Iot-based cold chain explicit data acquisition and visualization monitoring system

Abstract

The present application relates to the technical field of monitoring system, especially to a cold chain explicit data acquisition and visual monitoring system based on Internet of Things, the present application identifies transport box information through a data tracking module, continuously acquires the weight value of the whole batch of transport boxes in the whole process of transporting the whole batch of transport boxes from the transport vehicle to the designated place along the preset path, the classification unit divides the whole batch of transport boxes of single transport into categories, the transport box detection module controls the transport unit to transfer the transport boxes classified into the risk batch category to the detection point, and detects each transport box in turn, determines whether the transport box meets the storage condition based on the chroma value and the chroma value difference, the present application divides the whole batch of transport boxes of single transport, improves the subsequent detection and storage operation efficiency of fresh agricultural products in the transport box, and improves the accuracy of cargo state recognition by obtaining the cargo image in the transport box.

Description

Technical Field

[0001] This invention relates to the field of monitoring system technology, and in particular to a cold chain explicit data acquisition and visualization monitoring system based on the Internet of Things. Background Technology

[0002] With the rapid development of fresh food e-commerce and the increasing demand for freshness in the consumer market, cold chain transportation has become a core guarantee for the circulation of perishable goods such as fruits, vegetables, meat, and pharmaceuticals, and its application scenarios continue to expand and its scale continues to increase. However, in the actual cold chain transportation and subsequent warehousing management process, perishable goods are easily affected by multiple factors such as transportation bumps, interlayer compression, poor ventilation, and temperature and humidity fluctuations, which can easily lead to hidden damage and oxidative deterioration. This not only reduces the quality of goods but also causes high storage and transportation losses, hindering the refined development of the cold chain industry. Therefore, research on the status detection and full-process management technology of cold chain transported goods, optimizing management methods, and improving detection accuracy have become important issues that the industry urgently needs to address.

[0003] In the prior art, Chinese Patent Publication No. CN116308061A discloses a cold chain logistics inbound and outbound management system, including a central management module, a cargo data acquisition module, an inbound and outbound management module, a statistical database, a query module, a cargo positioning module, an equipment management module, a data recording module, and a personnel management module. The central management module is connected to the inbound and outbound management module, the cargo positioning module, the equipment management module, and the personnel management module. The inbound and outbound management module is connected to the cargo data acquisition module, the statistical database, and the data recording module. The statistical database is connected to the query module and the cargo positioning module. The system provided by this invention uses RFID technology and a temperature sensor to simultaneously identify refrigerated / frozen goods for inbound and outbound operations. It can continuously and quickly identify and process cargo information, promptly establish real-time and accurate data records for cargo, maximize the effectiveness of cargo storage within the most efficient time, and automate inbound and outbound management.

[0004] However, existing technologies do not perform primary classification of shipping containers based on their weight and weight fluctuations, nor do they identify hidden problems in the images of the goods inside the shipping containers, resulting in high warehousing loss rates and low overall turnover efficiency. Summary of the Invention

[0005] The purpose of this invention is to provide a cold chain explicit data acquisition and visualization monitoring system based on the Internet of Things, which can consider the primary classification of transport boxes based on their weight and weight fluctuation values, and identify hidden problems based on images of goods inside the transport boxes, thereby reducing storage loss rate and improving overall circulation efficiency.

[0006] This invention provides an IoT-based system for the explicit data acquisition and visualization monitoring of the cold chain, comprising: The data tracking module is used to identify information about the shipping containers; The transport container sorting module, connected to the data tracking module, includes a transport unit and a sorting unit. The transport unit is equipped with a weight sensor to continuously collect the weight value of the entire batch of transport boxes during the entire process of transporting the entire batch of transport boxes from the transport vehicle along the preset route to the designated location. The classification unit is used to receive the weight value of the entire batch of transport boxes collected by the weight sensor, calculate the average weight and weight fluctuation value, and classify the entire batch of transport boxes in a single transport into categories, including normal batch category and risk batch category. The transport box detection module, connected to the transport box classification module, is used to control the transport unit to transfer transport boxes classified into risk batch categories to the detection point, and to detect each transport box in sequence, collect several images of the goods inside the transport box, identify the color value of the goods in each image and the difference in color value of the goods, and determine whether the transport box meets the conditions for warehousing based on the color value and the difference in color value.

