Fresh food cold chain tracing and early warning system based on Internet of Things technology

Abstract

The invention discloses a fresh food cold chain tracing and early warning system based on the Internet of Things technology, and relates to the technical field of fresh food cold chain tracing, which integrates sensing modules such as GPS positioning, temperature and humidity monitoring, electronic fence management, parking identification, cargo compartment state monitoring and the like, and comprehensively judges the actual parking behavior of a vehicle through a data fusion analysis module. The path execution judgment module further combines a scoring result with a distribution task preset path to carry out intelligent comparison, whether each stop task is completed or not is accurately judged, and if the stop task is not completed, an abnormity early warning module reports abnormity information to a dispatching center in time; the whole-process intelligent identification and real-time early warning of the distribution behavior are realized, and the accuracy, integrity and system response capability of cold chain tracing are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fresh produce cold chain traceability, and in particular to a fresh produce cold chain traceability and early warning system based on Internet of Things technology. Background Art

[0002] The fresh produce cold chain traceability and early warning system based on Internet of Things technology refers to the use of Internet of Things technologies such as sensors, wireless communications, and cloud computing to collect and monitor key data such as temperature, humidity, and location of fresh produce throughout the cold chain transportation and storage process in real time, thereby achieving comprehensive traceability of the source, circulation path, and quality status of fresh produce, and issuing timely early warnings when abnormal conditions (such as temperature exceeding the standard) are discovered, thereby ensuring food safety and improving logistics efficiency.

[0003] The existing technology has the following shortcomings:

[0004] In urban cold chain delivery, when multiple stops are densely packed (e.g., less than 500 meters apart), if the platform system's GPS sampling frequency is low and only uses entry into electronic fences as a stop criterion, a vehicle's brief stop may not be accurately identified, leading the system to mistakenly identify it as a missed stop or skipped stop. This error can result in missing data during order tracing, incomplete user interface displays, and even be mistakenly identified as delivery fraud during audits, misleading consumers or regulators into believing there is a risk of cold chain disruption. Summary of the Invention

[0005] The purpose of the present invention is to provide a fresh cold chain traceability and early warning system based on Internet of Things technology to solve the shortcomings in the background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: a fresh cold chain traceability and early warning system based on Internet of Things technology, comprising a GPS positioning module, a temperature and humidity sensor module, an electronic fence management module, a parking recognition module, a cargo compartment status monitoring module, a data fusion analysis module, a path execution determination module, and an abnormality early warning module;

[0007] GPS positioning module, used to collect real-time location information of cold chain vehicles;

[0008] Temperature and humidity sensor module, used to collect temperature and humidity data of the refrigerated environment;

[0009] The electronic fence management module is used to set the geographical fence information of each stop point in the cold chain delivery task;

[0010] Parking recognition module, used to identify actual parking behavior based on vehicle speed changes and continuous stationary time;

[0011] Cargo compartment status monitoring module, used to detect the open or closed status of the vehicle-mounted cargo container;

[0012] The data fusion analysis module is used to integrate GPS positioning information, parking identification results and cargo compartment status data for analysis, and output the corresponding stop behavior credibility score;

[0013] The route execution determination module determines whether the vehicle has completed the docking task at the designated delivery point based on the credibility score and the comparison results of the preset route and docking point information in the delivery task;

[0014] The abnormal warning module, if not completed, will generate corresponding warning information and send it to the dispatch center.

[0015] Preferably, the electronic fence management module supports customized polygon settings of the fence area and configures a task number, a time window and a docking behavior requirement for each fence.

[0016] Preferably, the cargo compartment status monitoring module collects the cargo compartment switch status based on the door magnetic sensor, and allows the door opening operation when the vehicle is in a designated electronic fence. If the door opening behavior occurs in a non-preset area, an abnormal warning is automatically triggered.

