Methods, devices, equipment and storage media for dynamic tracking of logistics information

Abstract

This invention provides a method, apparatus, device, and storage medium for dynamic tracking of logistics information, belonging to the field of logistics information processing technology. The method includes: acquiring logistics information generated during the fresh produce logistics process and constructing disturbance segments to characterize the deviation process of environmental parameters; identifying the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment, and generating an operation behavior time window aligned with the time of the disturbance segment; extracting disturbance morphological features from the disturbance segment to characterize the change process of environmental parameters; determining the anomaly type corresponding to the disturbance segment based on the time coverage relationship between the disturbance segment and the operation behavior time window, and combining the disturbance morphological features; and associating the anomaly type with the corresponding operation behavior information to form a dynamic tracking result of logistics information. This invention enables the location and type determination of operational stages for environmental anomalies during fresh produce logistics, and forms a continuously traceable dynamic tracking result of logistics information.

Description

Technical Field

[0001] This invention relates to the field of logistics information processing technology, specifically to a dynamic tracking method for logistics information, a dynamic tracking device for logistics information, a dynamic tracking equipment for logistics information, and a storage medium. Background Technology

[0002] With the continuous expansion of fresh food logistics, the stability of fresh products' condition in various logistics stages, such as transportation, loading and unloading, sorting, and temporary storage, is receiving increasing attention. To reduce the quality risks of fresh food during logistics, existing logistics systems typically collect environmental parameters such as temperature and humidity to record and monitor the logistics process, and trigger anomaly alerts when parameters exceed preset thresholds, thereby assisting in logistics management and quality control.

[0003] However, in actual fresh food logistics scenarios, changes in the condition of fresh produce are often not caused by a single instantaneous anomaly in a parameter, but rather by the combined effects of multiple stages of operational activities and environmental disturbances. Especially during manual or semi-automatic operations such as loading, unloading, and sorting, environmental parameters may experience short-term fluctuations or repeated deviations, and their characteristics differ significantly from parameter anomalies caused by equipment or environmental factors during transportation. Existing logistics information processing methods typically only record the abnormal results, lacking an effective distinction between the context of the logistics operations in which the anomaly occurred, leading to anomalies from different sources being uniformly processed in logistics information.

[0004] Furthermore, existing logistics information records are mostly in the form of discrete abnormal events or simple time series, making it difficult to fully reflect the entire process of environmental parameters from deviation to recovery. After an anomaly occurs, the system usually cannot accurately determine the true duration of the anomaly and its temporal relationship with specific operational behaviors, thus hindering further analysis of the anomaly formation mechanism. This information representation method easily leads to fragmented anomaly information when facing multiple consecutive operations or complex logistics scenarios, affecting the understanding of the overall state of the logistics process.

[0005] The aforementioned problems are particularly prominent in the follow-up management and quality traceability of fresh food logistics. When quality disputes or liability determinations arise, existing logistics information often only provides records of parameter exceeding limits, making it difficult to determine whether the anomaly occurred during transportation or operation, and also difficult to reconstruct the evolution of the anomaly over time. This not only increases the difficulty of logistics management but also limits the application value of logistics information in risk assessment and decision support.

[0006] Therefore, how to process logistics information generated during the fresh food logistics process more precisely without relying on new hardware equipment, so that abnormal information can simultaneously reflect the characteristics of changes in environmental parameters and their corresponding logistics operation background, and be dynamically tracked in a structured form, has become a technical problem that urgently needs to be solved in the field of fresh food logistics information processing. Summary of the Invention

[0007] The purpose of this invention is to provide a method, device, equipment, and storage medium for dynamic tracking of logistics information, so as to at least solve the problems in existing logistics information processing where it is difficult to distinguish abnormal information from the background of logistics operations and difficult to trace the evolution of abnormalities.

[0008] To achieve the above objectives, the first aspect of the present invention provides a method for dynamic tracking of logistics information. The method includes: acquiring logistics information generated during the logistics process of fresh produce, and constructing a disturbance segment based on the logistics information to characterize the deviation process of environmental parameters; identifying the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment based on the logistics information, and generating an operation behavior time window aligned with the time of the disturbance segment; extracting disturbance morphological features from the disturbance segment under the constraint of the operation behavior time window to characterize the change process of environmental parameters; determining the anomaly type corresponding to the disturbance segment based on the time coverage relationship between the disturbance segment and the operation behavior time window, and in combination with the disturbance morphological features, and associating and recording the anomaly type with the corresponding operation behavior information to form a dynamic tracking result of logistics information.

[0009] Optionally, acquire logistics information generated during the fresh produce logistics process, and construct a disturbance segment based on the logistics information to characterize the deviation process of environmental parameters, including: performing trend analysis on the parameters reflecting changes in environmental state in the logistics information in a continuous time dimension to determine the starting time when the environmental parameters deviate from the corresponding baseline state; continuously tracking the change process of the environmental parameters from the starting time and recording the peak time when the environmental parameters reach the maximum deviation; continuously monitoring the regression process of the environmental parameters after the peak time, and determining the end time of the disturbance when the environmental parameters recover to a preset stable range; and constructing a disturbance segment to fully characterize the deviation process of environmental parameters based on the starting time, the peak time, and the end time.

[0010] Optionally, based on the logistics information, the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment is identified, and an operation behavior time window aligned with the time of the disturbance segment is generated. This includes: within the time range corresponding to the disturbance segment, analyzing the behavioral features in the logistics information reflecting changes in the location and operation status of fresh produce, and determining the operation behavior type of fresh produce within the time range; based on the operation behavior type, extracting the start time and end time of the operation corresponding to the time range of the disturbance segment, forming an operation behavior time interval to characterize the duration of the operation behavior; and aligning the operation behavior time interval with the start time, peak time, and end time of the disturbance segment to generate an operation behavior time window characterizing the operation background when the disturbance segment occurs.

[0011] Optionally, under the constraint of the operation behavior time window, disturbance morphology features for characterizing the environmental parameter change process are extracted from the disturbance segment, including: dividing the environmental parameter change process corresponding to the disturbance segment into a deviation phase and a recovery phase based on the start time, the peak time, and the end time; calculating an upward change feature parameter for characterizing the deviation rate of the environmental parameters based on the relationship between the environmental parameters and time during the deviation phase; calculating a downward change feature parameter for characterizing the return rate of the environmental parameters based on the relationship between the environmental parameters and time during the recovery phase; determining a duration feature parameter for characterizing the duration of the disturbance based on the time span between the peak time and the end time; and using the upward change feature parameter, the downward change feature parameter, and the duration feature parameter as the disturbance morphology features.

