Transportation strategy optimization method and system applied to cold chain transportation

Abstract

The invention provides a transportation strategy optimization method and system applied to cold-chain transportation, and the method comprises the steps: firstly obtaining a transportation data set composed of equipment operation parameters and transportation environment data of transportation equipment in a transportation period in a cold-chain transportation process, and then carrying out the feature extraction of the transportation data set; the equipment feature set and the environment feature set are input into a preset exception analysis model for joint exception analysis, an exception analysis result containing an equipment exception type and an environment exception type is generated, and the equipment exception type and the environment exception type are generated according to the exception analysis result and a preset report generation rule. According to the method, a transportation abnormality analysis report including abnormal condition description, occurrence time periods and influence evaluation is generated, and finally, a transportation optimization strategy for transportation equipment maintenance and transportation environment regulation and control is generated based on the report and historical transportation data and is fed back to a cold chain transportation management system, so that the cold chain transportation quality and efficiency can be improved, and the cargo safety is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cold chain transportation, in particular to a transportation strategy optimization method and system applied to cold chain transportation. BACKGROUND

[0002] In the cold chain transportation industry, it is crucial to ensure the quality and safety of goods during transportation. Cold chain transportation involves the transportation of goods that require strict control of environmental conditions such as temperature and humidity, such as fresh vegetables. During the cold chain transportation process, a large amount of transportation data can be generated, including operating parameters of transportation equipment such as power of refrigeration equipment, temperature adjustment frequency, and transportation environment data such as temperature and humidity inside the transportation compartment.

[0003] Currently, the analysis of cold chain transportation data mainly adopts traditional methods. These methods often analyze the operating parameters of transportation equipment or transportation environment data in isolation, lacking comprehensive consideration of the correlation between the two. For example, when analyzing equipment failures, only the operating parameters of the equipment itself may be focused on, while ignoring the impact of environmental factors on equipment operation; when analyzing environmental abnormalities, the adjusting effect of equipment operation status on environmental conditions may also not be fully considered. The above isolated analysis method is difficult to comprehensively and accurately identify possible abnormal situations during transportation, cannot take effective measures in a timely manner, is easy to cause damage to the quality of goods, increases transportation cost, and even affects the safety and effectiveness of goods, causing great economic loss and reputation risk to cold chain transportation enterprises. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a transportation strategy optimization method and system applied to cold chain transportation.

[0005] In combination with the first aspect of the present application, a transportation strategy optimization method applied to cold chain transportation is provided. The transportation strategy optimization method applied to cold chain transportation comprises: obtaining a set of transportation data generated during cold chain transportation, the set of transportation data comprising device operating parameters of transportation equipment within a transportation period and transportation environment data, the device operating parameters being used to reflect the working status of the transportation equipment, and the transportation environment data being used to reflect the environmental conditions in the transportation space; performing feature extraction processing on the set of transportation data to obtain a set of device features related to the working status of the transportation equipment and a set of environmental features related to the environmental conditions of the transportation environment, the set of device features comprising key features reflecting the operating status of the equipment, and the set of environmental features comprising key features reflecting the environmental status of the transportation environment; The set of equipment features and the set of environmental features are input into a preset anomaly analysis model. The anomaly analysis model is used to perform joint anomaly analysis on the working status of the transportation equipment and the transportation environment, and generate anomaly analysis results that include equipment anomaly types and environmental anomaly types. The anomaly analysis results are used to indicate possible anomalies during transportation. Based on the anomaly analysis results and the preset report generation rules, a transportation anomaly analysis report is generated, which includes a description of the anomaly, the time period of the anomaly, and an assessment of the anomaly's impact. Based on the transportation anomaly analysis report and historical transportation data, transportation optimization strategies for transportation equipment maintenance and transportation environment control are generated, and these strategies are fed back to the cold chain transportation management system to guide transportation operations.

[0006] In conjunction with the second aspect of this application, a transportation strategy optimization system for cold chain transportation is provided. The system includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the system implements the aforementioned transportation strategy optimization method for cold chain transportation.

[0007] In conjunction with a third aspect of this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, and when the computer-executable instructions are executed, the aforementioned transportation strategy optimization method applied to cold chain transportation is implemented.

[0008] By combining any of the above aspects and comprehensively acquiring the operating parameters of transportation equipment and transportation environment data during cold chain transportation, feature extraction processing is performed on the transportation data set to obtain equipment feature sets and environmental feature sets. This allows for the accurate extraction of key information reflecting the working status of transportation equipment and the condition of the transportation environment. The equipment feature sets and environmental feature sets are then input into a preset anomaly analysis model for joint anomaly analysis. This fully considers the correlation between equipment operating status and transportation environment conditions, enabling a more comprehensive and accurate identification of potential equipment and environmental anomaly types during transportation. Accurate anomaly analysis results are generated, and a transportation anomaly analysis report is produced based on the anomaly analysis results and preset report generation rules. This report details the anomaly, its occurrence time, and its impact assessment. Based on the transportation anomaly analysis report and historical transportation data, transportation optimization strategies are generated and fed back to the cold chain transportation management system. This provides precise guidance for transportation equipment maintenance and transportation environment control, helping to improve the quality and efficiency of cold chain transportation, reduce transportation costs, and ensure the safety and effectiveness of goods. Attached Figure Description

[0009] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained in conjunction with these drawings without creative effort.

[0010] Figure 1 This application provides a schematic flowchart of a transportation strategy optimization method for cold chain transportation. Detailed Implementation

[0011] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0013] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0014] Figure 1 This document illustrates a flowchart of a transportation strategy optimization method for cold chain transportation provided in an embodiment of this application. It should be understood that in other embodiments, the order of some steps in the transportation strategy optimization method for cold chain transportation in this embodiment can be shared based on actual needs, or some steps can be omitted or maintained. The detailed components of this transportation strategy optimization method for cold chain transportation include: Step S110: Obtain the transportation data set generated during the cold chain transportation process. The transportation data set includes the equipment operating parameters and transportation environment data of the transportation equipment during the transportation period. The equipment operating parameters are used to reflect the working status of the transportation equipment, and the transportation environment data are used to reflect the environmental conditions within the transportation space.

[0015] In the context of cold chain transportation of vegetables, the quality of vegetables is affected by the stringent requirements of the transportation environment. Any abnormal operation of the transportation equipment or unsuitable conditions in the transportation environment can impact the quality of the vegetables. Therefore, it is necessary to collect relevant data from multiple aspects. The transportation equipment operates continuously throughout the transportation period, and changes in its operating status directly affect the preservation conditions of the vegetables; moreover, the environmental conditions within the transportation space, such as temperature and humidity, are closely related to the freshness of the vegetables.

