443: Evaluate the impact degree of the potential risk type feature data to generate impact degree data; perform abnormal change frequency analysis on the impact degree data to obtain impact abnormal change frequency data; calculate the impact range of the segment risk factor data based on the impact abnormal change frequency data to obtain risk impact range data;

[0042] Step S444: identifying the risk concentration area of ​​the cold chain multi-dimensional correlation data through the risk impact range data to obtain risk concentration area data; assessing the risk level of the risk concentration area data to generate risk level data;

[0043] Step S445: Analyze the potential risks of the cold chain multi-dimensional associated data according to the potential risk type characteristic data, risk impact range data and risk level data, and generate cold chain potential risk data, wherein the cold chain potential risk data includes temperature potential risk data and equipment potential risk data.

[0044] The present invention generates multidimensional high-frequency fluctuation point data by monitoring the high-frequency fluctuation points of cold chain multidimensional correlation data, and performs impact segment analysis on the cold chain multidimensional correlation data based on the multidimensional high-frequency fluctuation point data to obtain high-frequency fluctuation impact segment data. The high-frequency fluctuation area can be accurately located to ensure that potential risk areas can be quickly identified in the cold chain logistics process. According to the segment risk factor data, the potential risk type characteristics of the cold chain multidimensional related data are analyzed to obtain the potential risk type characteristic data, effectively identify and classify the potential risk factors in the cold chain logistics, and ensure the pertinence and effectiveness of risk management; the impact range of the segment risk factor data is calculated by affecting the abnormal change frequency data to generate risk impact range data, which ensures the accurate prediction and range assessment of the potential risks of cold chain logistics, and helps to take corresponding measures in time; the risk level of the risk concentration area data is assessed to generate risk level data, so that the high-risk areas in the cold chain logistics can be accurately identified and classified, which helps to give priority to key risk areas; according to the potential risk type characteristic data, risk impact range data and risk level data, the potential risks of the cold chain multidimensional related data are analyzed and judged to generate cold chain potential risk data, which provides complete data support for the comprehensive assessment of potential risks in cold chain logistics and ensures the safety and stability of the cold chain logistics process.

[0045] Preferably, step S5 comprises the following steps:

[0046] Step S51: Intelligently regulate the cold chain potential risk data through the cold chain logistics intelligent regulation model to obtain cold chain risk regulation data;

[0047] Step S52: Real-time environmental parameter monitoring of cold chain logistics environment data is performed using cold chain risk control data to obtain real-time environmental parameter monitoring data;

[0048] Step S53: Real-time operation status monitoring of equipment operation data is performed using cold chain risk control data to obtain real-time monitoring data of equipment operation;

[0049] Step S54: Integrate the real-time monitoring data of environmental parameters and the real-time monitoring data of equipment operation to generate a real-time cold chain monitoring report;

[0050] Step S55: Perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; extract risk control data from the cold chain risk control data to obtain risk control information.

[0051] The present invention uses the cold chain logistics intelligent control model to intelligently control the cold chain potential risk data, generate cold chain risk control data, can effectively control the potential risks in the cold chain logistics process, and ensure the stable operation of the cold chain logistics. The cold chain risk control data is used to monitor the environmental parameters of the cold chain logistics environment in real time, generate real-time monitoring data of environmental parameters, ensure the real-time monitoring of the cold chain logistics environment, and can timely reflect the changes in environmental parameters; the cold chain risk control data is used to monitor the real-time operation status of the equipment operation data, generate real-time monitoring data of equipment operation, can monitor the operation status of the equipment in real time, and timely discover abnormal conditions in the operation of the equipment; by integrating the real-time monitoring data of environmental parameters and the real-time monitoring data of equipment operation, a real-time cold chain monitoring report is generated. The report comprehensively reflects the status of the environment and equipment in the cold chain logistics process, and provides comprehensive data support for the overall monitoring of the cold chain logistics; by performing early warning analysis on the real-time cold chain monitoring report, abnormal warning information is generated, and normal cold chain logistics data and risk control data are extracted, and normal cold chain logistics information and risk control information are obtained respectively, so as to realize the timely early warning of potential abnormalities in the cold chain logistics process, and also provide accurate feedback on the normal operation status and risk control situation.

[0052] Preferably, step S51 includes the following steps:

[0053] Step S511: performing cold chain risk type analysis on the temperature potential risk data to obtain cold chain temperature risk type data, wherein the cold chain temperature risk type data includes excessive temperature data and continuous abnormal temperature change data;

[0054] Step S512: Intelligently control the cold chain temperature risk type data through the cold chain logistics intelligent control model. If the cold chain temperature risk type data is too high temperature data, the cold chain equipment refrigeration is automatically triggered to generate too high temperature control data; if the cold chain temperature risk type data is continuous abnormal temperature change data, the working cycle power of the cold chain equipment is optimized to generate continuous temperature change control data; the over-high temperature control data and the continuous temperature change control data are integrated to obtain the temperature potential risk control data;

[0055] Step S513: performing equipment risk type analysis on the equipment potential risk data to obtain equipment risk type data, wherein the equipment risk type data includes equipment vibration frequency abnormality and equipment operating efficiency reduction data;

[0056] Step S514: Intelligently control the equipment risk type data through the cold chain logistics intelligent control model. If the equipment risk type data is abnormal equipment vibration frequency, the equipment load is automatically reduced to generate equipment vibration frequency control data; if the equipment risk type data is equipment operating efficiency reduction data, emergency shutdown and switching to backup equipment are triggered to generate equipment shutdown switching control data; the equipment vibration frequency control data and the equipment shutdown switching control data are integrated to obtain equipment potential risk control data;

[0057] Step S515: Integrate the temperature potential risk control data and the equipment potential risk control data to obtain cold chain risk control data.

[0058] The present invention performs cold chain risk type analysis on temperature potential risk data, generates cold chain temperature risk type data, including over-temperature data and continuous abnormal temperature change data, and clearly distinguishes different temperature-related risk types. The cold chain temperature risk type data is intelligently regulated by the cold chain logistics intelligent control model, ensuring that cold chain logistics can be adjusted quickly and accurately when facing different temperature risks, effectively preventing the impact of abnormal temperature on the cold chain process; for over-temperature data, the refrigeration function of the cold chain equipment is automatically triggered to generate over-temperature control data; for continuous abnormal temperature change data, the working cycle and power of the equipment are optimized to generate continuous temperature change control data. After integrating the control data, the temperature potential risk control data is obtained. By analyzing the potential risk data of equipment and generating equipment risk type data, it is possible to identify and classify the potential risks of equipment in operation; based on the intelligent control model of cold chain logistics, the equipment risk type data is intelligently controlled to ensure that when abnormal conditions occur, cold chain logistics can make timely adjustments to maintain the stable operation of the equipment; when the vibration frequency of the equipment is abnormal, the equipment load is automatically reduced to generate equipment vibration frequency control data; when the operating efficiency of the equipment decreases, an emergency shutdown is triggered and switched to the backup equipment, generating equipment shutdown switching control data. Finally, after integrating these control data, the potential risk control data of the equipment is obtained. By integrating the temperature potential risk control data and the equipment potential risk control data, cold chain risk control data is generated, ensuring the coordinated control of temperature and equipment risks in cold chain logistics.

[0059] Preferably, step S55 includes the following steps:

[0060] Step S551: performing joint abnormality analysis on the real-time cold chain monitoring report to obtain real-time joint abnormality data; performing stage analysis on the real-time joint abnormality data to obtain real-time abnormal stage data;

[0061] Step S552: performing weight division processing on the real-time abnormal stage data to obtain abnormal stage weight data; performing priority feature extraction on the abnormal stage weight data to generate abnormal stage priority data;

[0062] Step S553: ​​Performing grade scoring according to the abnormal stage priority data to obtain grade scoring data; performing early warning analysis according to the grade scoring data to obtain abnormal warning information;

[0063] Step S554: performing normal cold chain logistics status on the real-time cold chain monitoring report to obtain normal cold chain status data; extracting logistics data of the normal cold chain status data to obtain normal cold chain logistics information;

[0064] Step S555: Identify risk control measures for the cold chain risk control data according to the real-time cold chain monitoring report to obtain risk control measures data; extract risk control data from the risk control measures data to obtain risk control information.