[0012] Optionally, based on the time span between the peak time and the end time, a duration characteristic parameter for characterizing the duration of the disturbance is determined, including: within the time range between the peak time and the end time, determining the deviation state of the environmental parameter relative to the corresponding stable baseline, distinguishing between time intervals in the deviation state and time intervals in the stabilization state; within the time range, accumulating each time interval in the deviation state to obtain the effective duration for which the environmental parameter is actually maintained in the deviation state; and using the effective duration as the duration characteristic parameter to characterize the true duration of the environmental parameter's deviation from the stable state in the disturbance segment.

[0013] Optionally, based on the temporal coverage relationship between the disturbance segment and the operation behavior time window, and in conjunction with the disturbance morphology features, the anomaly type corresponding to the disturbance segment is determined, including: calculating the overlap time length of the disturbance segment within the operation behavior time window, and determining the temporal coverage relationship feature of the disturbance segment within the operation behavior time window based on the relationship between the overlap time length and the duration feature parameter of the disturbance segment; jointly analyzing the temporal coverage relationship feature and the disturbance morphology feature to obtain an anomaly determination feature combination used to characterize the formation mechanism of the disturbance segment; and performing anomaly type determination on the disturbance segment according to the anomaly type determination rule based on the anomaly determination feature combination to obtain the anomaly type corresponding to the disturbance segment.

[0014] Optionally, the abnormality type is associated with the corresponding operational behavior information to form a dynamic tracking result of logistics information, including: extracting the disturbance segment identifier information corresponding to the abnormality type and the operational behavior time window information corresponding to the disturbance segment based on the abnormality type corresponding to the disturbance segment; associating and encapsulating the abnormality type, the disturbance segment identifier information and the operational behavior time window information to generate an abnormality association record unit for characterizing the operational background of the abnormality type; and organizing the abnormality association record unit sequentially according to the occurrence order of the disturbance segment in the time dimension to form a dynamic tracking result of logistics information for reflecting the abnormality evolution process in fresh food logistics.

[0015] A second aspect of the present invention provides a dynamic tracking device for logistics information. The device includes: a data acquisition unit, configured to acquire logistics information generated during the fresh produce logistics process and construct a disturbance segment based on the logistics information to characterize the deviation process of environmental parameters; a processing unit, configured to identify the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment based on the logistics information and generate an operation behavior time window aligned with the time of the disturbance segment; a feature extraction unit, configured to extract disturbance morphological features from the disturbance segment under the constraint of the operation behavior time window to characterize the change process of environmental parameters; and a result output unit, configured to determine the anomaly type corresponding to the disturbance segment based on the time coverage relationship between the disturbance segment and the operation behavior time window, and in combination with the disturbance morphological features, and associate and record the anomaly type with the corresponding operation behavior information to form a dynamic tracking result for logistics information.

[0016] A third aspect of the present invention provides a dynamic tracking device for logistics information, wherein the device is equipped with the aforementioned dynamic tracking device for logistics information.

[0017] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions which, when executed on a computer, cause the computer to perform the above-described dynamic tracking method for logistics information.

[0018] Through the above technical solution, this invention transforms the abnormal changes in environmental parameters during fresh food logistics from discrete out-of-limit events into disturbance segments with initiation, evolution, and recovery processes, enabling logistics information to fully reflect the temporal structure characteristics of environmental parameter deviations. Furthermore, by temporally aligning the disturbance segments with corresponding logistics operations, a time window for operational behavior is constructed, establishing a clear association between abnormal information and the operational background at the time of its occurrence, thereby avoiding the overlap of abnormal information from different operational stages. Simultaneously, under the constraint of the operational behavior time window, disturbance morphological features are extracted, and anomaly type determination is performed based on the temporal coverage relationship between the disturbance segments and the operational behavior time window, allowing the anomaly type to reflect the differences in the mechanisms of anomaly formation. Finally, the anomaly type is associated with operational behavior information and recorded, forming a dynamic tracking result of logistics information with temporal continuity and operational semantics, thereby improving the expressive power and traceability of logistics information regarding the anomaly evolution process.

[0019] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0020] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0021] Figure 1 This is a flowchart of the steps of a dynamic tracking method for logistics information provided in one embodiment of the present invention;

[0022] Figure 2 This is a structural diagram of a logistics information dynamic tracking device provided in one embodiment of the present invention. Detailed Implementation

[0023] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0024] like Figure 1 As shown, embodiments of the present invention provide a method for dynamic tracking of logistics information, the method comprising:

[0025] Step S10: Obtain logistics information generated during the fresh food logistics process, and construct a disturbance segment based on the logistics information to characterize the deviation process of environmental parameters.

[0026] Specifically, trend analysis is performed on the parameters reflecting changes in environmental state in the logistics information over a continuous time dimension to determine the starting time when the environmental parameters deviate from the corresponding baseline state; starting from the starting time, the change process of the environmental parameters is continuously tracked, and the peak time when the environmental parameters reach the maximum degree of deviation is recorded; after the peak time, the regression process of the environmental parameters is continuously monitored, and the end time of the disturbance is determined when the environmental parameters recover to a preset stable range; based on the starting time, the peak time, and the end time, a disturbance segment is constructed to fully characterize the deviation process of the environmental parameters.

[0027] In this embodiment of the invention, logistics information generated during the fresh food logistics process is acquired, and a disturbance segment characterizing the deviation process of environmental parameters is constructed based on the logistics information. It should be noted that the logistics information can originate from existing data collection devices or information systems deployed in existing fresh food logistics systems, such as historical records and real-time data generated in cold chain monitoring systems, transportation management systems, or warehouse management systems. This invention does not limit the specific method of collecting logistics information, nor does it require the addition of new hardware equipment.

[0028] In practice, the logistics information typically includes data sequences reflecting the changes in environmental parameters over time, such as temperature, humidity, or other parameters that reflect environmental stability. This implementation does not limit the specific types of environmental parameters, but rather focuses on the trends of these parameters over time.