[0016] Step S111: Collect equipment operating parameters of the transportation equipment in real time by using sensors deployed on the transportation equipment. The equipment operating parameters include parameters that reflect the status of the transportation equipment's power system, parameters that reflect the status of the transportation equipment's refrigeration system, and parameters that reflect the positioning information of the transportation equipment.

[0017] To collect equipment operating parameters, various types of sensors are deployed on the transportation equipment. For the power system, sensors can collect several key parameters. For example, the engine's operating status is crucial for the normal operation of the transportation equipment. Sensors can collect engine speed, and changes in speed reflect the engine's workload. When the engine speed is too high or too low, it may indicate a malfunction or abnormal operating condition. Simultaneously, engine torque parameters can also be collected. Torque is related to the engine's output power, which can further help determine whether the engine's power output is stable. In addition, sensors can collect parameters such as engine oil temperature and coolant temperature. These parameters reflect the engine's heat dissipation and lubrication conditions, ensuring that the engine operates under suitable temperature and lubrication conditions.

[0018] In the refrigeration system, sensors collect a series of parameters related to cooling performance and system operation. The compressor is the core component of the refrigeration system, and sensors can collect its operating frequency; changes in the operating frequency affect the cooling capacity. Refrigerant pressure and temperature are also important parameters; abnormal changes in pressure and temperature may indicate leaks or blockages in the refrigeration system. Furthermore, the temperature and pressure of the condenser and evaporator can be collected, and these parameters reflect the heat exchange efficiency of the refrigeration system.

[0019] Location information is crucial for monitoring the position and progress of transportation equipment. GPS sensors can acquire the latitude and longitude information of the equipment in real time, thus determining its exact location on a map. Simultaneously, information such as the equipment's speed and direction of travel can be obtained, which helps monitor the rationality of the transportation route and whether the delivery is on time.

[0020] Step S112: Real-time collection of transportation environment data by sensors deployed in the transportation space, including temperature data, humidity data and gas composition data within the transportation space.

[0021] Within the transport space, various sensors are deployed to collect environmental data to ensure the vegetables are kept in a suitable environment. Temperature sensors are essential, continuously monitoring the temperature at different locations within the transport space. Because vegetables are highly sensitive to temperature, different types have different suitable storage temperature ranges. For example, some leafy vegetables are best stored at lower temperatures, while root vegetables may have relatively higher temperature requirements. By evenly distributing multiple temperature sensors within the transport space, a comprehensive understanding of the temperature distribution can be obtained, preventing localized excessively high or low temperatures.

[0022] Humidity sensors are used to measure the humidity of the air within the transport space. Excessive humidity can cause mold to grow on the surface of vegetables, while excessively low humidity will cause them to wilt and lose moisture. Therefore, it is necessary to monitor humidity levels in real time and adjust accordingly. Humidity sensors can be installed at different heights and locations within the transport space to obtain more accurate humidity data.

[0023] Gas composition sensors can detect the concentration of gases such as oxygen and carbon dioxide within the transport space. Vegetables undergo respiration during storage, consuming oxygen and producing carbon dioxide. If the oxygen concentration is too low or the carbon dioxide concentration is too high, it will affect the respiration process, leading to a decline in vegetable quality. By monitoring the gas composition concentration in real time, the ventilation system can be adjusted promptly to maintain a balance of gas composition within the transport space.

[0024] Step S113: Arrange the collected equipment operating parameters and transportation environment data according to the time sequence of data collection to generate a transportation data set with a time sequence relationship. Each data unit in the transportation data set contains corresponding timestamp information.

[0025] After collecting equipment operating parameters and transportation environment data, this data needs to be organized and arranged. Since the data was collected at different points in time, it needs to be arranged chronologically to clearly understand the changes during transportation. Each data unit contains a corresponding timestamp, accurate to the minute, such as hour, minute, or second. Through timestamps, different types of data can be correlated along the time dimension, forming a complete transportation data set.

[0026] For example, at a specific point in time, data such as engine speed, refrigeration system parameters, temperature, humidity, and gas composition within the transport space can be recorded simultaneously. Arranging these data sequentially in chronological order yields a transport data set with a time-series relationship. This transport data set can be used for subsequent data analysis and anomaly detection. By analyzing data trends, potential problems during transportation can be identified promptly.

[0027] Step S120: Perform feature extraction processing on the transportation data set to obtain a set of equipment features related to the working status of the transportation equipment and a set of environmental features related to the transportation environment. The set of equipment features includes key features that reflect the operating status of the equipment, and the set of environmental features includes key features that reflect the transportation environment.

[0028] After acquiring the transportation dataset, feature extraction is necessary to more effectively analyze the operational status of transportation equipment and the conditions of the transportation environment. The purpose of feature extraction is to extract features that reflect key information from a large amount of raw data, thereby reducing the dimensionality of the data and improving the efficiency and accuracy of the analysis.

[0029] Step S121: Filter the equipment operating parameters in the transportation data set, remove redundant parameters, and retain the key equipment operating parameters that can directly reflect the working status of the transportation equipment.

[0030] Within transportation datasets, equipment operating parameters contain a wealth of information, but some parameters may be redundant. This redundancy may stem from repeated sensor data collection or data correlation. To improve the efficiency and accuracy of data analysis, it is necessary to filter the equipment operating parameters. This filtering process is based on the correlation between the parameters and the operating status of the transportation equipment.

[0031] For example, multiple parameters related to engine operating status may be collected, but some of these parameters may exhibit strong correlations. In such cases, the most representative parameter can be selected as the key equipment operating parameter. Similarly, parameters for the refrigeration system need to be screened to remove those with minimal impact on the system's operating status or those highly correlated with other parameters. Through screening, key equipment operating parameters that directly reflect the operating status of the transportation equipment can be retained; these parameters will be used for subsequent feature extraction and analysis.

[0032] Step S122: Standardize the operating parameters of the key equipment to obtain standardized equipment operating parameters.

[0033] After identifying the key equipment operating parameters, it is necessary to standardize them to facilitate subsequent analysis and processing, as the dimensions and value ranges of different parameters may vary. The purpose of standardization is to transform the data of different parameters to the same scale and eliminate the influence of dimensions.

[0034] There are several common standardization methods. For example, normalization can be used to map the data of each parameter to a specific interval, such as the [0, 1] interval. Specifically, for each parameter, its maximum and minimum values ​​are first calculated. Then, the minimum value is subtracted from each data point, and the result is divided by the difference between the maximum and minimum values ​​to obtain the normalized value. Standardization makes data from different parameters comparable, improving the accuracy of subsequent analyses.

[0035] Step S123: Process the standardized equipment operating parameters, extract equipment features that reflect the changing trend of the working status of the transportation equipment, and generate a set of equipment features. Each equipment feature in the set of equipment features has a corresponding relationship with the key equipment operating parameters.