[0065] The present invention performs joint abnormal analysis through real-time cold chain monitoring reports, generates real-time joint abnormal data, and further performs stage analysis to obtain real-time abnormal stage data; by refining the abnormal analysis process, it ensures accurate positioning of abnormal situations at different stages in cold chain logistics. The real-time abnormal stage data is weighted to generate abnormal stage weight data, and priority features are extracted based on the data to generate abnormal stage priority data, effectively grading the severity of abnormal situations, so that when dealing with multiple abnormalities, the most urgent situations are given priority, thereby improving the efficiency and accuracy of risk response. Grade scoring is performed according to the abnormal stage priority data to generate grade scoring data, and further, early warning analysis is performed according to the grade scoring data to obtain abnormal warning information; by combining priority features and scoring mechanisms, the timeliness and accuracy of early warning information are ensured, and the early warning capability of cold chain logistics monitoring is enhanced. The normal cold chain logistics status in the real-time cold chain monitoring report is analyzed, normal cold chain status data is extracted and generated, and logistics data is further extracted to obtain normal cold chain logistics information; accurate monitoring of the normal cold chain status is ensured, and abnormal and normal operating states can be distinguished. According to the real-time cold chain monitoring report, the cold chain risk control data is identified, the risk control measures data is generated, and the risk control information is extracted. By identifying and extracting key risk control measures, it is ensured that corresponding control measures can be taken in time after the risk is identified, thereby reducing the impact of risks on cold chain logistics and ensuring the safety of the logistics process.

[0066] Preferably, step S6 comprises the following steps:

[0067] Step S61: constructing a monitoring cloud platform according to the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform, wherein the real-time cold chain monitoring cloud platform construction includes the construction of a real-time monitoring interface for the cold chain logistics environment and the construction of a real-time monitoring interface for equipment operation;

[0068] Step S62: partitioning the data stream based on the real-time cold chain monitoring cloud platform to obtain data stream partitioning information;

[0069] Step S63: Distinguish abnormal warning information, normal cold chain logistics information and risk control information according to the data flow partition information, and send the abnormal warning information, normal cold chain logistics information and risk control information to the designated equipment of the production team to perform cold chain logistics big data intelligent monitoring operations.

[0070] The present invention constructs a real-time cold chain monitoring cloud platform through real-time cold chain monitoring reports, including the construction of a real-time monitoring interface for the cold chain logistics environment and a real-time monitoring interface for equipment operation, ensuring real-time monitoring and visual management of each link of the cold chain logistics, making the monitoring process more intuitive and efficient, and providing an integrated monitoring environment, which is convenient for comprehensive monitoring of the entire cold chain logistics process. Data stream partitioning is performed based on the real-time cold chain monitoring cloud platform, and data stream partitioning information is generated. By reasonably dividing the data stream, the data processing path is optimized, the processing efficiency of the data stream is improved, and the independent processing and transmission of abnormal warning information, normal cold chain logistics information and risk control information are ensured, reducing the risk of cross-information interference. According to the data stream partition information, the abnormal warning information, normal cold chain logistics information and risk control information are effectively distinguished, and these information are accurately sent to the designated equipment of the production team, ensuring the accurate execution of the cold chain logistics big data intelligent monitoring operation, thereby enhancing the intelligent processing capability, ensuring the accurate transmission and execution of various types of information in the production link, and improving the overall safety and reliability of the cold chain logistics operation.

[0071] In this specification, a cold chain logistics big data intelligent monitoring system is provided, which is used to execute the above-mentioned cold chain logistics big data intelligent monitoring method. The cold chain logistics big data intelligent monitoring system includes:

[0072] The data acquisition module is used to acquire the original data set of cold chain logistics; perform data preprocessing on the original data set of cold chain logistics to obtain the standard cold chain logistics data set; perform environmental information monitoring on the standard cold chain logistics data set to obtain the cold chain logistics environmental data;

[0073] The cold chain environment anomaly module is used to perceive the parameters of the cold chain logistics environment data in real time and obtain the real-time data of the environmental parameters; identify the abnormal fluctuations of the real-time data of the environmental parameters and generate the real-time cold chain environment anomaly data;

[0074] The equipment real-time operation abnormality module is used to monitor the equipment operation information of the standard cold chain logistics data set to obtain the equipment operation data; perform real-time performance analysis on the equipment operation data to obtain real-time operation performance data; perform abnormality detection on the equipment operation data based on the real-time operation performance data to generate real-time equipment operation abnormality data;

[0075] The cold chain logistics intelligent control model module is used to perform multi-dimensional correlation analysis on the real-time cold chain environment abnormal data through the real-time equipment operation abnormal data to obtain the cold chain multi-dimensional correlation data; perform potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data; construct the cold chain logistics intelligent control model based on the real-time cold chain environment abnormal data and the real-time equipment operation abnormal data to obtain the cold chain logistics intelligent control model;

[0076] The intelligent control module is used to intelligently control the cold chain potential risk data through the cold chain logistics intelligent control model to obtain cold chain risk control data; to monitor the standard cold chain logistics data set in real time through the cold chain risk control data to generate a real-time cold chain monitoring report; to perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; to extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; to extract risk control data from the cold chain risk control data to obtain risk control information;

[0077] The monitoring cloud platform module is used to build a monitoring cloud platform based on the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform; based on the real-time cold chain monitoring cloud platform, abnormal warning information, normal cold chain logistics information and risk control information are sent to the designated equipment of the production team to perform cold chain logistics big data intelligent monitoring operations.

[0078] The data acquisition module of the present invention obtains a standardized cold chain logistics data set by extracting and processing data from the original cold chain logistics data set, and monitors the environmental information of the data set to generate cold chain logistics environmental data, laying a solid foundation for further analysis. The cold chain environment anomaly module is used for real-time parameter monitoring and anomaly detection of environmental data, and can identify changes in environmental conditions, thereby timely generating real-time cold chain environment anomaly data, and effectively improving the ability to respond to environmental changes. The equipment real-time operation anomaly module is used for monitoring equipment operation information and real-time performance analysis, which can detect equipment failures or performance problems early, so as to take necessary maintenance measures, reduce the impact of equipment failures on cold chain logistics, and improve equipment operation and maintenance efficiency and the reliability of overall cold chain logistics. The cold chain logistics intelligent control model module is used to perform multi-dimensional correlation analysis through equipment operation anomaly data and environmental anomaly data, which can reveal potential risks in cold chain logistics, and by generating cold chain potential risk data and cold chain logistics intelligent control models, it can achieve comprehensive monitoring and intelligent control of the cold chain environment and equipment status. The intelligent control module is used for the cold chain logistics intelligent control model to control the cold chain potential risk data, generate cold chain risk control data, and monitor the standard cold chain logistics data set in real time to generate a real-time cold chain monitoring report. The early warning analysis of the report can issue abnormal warnings in time, extract normal cold chain logistics information and risk control information, and realize all-round monitoring of cold chain logistics, so as to timely discover and solve potential problems and reduce the risks in the cold chain logistics process. The monitoring cloud platform module is used to build a real-time cold chain monitoring cloud platform, automatically process abnormal warnings, normal cold chain logistics information and risk control information, and transmit the information to the equipment specified by the production team, improve the efficiency and accuracy of information transmission, and enable the production team to respond quickly to actual needs, thereby optimizing the execution effect of the intelligent monitoring of cold chain logistics big data. Therefore, the present invention realizes multi-dimensional correlation analysis of abnormal situations in cold chain logistics through Internet of Things technology, multi-dimensional data analysis technology, intelligent control technology and visualization technology to deal with different risks and abnormal situations; and intelligently monitors and controls the cold chain logistics process, realizing real-time monitoring and precise control of cold chain logistics. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A schematic diagram of the steps of a cold chain logistics big data intelligent monitoring method;

[0080] Figure 2 for Figure 1 Detailed implementation steps of step S5;

[0081] Figure 3 for Figure 2 Detailed implementation steps of step S51 are shown in the flowchart;

[0082] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0083] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0084] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0085] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0086] To achieve this, please refer to Figures 1 to 3 , a cold chain logistics big data intelligent monitoring method, the method comprising the following steps:

[0087] Step S1: Acquire the original cold chain logistics data set; perform data preprocessing on the original cold chain logistics data set to obtain a standard cold chain logistics data set; perform environmental information monitoring on the standard cold chain logistics data set to obtain cold chain logistics environmental data;

[0088] Step S2: Real-time parameter perception of cold chain logistics environment data to obtain real-time environmental parameter data; abnormal fluctuation identification of real-time environmental parameter data to generate real-time cold chain environment abnormal data;

[0089] Step S3: Monitor the equipment operation information of the standard cold chain logistics data set to obtain equipment operation data; perform real-time performance analysis on the equipment operation data to obtain real-time operation performance data; perform anomaly detection on the equipment operation data according to the real-time operation performance data to generate real-time equipment operation anomaly data;

[0090] Step S4: Perform multi-dimensional correlation analysis on the real-time cold chain environment abnormal data through the real-time equipment operation abnormal data to obtain cold chain multi-dimensional correlation data; perform potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data; construct a cold chain logistics intelligent control model based on the real-time cold chain environment abnormal data and the real-time equipment operation abnormal data to obtain a cold chain logistics intelligent control model;

[0091] Step S5: Intelligently regulate the cold chain potential risk data through the cold chain logistics intelligent regulation model to obtain cold chain risk regulation data; monitor the standard cold chain logistics data set in real time through the cold chain risk regulation data to generate a real-time cold chain monitoring report; perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; extract risk regulation data from the cold chain risk regulation data to obtain risk regulation information;

[0092] Step S6: Build a monitoring cloud platform based on the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform; send abnormal warning information, normal cold chain logistics information and risk control information to the designated equipment of the production team based on the real-time cold chain monitoring cloud platform to perform cold chain logistics big data intelligent monitoring operations.