[0007] Furthermore, the data tracking module includes an RFID reader and an RFID electronic tag. The RFID electronic tag is affixed to the surface of each transport box, and the RFID reader is configured to read the transport box identity information, cargo category information, and origin and batch information stored in the RFID electronic tag.

[0008] Furthermore, the classification unit calculates the average weight and the weight fluctuation value, including, Obtain the weight values ​​of several batches of shipping containers; Calculate the average weight based on several weight values; The weight fluctuation value is calculated using the standard deviation formula.

[0009] Furthermore, the classification unit categorizes the entire batch of transport containers for a single shipment into different types. If the risk conditions are met, the entire batch of transport containers in a single shipment will be classified as a risky batch category. If the risk conditions are not met, the entire batch of transport containers for a single shipment will be classified as a normal batch. The risk condition is that the average weight of the entire batch of transport boxes is less than a preset weight comparison threshold, or the weight fluctuation value of the entire batch of transport boxes is greater than a preset weight fluctuation value comparison threshold.

[0010] Furthermore, the transport container detection module acquires several images of the goods inside the transport container, identifies the chromaticity values ​​of the goods in each image, and the differences in chromaticity values ​​of the goods, including... Capture images of goods in different areas inside the shipping container; Obtain the chromaticity values ​​of the cargo images in each region; Obtain the maximum and minimum chromaticity values ​​of the cargo images in each region, and calculate the chromaticity value difference of the cargo.

[0011] Furthermore, the transport box detection module determines whether the transport box meets the conditions for warehousing based on the chromaticity value and the difference between the chromaticity values. If the goods inside the transport box meet the chromaticity value warehousing conditions, then the transport box is determined to meet the warehousing conditions. If the goods inside the transport box do not meet the chromaticity value warehousing conditions, then the transport box is determined not to meet the warehousing conditions. The chromaticity value entry conditions are that the chromaticity values ​​of the goods images in each region are all within the preset chromaticity value range, and the difference in chromaticity values ​​of the goods is less than the preset chromaticity value difference comparison threshold.

[0012] Furthermore, the transport unit is a counterbalanced forklift, and the weight sensor is integrated inside the fork support beam of the counterbalanced forklift to collect the dynamic weight value of the transport box in real time during the transfer process.

[0013] Furthermore, it also includes an inbound module connected to the transport box detection module, used to extract the integrity of the goods from several images of the goods inside the transport box, and adjust the inbound area of ​​the transport box according to the integrity of the goods. The integrity of the goods is determined by the image analysis unit identifying the fruit stems on the surface of the goods and calculating the ratio of the number of goods with fruit stems to the total number of goods inside the transport box.

[0014] Furthermore, the warehousing module adjusts the warehousing area of ​​the transport box according to the integrity of the goods. If the percentage is greater than the preset integrity percentage comparison threshold, it is determined that the integrity of the goods meets the standard, and the transportation unit is controlled to transfer the transport box to the corresponding storage location for normal storage. If the percentage is less than or equal to the preset integrity percentage comparison threshold, it is determined that the integrity of the goods does not meet the standard, and the transportation unit is controlled to transfer the transport box to the priority outbound area.

[0015] Furthermore, it also includes a visualization module, which is connected to the data tracking module, the transport box classification module, and the transport box detection module to visualize the entire process data of the transport box.

[0016] Compared with existing technologies, this invention identifies transport box information through a data tracking module. Throughout the entire process of transporting a batch of transport boxes from a transport vehicle along a preset path to a designated location, the transport unit continuously collects the weight value of the entire batch. A classification unit categorizes the entire batch of transport boxes for a single transport. A transport box detection module controls the transport unit to transfer transport boxes classified as high-risk batches to the detection point and sequentially detects each transport box. Based on chromaticity values ​​and chromaticity value differences, it determines whether the transport box meets the conditions for warehousing. This invention improves the efficiency of subsequent detection and warehousing operations for fresh agricultural products inside transport boxes by classifying the entire batch of transport boxes for a single transport, and improves the accuracy of cargo status identification by acquiring images of the goods inside the transport boxes.