[0036] Standardized equipment operating parameters are processed to extract equipment characteristics that reflect the changing trends of the transportation equipment's working status. The specific processing can be divided into the following steps: Step S1231: Divide the standardized equipment operating parameters into multiple equipment parameter time periods according to the time series, and each equipment parameter time period contains multiple continuously collected equipment operating parameters.

[0037] To analyze the changing trends in the operating status of transportation equipment, standardized equipment operating parameters need to be divided into time series. The division is based on time intervals, dividing the entire transportation period into multiple equipment parameter time periods. Each equipment parameter time period contains multiple continuously collected equipment operating parameters, allowing for analysis of parameter changes within each time period.

[0038] For example, transportation periods can be divided into hourly segments, each containing all equipment operating parameters collected within that hour. This division allows for separate analysis of equipment operating parameters across different time periods, revealing how the transportation equipment's operational status changes over these time intervals.

[0039] Step S1232: For each time period of equipment parameters, calculate the mean, variance, and rate of change of the equipment operating parameters as the basic characteristics of the equipment status.

[0040] Within each time period for equipment parameters, statistical analysis is performed on the equipment operating parameters to calculate their mean, variance, and rate of change. The mean reflects the average level of the equipment operating parameters within that time period, the variance reflects the fluctuation of the equipment operating parameters, and the rate of change reflects the speed at which the equipment operating parameters change.

[0041] For example, for engine speed parameters, the mean, variance, and rate of change of the speed are calculated for each time period of the equipment parameters. The mean represents the average engine speed during that time period, the variance represents the degree of fluctuation in the speed, and the rate of change represents how quickly the speed changes. These statistical indicators can serve as basic characteristics of the equipment status, used to describe the working status of the transportation equipment during that time period.

[0042] Step S1233: Analyze the variation pattern of equipment operating parameters between different equipment parameter time periods, and extract equipment periodic features to reflect the periodic changes in equipment working status.

[0043] In addition to analyzing the changes in equipment operating parameters within each time period, it is also necessary to analyze the patterns of change in equipment operating parameters across different time periods. By observing the trends in equipment operating parameters over different time periods, it is possible to identify whether there are periodic changes in the equipment's operating status.

[0044] For example, by analyzing the changes in engine speed over different equipment parameters over time periods, it may be found that the engine speed exhibits certain periodic fluctuations. These periodic fluctuations may be related to the road conditions or operating mode of the transportation equipment. Extracting these periodic changes as equipment periodic characteristics can provide a more comprehensive understanding of the transportation equipment's operating status.

[0045] Step S1234: Combine the basic features of equipment status and the periodic features of equipment to generate a set of equipment features containing multiple dimensions. The set of equipment features is used to reflect the changes in the working status of the transportation equipment during the transportation period.

[0046] Finally, the basic characteristics of equipment status and the characteristics of equipment cycle are combined to generate a set of equipment features. The set of equipment features contains features of multiple dimensions, which reflect the changes in the working status of the transportation equipment during the transportation period from different perspectives.

[0047] For example, the equipment feature set may include multiple dimensions of characteristics such as the engine's mean speed, variance, rate of change, and periodic variation. By analyzing the equipment feature set, a more comprehensive and accurate understanding of the transportation equipment's operating status can be achieved, and potential anomalies can be detected in a timely manner.

[0048] Step S124: Filter the transportation environment data in the transportation data set to generate key transportation environment data that directly reflects the transportation environment status.

[0049] The transportation environment data within the transportation dataset also needs to be filtered. The purpose of filtering is to remove parameters that have little impact on the transportation environment or are highly correlated with other parameters, and to retain key transportation environment data that directly reflects the transportation environment.

[0050] For example, temperature data within a transportation space may be collected from multiple locations, but the temperature data from some locations may have a high correlation with the temperature data from other locations. In such cases, the temperature data from the most representative location can be selected as the key transportation environment data. Similar screening is required for humidity data and gas composition data.

[0051] Step S125: Standardize the key transportation environment data to obtain standardized transportation environment data.

[0052] After identifying the critical transportation environment data, it is necessary to standardize it to facilitate subsequent analysis and processing. The standardization method is similar to that used for critical equipment operating parameters; it involves converting data from different parameters to the same scale to eliminate the influence of dimensions.

[0053] For example, normalization methods can be used to map temperature, humidity, and gas composition data to the [0, 1] interval, respectively. Standardization makes different key transportation environment data comparable, improving the accuracy of subsequent analyses.

[0054] Step S126: Process the standardized transportation environment data, extract environmental features that reflect the changing trends of the transportation environment, and generate an environmental feature set. Each environmental feature in the environmental feature set corresponds to key transportation environment data.

[0055] Standardized transportation environment data is processed to extract environmental features that reflect trends in transportation environment conditions. The specific processing procedure is similar to that for standardizing equipment operating parameters.

[0056] Step S1261: Divide the standardized transportation environment data into multiple environmental data time periods according to the time series, and each environmental data time period contains multiple transportation environment data collected continuously.

[0057] Standardized transportation environment data is divided into multiple time-series segments, each containing continuously collected transportation environment data. This allows for analysis of changes in the transportation environment data within each time segment.

[0058] For example, transportation periods can be divided into hourly segments, each containing environmental data collected within that hour, such as temperature, humidity, and gas composition. This segmentation allows for separate analysis of environmental data across different time periods, revealing how environmental conditions change over time.

[0059] Step S1262: For each environmental data time period, calculate the mean, variance, and rate of change of the transportation environmental data as basic characteristics of the environmental state.

[0060] Within each environmental data period, statistical analysis is performed on the transportation environmental data to calculate its mean, variance, and rate of change. The mean reflects the average level of the transportation environmental data within that period, the variance reflects the fluctuation of the transportation environmental data, and the rate of change reflects the speed at which the transportation environmental data changes.

[0061] For example, for temperature data, within each environmental data time period, the mean, variance, and rate of change of temperature are calculated. The mean represents the average temperature of the transportation space during that time period, the variance represents the degree of temperature fluctuation, and the rate of change represents how quickly the temperature changes. These statistical indicators can serve as basic characteristics of the environmental state, used to describe the condition of the transportation environment during that time period.

[0062] Step S1263: Analyze the variation patterns of transportation environment data across different time periods and extract environmental periodic features to reflect the periodic changes in transportation environment conditions.

[0063] In addition to analyzing the changes in transportation environmental data within each specific time period, it is also necessary to analyze the patterns of change in transportation environmental data across different time periods. By observing the trends in transportation environmental data over different time periods, it is possible to identify whether there are periodic changes in the transportation environment.