[0093] The present invention obtains a standard cold chain logistics data set by acquiring and preprocessing the original cold chain logistics data set, and further monitors the environmental information of the standard cold chain logistics data set to generate cold chain logistics environmental data, ensuring the accuracy and completeness of the data, and providing a reliable basis for subsequent analysis. Real-time parameter perception and abnormal fluctuation identification of environmental data are performed, and real-time cold chain environmental abnormal data are generated in time, so as to effectively monitor and respond to changes in environmental conditions; by monitoring equipment operation information and performing real-time performance analysis, equipment failure or performance degradation can be discovered in time, so that measures can be taken in advance to reduce the impact of equipment failure on cold chain logistics, and improve the equipment operation and maintenance efficiency and the reliability of cold chain logistics; multi-dimensional correlation analysis of real-time equipment operation abnormal data and real-time cold chain environmental abnormal data can reveal potential cold chain risks, and by generating cold chain potential risk data and constructing an intelligent control model, the monitoring and intelligent control of the cold chain environment and equipment status are ensured. The cold chain potential risk data is regulated by the intelligent control model to generate cold chain risk control data, and the standard cold chain logistics data set is monitored in real time to generate a real-time cold chain monitoring report. Through early warning analysis of the report, abnormal warning information is issued in time, and normal cold chain logistics information and risk control information are extracted, so as to realize comprehensive monitoring of cold chain logistics, ensure timely discovery and response to potential problems, and reduce risks in the cold chain logistics process. Through the construction of a real-time cold chain monitoring cloud platform, the automatic transmission and processing of abnormal warning information, normal cold chain logistics information and risk control information are realized, thereby improving the efficiency and accuracy of information transmission, enabling the production team to respond to the actual needs of cold chain logistics in a timely manner, and optimizing the execution efficiency of cold chain logistics big data intelligent monitoring operations. Therefore, the present invention realizes multi-dimensional correlation analysis of abnormal situations in cold chain logistics through Internet of Things technology, multi-dimensional data analysis technology, intelligent control technology and visualization technology to deal with different risks and abnormal situations; and intelligent monitoring and regulation of the cold chain logistics process are carried out to realize real-time monitoring and precise control of cold chain logistics.

[0094] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a cold chain logistics big data intelligent monitoring method of the present invention. In this example, the cold chain logistics big data intelligent monitoring method includes the following steps:

[0095] Step S1: Acquire the original cold chain logistics data set; perform data preprocessing on the original cold chain logistics data set to obtain a standard cold chain logistics data set; perform environmental information monitoring on the standard cold chain logistics data set to obtain cold chain logistics environmental data;

[0096] In an embodiment of the present invention, a raw data set of cold chain logistics is obtained from a data source, and the data set includes environmental parameters, equipment operating status, and logistics operation data collected by sensors. Then, the MapReduce job in the Apache Hadoop framework is used to preprocess the raw data set of cold chain logistics. The data cleaning tool in Hadoop is used to remove invalid data, the missing values ​​are filled by the Imputation algorithm, and the timestamps of data from different sources are synchronized using time series alignment technology. After the processing is completed, a standard cold chain logistics data set is obtained. Subsequently, environmental information monitoring of the standard cold chain logistics data set is performed using sensors and monitoring systems deployed in cold chain logistics facilities. The temperature, humidity, and gas concentration environmental parameters are collected in real time through the Internet of Things (IoT) technology, and these monitoring data are uploaded to the data processing platform through the MQTT protocol to generate cold chain logistics environmental data.

[0097] Step S2: Real-time parameter perception of cold chain logistics environment data to obtain real-time environmental parameter data; abnormal fluctuation identification of real-time environmental parameter data to generate real-time cold chain environment abnormal data;

[0098] In an embodiment of the present invention, real-time parameter perception is performed through cold chain logistics environmental data, and environmental sensors (such as temperature sensors and humidity sensors) installed in cold chain logistics facilities are used to transmit environmental parameter data in real time to a data processing system through a data acquisition module to generate real-time environmental parameter data; next, abnormal fluctuations in the real-time environmental parameter data are identified, and statistical methods such as Z-Score analysis or adaptive threshold detection algorithms are used to perform real-time analysis on the real-time environmental parameter data to identify abnormal values ​​that exceed the normal fluctuation range. These abnormal values ​​are marked and organized into real-time cold chain environmental abnormality data for subsequent monitoring and processing.

[0099] Step S3: Monitor the equipment operation information of the standard cold chain logistics data set to obtain equipment operation data; perform real-time performance analysis on the equipment operation data to obtain real-time operation performance data; perform anomaly detection on the equipment operation data according to the real-time operation performance data to generate real-time equipment operation anomaly data;

[0100] In an embodiment of the present invention, the operating data of the equipment, including the operating temperature, vibration frequency and pressure of the equipment, is collected in real time through industrial control systems and sensors deployed on the cold chain equipment, such as temperature sensors, vibration sensors and pressure sensors; the data is transmitted to the data storage system through a data collector to generate equipment operating data; then, the equipment operating data is processed using a real-time performance analysis algorithm on a data analysis platform, such as a real-time Fourier transform (FFT) or a sliding window analysis, to extract key performance indicators (KPIs) and generate real-time operating performance data; based on the real-time operating performance data, anomaly detection is performed on the equipment operating data, and a machine learning model, such as anomaly detection algorithm, is used to train and predict the real-time operating performance data, identify abnormal operating conditions, and organize them into real-time equipment operating abnormality data for further processing and response.

[0101] Step S4: Perform multi-dimensional correlation analysis on the real-time cold chain environment abnormal data through the real-time equipment operation abnormal data to obtain cold chain multi-dimensional correlation data; perform potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data; construct a cold chain logistics intelligent control model based on the real-time cold chain environment abnormal data and the real-time equipment operation abnormal data to obtain a cold chain logistics intelligent control model;

[0102] In an embodiment of the present invention, the data mining tool Apache Spark technology is used to perform multidimensional correlation analysis on the real-time abnormal operation data of the equipment and the real-time abnormal cold chain environment data; multivariate analysis techniques, such as principal component analysis (PCA) or multidimensional scaling analysis (MDS), are applied to discover the potential relationship between equipment abnormalities and environmental abnormalities, and generate cold chain multidimensional correlation data. Then, a risk analysis algorithm (such as risk matrix method or Monte Carlo simulation) is used to perform potential risk analysis on the cold chain multidimensional correlation data; the cold chain multidimensional correlation data is processed to identify potential risk factors and generate cold chain potential risk data. A machine learning framework, such as TensorFlow technology, is used to construct a control model, and a cold chain logistics intelligent control model is constructed based on the real-time cold chain environment abnormal data and the real-time equipment operation abnormal data; the real-time cold chain environment abnormal data and the real-time equipment operation abnormal data are input, and the model parameters are optimized by using methods such as gradient descent to obtain a cold chain logistics intelligent control model, which can comprehensively consider the abnormal conditions of the environment and equipment to achieve dynamic control.