[0017] Preferably, the data fusion analysis module specifically includes:

[0018] Obtain vehicle GPS track information, parking identification data, and cargo compartment status data;

[0019] Aligning the data according to timestamps;

[0020] Extract stop behavior characteristics, including GPS dwell time deviation, door opening frequency anomalies, and the offset distance between the stop point and the fence center;

[0021] The characteristic values are normalized and the credibility score of the menstrual stop behavior is calculated based on the weighted average formula, with the score ranging from 0 to 1.

[0022] Preferably, the method for extracting the GPS dwell time deviation value is as follows: inputting a GPS trajectory point sequence P={(lat1, lon1, t1), (lat2, lon2, t2), ..., (lat n ,lon n ,t n )};lat i is the latitude of the i-th GPS point, lon i is the longitude of the i-th GPS point, t i is the timestamp of the i-th GPS point; map the GPS track points to the actual road or geographical location area, use the map matching algorithm to correct GPS drift and jump points, and output a set of track points with matching results, marking whether they are within the target fence: P′={(lat i ,loni ,t i ,inzone)}; inzone means being within the target fence; traverse the matching trajectory points, find the data segments with continuous in zone = true, obtain the actual entry time: Tenter, the actual exit time: Texit, and calculate the actual residence time Tactual: Tactual = Texit-Tenter; obtain the expected residence time of the task Texpected, calculate the GPS residence time deviation value ΔT, the expression is: ΔT = Tactual-Texpected.

[0023] Preferably, the method for extracting abnormal values of door opening frequency is as follows: each time the cargo door is opened, the sensor records an event: D = {(t1, loc1), (t2, loc2), ..., (t m ,loc m )}; Each data contains the door opening timestamp t i , door opening position coordinates loc i , m is the total number of coordinates; the preset tasks include: stop point list S = {s1, s2, ..., s z}; Whether each station requires the door to be opened; Set the expected number of door openings to: Nexpected = z; That is: if there are z delivery points, the expected number of door openings is z times, and count the actual number of door openings: Nactual = len(D); Count the total number of actual door opening events, and the door opening frequency abnormality value ΔN is defined as: ΔN = Nactual - Nexpected.

[0024] Preferably, the method for obtaining the offset distance is: in the task setting, a fence is set for each delivery point, and the coordinates of the center point are: C = (lat c ,lon c ); that is, the center of the electronic fence of the station, which is preset as the most ideal parking position; the parking point coordinates of the vehicle are obtained from the parking recognition module: P = (lat p ,lon p ); calculated using the Earth plane approximation: Where: Δlat = lat p -lat c ; Δlon=lon p -lon c ; D is the offset distance.

[0025] Preferably, the obtained credibility score of the stopover behavior is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the credibility score of the stopover behavior is compared with the first standard threshold and the second standard threshold respectively;

[0026] If the credibility score of the stop behavior is greater than the second standard threshold, it is judged as a highly credible delivery behavior; if the credibility score of the stop behavior is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it is judged as a medium credible delivery behavior; if the credibility score of the stop behavior is less than the first standard threshold, it is judged as a low credible delivery behavior.

[0027] Preferably, the preset route and stop information in the delivery task are compared, and the comparison results are combined with the credibility score for comprehensive analysis to determine whether the vehicle has completed the stop task at the designated delivery point, specifically:

[0028] Preset path data R={r1,r2,…,r p}: p is the total number of path data in the sequence; the actual trajectory data P = {(lat1, lon1, t1), (lat2, lon2, t2), ..., (lat n ,lon n ,t n )}; The credibility score of each stop point Gi∈[0,1]; Map matching is performed on the trajectory sequence to correct GPS jump points;

[0029] Calculate the trajectory similarity between the actual trajectory and the expected path segment: D dtw is the DTW distance between the actual and preset trajectory; Sim i ∈[0,1]: trajectory matching similarity;

[0030] Compare the trajectory results to Sim i Comprehensively analyze the behavior credibility score Ci to define the final path execution credibility F i :F i =α·Ci+(1-α)·Sim i ;α∈[0.5,0.9].