[0017] In particular, this invention calculates the average weight and weight fluctuation value through classification units to classify the entire batch of transport boxes in a single shipment, achieving multi-dimensional and accurate assessment of the condition of goods inside the transport boxes. On the one hand, weight deviation can directly reflect the degree of weight deviation of the entire batch of transport boxes in a single shipment, quickly identifying weight anomalies caused by juice loss, large-scale detachment of fruit stems, etc., and accurately locating obvious spoilage problems that may exist in the goods. On the other hand, weight fluctuation value can effectively capture scenarios where the weight meets the standard but there are hidden problems with the goods inside the box. For example, some goods may have damaged fruit peels due to collisions, or the cushioning material inside the box may have shifted, causing the goods to shake violently. These situations often do not cause obvious weight deviations, but they will lead to increased weight data fluctuations. By using weight fluctuation value, such hidden damage risks can be accurately identified, making up for the detection blind spots of a single weight indicator and more comprehensively reflecting the actual condition of the goods inside the transport box. At the same time, classifying the entire batch of transport boxes in a single shipment based on the two indicators can achieve hierarchical management of transport boxes, greatly improving the efficiency of subsequent inspection and warehousing operations.

[0018] In particular, this invention uses a transport box detection module to determine whether a transport box meets the conditions for warehousing based on chromaticity values ​​and their differences. Collecting several images of the goods inside the transport box allows for targeted capture of the differentiated states of goods in different layers. After loading, the middle layer is easily compressed by the upper and lower layers, leading to poor ventilation and damage to the fruit pulp. The bottom layer, due to insufficient cushioning from contact with the bottom of the box, is more susceptible to damage from transport collisions. The upper layer is relatively less susceptible to compression but may experience accelerated oxidation due to poor sealing of the box opening. Collecting several images of the goods inside the transport box can accurately locate the damage and spoilage risk points of each layer, avoiding the problem of missing local layers due to overall data collection. Chromaticity values, as a basic characterization indicator, can be used for rapid screening. If obviously spoiled goods are found, and the color value exceeds the preset standard range, it directly indicates that the goods have problems such as fading, mold, or overripeness, enabling rapid screening of unqualified goods. On the other hand, the color value difference can capture scenarios where the color value is qualified but there are hidden problems. For example, if the bottom layer of goods has fruit peel damage and oxidation due to collision, although the overall color value meets the standard, the color value difference between it and the middle and top layers of cherries exceeds the threshold. Or, if some goods in the same layer have uneven color due to compression and poor ventilation, these situations can indirectly reflect problems such as collision, compression, and poor ventilation inside the transport box. This makes up for the shortcomings of a single color value in being unable to identify hidden damage and more comprehensively characterizes the goods inside the box and the transport and storage status.

[0019] In particular, this invention adjusts the storage area of ​​transport boxes according to the integrity of the goods through the warehousing module. By storing goods in different areas, it can accurately match the storage needs and circulation priorities of goods with different freshness. Goods with higher integrity have higher freshness and longer shelf life, and can be stored in regular cold storage locations for planned outbound shipment according to normal inventory cycles. Transport boxes with lower integrity have shorter shelf life and are transferred to the priority outbound area, which can ensure that these transport boxes are prioritized for circulation to the sales end, avoiding spoilage and loss due to excessively long inventory cycles, and reducing the cold chain storage loss rate from the source. Attached Figure Description