[0103] Step S5: Intelligently regulate the cold chain potential risk data through the cold chain logistics intelligent regulation model to obtain cold chain risk regulation data; monitor the standard cold chain logistics data set in real time through the cold chain risk regulation data to generate a real-time cold chain monitoring report; perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; extract risk regulation data from the cold chain risk regulation data to obtain risk regulation information;

[0104] In the embodiment of the present invention, the cold chain potential risk data is intelligently regulated by the cold chain logistics intelligent regulation model, and the model reasoning technology is applied to process the input cold chain potential risk data using the cold chain logistics intelligent regulation model to generate cold chain risk regulation data. Then, the standard cold chain logistics data set is monitored in real time by the cold chain risk regulation data; the standard cold chain logistics data set is monitored in real time by the cold chain risk regulation data through the real-time data analysis technology, and a real-time cold chain monitoring report is generated, wherein the real-time cold chain monitoring report contains the current monitoring status and risk assessment results. Then, the early warning analysis algorithm is used to perform early warning analysis on the real-time cold chain monitoring report, analyze the data in the monitoring report, identify potential abnormal situations, and generate abnormal warning information. Further, the normal cold chain logistics data in the real-time cold chain monitoring report is extracted by the data extraction tool to obtain normal cold chain logistics information. Finally, the risk control data in the cold chain risk control data is extracted by the data filtering and aggregation tool to obtain risk control information, ensuring that all relevant risk control information is accurately extracted and ready for subsequent operations and decisions.

[0105] Step S6: Build a monitoring cloud platform based on the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform; send abnormal warning information, normal cold chain logistics information and risk control information to the designated equipment of the production team based on the real-time cold chain monitoring cloud platform to perform cold chain logistics big data intelligent monitoring operations.

[0106] In an embodiment of the present invention, a monitoring cloud platform is constructed through cloud computing platform technology based on the real-time cold chain monitoring report, and the real-time cold chain monitoring cloud platform is constructed, which includes a real-time monitoring interface for the cold chain logistics environment and a real-time monitoring interface for equipment operation. Virtualization technology is used to deploy the various components of the monitoring platform, and a database is configured to store real-time cold chain monitoring data. After the cloud platform is built, the cloud platform RabbitMQ message queue technology is used to send abnormal warning information, normal cold chain logistics information, and risk control information to the designated equipment of the production team respectively; and these information are pushed to the device or application through an API interface or Webhook to ensure that the production team receives them in real time and can perform intelligent monitoring operations on the cold chain logistics big data.

[0107] Preferably, step S2 comprises the following steps:

[0108] Step S21: extracting the characteristic type of the cold chain logistics environment data to obtain the cold chain environment characteristic type data; constructing a characteristic matrix for the cold chain environment characteristic type data to obtain the cold chain environment characteristic matrix;

[0109] Step S22: performing environmental parameter numerical identification on the cold chain environment characteristic matrix to generate environmental parameter numerical data; performing time series analysis on the cold chain environment characteristic matrix according to the environmental parameter numerical data to obtain cold chain environment time series data;

[0110] Step S23: Record the real-time parameter changes of the cold chain environment time series data to obtain real-time environmental parameter data;

[0111] Step S24: Calculate the change rate of the real-time data of the environmental parameters to obtain environmental change rate data; monitor the fluctuation duration of the real-time data of the environmental parameters through the environmental change rate data to generate parameter fluctuation time data;

[0112] Step S25: Identify the fluctuation frequency of the cold chain environment time series data according to the parameter fluctuation time data to generate fluctuation frequency data;

[0113] Step S26: Perform abnormal environment analysis on the cold chain environment feature matrix based on the fluctuation frequency data to generate real-time cold chain environment abnormal data.

[0114] In the embodiment of the present invention, the characteristic type of cold chain logistics environment data is extracted to obtain the cold chain environment characteristic type data; the cold chain environment characteristic type data is processed and summarized using feature engineering technology to obtain the cold chain environment feature matrix. The cold chain environment characteristic matrix is ​​subjected to environmental parameter numerical identification, and data mining technology such as support vector algorithm is used to identify the specific value of each feature to generate environmental parameter numerical data; based on the environmental parameter numerical data, the time series analysis technology is used to perform time series analysis on the cold chain environment characteristic matrix according to the environmental parameter numerical data to obtain the cold chain environment time series data. Using the Apache Kafka stream data processing framework, the real-time parameter changes of the cold chain environment time series data are recorded to generate real-time data of environmental parameters; using data differential operation technology, the change rate of the real-time environmental parameter data is calculated to obtain environmental change rate data; based on the environmental change rate data, the time series analysis method is used to monitor the duration of environmental parameter fluctuations to generate parameter fluctuation time data; the fluctuation duration data is determined by analyzing the peak and valley values ​​in the data; based on the parameter fluctuation time data, the fluctuation frequency of the cold chain environment time series data is identified, and the fast Fourier transform technology is used to identify the fluctuation frequency of the cold chain environment time series data. Using the local outlier factor anomaly detection algorithm, the cold chain environment feature matrix is ​​analyzed for abnormal environments based on the fluctuation frequency data, abnormal environments are identified, and real-time cold chain environment abnormal data is generated.

[0115] Preferably, step S3 comprises the following steps:

[0116] Step S31: extracting equipment information by stage from the standard cold chain logistics data set using sensors to obtain equipment information by stage;

[0117] Step S32: monitor the operation information of the equipment in different stages to obtain the equipment operation data;

[0118] Step S33: performing load bearing test on the equipment phase information according to the equipment operation data to generate operation phase load data; performing collaborative load processing on the operation phase load data to obtain operation phase collaborative load data;

[0119] Step S34: Perform distributed real-time performance analysis on the equipment operation data based on the collaborative load data in the operation phase to obtain real-time operation performance data;

[0120] Step S35: Record the performance degradation trend of the equipment stage information through the real-time operation performance data to generate operation performance degradation data; perform abnormal pattern recognition on the operation performance degradation data to obtain operation abnormality data;

[0121] Step S36: Perform equipment abnormality detection on the equipment operation data according to the abnormal operation data to obtain real-time abnormal operation data of the equipment.

[0122] In an embodiment of the present invention, a sensor is used to extract equipment information in stages from a standard cold chain logistics data set to obtain equipment stage information; real-time monitoring technology is used to monitor the operation information of the equipment stage information to obtain equipment operation data. According to the equipment operation data, a load bearing test is performed on the equipment stage information, and load testing technology is used to simulate different load conditions, record the performance data of the equipment under each load condition, and generate operation stage load data; collaborative load processing is performed on the operation stage load data, and principal component analysis technology is used to integrate the results from different load tests to obtain operation stage collaborative load data; distributed computing technology is used to perform distributed real-time performance analysis on the equipment operation data based on the operation stage collaborative load data, and real-time operation performance data is generated through a performance regression analysis algorithm. The performance attenuation trend of the equipment stage information is recorded through real-time operation performance data, and the equipment performance data is analyzed using a trend analysis tool to generate operation performance attenuation data. Abnormal pattern recognition is performed on the operation performance attenuation data, and a statistical anomaly detection algorithm is used to identify data that does not conform to the normal operating mode, and abnormal operation data is obtained. Perform equipment anomaly detection on the equipment operation data based on the abnormal operation data, use the equipment fault neural network detection algorithm to analyze the equipment operation data, identify abnormal patterns, generate real-time equipment operation abnormality data; and record the abnormal status and fault information of the equipment.

[0123] Preferably, step S4 comprises the following steps:

[0124] Step S41: performing multi-dimensional separation on the real-time cold chain environment abnormal data according to the real-time equipment operation abnormal data to obtain cold chain multi-dimensional separation data; independently arranging the cold chain multi-dimensional separation data to obtain cold chain multi-dimensional arrangement data;

[0125] Step S42: extracting features of each dimension of the cold chain multi-dimensional arrangement data to obtain cold chain multi-dimensional feature data; constructing a cold chain multi-dimensional feature matrix for the cold chain multi-dimensional feature data to obtain a cold chain multi-dimensional feature matrix;

[0126] Step S43: performing associated node identification on the cold chain multi-dimensional feature matrix to generate cold chain multi-dimensional associated node data; performing strength measurement of each associated node on the cold chain multi-dimensional feature matrix through the cold chain multi-dimensional associated node data to obtain cold chain node strength data; performing dimensional correlation analysis on the cold chain multi-dimensional feature matrix based on the cold chain node strength data to obtain cold chain multi-dimensional associated data;

[0127] Step S44: performing potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data;

[0128] Step S45: constructing a cold chain logistics intelligent control model according to the real-time cold chain environment abnormality data and the real-time equipment operation abnormality data to obtain a cold chain logistics intelligent control pre-model, and training the cold chain logistics intelligent control pre-model using the real-time cold chain environment abnormality data and the equipment in real time to obtain a cold chain logistics intelligent control training model;

[0129] Step S46: Perform model cross-validation evaluation on the cold chain logistics intelligent control training model to obtain cold chain logistics intelligent control model evaluation data; adjust model parameters of the cold chain logistics intelligent control training model using the cold chain logistics intelligent control model evaluation data to obtain the cold chain logistics intelligent control model.