[0064] For example, by analyzing temperature variations across different environmental data periods, it may be discovered that there are periodic fluctuations in temperature within the transportation space. These periodic fluctuations may be related to changes in the external environment or the operating mode of the transportation equipment's refrigeration system. Extracting these periodic variations as environmental periodic characteristics can provide a more comprehensive understanding of the transportation environment.

[0065] Step S1264: Combine the basic environmental state features and the environmental periodic features to generate an environmental feature set containing multiple dimensions of features. The environmental feature set is used to reflect the changes in the transportation environment during the transportation period.

[0066] Finally, the basic environmental state characteristics and environmental periodic characteristics are combined to generate an environmental feature set. This environmental feature set contains features across multiple dimensions, reflecting the changes in the transportation environment during the transportation period from different perspectives.

[0067] For example, the set of environmental features may include multiple dimensions such as the mean, variance, rate of change, and periodicity of temperature. By analyzing the set of environmental features, we can gain a more comprehensive and accurate understanding of the transportation environment and promptly identify any potential anomalies.

[0068] Step S130: Input the equipment feature set and the environmental feature set into a preset anomaly analysis model, and perform joint anomaly analysis on the working status of the transportation equipment and the transportation environment through the anomaly analysis model to generate anomaly analysis results containing equipment anomaly types and environmental anomaly types. The anomaly analysis results are used to indicate possible anomalies during transportation.

[0069] After obtaining the equipment feature set and the environmental feature set, in order to promptly detect potential anomalies during transportation, these sets need to be input into a pre-set anomaly analysis model for joint anomaly analysis. The anomaly analysis model is pre-trained and can analyze the input features, identify anomalies that do not conform to normal transportation status patterns, and determine the type of anomaly.

[0070] Step S131: Concatenate the device feature set and the environment feature set to generate a joint feature set containing both device features and environment features.

[0071] First, the equipment feature set and the environmental feature set are concatenated. The purpose of concatenation is to combine two different types of feature sets into a joint feature set containing more information. Each feature vector in the joint feature set contains information about both equipment and environmental features, thus providing a more comprehensive reflection of the status during transportation.

[0072] For example, the equipment feature set includes engine speed characteristics, refrigeration system parameter characteristics, etc., while the environmental feature set includes temperature characteristics, humidity characteristics, etc. After concatenating these two feature sets, each feature vector in the joint feature set simultaneously contains information about both equipment and environmental characteristics.

[0073] Step S132: Input the joint feature set into the feature processing layer of the anomaly analysis model, perform noise reduction and dimension transformation on the joint features, and obtain preprocessed features suitable for model analysis.

[0074] Next, the joint feature set is input into the feature processing layer of the anomaly analysis model. The main function of the feature processing layer is to perform noise reduction and dimensionality transformation on the joint features. Noise reduction can remove noise and interference that may exist in the joint features, improving the quality of the features. Dimensionality transformation can adjust the dimensions of the joint features to make them more suitable for the model's analysis.

[0075] For example, the feature processing layer can use filtering algorithms to denoise the joint features, removing noise caused by sensor errors or external interference. Simultaneously, the feature processing layer can use methods such as principal component analysis to perform dimensionality transformation on the joint features, converting high-dimensional joint features into low-dimensional preprocessed features, reducing computational load and improving analysis efficiency.

[0076] Step S133: Analyze the preprocessed features through the anomaly detection layer of the anomaly analysis model to identify abnormal features that do not conform to the normal transportation state feature pattern.

[0077] The anomaly detection layer of the anomaly analysis model analyzes the preprocessed features and identifies anomalous features that do not conform to the characteristics of normal transportation status. The working principle of the anomaly detection layer is based on a pre-trained normal transportation status feature model.

[0078] Step S1331: Using the pre-trained normal transportation state feature model in the anomaly analysis model, generate the feature distribution range under normal transportation state.

[0079] The normal transport status feature model is trained using a large amount of normal transport data, and it can learn the distribution patterns of features under normal transport conditions. Using this model, the feature distribution range under normal transport conditions can be generated.

[0080] For example, a normal transportation state characteristic model can use statistical analysis to calculate the mean and standard deviation of each characteristic under normal transportation conditions, thereby determining the distribution range of the characteristics.

[0081] Step S1332: Compare the preprocessed features with the feature distribution range under normal transportation conditions to determine whether the preprocessed features exceed the normal distribution range.

[0082] The preprocessed features are compared with the feature distribution range under normal transportation conditions to determine whether the preprocessed features exceed the normal distribution range. For each preprocessed feature vector, the feature values ​​of each dimension are compared one by one with the feature distribution range of the corresponding dimension under normal transportation conditions. If a feature value of a certain dimension exceeds the normal distribution range, then the feature value is considered to be abnormal. For example, for equipment features and environmental features included in the joint feature set, the engine speed feature in the equipment features and the temperature feature in the environmental features are checked to see if they exceed the normal range. For the engine speed feature, if its feature value at a certain moment is higher than the upper limit of the engine speed feature distribution range under normal transportation conditions, or lower than the lower limit, then the engine speed feature is marked as a possible abnormal feature. The same logic applies to the temperature feature; if its value is not within the normal temperature distribution range, it is considered a possible abnormal feature.

[0083] Step S1333: For preprocessing features that exceed the normal distribution range, identify them as abnormal features and record the corresponding equipment features and environmental features.

[0084] Once a preprocessed feature is determined to be outside the normal distribution range, it is identified as an anomalous feature. Simultaneously, the corresponding equipment and environmental features of this anomalous feature need to be recorded for subsequent analysis of the specific source of the anomaly. Since the joint feature set is composed of the equipment and environmental feature sets, the corresponding equipment and environmental features can be inferred from the position information of the preprocessed feature within the joint feature set. For example, if an anomalous feature is located within the position range of its corresponding equipment feature in the joint feature set, then it can be determined that the anomalous feature is related to equipment, and further analysis can be performed on the specific equipment operating parameters corresponding to the anomalous feature, such as engine speed or refrigeration system pressure. If an anomalous feature is located within the position range of its corresponding environmental feature in the joint feature set, then it can be determined that the anomalous feature is related to the environment, and its corresponding specific transportation environment data features, such as temperature and humidity, can be analyzed.

[0085] Step S1334: Assess the severity of the abnormal features based on their frequency and duration of occurrence.

[0086] The severity of anomalies depends not only on whether they exceed the normal range, but also on their frequency and duration. Frequent and prolonged anomalies generally indicate more serious problems. For each anomaly, its frequency throughout the transportation process is calculated—the ratio of the number of times the anomaly occurred to the total number of observations. Simultaneously, the duration of the anomaly is recorded—the time elapsed from its first occurrence to its last. These two indicators are used to comprehensively assess the severity of the anomaly. For example, if an abnormal engine speed occurs frequently and lasts for a long time each time, the corresponding engine problem can be considered serious and may affect the normal operation of the transportation equipment. Conversely, if an abnormal temperature occurs only occasionally and for a short duration, its severity is relatively low, possibly due to temporary external disturbances.