[0020] Figure 1 This is a structural diagram of an IoT-based cold chain explicit data acquisition and visualization monitoring system according to an embodiment of the present invention. Figure 2 This is a structural diagram of the transport box classification module according to an embodiment of the present invention; Figure 3 This is a logic diagram for classifying the entire batch of transport containers for a single transport in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0022] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0023] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0024] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0025] like Figures 1-3 As shown, Figure 1 This is a structural diagram of the IoT-based cold chain explicit data acquisition and visualization monitoring system according to an embodiment of the present invention. Figure 2 This is a structural diagram of the transport box classification module according to an embodiment of the present invention. Figure 3 This embodiment of the invention provides a logical decision diagram for classifying the categories of a single shipment of transport containers into categories. It also provides an IoT-based cold chain explicit data acquisition and visualization monitoring system, which includes: The data tracking module is used to identify information about the shipping containers; The transport container sorting module, connected to the data tracking module, includes a transport unit and a sorting unit. The transport unit is equipped with a weight sensor to continuously collect the weight value of the entire batch of transport boxes during the entire process of transporting the entire batch of transport boxes from the transport vehicle along the preset route to the designated location. The classification unit is used to receive the weight value of the entire batch of transport boxes collected by the weight sensor, calculate the average weight and weight fluctuation value, and classify the entire batch of transport boxes in a single transport into categories, including normal batch category and risk batch category. The transport box detection module, connected to the transport box classification module, is used to control the transport unit to transfer transport boxes classified into risk batch categories to the detection point, and to detect each transport box in sequence, collect several images of the goods inside the transport box, identify the color value of the goods in each image and the difference in color value of the goods, and determine whether the transport box meets the conditions for warehousing based on the color value and the difference in color value.

[0026] Specifically, the data tracking module includes an RFID reader and an RFID electronic tag. The RFID electronic tag is affixed to the surface of each transport box, and the RFID reader is configured to read the transport box identity information, cargo category information, and origin and batch information stored in the RFID electronic tag.

[0027] It is understandable that an IoT-based cold chain explicit data collection and visualization monitoring system can be applied to fresh agricultural products; in this embodiment, it is applied to cherries. In this embodiment, the data tracking module uses an RFID reader and waterproof, low-temperature resistant RFID electronic tags. The RFID electronic tags are affixed to the middle of the outer side of each box of fruit. The information stored in the tags includes: a unique ID for the transport box (e.g., "20250316-B001-005", representing box number 5 of batch B on March 16, 2025), the type of goods (e.g., cherries), the place of origin, the packing time, and the preset standard weight per box (2.5kg / box for cherries). The RFID reader is installed above the mast of a counterbalance forklift, with a reading distance set to 1.5m to ensure automatic information reading when the forklift approaches the transport box.

[0028] In this embodiment, the transport unit uses a counterbalanced forklift, and the weight sensor is a strain gauge sensor integrated inside the fork support beam. The measurement accuracy is ±0.02kg, and the sampling frequency is set to 2 times / second, which can collect the dynamic weight value of the transport box during the transfer process in real time.

[0029] Specifically, the classification unit calculates the average weight and the weight fluctuation value, including, Obtain the weight values ​​of several batches of shipping containers; Calculate the average weight based on several weight values; The weight fluctuation value is calculated using the standard deviation formula.

[0030] In this embodiment, the goods inside the transport box are cherries, and the preset standard weight of each transport box is 2.5kg / box.

[0031] Specifically, the classification unit divides the entire batch of transport containers for a single shipment into categories. If the risk conditions are met, the entire batch of transport containers in a single shipment will be classified as a risky batch category. If the risk conditions are not met, the entire batch of transport containers for a single shipment will be classified as a normal batch. The risk condition is that the average weight of the entire batch of transport boxes is less than a preset weight comparison threshold, or the weight fluctuation value of the entire batch of transport boxes is greater than a preset weight fluctuation value comparison threshold.

[0032] In this embodiment, the total number of transport boxes in a single shipment is 10 boxes, the preset weight comparison threshold is 24.25 kg, and the preset weight fluctuation value comparison threshold is 1.8%.