[0130] In an embodiment of the present invention, a data processing framework is used to perform multi-dimensional separation of equipment real-time operation abnormal data and real-time cold chain environment abnormal data to obtain cold chain multi-dimensional separation data; then, a dimension-based sorting algorithm is used to independently arrange the cold chain multi-dimensional separation data to obtain cold chain multi-dimensional arrangement data. Feature selection technology is used to extract key features from the cold chain multi-dimensional arrangement data to obtain cold chain multi-dimensional feature data; then, feature matrix construction technology is used to organize the cold chain multi-dimensional feature data into a cold chain multi-dimensional feature matrix; graph embedding technology is used to identify associated nodes in the matrix to generate cold chain multi-dimensional associated node data; weighted graph algorithm is used to measure the association strength between calculation nodes to obtain cold chain associated node strength data; based on the cold chain associated node strength data; dimension correlation analysis method is used to analyze the cold chain multi-dimensional feature matrix to generate cold chain multi-dimensional associated data. Through risk analysis technology, potential risk analysis is performed on the cold chain multi-dimensional associated data to generate cold chain potential risk data. According to real-time cold chain environment abnormal data and real-time equipment operation abnormal data, a cold chain logistics intelligent control pre-model is constructed through deep learning technology. The model structure includes a temporal convolutional neural network (TCN), which contains 8 convolutional layers, each layer is equipped with 64 convolution kernels, the convolution kernel size is 3×3, the stride is 1, and the ReLU activation function is used. In addition, a 3-layer long short-term memory network (LSTM) is used, each layer contains 128 LSTM units, the sequence length is set to 50, and the hidden layer dimension is 128. The self-attention mechanism is also introduced in the model, which is set to 8 attention heads, and the dimension of each head is 16. During the training process, the Adam optimization algorithm with an initial learning rate of 0.001 is used, the batch size is 64, the training rounds are 50 rounds, and the loss function is the mean square error (MSE). The pre-model is trained by real-time cold chain environment abnormal data and real-time equipment operation abnormal data to generate a cold chain logistics intelligent regulation training model. The cold chain logistics intelligent regulation training model is cross-validated and evaluated. Using the 10-fold cross-validation method, the dataset is divided into 10 subsets, 9 of which are used for training and 1 for testing, and repeated 10 times to evaluate the stability of the model. Evaluation indicators include accuracy, F1 score and mean square error (MSE). The Bayesian optimization algorithm is used to adjust the model's hyperparameters, including learning rate (range: 0.0001 to 0.01), number of LSTM layers (range: 2 to 4 layers), number of LSTM units per layer (range: 64 to 256 units), and convolution kernel size (range: 3×3 to 5×5). The hyperparameter combination that optimizes the model performance is selected to obtain the final cold chain logistics intelligent control model.

[0131] Preferably, step S44 includes the following steps:

[0132] Step S441: monitoring high-frequency fluctuation points of multi-dimensional correlation data of cold chain to generate multi-dimensional high-frequency fluctuation point data;

[0133] According to the multi-dimensional high-frequency fluctuation point data, the impact segment analysis of the cold chain multi-dimensional correlation data is carried out to obtain the high-frequency fluctuation impact segment data;

[0134] Step S442: Identify the risk factors of the high-frequency fluctuation affected segment data to obtain segment risk factor data;

[0135] According to the segment risk factor data, the potential risk type characteristics of the cold chain multi-dimensional correlation data are analyzed to obtain the potential risk type characteristic data;

[0136] Step S443: Evaluate the impact degree of the potential risk type feature data to generate impact degree data; perform abnormal change frequency analysis on the impact degree data to obtain impact abnormal change frequency data; calculate the impact range of the segment risk factor data based on the impact abnormal change frequency data to obtain risk impact range data;

[0137] Step S444: identifying the risk concentration area of ​​the cold chain multi-dimensional correlation data through the risk impact range data to obtain risk concentration area data; assessing the risk level of the risk concentration area data to generate risk level data;

[0138] Step S445: Analyze the potential risks of the cold chain multi-dimensional associated data according to the potential risk type characteristic data, risk impact range data and risk level data, and generate cold chain potential risk data, wherein the cold chain potential risk data includes temperature potential risk data and equipment potential risk data.

[0139] In the embodiment of the present invention, a high-frequency fluctuation detection algorithm is used to monitor the high-frequency fluctuation points of the cold chain multidimensional correlation data to identify the high-frequency fluctuation points in the data and generate multidimensional high-frequency fluctuation point data; through the multidimensional high-frequency fluctuation point data, a regional division algorithm is executed to analyze the impact segment of the cold chain multidimensional correlation data to obtain high-frequency fluctuation impact segment data. The IQR method of the statistical method is used to apply the risk factor identification technology to the high-frequency fluctuation impact segment data to identify the risk factors in the data and generate segment risk factor data; the principal component analysis technology is used to analyze the potential risk type characteristics of the cold chain multidimensional correlation data based on the segment risk factor data to obtain potential risk type characteristic data; the impact degree assessment is applied to the potential risk type characteristic data to generate the impact degree data; the impact degree data is analyzed by abnormal change frequency analysis to obtain the impact abnormal change frequency data. Based on the impact abnormal change frequency data and using the distance weighted regression algorithm, the impact range of the segment risk factor data is calculated to generate the risk impact range data. The risk clustering areas of cold chain multidimensional related data are identified through risk impact range data, and spatial clustering analysis technology is used to identify risk clustering area data, thereby obtaining risk clustering area data; the risk level of risk clustering area data is assessed through the risk matrix method to generate risk level data; the potential risks of cold chain multidimensional related data are analyzed and judged according to the potential risk type characteristic data, risk impact range data and risk level data, and the hierarchical analysis method is used to integrate the above data to generate cold chain potential risk data, wherein the cold chain potential risk data includes temperature potential risk data and equipment potential risk data.

[0140] As an example of the present invention, refer to Figure 2 As shown, in this example, step S5 includes:

[0141] Step S51: Intelligently regulate the cold chain potential risk data through the cold chain logistics intelligent regulation model to obtain cold chain risk regulation data;

[0142] Step S52: Real-time environmental parameter monitoring of cold chain logistics environment data is performed using cold chain risk control data to obtain real-time environmental parameter monitoring data;

[0143] Step S53: Real-time operation status monitoring of equipment operation data is performed using cold chain risk control data to obtain real-time monitoring data of equipment operation;

[0144] Step S54: Integrate the real-time monitoring data of environmental parameters and the real-time monitoring data of equipment operation to generate a real-time cold chain monitoring report;

[0145] Step S55: Perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; extract risk control data from the cold chain risk control data to obtain risk control information.

[0146] In an embodiment of the present invention, the cold chain potential risk data is intelligently regulated through a cold chain logistics intelligent regulation model. The model is based on a dynamically evolving deep reinforcement learning algorithm, and continuously optimizes model parameters through a real-time feedback mechanism to adapt to the changing cold chain environment, thereby obtaining cold chain risk regulation data. Based on the cold chain risk regulation data, real-time environmental parameter monitoring is performed on the cold chain logistics environmental data, and quantum dot temperature and humidity sensors and adaptive spectral sensors are used to monitor environmental parameters in real time; through edge computing technology, the sensor processes the environmental parameters in real time and uploads them to the cloud to generate high-precision real-time monitoring data of environmental parameters, achieving high accuracy and low latency in real-time monitoring. Real-time operation status monitoring of equipment operation data is performed through cold chain risk regulation data, and the equipment status is monitored in real time in combination with deep learning technology to generate real-time monitoring data for equipment operation. Based on the graph neural network fusion algorithm, the real-time monitoring data of environmental parameters and the real-time monitoring data of equipment operation are integrated to generate a real-time cold chain monitoring report, providing a comprehensive and real-time monitoring report that can more accurately reflect the overall status of the cold chain system; innovative multi-level early warning analysis is performed on the real-time cold chain monitoring report, combined with automated feature selection and reinforcement learning algorithms to automatically identify and adapt to different types of abnormal patterns, thereby generating abnormal warning information; at the same time, normal cold chain logistics data and cold chain risk control data in the real-time cold chain monitoring report are extracted, and intelligent data analysis technology is used to obtain detailed normal cold chain logistics information and risk control information, ensuring the comprehensiveness and accuracy of data processing.