[0087] Step S134: Determine the equipment anomaly type and the environmental anomaly type based on the equipment characteristics and environmental characteristics corresponding to the anomaly characteristics.

[0088] After identifying anomalous features, the type of anomaly is determined based on the corresponding equipment and environmental characteristics. For equipment-related anomalous features, the specific equipment operating parameters are analyzed, and the equipment's working principle and common failure modes are considered to determine the anomalous type. For example, if the engine speed is abnormally high and accompanied by an abnormally high engine temperature, the anomalous type could be a failure in the engine's cooling system or fuel supply system. For refrigeration system anomalous features, such as abnormally low refrigerant pressure, combined with the refrigeration system's working principle, the anomalous type could be a refrigeration system leak. For environment-related anomalous features, the specific transportation environment data is analyzed to determine the environmental anomalous type. For example, if the temperature in the transportation space is abnormally high and the humidity is abnormally low, the environmental anomalous type could be a ventilation system failure or insufficient cooling capacity of the refrigeration system.

[0089] Step S135: Generate anomaly analysis results that include equipment anomaly type, environmental anomaly type, and anomaly occurrence time. The anomaly analysis results can accurately indicate abnormal conditions of equipment and environment during transportation.

[0090] Based on the above analysis, anomaly analysis results are generated. These results include information such as equipment anomaly type, environmental anomaly type, and the time period of the anomaly. The time period of the anomaly can be determined based on the timestamps of the anomaly characteristics, recording the first and last occurrence times of the anomaly characteristics to determine the start and end times of the anomaly. For example, the anomaly analysis results might indicate that during a certain period of the transportation process, the equipment anomaly type is an engine cooling system failure, and the environmental anomaly type is excessively high temperature in the transportation space, clearly specifying the exact time range of the anomaly, such as from one hour after the start of transportation to another. These anomaly analysis results accurately indicate abnormal conditions of equipment and the environment during transportation.

[0091] Step S140: Based on the anomaly analysis results and the preset report generation rules, generate a transportation anomaly analysis report that includes a description of the anomaly, the time period of the anomaly, and an assessment of the anomaly's impact.

[0092] After obtaining the anomaly analysis results, a transportation anomaly analysis report needs to be generated according to the preset report generation rules. The transportation anomaly analysis report can comprehensively and in detail present the abnormal situations during the transportation process.

[0093] Step S141: Analyze the equipment anomaly type and environmental anomaly type in the anomaly analysis results, and generate a detailed anomaly description by combining it with the preset anomaly description library. The anomaly description is used to express the specific anomaly problems existing in the transportation equipment and transportation environment.

[0094] First, the equipment anomaly types and environmental anomaly types in the anomaly analysis results are parsed. An anomaly description library is pre-built and contains detailed descriptions of various possible equipment and environmental anomaly types. Based on the parsed equipment and environmental anomaly types, the corresponding descriptions are retrieved from the anomaly description library to generate detailed anomaly descriptions. For example, if the equipment anomaly type is an engine cooling system malfunction, a detailed description of the engine cooling system malfunction is retrieved from the anomaly description library, such as "A malfunction in the engine cooling system may lead to excessively high engine temperatures, affecting the engine's normal performance and lifespan." For environmental anomaly types, such as excessively high temperatures in the transport space, relevant descriptions are obtained from the anomaly description library, such as "Temperatures in the transport space exceeding the normal range may accelerate the spoilage of vegetables, affecting their quality."

[0095] Step S142: Extract the timestamp information of the anomaly from the anomaly analysis results, determine the start and end time periods of the anomaly, and generate anomaly occurrence time period information.

[0096] Next, the timestamp information of the anomaly occurrence is extracted from the anomaly analysis results. Based on this timestamp information, the start and end times of the anomaly occurrence are determined. The start and end times are then organized into clear anomaly occurrence time information. For example, if the anomaly analysis results record that the anomaly first appeared in the 2nd hour after the start of transportation and last appeared in the 4th hour, then the anomaly occurrence time information can be clearly represented as "the anomaly occurred from the 2nd to the 4th hour after the start of transportation".

[0097] Step S143: Based on the type, severity, and time period of the anomaly, and in conjunction with the impact of similar anomalies on the quality and efficiency of transported goods in historical transportation data, assess the potential impact of the current anomaly and generate an anomaly impact assessment.

[0098] Assessing the potential impact of the current anomaly is a crucial step in generating a transportation anomaly analysis report. The specific steps are as follows: Step S1431: Filter out historical anomaly records from historical transportation data that are the same as or similar to the current anomaly in terms of type and severity.

[0099] Filter through historical transportation data to find historical anomaly records that are the same or similar in type and severity to the current anomaly. This requires classifying and tagging anomalies in historical transportation data to accurately match similar anomaly records. For example, for the current engine cooling system failure anomaly, search through historical transportation data for historical anomaly records that also involve engine cooling system failures and have similar severity. A similar filtering process is applied to environmental anomalies such as excessively high temperatures in the transportation space.

[0100] Step S1432: Analyze the relationship between the time period of the anomaly in the historical anomaly records and the changes in the quality and efficiency of transported goods, and determine the impact pattern of the anomaly on the quality and efficiency of transported goods.

[0101] A thorough analysis of selected historical anomaly records was conducted to study the relationship between the timing of anomalies and changes in the quality and efficiency of transported goods. Through statistical analysis of a large number of historical anomaly records, the impact patterns of anomalies on the quality and efficiency of transported goods were summarized. For example, the analysis revealed that when engine cooling system malfunctions persist for an extended period, transport efficiency significantly decreases because reduced engine performance can slow down transport equipment. Simultaneously, the quality of transported goods may also be affected, as equipment failure can disrupt the normal operation of the refrigeration system, thus impacting the environment of the transport space. For anomalies involving excessively high temperatures in the transport space, the analysis showed that the longer the temperature anomaly persists, the faster the vegetables rot and the more pronounced the decline in the quality of transported goods. This may necessitate additional measures to adjust the temperature, thereby affecting transport efficiency.

[0102] Step S1433: Based on the type, severity, and time period of the current abnormal situation, use the aforementioned influence law to predict the degree of change in the quality of transported goods and the degree of reduction in transport efficiency that the current abnormal situation may cause.