[0029] Specifically, trend analysis is performed on the parameters reflecting changes in environmental state in the logistics information over a continuous time dimension. This trend analysis is not a simple threshold judgment, but rather identifies whether environmental parameters have continuously deviated from their corresponding baseline state based on the overall changes in the environmental parameters over time. The baseline state can be pre-set according to the logistics scenario, such as the stable parameter range of fresh produce under normal transportation or storage conditions, or it can be dynamically determined based on historical data; this invention does not limit this.

[0030] When an environmental parameter is detected to deviate from its corresponding baseline state, the time point at which this deviation first occurs and persists is determined as the starting point of the environmental parameter deviation process. It should be noted that this starting point is not equivalent to an instantaneous fluctuation point, but rather refers to the time position at which the environmental parameter enters a deviation state and exhibits a certain degree of continuity, thereby avoiding misjudging occasional noise as a valid disturbance.

[0031] Starting from the initial moment, the changes in environmental parameters are continuously tracked. During this process, the magnitude of these changes is continuously monitored, and the point in time when the environmental parameters reach their maximum deviation from the baseline state is recorded as the peak moment of the disturbance process. This peak moment characterizes the extreme position of the environmental parameter deviation, reflecting a key node in the disturbance process and providing a basis for subsequent analysis of the disturbance pattern.

[0032] After the peak time, the changes in environmental parameters continue to be monitored, with a focus on whether the environmental parameters gradually return to the baseline state. When the environmental parameters return to a preset stable range, the disturbance process is determined to have ended, and this time point is defined as the disturbance end time. The preset stable range is used to indicate that the environmental parameters have recovered to a state that can be considered stable. Its specific value can be set according to the type of fresh produce, logistics links, or management requirements, and this invention does not impose specific limitations on it.

[0033] Using the methods described above, the start time, peak time, and end time of the disturbance are obtained respectively. Based on the start time, peak time, and end time, a disturbance segment is constructed to fully characterize the entire process of a single deviation and recovery of environmental parameters. This disturbance segment describes the complete process of environmental parameters deviating from a stable state, reaching the maximum deviation, and finally recovering to stability in the form of a time structure, thus integrating the originally scattered abnormal changes in the time series into a structured object with clear start and end boundaries and an evolutionary process.

[0034] By constructing abnormal changes in environmental parameters as disturbance fragments, this implementation provides a unified time basis for subsequent analysis of the background of anomalies in conjunction with logistics operations. This allows changes in environmental parameters to no longer exist only as discrete data points, but to participate in the subsequent dynamic tracking of logistics information in a process-oriented and analyzable form.

[0035] Step S20: Based on the logistics information, identify the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment, and generate an operation behavior time window aligned with the time of the disturbance segment.

[0036] Specifically, identifying the logistics operations of fresh produce within the time range corresponding to the disturbance segment and generating an operation behavior time window aligned with the time of the disturbance segment includes: analyzing the behavioral features in the logistics information reflecting changes in the location and operational status of fresh produce within the time range corresponding to the disturbance segment to determine the operation behavior type of fresh produce within the time range; based on the operation behavior type, extracting the start time and end time of the operation corresponding to the time range of the disturbance segment to form an operation behavior time interval for characterizing the duration of the operation behavior; and aligning the operation behavior time interval with the start time, peak time, and end time of the disturbance segment to generate an operation behavior time window for characterizing the operational background when the disturbance segment occurs.

[0037] In this embodiment of the invention, based on the logistics information, the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment is identified, and an operation behavior time window aligned with the time of the disturbance segment is generated. It should be noted that the logistics operation behavior is not pre-labeled or manually input, but rather identified based on the behavioral characteristics objectively reflecting the state of fresh produce and logistics activities in the logistics information, thereby ensuring the automation and consistency of the operation behavior identification process.

[0038] Specifically, within the time range corresponding to the disturbance segment, the behavioral characteristics reflecting changes in the location and operational status of fresh produce in the logistics information are analyzed. These behavioral characteristics may include, but are not limited to, changes in the spatial location of the fresh produce, the continuity of these location changes, the duration of their dwell time, and status change information related to logistics nodes. This embodiment does not limit the specific form of the behavioral characteristics, but rather uses a comprehensive analysis of these characteristics to determine the main operational behavior type of the fresh produce within the stated time range.

[0039] In practical applications, for example, when logistics information shows that the location of fresh produce changes continuously over a relatively long period and the trajectory of these changes is continuous, it can be determined that the fresh produce is engaged in transportation-based operations. When logistics information shows that the location of fresh produce remains basically unchanged or changes frequently within a limited range, accompanied by changes in operational status, it can be determined that the fresh produce is engaged in loading, unloading, sorting, or temporary storage operations. By using these methods, the type of operational behavior of fresh produce within the corresponding time range of the disturbance segment can be determined, thus providing a basis for subsequent time interval extraction.

[0040] After determining the type of operational activity, the start and end times of the operation, corresponding to the time range of the disturbance segment, are extracted from the logistics information based on the operational activity type to form an operational activity time interval characterizing the duration of the operational activity. The start time indicates the time position of fresh produce entering the current operational activity, and the end time indicates the time position of fresh produce leaving the current operational activity. By clearly defining the start and end times of the operational activities, continuous logistics information can be divided into operational activity intervals with clearly defined time boundaries.

[0041] After obtaining the time interval of the operational behavior, the time interval is time-aligned with the start time, peak time, and end time of the disturbance segment. This time alignment process determines the relative relationship between the operational behavior time interval and the disturbance segment on the time axis, such as whether the operational behavior occurs before, after, or overlaps with the disturbance segment, and the specific time range of the overlap. Through this alignment process, the environmental parameter changes corresponding to the disturbance segment can be uniformly mapped to the logistics operation background at the time of its occurrence.

[0042] Based on the aforementioned time alignment results, a time window for operational behavior is generated to characterize the operational background when the disturbance segment occurs. This time window describes the main operational behaviors and their duration characteristics experienced by the fresh produce within the time range corresponding to the disturbance segment, thus providing a foundation for subsequent analysis combining the temporal relationship between the disturbance segment and operational behaviors. By introducing the operational behavior time window, the disturbance process of environmental parameters is no longer viewed in isolation but is placed within a clear logistics operational context, which helps in subsequent judgment of the disturbance formation mechanism and differentiation of anomaly types.