[0147] As an example of the present invention, refer to Figure 3 As shown, in this example, step S51 includes:

[0148] Step S511: performing cold chain risk type analysis on the temperature potential risk data to obtain cold chain temperature risk type data, wherein the cold chain temperature risk type data includes excessive temperature data and continuous abnormal temperature change data;

[0149] Step S512: Intelligently control the cold chain temperature risk type data through the cold chain logistics intelligent control model. If the cold chain temperature risk type data is too high temperature data, the cold chain equipment refrigeration is automatically triggered to generate too high temperature control data; if the cold chain temperature risk type data is continuous abnormal temperature change data, the working cycle power of the cold chain equipment is optimized to generate continuous temperature change control data; the over-high temperature control data and the continuous temperature change control data are integrated to obtain the temperature potential risk control data;

[0150] Step S513: performing equipment risk type analysis on the equipment potential risk data to obtain equipment risk type data, wherein the equipment risk type data includes equipment vibration frequency abnormality and equipment operating efficiency reduction data;

[0151] Step S514: Intelligently control the equipment risk type data through the cold chain logistics intelligent control model. If the equipment risk type data is abnormal equipment vibration frequency, the equipment load is automatically reduced to generate equipment vibration frequency control data; if the equipment risk type data is equipment operating efficiency reduction data, emergency shutdown and switching to backup equipment are triggered to generate equipment shutdown switching control data; the equipment vibration frequency control data and the equipment shutdown switching control data are integrated to obtain equipment potential risk control data;

[0152] Step S515: Integrate the temperature potential risk control data and the equipment potential risk control data to obtain cold chain risk control data.

[0153] In an embodiment of the present invention, a cold chain risk type analysis is performed on the temperature potential risk data to obtain cold chain temperature risk type data, wherein the cold chain temperature risk type data includes over-temperature data and continuous abnormal temperature change data. The cold chain temperature risk type data is intelligently regulated by a cold chain logistics intelligent regulation model; for the identified over-temperature data, the model automatically triggers the refrigeration system of the cold chain equipment, adjusts the power and operating status of the refrigeration unit through the controller, and generates over-temperature regulation data. For the continuous abnormal temperature change data, the model optimizes the working cycle power of the cold chain equipment, and generates continuous temperature change regulation data by adjusting the operating cycle and power configuration of the equipment. Finally, the over-temperature regulation data and the continuous temperature change regulation data are integrated by using data integration technology to obtain temperature potential risk regulation data. An equipment risk type analysis is performed on the equipment potential risk data to obtain equipment risk type data, wherein the equipment risk type data includes abnormal equipment vibration frequency and decreased equipment operating efficiency data. The cold chain logistics intelligent control model is used to intelligently control the equipment risk type data; for abnormal equipment vibration frequency data, the model automatically reduces the equipment load and generates equipment vibration frequency control data by adjusting the control parameters of the load management system; for equipment operating efficiency reduction data, the model triggers the emergency shutdown program and switches to the backup equipment to generate equipment shutdown switching control data; the equipment vibration frequency control data is integrated with the equipment shutdown switching control data to obtain equipment potential risk control data. Using the data fusion algorithm, the temperature potential risk control data and the equipment potential risk control data are integrated to generate cold chain risk control data.

[0154] Preferably, step S55 includes the following steps:

[0155] Step S551: performing joint abnormality analysis on the real-time cold chain monitoring report to obtain real-time joint abnormality data; performing stage analysis on the real-time joint abnormality data to obtain real-time abnormal stage data;

[0156] Step S552: performing weight division processing on the real-time abnormal stage data to obtain abnormal stage weight data; performing priority feature extraction on the abnormal stage weight data to generate abnormal stage priority data;

[0157] Step S553: ​​Performing grade scoring according to the abnormal stage priority data to obtain grade scoring data; performing early warning analysis according to the grade scoring data to obtain abnormal warning information;

[0158] Step S554: performing normal cold chain logistics status on the real-time cold chain monitoring report to obtain normal cold chain status data; extracting logistics data of the normal cold chain status data to obtain normal cold chain logistics information;

[0159] Step S555: Identify risk control measures for the cold chain risk control data according to the real-time cold chain monitoring report to obtain risk control measures data; extract risk control data from the risk control measures data to obtain risk control information.

[0160] In an embodiment of the present invention, a joint abnormal analysis is performed on the real-time cold chain monitoring report, and a multivariate abnormality detection algorithm is used to identify and process multiple abnormal data points in the report, thereby obtaining real-time abnormal stage data; a weighted algorithm is used to assign weights to each stage according to the severity and frequency of the abnormal data, and abnormal stage weight data is generated; further, a feature extraction algorithm is used to extract priority features from the abnormal stage weight data to generate abnormal stage priority data. Grade scoring is performed according to the abnormal stage priority data, and the Z-score standardized scoring model is applied to grade the abnormal stage priority data to obtain grade scoring data; an early warning analysis is performed on the cold chain system according to the scoring data, and a threshold judgment method is applied to generate abnormal warning information from the grade scoring data, thereby generating early warning information; a normal cold chain logistics state analysis is performed on the real-time cold chain monitoring report, and the normal cold chain state is identified by the state detection algorithm to generate normal cold chain state data. The logistics data in the normal cold chain state data is extracted, and the normal cold chain logistics information is obtained from the normal state data using data extraction technology. A risk assessment method is adopted to identify risk control measures for cold chain risk control data based on real-time cold chain monitoring reports, identify the required risk control measures, and generate risk control measures data; data extraction technology is used to extract specific risk control data from the risk control measures data to obtain risk control information.

[0161] Preferably, step S6 comprises the following steps:

[0162] Step S61: constructing a monitoring cloud platform according to the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform, wherein the real-time cold chain monitoring cloud platform construction includes the construction of a real-time monitoring interface for the cold chain logistics environment and the construction of a real-time monitoring interface for equipment operation;

[0163] Step S62: partitioning the data stream based on the real-time cold chain monitoring cloud platform to obtain data stream partitioning information;

[0164] Step S63: Distinguish abnormal warning information, normal cold chain logistics information and risk control information according to the data flow partition information, and send the abnormal warning information, normal cold chain logistics information and risk control information to the designated equipment of the production team to perform cold chain logistics big data intelligent monitoring operations.

[0165] In an embodiment of the present invention, a monitoring cloud platform is constructed through a real-time cold chain monitoring report, and the microservice framework in the cloud computing architecture is used to develop and deploy the platform. First, a real-time monitoring interface for the cold chain logistics environment is constructed, and a front-end development framework, such as React or Angular, is used to design and implement a user interface, which integrates real-time data visualization component charts and dashboards to display environmental monitoring data; secondly, a real-time monitoring interface for equipment operation is constructed, and the same front-end development technology is used to design an equipment status display module to reflect the operating status of the equipment in real time; the data of this interface is obtained and updated from the real-time data stream by the background service through a RESTful API or a GraphQL interface. Data stream partitioning is performed based on the real-time cold chain monitoring cloud platform, and a stream processing framework is applied to perform data stream partitioning; data stream partitioning rules are set to divide data into different categories, such as environmental parameter data and equipment status data categories; data stream partitioning information is generated and recorded by configuring Kafka topic partitions or Flink data stream processing tasks. According to the data stream partition information, the abnormal warning information, normal cold chain logistics information and risk control information are distinguished; the data stream partition information is analyzed using the data routing algorithm, the data is classified into corresponding categories, and the classified abnormal warning information, normal cold chain logistics information and risk control information are sent to the designated equipment of the production team through the data transmission protocol to perform the intelligent monitoring operation of cold chain logistics big data.