[0031] Preferably, the final route execution credibility is compared with a predetermined threshold. If the route execution credibility is greater than or equal to the predetermined threshold, the route execution is determined to be successful, indicating that the vehicle's behavior at all stops during the entire delivery task complies with the credibility rules set by the system.

[0032] If the path execution credibility is less than the predetermined threshold, it is judged as path execution abnormality, indicating that the vehicle has obvious abnormal behavior in this delivery task, and an abnormal warning is automatically sent to the dispatching platform.

[0033] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0034] 1. This invention overcomes the problem of misjudgment of stop identification in traditional cold chain delivery systems, caused by the low granularity of GPS data and a single decision mechanism, by introducing a multi-module collaborative IoT architecture. By combining multi-dimensional sensory data such as GPS positioning, temperature and humidity sensing, fence recognition, parking detection, and cargo compartment opening and closing status, and outputting a credibility score for stop behavior through a fusion analysis model, this system not only significantly improves the accuracy and robustness of delivery behavior identification at high-density delivery stops, but also avoids common misjudgments such as missed stops and skipped stops, thereby ensuring the integrity and verifiability of order traceability data.

[0035] 2. The proposed path execution determination and grading mechanism intelligently distinguishes the trustworthiness of delivery behaviors. Combined with the anomaly warning module, it automates and intelligently processes behavior recognition, risk detection, and response during the delivery process. The overall system enhances the monitorability, traceability, and emergency response capabilities of cold chain logistics. It is suitable for use in food, pharmaceuticals, and other applications requiring extremely high cold chain continuity, demonstrating promising prospects for industry adoption and practical application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0037] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0039] For examples, see Figure 1 As shown, the fresh cold chain traceability and early warning system based on Internet of Things technology described in this embodiment includes a GPS positioning module, a temperature and humidity sensor module, an electronic fence management module, a parking recognition module, a cargo compartment status monitoring module, a data fusion analysis module, a path execution determination module, and an abnormality early warning module;

[0040] GPS positioning module, used to collect real-time location information of cold chain vehicles;

[0041] Temperature and humidity sensor module, used to collect temperature and humidity data of the refrigerated environment;

[0042] The electronic fence management module is used to set the geographical fence information of each stop point in the cold chain delivery task;

[0043] Parking recognition module, used to identify actual parking behavior based on vehicle speed changes and continuous stationary time;

[0044] Cargo compartment status monitoring module, used to detect the open or closed status of the vehicle-mounted cargo container;

[0045] The data fusion analysis module is used to integrate GPS positioning information, parking identification results and cargo compartment status data for analysis, and output the corresponding stop behavior credibility score;

[0046] The route execution determination module determines whether the vehicle has completed the docking task at the designated delivery point based on the credibility score and the comparison results of the preset route and docking point information in the delivery task;

[0047] The abnormal warning module, if not completed, will generate corresponding warning information and send it to the dispatch center.

[0048] The GPS positioning module is used to collect and record the real-time trajectory of cold chain transport vehicles, and obtain data such as the latitude and longitude, speed, driving direction, timestamp, etc. of the vehicle during the delivery process.

[0049] It has a built-in global positioning system (GPS) or Beidou satellite module and supports high-frequency sampling (such as once every 5 seconds). It supports differential positioning (DGPS) or RTK enhancement to improve positioning accuracy to sub-meter level. It has a signal loss buffer mechanism that can automatically store positioning data in obstructed environments such as tunnels and viaducts, and automatically retransmit it after the signal is restored. It supports API docking with map services (such as Baidu Maps and Amap) to achieve path visualization and playback. Positioning information is uploaded to the cold chain cloud platform via cellular networks (such as 4G / 5G) or NB-IoT. It provides basic location data for path deviation detection, electronic fence identification, trajectory backtracking, and transportation compliance review.