[0043] In one specific implementation, taking a logistics scenario where a batch of refrigerated fresh fruit is unloaded and temporarily stored at an urban sorting center as an example, the process of identifying the logistics operation behavior of fresh fruit within the time range corresponding to the disturbance segment based on logistics information and generating an operation behavior time window aligned with the time of the disturbance segment is explained.

[0044] In this embodiment, after a disturbance segment has been constructed based on logistics information, the time range corresponding to the disturbance segment is first determined, i.e., from the start time of the disturbance to the end time of the disturbance. Subsequently, only the logistics information formed within this time range is processed for operation behavior identification, without analyzing the information of the entire fresh food logistics process, in order to limit the time range of operation behavior identification.

[0045] Specifically, within the time range corresponding to the disturbance segment, the behavioral characteristics reflecting changes in the location and operational status of fresh produce in the logistics information are analyzed. In this embodiment, the behavioral characteristics include the location changes of fresh produce within the sorting center area, the frequency of location changes, and the switching of operational status. Through comprehensive analysis of the above behavioral characteristics, it is possible to identify whether the fresh produce has undergone continuous displacement, local displacement, or a basically unchanged position within the time range corresponding to the disturbance segment.

[0046] For example, when logistics information indicates that the overall location of fresh produce has not undergone long-distance migration within the time range corresponding to the disturbance segment, but there are multiple short-distance location changes within a limited space, and at the same time the operation status changes from transportation-related status to sorting or loading and unloading-related status, it can be determined that the logistics operation behavior of fresh produce within that time range is an operational operation behavior.

[0047] After determining the type of operational behavior, the start and end times of the operational behavior are extracted from the logistics information within the corresponding time range of the disturbance segment, based on the operational behavior type. The start time corresponds to the point in time when fresh produce enters the current operational behavior and the operational state switches, and the end time corresponds to the point in time when fresh produce exits the current operational behavior and enters the next state. This forms an operational behavior time interval characterizing the duration of the operational behavior.

[0048] After obtaining the time interval of the work activity, the time interval is time-aligned with the start, peak, and end times of the disturbance segment. Specifically, the start, peak, and end times of the disturbance segment are marked on the same time axis, and the start and end positions of the time interval of the work activity are also marked to clarify the correspondence between the time interval of the work activity and the disturbance segment in the time dimension. Through the above time alignment process, a time window for the work activity is generated to characterize the work background when the disturbance segment occurs.

[0049] Through the above implementation method, without introducing the concept of an execution subject, the identification of logistics operation behavior when a disturbance occurs can be completed based solely on the behavioral characteristics reflected in the logistics information. The background of the operation behavior can be expressed in the form of a time window, providing a time basis for subsequent analysis of the disturbance segment based on the operation background.

[0050] In another possible implementation, when identifying the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment, instead of directly judging based on the magnitude of location change or the switching of operation status, an operation behavior identification method based on the consistency of behavioral rhythm is introduced.

[0051] Specifically, within the time range corresponding to the disturbance segment, the rhythm of changes in environmental parameters and location of fresh produce reflected in the logistics information is analyzed synchronously to obtain the rhythmic characteristics of the environmental parameter change sequence and the location change sequence in the time dimension. In this embodiment, the rhythmic characteristics are used to characterize the repeatability, continuity, or discontinuity of parameter changes and location changes within a unit of time.

[0052] When the analysis results show that, within the time range corresponding to the disturbance segment, the rhythm of environmental parameter changes and the rhythm of location changes exhibit highly synchronized short-period fluctuation characteristics, it can be determined that the logistics operation behavior of fresh produce within that time range is an operational operation behavior; when the rhythm of environmental parameter changes and the rhythm of location changes exhibit low-frequency, continuous change characteristics, it can be determined that the logistics operation behavior of fresh produce within that time range is a transportation operation behavior.

[0053] After determining the type of work behavior based on rhythm consistency, the start time and end time of the work behavior are further extracted from the logistics information within the time range corresponding to the disturbance segment based on the type of work behavior to form a corresponding time interval of work behavior. The time interval of work behavior is then time-aligned with the start time, peak time and end time of the disturbance segment to generate a time window of work behavior used to characterize the background of work when the disturbance segment occurs.

[0054] The above method enables the identification of operational behaviors by utilizing the rhythmic relationships between multiple time series in logistics information without relying on explicit operational status identifiers, thus expanding the means of generating operational behavior time windows.

[0055] Step S30: Under the constraints of the operation behavior time window, extract the disturbance morphology features of the disturbance segment to characterize the process of environmental parameter change.

[0056] Specifically, based on the start time, the peak time, and the end time, the environmental parameter change process corresponding to the disturbance segment is divided into a deviation phase and a recovery phase. Within the deviation phase, based on the relationship between environmental parameters and time, an upward change characteristic parameter characterizing the deviation rate of the environmental parameters is calculated. Within the recovery phase, based on the relationship between environmental parameters and time, a downward change characteristic parameter characterizing the return rate of the environmental parameters is calculated. Based on the time span between the peak time and the end time, a duration characteristic parameter characterizing the duration of the disturbance is determined. The upward change characteristic parameter, the downward change characteristic parameter, and the duration characteristic parameter are used as the disturbance morphological characteristics.

[0057] Furthermore, based on the time span between the peak time and the end time, a duration characteristic parameter for characterizing the degree of disturbance persistence is determined, including: within the time range between the peak time and the end time, determining the state of the environmental parameter's deviation from the corresponding stable baseline, distinguishing between time intervals in the deviation state and time intervals in the stabilization state; within the time range, accumulating each time interval in the deviation state to obtain the effective duration for which the environmental parameter is actually maintained in the deviation state; and using the effective duration as the duration characteristic parameter to characterize the true degree of deviation of the environmental parameter from the stable state in the disturbance segment.