[0103] Based on the type, severity, and timing of the current anomaly, and combined with the previously summarized impact patterns, the potential changes in cargo quality and the reduction in transportation efficiency caused by the current anomaly can be predicted. For example, if the severity of the current engine cooling system malfunction is similar to a historical malfunction, and the timing of the anomaly is also similar, then the potential impact of the current malfunction can be predicted based on the historical impact of that malfunction on cargo quality and transportation efficiency. Similarly, for anomalies such as excessively high temperatures in the transport space, if the timing and severity of the current anomaly are similar to historical cases, the impact patterns can be used to predict the degree of spoilage and deterioration of vegetables and the extent of the reduction in transportation efficiency.

[0104] Step S1434: Organize and describe the prediction results to generate anomaly impact assessment content.

[0105] The predicted changes in the quality of transported goods and the degree of reduction in transport efficiency are compiled and described to form the anomaly impact assessment. The anomaly impact assessment should clearly and accurately express the potential impact of the current anomaly on the quality and efficiency of transported goods. For example, the anomaly impact assessment might describe it as follows: "This engine cooling system failure is expected to reduce transport efficiency by a certain percentage, and may also cause a certain degree of quality degradation in the vegetable portion of the transported goods. The anomaly of excessively high temperatures in the transport space is expected to accelerate the spoilage of vegetables; during the period of the anomaly, the freshness of the vegetables will be significantly reduced, and transport efficiency will also be affected to some extent due to the need for temperature adjustments."

[0106] Step S144: Integrate the description of the abnormal situation, the time period of the abnormality, and the content of the abnormality impact assessment according to the preset report format to generate a complete transportation abnormality analysis report.

[0107] Finally, following the preset report format, the description of the anomaly, the time period of the anomaly, and the impact assessment are integrated. The preset report format typically includes a report title, basic information such as the transport task number and start time, a detailed description of the anomaly, an explanation of the time period of the anomaly, and an impact assessment. The previously generated description of the anomaly, the time period information, and the impact assessment are then filled into the corresponding sections of the report to form a complete transport anomaly analysis report. For example, the anomaly description section details the specific types of equipment and environmental anomalies, the time period section clearly states the specific time frame of the anomaly, and the impact assessment section comprehensively presents the assessment of the impact on the quality and efficiency of the transported goods.

[0108] Step S150: Based on the transportation anomaly analysis report and historical transportation data, generate transportation optimization strategies for transportation equipment maintenance and transportation environment control, and feed the transportation optimization strategies back to the cold chain transportation management system to guide transportation operations.

[0109] After receiving the transportation anomaly analysis report, and combining it with historical transportation data, a transportation optimization strategy is generated to improve the quality and efficiency of cold chain transportation.

[0110] Step S151: Analyze the description of the abnormal situation, the time period of the abnormality, and the content of the abnormality impact assessment in the transportation anomaly analysis report to determine the needs for transportation equipment maintenance and transportation environment control.

[0111] A thorough analysis of transportation anomaly reports is conducted. Based on the description of the anomaly, the time period of its occurrence, and the content of the impact assessment, the needs for transportation equipment maintenance and transportation environment control are determined. For example, if the transportation anomaly analysis report indicates that an engine cooling system malfunction has led to reduced transportation efficiency and a certain impact on cargo quality, then maintenance of the engine cooling system is required, including checking whether the cooling fan is operating normally and whether the coolant level is sufficient. For environmental anomalies such as excessively high temperatures in the transportation space, it is determined that the refrigeration system needs to be inspected and controlled to ensure that the temperature within the transportation space is maintained within a suitable range.

[0112] Step S152: Extract effective handling and prevention measures for similar abnormal situations from historical transportation data as a reference.

[0113] By analyzing historical transportation data, effective handling and preventative measures for similar anomalies can be identified. Historical transportation data records past experiences and methods for handling various anomalies; analyzing this data can reveal measures applicable to current anomalies. For example, for engine cooling system failures, historical data may record measures taken when similar problems occurred, such as replacing the cooling fan or adding coolant, which effectively resolved the issue. These measures can then be used as a reference. Similarly, for anomalies such as excessively high temperatures in the transport space, historical data may contain effective preventative measures such as adjusting refrigeration system operating parameters or adding ventilation equipment; these should also be extracted and used as a reference.

[0114] Step S153: Adjust and optimize the handling and preventive measures in the reference basis based on the actual condition of the current transportation equipment and the actual needs of the transportation environment.

[0115] After obtaining the reference data, and considering the actual condition of the current transportation equipment and the specific needs of the transportation environment, the handling and preventative measures should be adjusted and optimized. Because different transportation tasks and equipment may differ, historical experience cannot be completely copied; adjustments must be made based on the actual situation. For example, regarding handling engine cooling system malfunctions, if the engine model of the current transportation equipment differs from historical records, it may be necessary to adjust the specific model of the cooling fan to be replaced. Similarly, regarding preventative measures for temperature control in the transportation space, if the temperature requirements of the vegetables being transported differ from the past, the operating parameters of the refrigeration system need to be adjusted according to the new requirements.

[0116] Step S154: Develop a specific maintenance strategy for transportation equipment, including maintenance items, maintenance time, and maintenance methods.

[0117] Based on the preceding analysis and adjustments, a specific maintenance strategy for the transportation equipment is constructed. This strategy includes maintenance items, maintenance time, and maintenance methods. For maintenance items, the specific components and systems requiring maintenance are clearly listed, such as various engine parts, the compressor and condenser of the refrigeration system, etc. For maintenance time, a reasonable maintenance time is determined based on the timing of the anomaly and the transportation task schedule to minimize impact on the transportation task. For example, if the anomaly occurs during transportation, maintenance can be scheduled immediately after the transportation task is completed; if the anomaly is severe, it may be necessary to arrange an emergency stop for emergency maintenance. For maintenance methods, the specific operating procedures for each maintenance item are detailed. For example, the maintenance method for the engine cooling system might include checking for blockages in the cooling pipes and cleaning the radiator.

[0118] Step S155: Construct specific transportation environment control strategies, including control objectives, control methods, and control time.

[0119] Simultaneously, specific transportation environment control strategies are constructed. These strategies include control objectives, control methods, and control timing. The control objective is to determine the ideal range of environmental parameters such as temperature, humidity, and gas composition within the transportation space, based on the requirements of the transported goods and the normal standards of the transportation environment. Control methods include adjusting the operating parameters of the refrigeration system, activating ventilation equipment, and distributing humidity-regulating materials. The control timing is determined based on the time of the anomaly and the progress of the transportation task. For example, if an abnormally high temperature in the transportation space occurs some time after the start of transportation, the refrigeration system can be activated immediately upon detection of the anomaly, adjusting its operating frequency and temperature setpoint to restore the temperature to the normal range as quickly as possible.