[0166] In this specification, a cold chain logistics big data intelligent monitoring system is provided, which is used to execute the above-mentioned cold chain logistics big data intelligent monitoring method. The cold chain logistics big data intelligent monitoring system includes:

[0167] The data acquisition module is used to acquire the original data set of cold chain logistics; perform data preprocessing on the original data set of cold chain logistics to obtain the standard cold chain logistics data set; perform environmental information monitoring on the standard cold chain logistics data set to obtain the cold chain logistics environmental data;

[0168] The cold chain environment anomaly module is used to perceive the parameters of the cold chain logistics environment data in real time and obtain the real-time data of the environmental parameters; identify the abnormal fluctuations of the real-time data of the environmental parameters and generate the real-time cold chain environment anomaly data;

[0169] The equipment real-time operation abnormality module is used to monitor the equipment operation information of the standard cold chain logistics data set to obtain the equipment operation data; perform real-time performance analysis on the equipment operation data to obtain real-time operation performance data; perform abnormality detection on the equipment operation data based on the real-time operation performance data to generate real-time equipment operation abnormality data;

[0170] The cold chain logistics intelligent control model module is used to perform multi-dimensional correlation analysis on the real-time cold chain environment abnormal data through the real-time equipment operation abnormal data to obtain the cold chain multi-dimensional correlation data; perform potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data; construct the cold chain logistics intelligent control model based on the real-time cold chain environment abnormal data and the real-time equipment operation abnormal data to obtain the cold chain logistics intelligent control model;

[0171] The intelligent control module is used to intelligently control the cold chain potential risk data through the cold chain logistics intelligent control model to obtain cold chain risk control data; to monitor the standard cold chain logistics data set in real time through the cold chain risk control data to generate a real-time cold chain monitoring report; to perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; to extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; to extract risk control data from the cold chain risk control data to obtain risk control information;

[0172] The monitoring cloud platform module is used to build a monitoring cloud platform based on the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform; based on the real-time cold chain monitoring cloud platform, abnormal warning information, normal cold chain logistics information and risk control information are sent to the designated equipment of the production team to perform cold chain logistics big data intelligent monitoring operations.

[0173] The data acquisition module of the present invention obtains a standardized cold chain logistics data set by extracting and processing data from the original cold chain logistics data set, and monitors the environmental information of the data set to generate cold chain logistics environmental data, laying a solid foundation for further analysis. The cold chain environment anomaly module is used to perform real-time parameter monitoring and anomaly detection on environmental data, which can identify changes in environmental conditions, thereby generating real-time cold chain environment anomaly data in a timely manner, and effectively improving the ability to respond to environmental changes. The equipment real-time operation anomaly module is used for monitoring equipment operation information and real-time performance analysis, which can detect equipment failures or performance problems early, so as to take necessary maintenance measures, reduce the impact of equipment failures on cold chain logistics, and improve equipment operation and maintenance efficiency and the reliability of overall cold chain logistics. The cold chain logistics intelligent control model module is used to perform multi-dimensional correlation analysis through equipment operation anomaly data and environmental anomaly data, which can reveal potential risks in cold chain logistics, and by generating cold chain potential risk data and cold chain logistics intelligent control models, it can achieve comprehensive monitoring and intelligent control of the cold chain environment and equipment status. The intelligent control module is used for the cold chain logistics intelligent control model to control the cold chain potential risk data, generate cold chain risk control data, and monitor the standard cold chain logistics data set in real time to generate a real-time cold chain monitoring report. The early warning analysis of the report can issue abnormal warnings in time, extract normal cold chain logistics information and risk control information, and realize all-round monitoring of cold chain logistics, so as to timely discover and solve potential problems and reduce the risks in the cold chain logistics process. The monitoring cloud platform module is used to build a real-time cold chain monitoring cloud platform, automatically process abnormal warnings, normal cold chain logistics information and risk control information, and transmit the information to the equipment specified by the production team, improve the efficiency and accuracy of information transmission, and enable the production team to respond quickly to actual needs, thereby optimizing the execution effect of the intelligent monitoring of cold chain logistics big data. Therefore, the present invention realizes multi-dimensional correlation analysis of abnormal situations in cold chain logistics through Internet of Things technology, multi-dimensional data analysis technology, intelligent control technology and visualization technology to deal with different risks and abnormal situations; and intelligently monitors and controls the cold chain logistics process, realizing real-time monitoring and precise control of cold chain logistics.

[0174] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0175] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A cold chain logistics big data intelligent monitoring method, characterized in that: The following steps are involved: Step S1: Acquire the original cold chain logistics data set; perform data preprocessing on the original cold chain logistics data set to obtain a standard cold chain logistics data set; Conduct environmental information monitoring on the standard cold chain logistics data set to obtain cold chain logistics environmental data; Step S2: Real-time perception of parameters of cold chain logistics environment data to obtain real-time data of environmental parameters; Identify abnormal fluctuations in real-time environmental parameter data and generate real-time cold chain environmental abnormality data; Step S3: Monitor the equipment operation information of the standard cold chain logistics data set to obtain equipment operation data; Conduct real-time performance analysis on equipment operation data to obtain real-time operation performance data; Perform anomaly detection on equipment operation data based on real-time operation performance data to generate real-time equipment operation anomaly data; Step S4: Perform multi-dimensional correlation analysis on the real-time cold chain environment abnormal data through the real-time equipment operation abnormal data to obtain cold chain multi-dimensional correlation data; Conduct potential risk analysis on multi-dimensional cold chain related data to generate cold chain potential risk data; construct a cold chain logistics intelligent control model based on real-time cold chain environment abnormal data and real-time equipment operation abnormal data to obtain a cold chain logistics intelligent control model; Step S5: Intelligently regulate the cold chain potential risk data through the cold chain logistics intelligent regulation model to obtain cold chain risk regulation data; Real-time monitoring of standard cold chain logistics data sets through cold chain risk control data, generating real-time cold chain monitoring reports; Conduct early warning analysis on real-time cold chain monitoring reports to obtain abnormal warning information; Extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; Extract risk control data of cold chain risk control data to obtain risk control information; Step S6: constructing a monitoring cloud platform according to the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform; Based on the real-time cold chain monitoring cloud platform, abnormal warning information, normal cold chain logistics information and risk control information are sent to the designated equipment of the production team to perform cold chain logistics big data intelligent monitoring operations.

2. According to claim 1, a cold chain logistics big data intelligent monitoring method is characterized in that: Step S2 includes the following steps: Step S21: extracting the characteristic type of the cold chain logistics environment data to obtain the cold chain environment characteristic type data; constructing a characteristic matrix for the cold chain environment characteristic type data to obtain the cold chain environment characteristic matrix; Step S22: performing environmental parameter numerical identification on the cold chain environment characteristic matrix to generate environmental parameter numerical data; performing time series analysis on the cold chain environment characteristic matrix according to the environmental parameter numerical data to obtain cold chain environment time series data; Step S23: Record the real-time parameter changes of the cold chain environment time series data to obtain real-time environmental parameter data; Step S24: Calculate the change rate of the real-time data of the environmental parameters to obtain environmental change rate data; monitor the fluctuation duration of the real-time data of the environmental parameters through the environmental change rate data to generate parameter fluctuation time data; Step S25: Identify the fluctuation frequency of the cold chain environment time series data according to the parameter fluctuation time data to generate fluctuation frequency data; Step S26: Perform abnormal environment analysis on the cold chain environment feature matrix based on the fluctuation frequency data to generate real-time cold chain environment abnormal data.

3. According to claim 1, a cold chain logistics big data intelligent monitoring method is characterized in that: Step S3 includes the following steps: Step S31: extracting equipment information by stage from the standard cold chain logistics data set using sensors to obtain equipment information by stage; Step S32: monitor the operation information of the equipment in different stages to obtain the equipment operation data; Step S33: performing load bearing test on the equipment phase information according to the equipment operation data to generate operation phase load data; performing collaborative load processing on the operation phase load data to obtain operation phase collaborative load data; Step S34: Perform distributed real-time performance analysis on the equipment operation data based on the collaborative load data in the operation phase to obtain real-time operation performance data; Step S35: Record the performance degradation trend of the equipment stage information through the real-time operation performance data to generate operation performance degradation data; perform abnormal pattern recognition on the operation performance degradation data to obtain operation abnormality data; Step S36: Perform equipment abnormality detection on the equipment operation data according to the abnormal operation data to obtain real-time abnormal operation data of the equipment.

4. According to claim 1, a cold chain logistics big data intelligent monitoring method is characterized in that: Step S4 includes the following steps: Step S41: performing multi-dimensional separation on the real-time cold chain environment abnormal data according to the real-time equipment operation abnormal data to obtain cold chain multi-dimensional separation data; independently arranging the cold chain multi-dimensional separation data to obtain cold chain multi-dimensional arrangement data; Step S42: extracting features of each dimension of the cold chain multi-dimensional arrangement data to obtain cold chain multi-dimensional feature data; constructing a cold chain multi-dimensional feature matrix for the cold chain multi-dimensional feature data to obtain a cold chain multi-dimensional feature matrix; Step S43: performing associated node identification on the cold chain multi-dimensional feature matrix to generate cold chain multi-dimensional associated node data; performing strength measurement of each associated node on the cold chain multi-dimensional feature matrix through the cold chain multi-dimensional associated node data to obtain cold chain node strength data; performing dimensional correlation analysis on the cold chain multi-dimensional feature matrix based on the cold chain node strength data to obtain cold chain multi-dimensional associated data; Step S44: performing potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data; Step S45: constructing a cold chain logistics intelligent control model according to the real-time cold chain environment abnormality data and the real-time equipment operation abnormality data to obtain a cold chain logistics intelligent control pre-model, and training the cold chain logistics intelligent control pre-model using the real-time cold chain environment abnormality data and the equipment in real time to obtain a cold chain logistics intelligent control training model; Step S46: Perform model cross-validation evaluation on the cold chain logistics intelligent control training model to obtain cold chain logistics intelligent control model evaluation data; adjust model parameters of the cold chain logistics intelligent control training model using the cold chain logistics intelligent control model evaluation data to obtain the cold chain logistics intelligent control model.