[0050] The temperature and humidity sensing module continuously monitors the refrigerated environment within cold chain transport vehicles, collecting and uploading temperature and humidity data to ensure that the transportation process meets fresh produce preservation standards. It utilizes high-precision digital temperature and humidity sensors (such as SHT35 and DHT22) with an accuracy of ±0.1°C and ±1.5% RH. Modules can be deployed at multiple locations based on the temperature distribution characteristics of the refrigerated space to prevent localized temperature measurement distortion. It supports real-time sampling and local caching, with a configurable sampling interval (e.g., 1 minute). It provides an alarm function for abnormal temperature exceeding the limit, instantly sending warnings when thresholds are exceeded. It can be integrated into the vehicle controller or exist as a standalone Bluetooth / LoRa module. It provides evidence of the integrity of the temperature control chain, providing critical monitoring support for the "uninterrupted cold chain" requirement and serving as a vital data source for traceability and early warning systems.

[0051] The electronic fence management module is used to set a virtual geographic boundary (Geo-fence) for each preset stop point in the cold chain distribution task (such as distribution stations, stores, and receiving points), so as to realize intelligent judgment of vehicles "entering" or "leaving" a certain area. It is based on the comparison of GPS positioning data with the set fence latitude and longitude radius. It supports the modeling of circular fences, rectangular fences and custom polygonal fences. The fence size is configured according to the actual situation of the site (such as 50m, 100m radius). Each fence is equipped with a logical trigger: entry fence event, exit fence event, and non-entry timeout event. The system supports binding fences with task IDs to prevent identification confusion caused by overlapping paths. It can be used as a basic mechanism to determine whether the preset stop point has been reached, and cooperate with other modules to identify whether the delivery has been completed.

[0052] The parking recognition module is used to determine whether the vehicle has actually "stopped" at a certain location by analyzing the vehicle's speed data and inertia changes, thereby assisting in determining whether delivery has been made.

[0053] By analyzing the GPS speed values at multiple consecutive time points (such as less than 5km / h for more than 30 seconds), it is determined that the vehicle is in a "stationary" state. Redundant verification is performed in conjunction with the vehicle inertial sensor (IMU) signal or OBD interface information. The parking behavior must meet both the "stationary duration threshold" and the "location within the fence" conditions to trigger the "valid stop" event. The module can adapt to short stops, temporary waiting, traffic congestion and other situations, and eliminate misjudgments through time-location joint analysis. It compensates for the problem of electronic fences failing to judge due to GPS drift or short-term stops, and improves the accuracy and robustness of stop judgments.

[0054] The cargo compartment status monitoring module is used to monitor the opening / closing behavior of the vehicle's refrigerated cargo compartment to determine whether loading and unloading actions have occurred. It is an important clue to determine whether the delivery behavior is actually carried out.

[0055] Hall sensors, reed switches, or photoelectric switches are installed on the edge of the cargo door to detect changes in the door's opening and closing status. It can be paired with a vibration detection module (accelerometer) to determine whether items are being moved. It supports event-triggered data uploads, such as "door opening time, door closing time, and door opening duration." It can be set to allow doors to be opened only in highly sensitive areas (such as within store fences). Door openings in other areas are considered abnormal and issue warnings. Data is uploaded synchronously with GPS location information to achieve location-behavior binding. It can be used directly to verify whether actual loading and unloading operations are being performed at specific sites, and is an important auxiliary signal to enhance the credibility of delivery behavior identification.

[0056] The data fusion analysis module is used to integrate GPS positioning information, parking identification results and cargo compartment status data for analysis, and output the corresponding stop behavior credibility score, specifically:

[0057] Input data types: GPS trajectory data: current location, speed, historical trajectory points, fence entry / exit time; parking behavior data: duration of vehicle stationary state within a fence, speed curve, inertia change; cargo compartment status data: door opening / closing time, opening duration, whether door opening occurs;

[0058] The above three types of data are aligned by timestamp to ensure that the behavioral characteristics within the same time period can be cross-judged.