[0058] In this embodiment of the invention, under the constraint of the operation behavior time window, disturbance morphological features are extracted from the disturbance segment to characterize the environmental parameter change process. The constraint here means that feature extraction is performed only on the effective overlap between the disturbance segment and the operation behavior time window on the time axis, avoiding the mixing of slow drifts outside the disturbance segment, fluctuations in other operation stages, or sampling noise into the feature calculation. The purpose of this is simple: the same disturbance segment may have different evolutionary rhythms under different operation backgrounds. If the data range is not first limited by the operation behavior time window, subsequent anomaly type determination based on coverage relationship and morphological features will result in semantic drift, meaning that the morphological features do not correspond to the disturbance process under that operation background. Specifically, it includes the following steps:

[0059] 1) Time range limitation and stage division: Suppose that the disturbance segment starts from the initial time t s Peak time t p End time t e It is determined, and satisfies t s <t p <t e Let the time window for the task be... First, construct the effective time period [t] for calculating the features. a , t b The method takes the overlapping interval between the disturbance segment and the operation behavior time window to ensure that the meaning under the constraint of the operation behavior time window is realized at the data level.

[0060]

[0061] Among them, t a t is the starting point of the valid time period. b This is the end point of the valid time period. When t a ≥t b If the perturbation segment is considered to lack valid data within the time window of the operation, it can be skipped or marked as an undecidable sample according to preset rules, which will not be elaborated here. Subsequent actions will only be taken when t∈[t... a , tb The internal processing environment parameter sequence. Let the time series of the environment parameters be x(t). If it is discrete sampling, let the sampling time be t. i The sampled value is x i =x(t i Let i = 1, 2, ..., N, and satisfy t1 ≥ ta, t N ≤t b .

[0062] Based on t s t p t e The disturbance process is divided into a deviation phase and a recovery phase. To align with the effective time period, this implementation uses a truncated phase definition: the deviation phase is the part from the disturbance entering a deviation and continuing to develop; the recovery phase is the part returning to stability after the peak.

[0063]

[0064] Here, the superscript 'u' indicates the deviation phase, and the superscript 'd' indicates the recovery phase. If a certain phase occurs... or This indicates that there are no available samples within the valid time period in this stage. The corresponding features of this stage can be recorded according to the preset missing data handling rules to ensure data closure.

[0065] 2) The characteristic parameter k of the upward change up The calculation of k: The rising change characteristic parameter is used to characterize the deviation rate during the deviation phase, which intuitively represents how fast the deviation occurs. Considering the sampling jitter and quantization noise commonly found in logistics data, this implementation method does not directly use the adjacent difference as the slope, but instead uses the least squares fitting slope within the deviation phase as k. up This can reduce the amplification effect of individual outliers on the slope.

[0066] First, define the set of sampling point indices for the deviation phase I. u ,satisfy Define the mean of the deviation phase and the mean of the parameters:

[0067]

[0068] in, For set I u The number of sampling points in the middle. Then k up Take it as the slope term of the linear regression:

[0069]

[0070] In equation (4), k upThe unit is the environmental parameter unit divided by the time unit. For example, temperature scenarios can be understood as degrees Celsius per second or degrees Celsius per minute, depending on t. i The unit of time measurement used. If the deviation from the phase t... i The near-unchanging denominator, approaching 0, indicates insufficient sampling support at this stage. k can be adjusted according to preset rules. up Record it as missing and output the missing flag.

[0071] 3) Characteristic parameter k of the decline change down The calculation of the regression characteristic parameter is used to characterize the regression rate during the recovery phase, i.e., how quickly the price stabilizes. Consistent with the deviation phase, the least squares slope is used as k in the recovery phase. down To maintain consistent feature size and avoid scale deviation caused by different calculation methods;

[0072] Define the set of sampling point indices I for the recovery phase. d ,satisfy Similarly, the mean is defined as follows:

[0073]

[0074] The slope of the decline is:

[0075]

[0076] Typically, if environmental parameters return to stability after reaching their peak, k down The value is negative. A sign is not strictly required here, as the deviation directions of different environmental parameters may be opposite; for example, some parameters may deviate as a decrease rather than an increase. Subsequent anomaly type determination can be based on k. up With k down The symbol combination or its absolute value participates in the rule calculation.

[0077] 4) Effective duration of the duration feature parameter : Only use (t) e -t p Describing the duration of a peak in fresh food delivery presents a practical problem: the recovery phase after a peak may involve alternating periods of brief stabilization and renewed deviation, such as during loading / unloading breaks, multiple opening and closing of cargo doors, or localized warming of the cargo compartment followed by refrigeration. In such cases, the "span from peak to end" does not accurately represent the cumulative time the environmental parameters were actually in a deviated state. This implementation introduces a deviation state determination mechanism, decomposing the recovery phase into a deviation state interval and a stabilization state interval, and summing the durations of the deviation state intervals to obtain the effective duration. .

[0078] First, the stable baseline b and the stable bandwidth are given. b can be determined by a preset baseline state, such as the mean of a stable sample before the start of the task's time window. It can be determined by a preset stability range or derived from the fluctuation level of the stable sample. b. Determined by the stability interval corresponding to the baseline state, or calculated from the same preset stability range. Based on (b, Define the stability interval Define the deviation state indicator function s(t):

[0079]

[0080] Where s(t)=1 indicates that the environmental parameters at time t are still deviating from the stable range, and s(t)=0 indicates that they have stabilized. Based on this, the effective duration is defined as the time from t to t. p , t e Integral time occupied by the internal deviation state:

[0081]

[0082] Equation (8) represents the cumulative duration of the deviation state after the peak. For discrete sampled data, a piecewise constant approximation can be used, and unequal interval sampling can be explicitly considered. Let I pe To meet The index set, and define Then we have:

[0083]

[0084] in, For adjacent sampling intervals, s i This is a discrete deviation state indicator. The advantage of this form is that even if the sampling interval is not constant, the accumulation is still weighted by the actual time length, preventing systematic bias caused by overestimation in densely sampled areas and underestimation in sparsely sampled areas. It is important to emphasize that t... e The condition is determined by "recovery to the preset stable range" during the construction of the perturbation segment, therefore (b, The same or mappable consistent aperture should be used with the preset stable range to avoid... With t e Definition conflict.

[0085] 5) Organization and output of perturbation morphological characteristics: After obtaining k up k down With τ eff Then, it is used as the core component of the perturbation morphological features and formed a feature vector f, so that it can be used in conjunction with the time coverage relationship to determine the anomaly type:

[0086]

[0087] Wherein, the first component of f reflects the average deviation rate during the deviation phase, the second component reflects the average regression rate during the recovery phase, and the third component reflects the effective duration of the actual deviation state after the peak. If a component cannot be calculated due to missing phases or insufficient sampling support, a missing marker is output according to preset rules while other computable components are retained to ensure that the output chain from the perturbation segment to the perturbation morphological feature remains unbroken.