[0033] It is understandable that cherries are small, with very thin skin and delicate flesh. The stems are easily detached, and the fruit is easily damaged by squeezing. During normal transportation, the weight fluctuation caused by slight shaking is usually ≤1.5%. The preset weight fluctuation value comparison threshold is set at 1.8%. If it exceeds 1.8%, there may be damage to the cherries' skin and stems caused by collisions inside the box, or the cushioning material inside the box may have shifted, resulting in excessive porosity, violent shaking of the cherries, and a significant increase in the risk of hidden damage and rot.

[0034] It is understandable that, considering the slight evaporation of moisture and minor detachment of fruit stems during cold chain transportation, the weight deviation is within 3%. If the deviation exceeds 3%, some cherries may be damaged and rotten, resulting in juice loss, and the entire batch should be classified as a high-risk batch.

[0035] Specifically, this invention calculates the average weight and weight fluctuation value through classification units to categorize the entire batch of transport boxes in a single shipment. This enables multi-dimensional and accurate assessment of the condition of goods within the transport boxes. On one hand, weight deviation directly reflects the degree of weight deviation of the entire batch of transport boxes in a single shipment, quickly identifying weight anomalies caused by juice loss, excessive stem shedding, etc., and accurately locating potential obvious spoilage problems. On the other hand, weight fluctuation value can effectively capture scenarios where the weight meets the standard but there are hidden problems with the goods inside the box. For example, some goods may have damaged fruit peels due to collisions, or the cushioning material inside the box may have shifted, causing the goods to shake violently. These situations often do not cause obvious weight deviations, but they can lead to increased weight data fluctuations. By using weight fluctuation value, such hidden damage risks can be accurately identified, making up for the detection blind spots of a single weight indicator and more comprehensively reflecting the actual condition of the goods inside the transport box. At the same time, classifying the entire batch of transport boxes in a single shipment based on these two indicators enables hierarchical management of transport boxes, significantly improving the efficiency of subsequent inspection and warehousing operations.

[0036] Specifically, the transport container detection module acquires several images of the goods inside the transport container, identifies the chromaticity values ​​of the goods in each image, and the differences in chromaticity values, including... Capture images of goods in different areas inside the shipping container; Obtain the chromaticity values ​​of the cargo images in each region; Obtain the maximum and minimum chromaticity values ​​of the cargo images in each region, and calculate the chromaticity value difference of the cargo.

[0037] In this embodiment, the image acquisition unit is an industrial camera.

[0038] In this embodiment, images of the goods inside the transport container are collected in different areas, including images of the upper layer of goods, the middle layer of goods, and the bottom layer of goods.

[0039] In this embodiment, image analysis software is used to obtain the chromaticity values ​​of each cargo image. The image analysis software can be MATLAB.

[0040] In this embodiment, three cargo images are acquired for a single transport container. The maximum and minimum chromaticity values ​​among the three cargo images are selected, and the difference between the maximum and minimum chromaticity values ​​is the chromaticity value difference of the cargo.

[0041] Specifically, the transport box detection module determines whether the transport box meets the conditions for warehousing based on the chromaticity value and the difference between the chromaticity values. If the goods inside the transport box meet the chromaticity value warehousing conditions, then the transport box is determined to meet the warehousing conditions. If the goods inside the transport box do not meet the chromaticity value warehousing conditions, then the transport box is determined not to meet the warehousing conditions. The chromaticity value entry conditions are that the chromaticity values ​​of the goods images in each region are all within the preset chromaticity value range, and the difference in chromaticity values ​​of the goods is less than the preset chromaticity value difference comparison threshold.

[0042] In this embodiment, the preset chromaticity value range is RGB (150-200, 20-50, 20-50), and the preset chromaticity value difference comparison threshold is 12 (the sum of the differences between the three RGB colors).

[0043] It is understandable that there are slight differences in the color values ​​of cherries from different perspectives. The total color difference of fresh cherries should not exceed 8. If the difference exceeds 12, it means that the cherries may have oxidized and turned black after the skin was damaged or have slight mold.