[0059] Extract and standardize multiple behavioral feature indicators (Features), such as GPS dwell time deviation, door opening frequency anomalies, and the offset distance between the parking point and the fence center;

[0060] The method for extracting the GPS dwell time deviation value is as follows: input the GPS trajectory point sequence P = {(lat1, lon1, t1), (lat2, lon2, t2), ..., (lat n ,lon n ,t n )};lat i is the latitude of the i-th GPS point, lon i is the longitude of the i-th GPS point, t i is the timestamp of the i-th GPS point; filters out points with low accuracy (high HDOP, abnormal speed), and unifies the time interval (e.g., one every 10 seconds).

[0061] Map GPS track points to actual roads or geographic locations to identify whether the vehicle enters or leaves the preset electronic fence. Use map matching algorithms (such as HMM / Viterbi) to correct GPS drift and jump points. Output a set of track points with matching results, marking whether they are within the target fence: P′={(lat i ,lon i,t i ,inzone)}; inzone means being within the target fence.

[0062] Traverse the matching trajectory points and find the data segment with continuous in zone = true. Determine whether the time span of the segment exceeds the minimum residence threshold (such as 30 seconds).

[0063] Assume that the following are detected: actual entry time: Tenter, actual exit time: Texit, calculate the actual residence time Tactual: Tactual = Texit - Tenter; multiple residence segments can be accumulated (such as repeated entry and exit); obtain the expected residence time of the task Texpected, calculate the GPS residence time deviation value ΔT, the expression is: ΔT = Tactual - Texpected; if: ΔT>0: timed out; ΔT<0: insufficient residence; ΔT = 0: consistent with expectations.

[0064] The door opening frequency anomaly value refers to the degree of deviation between the actual number of times the vehicle cargo compartment door is opened and the number of times the system expects the door to be opened within a certain cold chain distribution task cycle. It is used to detect abnormal behaviors such as excessive door openings, no door openings, or door openings in abnormal areas.

[0065] The method for extracting abnormal values of door opening frequency is as follows: each time the cargo door is opened, the sensor records an event: D = {(t1,loc1), (t2,loc2),…, (t m ,loc m )}; Each data contains the door opening timestamp t i , door opening position coordinates loc i (or fence area ID), m is the total number of coordinates; the preset tasks in the system usually include: stop point list S = {s1, s2, ..., s z Whether each station requires door opening (the default is to open the door once per station); Set the expected number of door openings to: Nexpected = z; that is, if there are z delivery points, the expected number of door openings is z times. Count the actual number of door openings: Nactual = len(D); Count the total number of actual door opening events. The door opening frequency anomaly value, ΔN, is defined as: ΔN = Nactual - Nexpected; If ΔN > 0, frequent door openings are suspected, indicating illegal removal of goods or frequent manipulation; If ΔN < 0, the delivery station is suspected to have not been completed or the goods have not been delivered; If ΔN = 0, the task is consistent with the mission plan and is considered normal.

[0066] The offset distance refers to the geographic distance between the vehicle's "actual parking position" at a delivery point and the "preset electronic fence center point" of the site, usually expressed in meters.

[0067] In the task setting of the system, a fence is usually set for each delivery point, and its center point coordinates are: C = (lat c , lon c ); that is, the center of the electronic fence of the site is preset as the most ideal parking position.

[0068] Obtain the parking point coordinates of the vehicle from the parking recognition module: P = (lat p , lon p ); The midpoint, starting point or weighted average position of the parking section can be taken as the representative point.

[0069] Adopt the earth plane approximation method for calculation: Where: Δlat = lat p - lat c ; Δlon = lon p - lon c ; D is the offset distance, with the unit of meter (m); 111,000 means that each degree on the earth is approximately equal to 111 kilometers (rough conversion). An offset threshold can be set: D ≤ 30m: normal approaching the point; 30 < D ≤ 100m: edge docking, manual verification is required; D > 100m: suspected non-docking or false residence.