[0088] Step S40: Based on the time coverage relationship between the disturbance segment and the operation behavior time window, and combined with the disturbance morphology characteristics, determine the anomaly type corresponding to the disturbance segment, and associate the anomaly type with the corresponding operation behavior information to form a dynamic tracking result of logistics information.

[0089] Specifically, based on the temporal coverage relationship between the disturbance segment and the operation behavior time window, and combined with the disturbance morphology characteristics, the anomaly type corresponding to the disturbance segment is determined, including: calculating the overlap time length of the disturbance segment within the operation behavior time window, and determining the temporal coverage relationship characteristics of the disturbance segment within the operation behavior time window based on the relationship between the overlap time length and the duration characteristic parameter of the disturbance segment; jointly analyzing the temporal coverage relationship characteristics and the disturbance morphology characteristics to obtain an anomaly determination feature combination used to characterize the formation mechanism of the disturbance segment; and performing anomaly type determination on the disturbance segment according to the preset anomaly type determination rules based on the anomaly determination feature combination to obtain the anomaly type corresponding to the disturbance segment.

[0090] Furthermore, the abnormality type is associated with the corresponding operational behavior information to form a dynamic tracking result of logistics information, including: extracting the disturbance segment identifier information and the operational behavior time window information corresponding to the disturbance segment based on the abnormality type corresponding to the disturbance segment; associating and encapsulating the abnormality type, the disturbance segment identifier information and the operational behavior time window information to generate an abnormality association record unit for characterizing the operational background of the abnormality type; and organizing the abnormality association record unit sequentially according to the occurrence order of the disturbance segment in the time dimension to form a dynamic tracking result of logistics information for reflecting the abnormal evolution process in fresh food logistics.

[0091] In this embodiment of the invention, based on the already obtained disturbance segments, operation behavior time windows and disturbance morphology features, the abnormality type corresponding to the disturbance segment is further determined based on the time coverage relationship between the disturbance segment and the operation behavior time window, and combined with the disturbance morphology features. The determined abnormality type is then associated with the corresponding operation behavior information and recorded to form a dynamic tracking result of logistics information.

[0092] The temporal relationship between disturbance segments and work activity time windows is quantitatively described. Specifically, the start and end times of the disturbance segment and the start and end times of the work activity time window are determined on the time axis, and the overlap interval between them in the time dimension is calculated. When the disturbance segment and the work activity time window intersect on the time axis, the overlap time length corresponding to the intersection is extracted; when there is no valid intersection, the overlap time length is determined to be zero. In this way, the fact that whether a disturbance segment occurs during a specific work activity is transformed into a quantifiable time parameter.

[0093] After obtaining the overlap time length, the overlap time length is compared and analyzed with the duration feature parameter corresponding to the disturbance segment to determine the temporal coverage relationship characteristics of the disturbance segment within the operation behavior time window. Specifically, by analyzing the proportional relationship between the overlap time length and the duration feature parameter of the disturbance segment, different coverage scenarios are distinguished: the disturbance segment mainly occurs during the operation behavior, partially occurs during the operation behavior, or is basically independent of the operation behavior time window. This temporal coverage relationship feature is used to characterize the degree of temporal coupling between the disturbance segment and the operation behavior, providing a temporal dimension basis for subsequent anomaly type determination.

[0094] Based on this, the temporal coverage relationship features are jointly analyzed with the previously extracted disturbance morphology features. The disturbance morphology features include rising change feature parameters characterizing the rate of deviation of environmental parameters, falling change feature parameters characterizing the rate of return of environmental parameters, and duration feature parameters characterizing the degree of disturbance persistence. By combining the temporal coverage relationship features with the disturbance morphology features, an anomaly detection feature combination is constructed to characterize the formation mechanism of disturbance segments. This anomaly detection feature combination can simultaneously reflect the temporal background of the disturbance and the changing morphology features of the disturbance itself, thereby avoiding the ambiguity caused by relying solely on a single dimension of information for anomaly judgment.

[0095] Furthermore, based on the aforementioned combination of anomaly detection features, anomaly type determination is performed on the disturbance segment according to preset anomaly type determination rules. These anomaly type determination rules describe the mapping relationship between different combinations of time coverage features and different disturbance morphology features. For example, when a disturbance segment has a high time coverage ratio within the operation behavior time window, and the disturbance morphology features exhibit rapid deviation and rapid fallback, the anomaly type corresponding to this disturbance segment can be determined to be related to operational behavior; when the coverage ratio of the disturbance segment within the operation behavior time window is low, and the disturbance duration is long, the disturbance segment can be determined to be more likely related to environmental control anomalies during transportation. Through the above rule-based determination process, the anomaly type corresponding to the disturbance segment is obtained.

[0096] After determining the anomaly type, the anomaly type is further associated with the corresponding operational behavior information to form a dynamic tracking result for logistics information. Specifically, based on the anomaly type corresponding to the disturbance segment, the disturbance segment identifier information corresponding to that anomaly type is extracted, and the operational behavior time window information corresponding to the disturbance segment is also extracted. The disturbance segment identifier information is used to distinguish different disturbance segments, and the operational behavior time window information is used to characterize the operational background when the anomaly occurs.

[0097] Furthermore, the anomaly type, disturbance segment identification information, and operation behavior time window information are associated and encapsulated to generate an anomaly association record unit. This anomaly association record unit is used to fully describe the type characteristics, time characteristics, and corresponding operation behavior background of an anomaly event, thereby forming a structured anomaly record with clear semantic meaning.

[0098] Based on the temporal order of occurrence of disturbance segments, multiple anomaly-related record units are sequentially organized to form dynamic tracking results of logistics information that reflect the evolution of anomalies in fresh food logistics. In this way, the dynamic tracking results of logistics information can not only reflect individual anomaly events, but also present the order of occurrence and evolution of anomalies over time, thus providing a complete data foundation for subsequent anomaly analysis, accountability tracing, or process assessment.

[0099] In another possible implementation, when determining the anomaly type based on the temporal coverage relationship between the disturbance segment and the operation behavior time window and the disturbance morphology characteristics, not only is the overall coverage ratio of the disturbance segment within the operation behavior time window considered, but also the temporal position characteristics of the disturbance segment within the operation behavior time window are further introduced to characterize the sequential relationship between the disturbance occurrence and the operation behavior stage.