[0044] Specifically, this invention uses a transport box detection module to determine whether a transport box meets the conditions for warehousing based on chromaticity values ​​and their differences. Collecting several images of the goods inside the transport box allows for targeted capture of the differentiated states of goods in different layers. After loading, the middle layer is easily compressed by the upper and lower layers, leading to poor ventilation and damage to the fruit pulp. The bottom layer, due to insufficient cushioning from contact with the bottom of the box, is more susceptible to damage from transport collisions. The upper layer is relatively less susceptible to compression but may experience accelerated oxidation due to poor sealing of the box opening. Collecting several images of the goods inside the transport box can accurately locate the damage and spoilage risk points of each layer, avoiding the problem of missing local layers due to overall data collection. Chromaticity values, as a basic characterization indicator, can quickly screen... The system selects obviously deteriorated goods. If the color value exceeds the preset standard range, it directly indicates that the goods have problems such as fading, mold, or overripeness, enabling rapid screening of unqualified goods. The color value difference can capture scenarios where the color value is qualified but there are hidden problems. For example, if the bottom layer of goods has fruit peel damage and oxidation due to collision, although the overall color value meets the standard, the color value difference between it and the middle and top layers of cherries exceeds the threshold. Or, if some goods in the same layer have uneven color due to compression and poor ventilation, these situations can indirectly reflect problems such as collision, compression, and poor ventilation inside the transport box. This makes up for the shortcomings of a single color value in identifying hidden damage and more comprehensively characterizes the goods inside the box and the transport and storage status.

[0045] Specifically, the transport unit is a counterbalance forklift, and the weight sensor is integrated inside the fork support beam of the counterbalance forklift to collect the dynamic weight value of the transport box in real time during the transfer process.

[0046] Specifically, it also includes an inbound module connected to the transport box detection module, used to extract the integrity of goods from several images of goods inside the transport box, and adjust the inbound area of ​​the transport box according to the integrity of goods. The integrity of goods is determined by the image analysis unit to identify the fruit stems on the surface of the goods and to calculate the ratio of the number of goods with fruit stems to the total number of goods inside the transport box.

[0047] Specifically, the warehousing module adjusts the warehousing area of ​​the transport box according to the integrity of the goods. If the percentage is greater than the preset integrity percentage comparison threshold, it is determined that the integrity of the goods meets the standard, and the transportation unit is controlled to transfer the transport box to the corresponding storage location for normal storage. If the percentage is less than or equal to the preset integrity percentage comparison threshold, it is determined that the integrity of the goods does not meet the standard, and the transportation unit is controlled to transfer the transport box to the priority outbound area.

[0048] In this embodiment, the preset integrity percentage comparison threshold is 90%.

[0049] In this embodiment, the warehouse is divided into a normal area and a priority outbound area. For transport boxes with low integrity, transporting the transport boxes to the priority outbound area can facilitate the priority outbound of the transport boxes and ensure the freshness of the goods inside the transport boxes.

[0050] Specifically, this invention adjusts the storage area of ​​transport boxes based on the integrity of the goods through the warehousing module. By storing goods in different areas, it can accurately match the storage needs and circulation priorities of goods with different freshness levels. Goods with higher integrity levels have higher freshness and longer shelf life, and can be stored in regular cold storage locations for planned outbound shipments according to normal inventory cycles. Transport boxes with lower integrity levels have shorter shelf life and are transferred to the priority outbound area. This ensures that these transport boxes are prioritized for circulation to the sales end, avoiding spoilage and loss due to excessively long inventory cycles, and reducing the cold chain storage loss rate from the source.

[0051] Specifically, it also includes a visualization module, which is connected to the data tracking module, the transport box classification module, and the transport box detection module to visualize the entire process data of the transport box.

[0052] The modules described in the embodiments of this application can be implemented in software or hardware. These modules can also be located within a processor.