[0070] Normalize the GPS residence time deviation value, door opening frequency anomaly value, and the offset distance between the parking point and the fence center, so that they are all within [0, 1]. According to the normalized GPS residence time deviation value, door opening frequency anomaly value, and the offset distance between the parking point and the fence center, calculate the credibility score of the stopping behavior through weighted average summation.

[0071] Compare the obtained credibility score of the stopping behavior with the gradient standard thresholds. The gradient standard thresholds include the first standard threshold and the second standard threshold, and the first standard threshold is less than the second standard threshold. Compare the credibility score of the stopping behavior with the first standard threshold and the second standard threshold respectively;

[0072] If the credibility score of the stopping behavior is greater than the second standard threshold, it is determined as a high-confidence delivery behavior, indicating that the vehicle's docking behavior at this site is stable, compliant, and reliable, and can be recorded as "effectively completing the task" without intervention, and the score recommendation is the green status;

[0073] If the credibility score of the stopping behavior is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it is determined as a medium-confidence delivery behavior, indicating that the behavior partly meets the expectations but there are slight anomalies. The system can mark it as "suspicious completion", and it is recommended that the dispatcher conduct a manual review, which can be used to generate subsequent quality inspection or spot-check tasks;

[0074] If the credibility score of the stopover behavior is lower than the first standard threshold, it is judged as a low-credibility delivery behavior, and it is suspected that the delivery was not actually completed, the stop was false, or the task was evaded. The system should immediately issue an alert and record the abnormal behavior, triggering a traceability intervention process, such as freezing the order traceability chain.

[0075] Compare the preset routes and stop information in the delivery task, and conduct a comprehensive analysis of the comparison results combined with the credibility score to determine whether the vehicle has completed the stop task at the designated delivery point. Specifically:

[0076] Preset path data R={r1,r2,…,r p}: p is the total number of path data in the sequence, including the latitude and longitude, fence radius, and residence time requirement of each delivery point;

[0077] Actual trajectory data P = {(lat1, lon1, t1), (lat2, lon2, t2), ..., (lat n ,lon n ,t n )}: GPS sampling trajectory sequence;

[0078] The credibility score Gi∈[0,1] of each stop;

[0079] Perform map matching on the trajectory sequence and correct GPS jump points;

[0080] Traverse each stop r I , perform the following judgment:

[0081] Is there any trajectory point in the trajectory P that falls within the fence Ei (set radius area);

[0082] Whether there is a continuous stay time exceeding the set threshold (such as >30 seconds);

[0083] Compute trajectory similarity between actual trajectory and expected path segments (using DTW or Frechet distance): D dtw is the DTW distance between the actual and preset trajectory; Sim i ∈[0,1]: trajectory matching similarity;

[0084] Compare the trajectory results to Sim i Comprehensive analysis and behavior credibility score Ci are performed to calculate the comprehensive score: the final path execution credibility F can be defined i :F i =α·Ci+(1-α)·Sim i ; α∈[0.5,0.9]: weighting coefficient between credibility score and trajectory similarity (biased towards behavior score);

[0085] The final route execution credibility is compared with a predefined threshold. If the credibility is greater than or equal to the threshold, the route is deemed successfully executed, indicating that the vehicle's behavior at all (or major) stops throughout the delivery mission complies with the system's established credibility rules. This indicates that the vehicle has essentially completed all stops according to the predefined route and requirements, and the delivery behavior is authentic and trustworthy. The system marks the mission path as "validly completed," allowing the order reconciliation, settlement, and traceability chain generation processes to proceed. No dispatcher intervention or exception review is required.