[0100] Specifically, when it is determined that there is a valid overlap between the disturbance segment and the operation behavior time window, the operation behavior time window is divided into three sub-stages: the initial stage of the operation, the intermediate stabilization stage, and the operation completion stage. The time range of each sub-stage is obtained by dividing the start and end times of the operation behavior time window according to a preset ratio. Subsequently, based on the overlapping interval of the disturbance segment within the operation behavior time window, the location characteristics of the operation stage in which the disturbance segment mainly occurs are determined.

[0101] In this embodiment, when the peak time of the disturbance segment falls in the initial stage of the operation, and the disturbance morphology is characterized by a large upward change parameter and a short duration parameter, the disturbance is considered to be more likely to be related to environmental exposure or equipment state switching during the operation start-up process; when the peak time of the disturbance segment falls in the middle stable stage of the operation, and the disturbance duration is relatively long, the disturbance is considered to be more likely to reflect insufficient environmental control capabilities during the operation; when the disturbance segment is mainly concentrated in the end stage of the operation, and the decline parameter is relatively slow, the disturbance is considered to be more likely to be related to the closure delay or transfer connection in the operation closing stage.

[0102] Based on this, the operational phase location features, the aforementioned time coverage relationship features, and the disturbance morphology features are all incorporated into the anomaly detection feature combination, and anomaly type detection is performed according to preset anomaly type detection rules. By introducing the phased location features of the disturbance within the operational behavior time window, anomaly type detection not only focuses on how long the disturbance has occurred and how quickly it has changed, but also further focuses on which stage of the operation the disturbance occurs in, thereby improving the ability to distinguish anomaly types.

[0103] After determining the anomaly type, the anomaly type is associated and encapsulated with the disturbance segment identifier information and the corresponding operation behavior time window information in the aforementioned manner to generate an anomaly association record unit, which is then organized in chronological order to form a dynamic tracking result for logistics information. Through this implementation method, the dynamic tracking result for logistics information can further reflect the phased distribution characteristics of anomalies within the operation process, providing a more targeted reference for anomaly cause analysis and operation process optimization.

[0104] In one specific implementation, the execution process of the dynamic tracking method for logistics information described in this invention is illustrated using a logistics scenario of a batch of fresh-cut fruit transported via cold chain in urban distribution as an example.

[0105] In this embodiment, the fresh produce is transported by refrigerated transport vehicles during the delivery process, and logistics information is continuously collected during delivery. This logistics information includes at least environmental parameter information, location information, and time information. The environmental parameter information is the internal temperature of the container, with a sampling period of 30 seconds. Before transportation, a stable temperature baseline of 4°C and a stability bandwidth of ±0.5°C are determined based on historical stable transportation data.

[0106] During a certain delivery process, based on continuously collected temperature data, the temperature was detected to be rising continuously from 4.1℃ on the time axis, and first exceeding 4.5℃ at 10:15:00. This determined the start time t of the disturbance segment. s The time was 10:15:00. The temperature then continued to rise, reaching a maximum of 8.0℃ at 10:22:30, corresponding to the peak time t. pThe time was 10:22:30. Afterwards, the temperature began to drop and recovered to below 4.5℃ by 10:35:00, thus determining the end time t of the disturbance. e At 10:35:00, a complete perturbation segment is constructed.

[0107] Based on the aforementioned disturbance segment, behavioral characteristics reflecting changes in location and operational status in logistics information were analyzed within the same time range. The analysis results show that from 10:14:30 to 10:28:00, the location of fresh produce remained largely unchanged, and the corresponding location was within the range of a certain delivery station. Therefore, it was determined that the fresh produce was undergoing operational activities during this time period, and the start time of the corresponding operational activity time window was [missing information]. The end time is .

[0108] Further calculations revealed a temporal overlap between the disturbance segment and the operation time window, with an overlap duration of 13 minutes between 10:15:00 and 10:28:00. The total duration of the disturbance segment was 20 minutes, thus determining that the time coverage ratio of the disturbance segment within the operation time window was approximately 65%.

[0109] Under the constraint of the operation time window, disturbance morphology features are extracted from the disturbance segments. The deviation phase lasts from 10:15:00 to 10:22:30, a duration of 7.5 min, with a temperature rise of 3.9℃, and the calculated rise change characteristic parameter is 0.52℃ / min; the recovery phase lasts from 10:22:30 to 10:35:00, a duration of 12.5 min, and the calculated fall change characteristic parameter is −0.28℃ / min; the effective duration is obtained by accumulating the time when the temperature is in the deviation range from the peak time to the end time. It takes 9.8 minutes.

[0110] Based on the temporal coverage characteristics and the aforementioned disturbance morphology characteristics, an anomaly detection feature combination was constructed, and judgment was made according to preset anomaly type judgment rules. The judgment results showed that the disturbance segment had a high temporal coverage ratio during operational activities and exhibited a rapid temperature rise followed by a slow temperature fall. Ultimately, the anomaly type corresponding to this disturbance segment was determined to be a short-term temperature control anomaly caused by operational activities. Finally, the anomaly type, disturbance segment identification information, and corresponding operational activity time window information were associated and encapsulated to form an anomaly association record unit. This record unit was then incorporated into the dynamic tracking results of logistics information in chronological order to reflect the anomaly evolution of this batch of fresh produce during the delivery process.

[0111] like Figure 2As shown, this invention provides a dynamic tracking device for logistics information. The device includes: a data acquisition unit, used to acquire logistics information generated during the fresh produce logistics process, and construct a disturbance segment based on the logistics information to characterize the deviation process of environmental parameters; a processing unit, used to identify the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment based on the logistics information, and generate an operation behavior time window aligned with the time of the disturbance segment; a feature extraction unit, used to extract disturbance morphological features from the disturbance segment under the constraint of the operation behavior time window to characterize the change process of environmental parameters; and a result output unit, used to determine the anomaly type corresponding to the disturbance segment based on the time coverage relationship between the disturbance segment and the operation behavior time window, and in combination with the disturbance morphological features, and associate the anomaly type with the corresponding operation behavior information to form a dynamic tracking result for logistics information.

[0112] A third aspect of the present invention provides a dynamic tracking device for logistics information, wherein the device is equipped with the aforementioned dynamic tracking device for logistics information.