[0120] Step S156: Integrate the transportation equipment maintenance strategy and the transportation environment control strategy to generate a complete transportation optimization strategy.

[0121] Finally, the transportation equipment maintenance strategy and the transportation environment control strategy are integrated to generate a complete transportation optimization strategy. This strategy encompasses both transportation equipment maintenance and transportation environment control, providing comprehensive guidance for cold chain transportation operations. The optimization strategy is then fed back to the cold chain transportation management system, which can use it to schedule maintenance for transportation equipment and control the transportation environment in real time, thereby improving the quality and efficiency of cold chain transportation and ensuring the quality of transported goods. For example, the system can schedule maintenance personnel to perform maintenance on transportation equipment based on the maintenance timeline in the optimization strategy; and automatically adjust the operating status of the refrigeration system and ventilation equipment according to the control time and methods specified in the environmental control strategy, ensuring that the environment within the transportation space meets requirements.

[0122] In the above embodiments, the transportation strategy optimization system for cold chain transportation used to perform the above method embodiments has at least one processor, a control module (chipset) coupled to at least one of the processors, a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one load to / output device coupled to the control module, and a network interface coupled to the control module.

[0123] The processor may include at least one single-core or multi-core processor, and may include any combination of general-purpose processors or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). For some alternative implementations, the transportation strategy optimization system applied to cold chain transportation can serve as an electronic device such as the gateway described in the embodiments of this application.

[0124] In some alternative implementations, a transport strategy optimization system for cold chain transportation may include at least one computer-readable medium (e.g., a memory or NVM / storage device) having instructions and at least one processor fused with the at least one computer-readable medium and configured to execute the instructions to implement the module thereby performing the actions described in this disclosure.

[0125] In one embodiment, the control module may include any suitable interface controller to provide any suitable interface to at least one of the processors and / or any suitable device or component communicating with the control module.

[0126] The control module may include a memory controller module to provide an interface to the memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0127] The memory can be used, for example, to load and store data and / or instructions for a transportation strategy optimization system applied to cold chain transportation. In one embodiment, the memory may include any suitable volatile memory, such as suitable DRAM.

[0128] In one embodiment, the control module may include at least one load-to-output controller to provide an interface to the NVM / storage device and (at least one) load-to-output device.

[0129] For example, an NVM / storage device can be used to store data and / or instructions. An NVM / storage device may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (at least one) non-volatile storage device (e.g., at least one hard disk drive (HDD), at least one optical disc (CD) drive, and / or at least one digital universal optical disc (DVD) drive).

[0130] NVM / storage devices may include storage resources that are physically installed as part of a transport strategy optimization system used for cold chain transportation, or that can be accessed by the device without needing to be part of it. For example, NVM / storage devices may be accessed over a network via (at least one) load-to-output device.

[0131] At least one loading / output device may provide an interface for the transportation strategy optimization system applied to cold chain transportation to communicate with any other suitable device. The loading / output device may include communication components, pinyin components, sensor components, etc. A network interface may provide an interface for the transportation strategy optimization system applied to cold chain transportation to communicate based on at least one network. The transportation strategy optimization system applied to cold chain transportation may wirelessly communicate with at least one component of a wireless network based on at least one wireless network prior and / or protocol, such as accessing a wireless network based on communication priors.

[0132] In one embodiment, at least one of the processors may be integrated with the logic of at least one controller of the control module (e.g., a memory controller module). In one embodiment, at least one of the processors may be integrated with the logic of at least one controller of the control module to form a system-level integration. In one embodiment, at least one of the processors may be fused with the logic of at least one controller of the control module on the same die. In one embodiment, at least one of the processors may be fused with the logic of at least one controller of the control module on the same die to form a system-on-a-chip (SoC).

[0133] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0134] This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps in the transportation strategy optimization method for cold chain transportation described in the foregoing embodiments.

[0135] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the transportation strategy optimization method for cold chain transportation described in the foregoing embodiments.

[0136] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0137] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electronically erasable rewritable read-only memory (EEPROM), compact optical disc (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to have or store data.

[0138] Finally, it should be noted that the above-disclosed embodiments are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing transportation strategy applied to cold chain transportation, characterized in that, The method comprises: acquiring a set of transportation data generated in a cold-chain transportation process, the set of transportation data comprising device operation parameters of a transportation device within a transportation period and transportation environment data, the device operation parameters being used to reflect a working state of the transportation device, and the transportation environment data being used to reflect an environmental condition within a transportation space; performing feature extraction processing on the set of transportation data to obtain a device feature set related to the working state of the transportation device and an environmental feature set related to the environmental condition, the device feature set comprising key features used to reflect the device operation state, and the environmental feature set comprising key features used to reflect the transportation environment state; inputting the device feature set and the environmental feature set into a preset abnormality analysis model to perform joint abnormality analysis on the working state of the transportation device and the environmental condition by using the abnormality analysis model, and generating an abnormality analysis result comprising device abnormality types and environmental abnormality types, the abnormality analysis result being used to indicate possible abnormal situations in the transportation process; generating a transportation abnormality analysis report comprising an abnormal situation description, an abnormal occurrence period, and an abnormal influence evaluation according to the abnormality analysis result and a preset report generation rule; generating a transportation optimization strategy for transportation device maintenance and transportation environment regulation based on the transportation abnormality analysis report and historical transportation data, and feeding back the transportation optimization strategy to a cold-chain transportation management system to guide transportation operations.

2. The transportation strategy optimization method for cold chain transportation according to claim 1, characterized in that, The acquiring of the set of transportation data generated in the cold-chain transportation process, the set of transportation data comprising the device operation parameters of the transportation device within the transportation period and the transportation environment data, comprises: real-time collection of the device operation parameters of the transportation device by sensors arranged on the transportation device, the device operation parameters comprising parameters capable of reflecting a power system state of the transportation device, parameters capable of reflecting a refrigeration system state of the transportation device, and parameters capable of reflecting positioning information of the transportation device; real-time collection of the transportation environment data by sensors arranged in the transportation space, the transportation environment data comprising temperature data, humidity data, and gas composition data in the transportation space; arrangement of the collected device operation parameters and transportation environment data in a time sequence to generate a set of transportation data having a time sequence relationship, each data unit in the set of transportation data comprising corresponding timestamp information.

3. The transportation strategy optimization method for cold chain transportation according to claim 1, characterized in that, The feature extraction processing on the set of transportation data to obtain the device feature set related to the working state of the transportation device and the environmental feature set related to the environmental condition comprises: screening of the device operation parameters in the set of transportation data to remove redundant parameters and retain key device operation parameters capable of directly reflecting the working state of the transportation device; standardization processing of the key device operation parameters to obtain standardized device operation parameters; processing of the standardized device operation parameters to extract device features used to reflect a working state change trend of the transportation device, and generation of a device feature set, each device feature in the device feature set having a corresponding relationship with a key device operation parameter; Screening the transportation environment data in the transportation data set to generate key transportation environment data directly reflecting the transportation environment status; Standardizing the key transportation environment data to obtain standardized transportation environment data; Processing the standardized transportation environment data to extract environment features reflecting the change trend of the transportation environment status, and generating an environment feature set, each environment feature in the environment feature set having a corresponding relationship with the key transportation environment data.