[0086] If the path execution credibility is less than the predetermined threshold, it is judged as path execution abnormality, indicating that the vehicle has obvious abnormal behavior in this delivery task, such as: missing some stations; failing to reach a reasonable residence time; abnormal frequency of door opening behavior; the actual trajectory seriously deviates from the preset path; the system marks the task path as "delivery abnormality or interruption", which may trigger the following operations: automatically sending an abnormality warning to the dispatching platform; transferring the task to the manual review process; freezing the traceability records or settlement of the batch of orders; and incorporating it into the behavior scoring system for driver or carrier assessment.

[0087] The Abnormal Warning Module automatically generates abnormal warning information when the Route Execution Determination Module determines that a delivery vehicle has not completed a designated route or key stops. This information is then sent to the dispatch center for further processing. An abnormality in route execution is considered present when the system determines that the route execution confidence level falls below a set threshold, when the behavioral confidence score for any key stop is significantly low, or when the offset between the actual stop and the center of the pre-set fence exceeds a reasonable range.

[0088] When any of the above abnormal situations occur, the abnormality warning module immediately generates an early warning message containing key information such as the abnormality type, abnormality occurrence time, abnormality location, and path score. This warning information is transmitted to the dispatch center system through the communication interface within the platform, or sent to relevant management personnel in real time via a configured message push mechanism (such as API call, message queue, mobile terminal push), so that timely measures such as dispatch intervention, task review, re-dispatch of vehicles, or abnormality reporting can be taken.

[0089] Furthermore, every abnormal warning event is recorded in the system's log database, serving as a basis for subsequent cold chain traceability, task audits, and performance evaluations. This module enables automated monitoring, intelligent identification, and instant feedback at the delivery level, ensuring the standardization and controllability of the cold chain transportation process and significantly improving the overall traceability system's security and response efficiency.

[0090] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0091] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0092] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. The fresh cold chain traceability and early warning system based on Internet of Things technology is characterized by: It includes GPS positioning module, temperature and humidity sensor module, electronic fence management module, parking recognition module, cargo compartment status monitoring module, data fusion analysis module, path execution judgment module and abnormal warning module; GPS positioning module, used to collect real-time location information of cold chain vehicles; Temperature and humidity sensor module, used to collect temperature and humidity data of the refrigerated environment; The electronic fence management module is used to set the geographical fence information of each stop point in the cold chain delivery task; Parking recognition module, used to identify actual parking behavior based on vehicle speed changes and continuous stationary time; Cargo compartment status monitoring module, used to detect the open or closed status of the vehicle-mounted cargo container; The data fusion analysis module is used to integrate GPS positioning information, parking identification results and cargo compartment status data for analysis, and output the corresponding stop behavior credibility score; The route execution determination module determines whether the vehicle has completed the docking task at the designated delivery point based on the credibility score and the comparison results of the preset route and docking point information in the delivery task; The abnormal warning module, if not completed, will generate corresponding warning information and send it to the dispatch center.

2. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 1 is characterized by: The electronic fence management module supports customized polygon settings of the fence area and configures the task number, time window and docking behavior requirements for each fence.

3. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 1 is characterized by: The cargo compartment status monitoring module collects the cargo compartment switch status based on the door magnetic sensor, and allows the door opening operation when the vehicle is within the specified electronic fence. If the door opening behavior occurs in a non-preset area, an abnormal warning will be automatically triggered.

4. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 1 is characterized by: The data fusion analysis module specifically includes: Obtain vehicle GPS track information, parking identification data, and cargo compartment status data; Aligning the data according to timestamps; Extract stop behavior characteristics, including GPS dwell time deviation, door opening frequency anomalies, and the offset distance between the stop point and the fence center; The characteristic values are normalized and the credibility score of the menstrual stop behavior is calculated based on the weighted average formula, with the score ranging from 0 to 1.

5. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 4 is characterized by: in, The method for extracting GPS dwell time deviation value is as follows: input GPS trajectory point sequence P = {(lat1, lon1, t1), (lat2, lon2, t2), ..., (lat n ,lon n ,t n )};lat i is the latitude of the i-th GPS point, lon i is the longitude of the i-th GPS point, t i is the timestamp of the i-th GPS point; map the GPS track points to the actual road or geographical location area, use the map matching algorithm to correct GPS drift and jump points, and output a set of track points with matching results, marking whether they are within the target fence: P′={(lat i ,lon i ,t i ,inzone)}; inzone means being inside the target fence; traverse the matching trajectory points, find the data segments with continuous inzone = true, obtain the actual entry time: Tenter, the actual exit time: Texit, and calculate the actual residence time Tactual: Tactual = Texit-Tenter; Get the expected dwell time Texpected for the mission and calculate the GPS dwell time deviation ΔT using the expression: ΔT = Tactual - Texpected.

6. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 5 is characterized by: The method for extracting abnormal values of door opening frequency is as follows: each time the cargo door is opened, the sensor records an event: D = {(t1,loc1), (t2,loc2),…, (t m ,loc m )}; Each data contains the door opening timestamp t i , door opening position coordinates loc i , m is the total number of coordinates; the preset tasks include: stop point list S = {s1, s2, ..., s z }; Whether each station requires the door to be opened; Set the expected number of door openings to: Nexpected = z; That is: if there are z delivery points, the expected number of door openings is z times, and count the actual number of door openings: Nactual = len(D); Count the total number of actual door opening events, and the door opening frequency abnormality value ΔN is defined as: ΔN = Nactual - Nexpected.

7. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 6 is characterized by: The method for obtaining the offset distance is as follows: In the task setting, a fence is set for each delivery point, and the coordinates of its center point are: C = (lat c ,lon c ); that is, the center of the electronic fence of the station, which is preset as the most ideal parking position; the parking point coordinates of the vehicle are obtained from the parking recognition module: P = (lat p ,lon p ); calculated using the Earth plane approximation: Where: Δlat = lat p -lat c ; Δlon=lon p -lon c ; D is the offset distance.

8. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 7 is characterized by: Comparing the obtained credibility score of the stopover behavior with a gradient standard threshold, where the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the credibility score of the stopover behavior with the first standard threshold and the second standard threshold respectively; If the credibility score of the stop behavior is greater than the second standard threshold, it is judged as a highly credible delivery behavior; if the credibility score of the stop behavior is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it is judged as a medium credible delivery behavior; if the credibility score of the stop behavior is less than the first standard threshold, it is judged as a low credible delivery behavior.

9. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 8, characterized in that: Compare the preset routes and stop information in the delivery task, and conduct a comprehensive analysis of the comparison results combined with the credibility score to determine whether the vehicle has completed the stop task at the designated delivery point. Specifically: Preset path data R={r1,r2,…,r p }: p is the total number of path data in the sequence; the actual trajectory data P = {(lat1, lon1, t1), (lat2, lon2, t2), ..., (lat n ,lon n ,t n )};The credibility score of each stop Gi∈[0,1]; Perform map matching on the trajectory sequence and correct GPS jump points; Calculate the trajectory similarity between the actual trajectory and the expected path segment: D dtw is the DTW distance between the actual and preset trajectory; Sim i ∈[0,1]: trajectory matching similarity; Simulate the trajectory comparison results i Comprehensively analyze the behavior credibility score Ci to define the final path execution credibility F i :F i =α·Ci+(1-α)·Sim i ;α∈[0.5,0.9].

10. The fresh produce cold chain traceability and early warning system based on Internet of Things technology according to claim 9, characterized in that: The final route execution credibility is compared with a predetermined threshold. If the route execution credibility is greater than or equal to the predetermined threshold, the route execution is considered successful, indicating that the vehicle's behavior at all stops during the entire delivery task complies with the credibility rules set by the system. If the path execution credibility is less than the predetermined threshold, it is judged as path execution abnormality, indicating that the vehicle has obvious abnormal behavior in this delivery task, and an abnormal warning is automatically sent to the dispatching platform.

Images