[0113] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions which, when executed on a computer, cause the computer to perform the above-described dynamic tracking method for logistics information.

[0114] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0115] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details described above. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe the various possible combinations.

[0116] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the embodiments of the present invention, they should also be regarded as the content disclosed by the embodiments of the present invention.

Claims

1. A method for dynamic tracking of logistics information, characterized in that, The method includes: Acquire logistics information generated during the fresh produce logistics process, and construct a disturbance segment based on the logistics information to characterize the deviation process of environmental parameters, including: Trend analysis is performed on the parameters reflecting environmental state changes in the logistics information over a continuous time dimension to determine the starting moment when the environmental parameters deviate from the corresponding baseline state. Starting from the starting moment, the change process of the environmental parameters is continuously tracked, and the peak moment when the environmental parameters reach the maximum degree of deviation is recorded. After the peak moment, the regression process of the environmental parameters is continuously monitored, and the end moment of the disturbance is determined when the environmental parameters recover to a preset stable range. Based on the starting moment, the peak moment, and the end moment, a disturbance segment is constructed to fully characterize the deviation process of the environmental parameters. Based on the logistics information, the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment is identified, and an operation behavior time window aligned with the time of the disturbance segment is generated, including: Within the time range corresponding to the disturbance segment, the behavioral characteristics reflecting changes in the location and operational status of fresh produce in the logistics information are analyzed to determine the operational behavior type of fresh produce within the time range. Based on the operational behavior type, the start and end times of the operation corresponding to the time range of the disturbance segment are extracted to form an operational behavior time interval for characterizing the duration of the operational behavior. The operational behavior time interval is time-aligned with the start, peak, and end times of the disturbance segment to generate an operational behavior time window for characterizing the operational background when the disturbance segment occurs. Under the constraints of the operation behavior time window, disturbance morphology features are extracted from the disturbance segment to characterize the process of environmental parameter change; Based on the time coverage relationship between the disturbance segment and the time window of the operation behavior, and combined with the disturbance morphology characteristics, the abnormality type corresponding to the disturbance segment is determined, and the abnormality type is associated with the corresponding operation behavior information and recorded to form a dynamic tracking result of logistics information.

2. The dynamic tracking method for logistics information according to claim 1, characterized in that, Under the constraints of the operation behavior time window, disturbance morphological features for characterizing the environmental parameter change process are extracted from the disturbance segment, including: Based on the start time, the peak time, and the end time, the environmental parameter change process corresponding to the disturbance segment is divided into a deviation phase and a recovery phase; During the deviation phase, based on the relationship between environmental parameters and time, characteristic parameters of rising change are calculated to characterize the rate of deviation of environmental parameters; During the recovery phase, based on the relationship between environmental parameters and time, a regression change characteristic parameter is calculated to characterize the regression rate of environmental parameters. Based on the time span between the peak time and the end time, a duration characteristic parameter for characterizing the duration of the disturbance is determined; The rising change characteristic parameter, the falling change characteristic parameter, and the duration characteristic parameter are used as the disturbance morphology features.

3. The dynamic tracking method for logistics information according to claim 2, characterized in that, Based on the time span between the peak time and the end time, duration characteristic parameters for characterizing the duration of the disturbance are determined, including: Within the time range between the peak time and the end time, the deviation of the environmental parameters from the corresponding stable baseline is determined, and the time interval in the deviation state is distinguished from the time interval in the stabilization state. Within the stated time range, the time intervals in the deviated state are summed to obtain the effective duration for which the environmental parameters are actually maintained in the deviated state. The effective duration is used as the duration feature parameter to characterize the true extent to which environmental parameters deviate from the steady state in the perturbation segment.

4. The dynamic tracking method for logistics information according to claim 3, characterized in that, Based on the temporal coverage relationship between the disturbance segment and the operation behavior time window, and in conjunction with the disturbance morphology characteristics, the anomaly type corresponding to the disturbance segment is determined, including: Calculate the overlap time length of the disturbance segment within the operation behavior time window, and determine the time coverage relationship characteristics of the disturbance segment within the operation behavior time window based on the relationship between the overlap time length and the duration characteristic parameter of the disturbance segment; By jointly analyzing the time coverage relationship features and the perturbation morphology features, an anomaly determination feature combination for characterizing the formation mechanism of perturbation segments is obtained; Based on the combination of anomaly detection features, the anomaly type is determined according to the preset anomaly type determination rules to obtain the anomaly type corresponding to the anomaly segment.

5. The dynamic tracking method for logistics information according to claim 4, characterized in that, The anomaly types are associated with and recorded with the corresponding operational behavior information to form dynamic tracking results of logistics information, including: Based on the anomaly type corresponding to the disturbance segment, extract the disturbance segment identifier information corresponding to the anomaly type and the operation behavior time window information corresponding to the disturbance segment; The anomaly type, the disturbance segment identification information, and the operation behavior time window information are associated and encapsulated to generate an anomaly association record unit that characterizes the operation background of the anomaly type. The abnormal correlation recording units are organized sequentially according to the order in which the disturbance segments occur in the time dimension, forming a dynamic tracking result of logistics information that reflects the abnormal evolution process in fresh food logistics.

6. A dynamic tracking device for logistics information, characterized in that, The apparatus is used to perform the dynamic tracking method for logistics information according to any one of claims 1-5, and the apparatus comprises: The acquisition unit is used to acquire logistics information generated during the fresh food logistics process, and to construct a disturbance segment based on the logistics information to characterize the deviation process of environmental parameters. The processing unit is used to identify the logistics operation behavior of fresh produce within the time range corresponding to the disturbance segment based on the logistics information, and generate an operation behavior time window aligned with the time of the disturbance segment; The feature extraction unit is used to extract disturbance morphological features from the disturbance segment under the constraints of the operation behavior time window to characterize the process of environmental parameter change. The result output unit is used to determine the anomaly type corresponding to the disturbance segment based on the time coverage relationship between the disturbance segment and the operation behavior time window, and in combination with the disturbance morphology characteristics, and to associate and record the anomaly type with the corresponding operation behavior information to form a dynamic tracking result of logistics information.

7. A dynamic tracking device for logistics information, characterized in that, The device is equipped with the logistics information dynamic tracking device as described in claim 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the dynamic tracking method for logistics information as described in any one of claims 1-5.

Images