5. The cold chain logistics big data intelligent monitoring method according to claim 4 is characterized in that: Step S44 includes the following steps: Step S441: monitoring high-frequency fluctuation points of multi-dimensional correlation data of cold chain to generate multi-dimensional high-frequency fluctuation point data; According to the multi-dimensional high-frequency fluctuation point data, the impact segment analysis of the cold chain multi-dimensional correlation data is carried out to obtain the high-frequency fluctuation impact segment data; Step S442: Identify the risk factors of the high-frequency fluctuation affected segment data to obtain segment risk factor data; According to the segment risk factor data, the potential risk type characteristics of the cold chain multi-dimensional correlation data are analyzed to obtain the potential risk type characteristic data; Step S443: Evaluate the impact degree of the potential risk type feature data to generate impact degree data; perform abnormal change frequency analysis on the impact degree data to obtain impact abnormal change frequency data; calculate the impact range of the segment risk factor data based on the impact abnormal change frequency data to obtain risk impact range data; Step S444: identifying the risk concentration area of ​​the cold chain multi-dimensional correlation data through the risk impact range data to obtain risk concentration area data; assessing the risk level of the risk concentration area data to generate risk level data; Step S445: Analyze the potential risks of the cold chain multi-dimensional associated data according to the potential risk type characteristic data, risk impact range data and risk level data, and generate cold chain potential risk data, wherein the cold chain potential risk data includes temperature potential risk data and equipment potential risk data.

6. The cold chain logistics big data intelligent monitoring method according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: Intelligently regulate the cold chain potential risk data through the cold chain logistics intelligent regulation model to obtain cold chain risk regulation data; Step S52: Real-time environmental parameter monitoring of cold chain logistics environment data is performed using cold chain risk control data to obtain real-time environmental parameter monitoring data; Step S53: Real-time operation status monitoring of equipment operation data is performed using cold chain risk control data to obtain real-time monitoring data of equipment operation; Step S54: Integrate the real-time monitoring data of environmental parameters and the real-time monitoring data of equipment operation to generate a real-time cold chain monitoring report; Step S55: Perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; extract risk control data from the cold chain risk control data to obtain risk control information.

7. The cold chain logistics big data intelligent monitoring method according to claim 6 is characterized in that: Step S51 includes the following steps: Step S511: performing cold chain risk type analysis on the temperature potential risk data to obtain cold chain temperature risk type data, wherein the cold chain temperature risk type data includes excessive temperature data and continuous abnormal temperature change data; Step S512: Intelligently control the cold chain temperature risk type data through the cold chain logistics intelligent control model. If the cold chain temperature risk type data is too high temperature data, the cold chain equipment refrigeration is automatically triggered to generate too high temperature control data; if the cold chain temperature risk type data is continuous abnormal temperature change data, the working cycle power of the cold chain equipment is optimized to generate continuous temperature change control data; integrate the excessive temperature control data and the continuous temperature change control data to obtain temperature potential risk control data; Step S513: performing equipment risk type analysis on the equipment potential risk data to obtain equipment risk type data, wherein the equipment risk type data includes equipment vibration frequency abnormality and equipment operating efficiency reduction data; Step S514: Intelligently control the equipment risk type data through the cold chain logistics intelligent control model. If the equipment risk type data is abnormal equipment vibration frequency, the equipment load is automatically reduced to generate equipment vibration frequency control data; if the equipment risk type data is equipment operating efficiency reduction data, emergency shutdown and switching to backup equipment are triggered to generate equipment shutdown switching control data; the equipment vibration frequency control data and the equipment shutdown switching control data are integrated to obtain equipment potential risk control data; Step S515: Integrate the temperature potential risk control data and the equipment potential risk control data to obtain cold chain risk control data.

8. The cold chain logistics big data intelligent monitoring method according to claim 6 is characterized in that: Step S55 includes the following steps: Step S551: performing joint abnormality analysis on the real-time cold chain monitoring report to obtain real-time joint abnormality data; performing stage analysis on the real-time joint abnormality data to obtain real-time abnormal stage data; Step S552: performing weight division processing on the real-time abnormal stage data to obtain abnormal stage weight data; performing priority feature extraction on the abnormal stage weight data to generate abnormal stage priority data; Step S553: ​​Performing grade scoring according to the abnormal stage priority data to obtain grade scoring data; performing early warning analysis according to the grade scoring data to obtain abnormal warning information; Step S554: performing normal cold chain logistics status on the real-time cold chain monitoring report to obtain normal cold chain status data; extracting logistics data of the normal cold chain status data to obtain normal cold chain logistics information; Step S555: Identify risk control measures for the cold chain risk control data according to the real-time cold chain monitoring report to obtain risk control measures data; extract risk control data from the risk control measures data to obtain risk control information.

9. The cold chain logistics big data intelligent monitoring method according to claim 1 is characterized in that: Step S6 includes the following steps: Step S61: constructing a monitoring cloud platform according to the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform, wherein the real-time cold chain monitoring cloud platform construction includes the construction of a real-time monitoring interface for the cold chain logistics environment and the construction of a real-time monitoring interface for equipment operation; Step S62: partitioning the data stream based on the real-time cold chain monitoring cloud platform to obtain data stream partitioning information; Step S63: Distinguish abnormal warning information, normal cold chain logistics information and risk control information according to the data flow partition information, and send the abnormal warning information, normal cold chain logistics information and risk control information to the designated equipment of the production team to perform cold chain logistics big data intelligent monitoring operations.

10. A cold chain logistics big data intelligent monitoring system, characterized in that: Used to execute a cold chain logistics big data intelligent monitoring method as claimed in claim 1, the cold chain logistics big data intelligent monitoring system comprises: The data acquisition module is used to acquire the original data set of cold chain logistics; perform data preprocessing on the original data set of cold chain logistics to obtain the standard cold chain logistics data set; perform environmental information monitoring on the standard cold chain logistics data set to obtain the cold chain logistics environmental data; The cold chain environment anomaly module is used to perceive the parameters of the cold chain logistics environment data in real time and obtain the real-time data of the environmental parameters; identify the abnormal fluctuations of the real-time data of the environmental parameters and generate the real-time cold chain environment anomaly data; The equipment real-time operation abnormality module is used to monitor the equipment operation information of the standard cold chain logistics data set to obtain the equipment operation data; perform real-time performance analysis on the equipment operation data to obtain real-time operation performance data; perform abnormality detection on the equipment operation data based on the real-time operation performance data to generate real-time equipment operation abnormality data; The cold chain logistics intelligent control model module is used to perform multi-dimensional correlation analysis on the real-time cold chain environment abnormal data through the real-time equipment operation abnormal data to obtain the cold chain multi-dimensional correlation data; perform potential risk analysis on the cold chain multi-dimensional correlation data to generate cold chain potential risk data; construct the cold chain logistics intelligent control model based on the real-time cold chain environment abnormal data and the real-time equipment operation abnormal data to obtain the cold chain logistics intelligent control model; The intelligent control module is used to intelligently control the cold chain potential risk data through the cold chain logistics intelligent control model to obtain cold chain risk control data; to monitor the standard cold chain logistics data set in real time through the cold chain risk control data to generate a real-time cold chain monitoring report; to perform early warning analysis on the real-time cold chain monitoring report to obtain abnormal warning information; to extract normal cold chain logistics data from the real-time cold chain monitoring report to obtain normal cold chain logistics information; to extract risk control data from the cold chain risk control data to obtain risk control information; The monitoring cloud platform module is used to build a monitoring cloud platform based on the real-time cold chain monitoring report to obtain a real-time cold chain monitoring cloud platform; based on the real-time cold chain monitoring cloud platform, abnormal warning information, normal cold chain logistics information and risk control information are sent to the designated equipment of the production team to perform cold chain logistics big data intelligent monitoring operations.

Images