Cold-chain logistics monitoring method and device, storage medium and electronic equipment
By acquiring multi-dimensional environmental data in cold chain logistics and processing it into event fragments, a responsibility attribution map is constructed, which solves the problem of traceability difficulties caused by data fragmentation and enables rapid and accurate responsibility positioning and optimization of the claims process.
Patent Information
- Application Number
- CN202511662611.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-13
- Publication Date
- 2026-02-24
AI Technical Summary
In cold chain logistics, data fragmentation makes it difficult to trace the source of problems and to quickly and accurately pinpoint specific links and responsible parties.
By acquiring multi-dimensional environmental data collected by smart sensor tags, fragmented event processing is performed to determine the quality risk of goods, and a responsibility attribution map is constructed based on event feature data. Combined with transportation contract terms, breach of contract events and target responsible parties are identified.
It enables rapid and accurate identification of specific links and responsible parties in cold chain logistics, reducing traceability difficulties, improving claims efficiency, and lowering damage rates and communication costs.
Smart Images
Figure CN121563380A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of cold chain logistics technology, and more specifically, to a cold chain logistics monitoring method, device, storage medium, and electronic equipment. Background Technology
[0002] Cold chain logistics is a systematic project designed to ensure that food, pharmaceuticals, and fresh produce remain in a specified low-temperature environment throughout the entire process from production, storage, transportation, and sales to consumption. By strictly controlling temperature conditions, this system can effectively guarantee product quality and reduce losses caused by temperature fluctuations.
[0003] However, in the actual operation of cold chain logistics, when goods suffer quality degradation or damage due to factors such as abnormal temperature or mechanical vibration, the data generated at each stage is often scattered across different systems. This data fragmentation makes it difficult to trace the source of problems and to quickly and accurately pinpoint the specific stage and responsible party. Summary of the Invention
[0004] In view of this, the present invention discloses a cold chain logistics monitoring method, device, storage medium and electronic equipment to solve the problem that the existing solutions are difficult to trace the source of problems due to data fragmentation, and it is difficult to quickly and accurately locate specific links and responsible parties.
[0005] A cold chain logistics monitoring method, comprising:
[0006] Acquire multidimensional environmental data collected by smart sensor tags installed in the logistics unit to be monitored, and associate the multidimensional environmental data with logistics information;
[0007] The multidimensional environmental data is processed using an event fragmentation method to obtain event feature data corresponding to each event fragment;
[0008] Based on the event characteristic data, determine the current item quality risk score;
[0009] Based on the current item quality risk score, responsibility weights are assigned to the responsibility relationships of each event segment and its associated responsible parties, thus constructing a responsibility attribution map. The responsibility relationships are determined based on event attribution association information.
[0010] Each event segment in the liability attribution map is compared with the corresponding transportation contract terms to identify the breach event segment and the corresponding target responsible party.
[0011] Optionally, the step of processing the multidimensional environmental data using an event fragmentation method to obtain event feature data corresponding to each event fragment includes:
[0012] The multidimensional environmental data is monitored based on multiple predefined event types;
[0013] When the multidimensional environmental data is detected to meet the event start condition corresponding to any event type, the creation of the corresponding event segment begins, and the creation of the event segment ends when the event end condition corresponding to the same event type is met.
[0014] After monitoring of the multidimensional environmental data is completed, a set of event fragments consisting of multiple event fragments is obtained;
[0015] Feature engineering calculations are performed on each event segment in the event segment set to obtain the event feature data corresponding to each event segment.
[0016] Optionally, determining the current item quality risk score based on the event feature data includes:
[0017] Based on the event features contained in each of the event feature data, and combined with the basic risk coefficient, the event risk increment of the corresponding event segment is obtained;
[0018] Calculate the sum of the event risk increments for all newly added event segments of each event type within the time period from the previous moment to the current moment;
[0019] For each event type, the item quality risk score at the previous moment is added to the sum of the event risk increments to obtain the item quality risk score at the current moment.
[0020] Optionally, the process of assigning responsibility weights to each event segment and its associated responsible parties based on the current item quality risk score, thereby constructing a responsibility attribution map, includes:
[0021] Based on event attribution association information, each event segment is associated with the corresponding responsible party to establish a responsibility relationship;
[0022] Under each event type, responsibility weights are assigned to the corresponding responsibility relationships based on the current item quality risk score, thereby constructing the responsibility attribution map.
[0023] Optionally, comparing each event segment in the liability attribution map with the corresponding transportation contract terms to identify the breach event segment and the corresponding target liable party includes:
[0024] Parameterize transportation contract terms and establish a rule engine;
[0025] Each event fragment in the liability attribution graph is compared with each clause and rule in the rule engine to identify the breach event and the corresponding target responsible party.
[0026] Optionally, it also includes:
[0027] Based on the breach of contract event and the target responsible party, a liability determination report containing tamper-proof evidence fingerprints is generated. The liability determination report includes any one or more of the following: liability division, claim recommendations, and evidence list.
[0028] Optionally, it also includes:
[0029] The proposed liability assessment report will be output to the cold chain logistics management system.
[0030] Update the risk score in the credit file of the target responsible entity, and perform corresponding operations based on the magnitude of the risk score.