[0053] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using dedicated hardware-based apparatus to perform the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0054] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A cold chain visible data acquisition and visualization monitoring system based on the Internet of Things, characterized in that, include: The data tracking module is used to identify information about the shipping containers; The transport container sorting module, connected to the data tracking module, includes a transport unit and a sorting unit. The transport unit is equipped with a weight sensor to continuously collect the weight value of the entire batch of transport boxes during the entire process of transporting the entire batch of transport boxes from the transport vehicle along the preset route to the designated location. The classification unit is used to receive the weight value of the entire batch of transport boxes collected by the weight sensor, calculate the average weight and weight fluctuation value, and classify the entire batch of transport boxes in a single transport into categories, including normal batch category and risk batch category. The transport box detection module, connected to the transport box classification module, is used to control the transport unit to transfer transport boxes classified into risk batch categories to the detection point, and to detect each transport box in sequence, collect several images of the goods inside the transport box, identify the color values ​​of the goods in each image and the color value difference of the goods, and determine whether the transport box meets the conditions for warehousing based on the color values ​​and color value differences.

2. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 1, characterized in that, The data tracking module includes an RFID reader and an RFID electronic tag. The RFID electronic tag is affixed to the surface of each transport box. The RFID reader is configured to read the transport box identity information, cargo category information, and origin and batch information stored in the RFID electronic tag.

3. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 2, characterized in that, The classification unit calculates the average weight and weight fluctuation value, including, Obtain the weight values ​​of several batches of shipping containers; Calculate the average weight based on several weight values; The weight fluctuation value is calculated using the standard deviation formula.

4. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 3, characterized in that, The classification unit categorizes the entire batch of transport containers for a single shipment into different types. If the risk conditions are met, the entire batch of transport containers in a single shipment will be classified as a risky batch category. If the risk conditions are not met, the entire batch of transport containers for a single shipment will be classified as a normal batch. The risk condition is that the average weight of the entire batch of transport boxes is less than a preset weight comparison threshold, or the weight fluctuation value of the entire batch of transport boxes is greater than a preset weight fluctuation value comparison threshold.

5. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 1, characterized in that, The transport container detection module acquires several images of the goods inside the transport container, identifies the chromaticity values ​​of the goods in each image, and the differences in chromaticity values, including... Capture images of goods in different areas inside the shipping container; Obtain the chromaticity values ​​of the cargo images in each region; Obtain the maximum and minimum chromaticity values ​​of the cargo images in each region, and calculate the chromaticity value difference of the cargo.

6. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 5, characterized in that, The transport box detection module determines whether the transport box meets the conditions for warehousing based on the chromaticity value and the difference between the chromaticity values. If the goods inside the transport box meet the chromaticity value warehousing conditions, then the transport box is determined to meet the warehousing conditions. If the goods inside the transport box do not meet the chromaticity value warehousing conditions, then the transport box is determined not to meet the warehousing conditions. The chromaticity value entry conditions are that the chromaticity values ​​of the goods images in each region are all within the preset chromaticity value range, and the difference in chromaticity values ​​of the goods is less than the preset chromaticity value difference comparison threshold.

7. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 1, characterized in that, The transport unit is a counterbalance forklift, and the weight sensor is integrated inside the fork support beam of the counterbalance forklift to collect the dynamic weight value of the transport box in real time during the transfer process.

8. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 1, characterized in that, It also includes an inbound module, which is connected to the transport box detection module, to extract the integrity of the goods from several images of the goods in the transport box, and adjust the inbound area of ​​the transport box according to the integrity of the goods. The integrity of the goods is determined by the image analysis unit to identify the fruit stems on the surface of the goods and to calculate the ratio of the number of goods with fruit stems to the total number of goods in the transport box.

9. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 8, characterized in that, The warehousing module adjusts the warehousing area of ​​the transport box according to the integrity of the goods. If the percentage is greater than the preset integrity percentage comparison threshold, it is determined that the integrity of the goods meets the standard, and the transportation unit is controlled to transfer the transport box to the corresponding storage location for normal storage. If the percentage is less than or equal to the preset integrity percentage comparison threshold, it is determined that the integrity of the goods does not meet the standard, and the transportation unit is controlled to transfer the transport box to the priority outbound area.

10. The IoT-based cold chain explicit data acquisition and visualization monitoring system according to claim 1, characterized in that, It also includes a visualization module, which is connected to the data tracking module, the shipping box classification module, and the shipping box detection module to visualize the data of the entire shipping box process.

Images