4. The transportation strategy optimization method for cold chain transportation according to claim 3, characterized in that, The processing of the standardized device operation parameters to extract device features reflecting the change trend of the transportation device working state, and generating a device feature set, includes: Dividing the standardized device operation parameters into multiple device parameter time periods according to time sequence, each device parameter time period containing multiple continuously collected device operation parameters; For each device parameter time period, calculating the mean, variance and change rate of the device operation parameters as device state basic features; Analyzing the change rule of the device operation parameters between different device parameter time periods to extract device periodic features reflecting the periodic change of the device working state; Combining the device state basic features and the device periodic features to generate a device feature set containing multiple dimension features, the device feature set being used to reflect the working state change of the transportation device in the transportation period.

5. The transportation strategy optimization method for cold chain transportation according to claim 3, wherein, The processing of the standardized transportation environment data to extract environment features reflecting the change trend of the transportation environment status, and generating an environment feature set, includes: Dividing the standardized transportation environment data into multiple environment data time periods according to time sequence, each environment data time period containing multiple continuously collected transportation environment data; For each environment data time period, calculating the mean, variance and change rate of the transportation environment data as environment state basic features; Analyzing the change rule of the transportation environment data between different environment data time periods to extract environment periodic features reflecting the periodic change of the transportation environment status; Combining the environment state basic features and the environment periodic features to generate an environment feature set containing multiple dimension features, the environment feature set being used to reflect the status change of the transportation environment in the transportation period.

6. The transportation strategy optimization method for cold chain transportation of claim 1, wherein, The input of the device feature set and the environment feature set into a preset abnormality analysis model, the joint abnormality analysis of the transportation device working state and the transportation environment status through the abnormality analysis model, and the generation of an abnormality analysis result containing device abnormality types and environment abnormality types, includes: Splicing the device feature set and the environment feature set to generate a joint feature set containing device features and environment features; Inputting the joint feature set into the feature processing layer of the abnormality analysis model to perform noise reduction and dimension conversion processing on the joint features to obtain preprocessed features suitable for model analysis; Analyzing the preprocessed features through the abnormality detection layer of the abnormality analysis model to identify abnormal features that do not conform to the normal transportation state feature mode; Determining the device abnormality types and the environment abnormality types according to the device features and the environment features corresponding to the abnormal features; The abnormality analysis result includes the device abnormality type, the environment abnormality type, and the abnormality occurrence period, and can accurately indicate the abnormality of the device and the environment in the transportation process.

7. The transportation strategy optimization method for cold chain transportation according to claim 6, characterized in that, The abnormality detection layer of the abnormality analysis model analyzes the preprocessed features, and identifies abnormal features that do not conform to the feature mode of the normal transportation state, including: A normal transportation state feature model is trained in advance in the abnormality analysis model, and a feature distribution range in the normal transportation state is generated; The preprocessed features are compared with the feature distribution range in the normal transportation state to determine whether the preprocessed features exceed the normal distribution range; For the preprocessed features that exceed the normal distribution range, the preprocessed features are determined as abnormal features, and the device features and environment features corresponding to the abnormal features are recorded; The severity of the abnormal features is evaluated according to the frequency and duration of the abnormal features.

8. The transportation strategy optimization method for cold chain transportation of claim 1, wherein, The transportation abnormality analysis report includes the abnormality description, the abnormality occurrence period, and the abnormality impact evaluation, and is generated according to the abnormality analysis result and the preset report generation rule, including: The device abnormality type and the environment abnormality type in the abnormality analysis result are analyzed, and a detailed abnormality description is generated by combining a preset abnormality description library. The abnormality description is used to express specific abnormal problems of the transportation device and the transportation environment; Timestamp information of the abnormality occurrence is extracted from the abnormality analysis result to determine the start period and the end period of the abnormality occurrence, and the abnormality occurrence period information is generated; According to the type, severity, and occurrence period of the abnormality, the influence of similar abnormal situations in historical transportation data on the transportation cargo quality and the transportation efficiency is combined to evaluate the possible impact of the current abnormal situation, and the abnormality impact evaluation content is generated; The abnormality description, the abnormality occurrence period, and the abnormality impact evaluation content are integrated according to the preset report format to generate a complete transportation abnormality analysis report; According to the type, severity, and occurrence period of the abnormality, the influence of similar abnormal situations in historical transportation data on the transportation cargo quality and the transportation efficiency is combined to evaluate the possible impact of the current abnormal situation, and the abnormality impact evaluation content is generated, including: The historical abnormal records with the same or similar type and severity of the current abnormal situation are filtered from the historical transportation data; The relationship between the abnormality occurrence period and the changes of the transportation cargo quality and the transportation efficiency in the historical abnormal records is analyzed to determine the influence law of the abnormal situation on the transportation cargo quality and the transportation efficiency; According to the type, severity, and occurrence period of the current abnormal situation, the influence law is used to predict the degree of change of the transportation cargo quality and the degree of reduction of the transportation efficiency caused by the current abnormal situation; The prediction results are arranged and described to generate the abnormality impact evaluation content.

9. The transportation strategy optimization method for cold chain transportation according to claim 1, wherein, The transportation optimization strategy for the transportation device maintenance and the transportation environment regulation is generated based on the transportation abnormality analysis report and the historical transportation data, including: The abnormality description, the abnormality occurrence period, and the abnormality impact evaluation content in the transportation abnormality analysis report are analyzed to determine the demand for the transportation device maintenance and the transportation environment regulation; Extracting effective treatment measures and preventive measures for similar abnormal situations from historical transportation data as reference; Adjusting and optimizing the treatment measures and preventive measures in the reference according to the actual status of the current transportation equipment and the actual needs of the transportation environment; Building specific transportation equipment maintenance strategies, including maintenance items, maintenance time, and maintenance methods; Building specific transportation environment regulation strategies, including regulation targets, regulation means, and regulation time; Integrating the transportation equipment maintenance strategies and the transportation environment regulation strategies to generate a complete transportation optimization strategy.

10. A transportation strategy optimization system for cold chain transportation, characterized in that, The application further provides a computer readable storage medium having stored therein computer executable instructions, which, when executed by a computer, implement the transportation strategy optimization method for cold chain transportation according to any one of claims 1-8.

Images