[0031] Optionally, the step of acquiring multidimensional environmental data collected by smart sensor tags installed in the logistics unit to be monitored, and associating the multidimensional environmental data with logistics information, includes:
[0032] Obtain the tag ID of the smart sensor tag, the logistics information, and the multidimensional environmental data collected by the smart sensor tag;
[0033] The tag ID is bound to the logistics information to associate the multidimensional environmental data with the logistics information.
[0034] A cold chain logistics monitoring device, comprising:
[0035] The acquisition unit is used to acquire multi-dimensional environmental data collected by smart sensor tags set in the logistics unit to be monitored, and to associate the multi-dimensional environmental data with logistics information;
[0036] The fragmentation processing unit is used to process the multidimensional environmental data using an event fragmentation method to obtain event feature data corresponding to each event fragment;
[0037] A quality risk score determination unit is used to determine the quality risk score of an item at the current moment based on the event feature data.
[0038] The graph construction unit is used to assign responsibility weights to each event segment and its associated responsible parties based on the current item quality risk score, thereby constructing a responsibility attribution graph. The responsibility relationship is determined based on event attribution association information.
[0039] The breach of contract identification unit is used to compare each event segment in the liability attribution map with the corresponding transportation contract terms to identify the breach of contract event segment and the corresponding target responsible party.
[0040] A computer storage medium storing at least one instruction, which, when executed by a processor, implements any of the described cold chain logistics monitoring methods.
[0041] An electronic device, comprising: a memory and a processor;
[0042] The memory is used to store at least one instruction;
[0043] The processor is used to execute at least one instruction to implement any of the described cold chain logistics monitoring methods.
[0044] As can be seen from the above technical solution, this invention discloses a cold chain logistics monitoring method, device, storage medium, and electronic equipment. It acquires multi-dimensional environmental data collected by smart sensor tags installed in the logistics unit to be monitored, and associates this multi-dimensional environmental data with logistics information. The multi-dimensional environmental data is processed using an event fragmentation method to obtain event feature data corresponding to each event fragment. Based on the event feature data, the current-time item quality risk score is determined. Based on the magnitude of the current-time item quality risk score, responsibility weights are assigned to the responsibility relationships formed by each event fragment and its associated responsible parties, constructing a responsibility attribution graph. Each event fragment in the responsibility attribution graph is compared with the corresponding transportation contract terms to identify breach of contract event fragments and their corresponding target responsible parties. This invention associates multi-dimensional environmental data of goods at various stages of cold chain logistics with logistics information. By processing the multi-dimensional environmental data into event fragments, each event fragment can be obtained, and the current-time item quality risk score can be determined accordingly. Simultaneously, using event attribution association information, each event fragment is associated with its associated responsible parties to construct a responsibility attribution graph. Then, based on the magnitude of the current-time item quality risk score, responsibility weights are assigned to the corresponding responsibility relationships. This effectively solves the problem of difficulty in tracing the source of problems caused by data fragmentation. By comparing the responsibility attribution map with the terms of the transportation contract, it is possible to quickly and accurately locate the specific links and the target responsible parties. Attached Figure Description
[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the published drawings without creative effort.
[0046] Figure 1 This is a flowchart of a cold chain logistics monitoring method disclosed in an embodiment of the present invention;
[0047] Figure 2 This is a schematic diagram of the structure of a cold chain logistics monitoring device disclosed in an embodiment of the present invention;
[0048] Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. Detailed Implementation
[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0050] This invention discloses a cold chain logistics monitoring method, device, storage medium, and electronic equipment. It correlates multi-dimensional environmental data of goods at various stages of cold chain logistics with logistics information. By processing the multi-dimensional environmental data into event fragments, individual event fragments can be obtained, and the quality risk score of the goods at the current moment can be determined accordingly. Simultaneously, using event attribution association information, each event fragment is associated with its corresponding responsible party, constructing a responsibility attribution graph. Then, based on the current quality risk score of the goods, responsibility weights are assigned to the corresponding responsibility relationships. This effectively solves the problem of difficulty in tracing the source of problems caused by data fragmentation. By comparing the responsibility attribution graph with the transportation contract terms, specific stages and target responsible parties can be quickly and accurately located.
[0051] See Figure 1 The present invention discloses a flowchart of a cold chain logistics monitoring method, which is applied in the cloud and includes the following steps:
[0052] Step S101: Obtain multi-dimensional environmental data collected by the smart sensor tags set in the logistics unit to be monitored, and associate the multi-dimensional environmental data with logistics information.
[0053] In this embodiment, the logistics unit to be monitored refers to a container used to place goods such as food, medicine, and fresh produce in cold chain logistics, such as a pallet or insulated box.
[0054] In practical applications, one or more smart sensor tags are set on the logistics unit to be monitored. Each smart sensor tag integrates at least a temperature sensor, a vibration sensor, and a door opening / closing sensor (such as a Hall sensor or a light sensor). Therefore, it can collect multi-dimensional environmental data such as temperature, vibration, and door opening / closing of the logistics unit to be monitored.
[0055] The smart sensor tag adopts a hierarchical power consumption management strategy. The vibration sensor and Hall sensor are normally in a low-power sleep state and work by combining "duty cycle wake-up" (short periodic wake-up for regular sampling) and "event-triggered wake-up" (immediate wake-up and increased sampling frequency when a violent vibration or door opening signal is detected).
[0056] The smart sensor tag has a built-in microcontroller unit (MCU). When the low-power monitoring circuit in the vibration sensor detects vibration, and / or the low-power monitoring circuit in the Hall sensor detects a change in the magnetic field, the MCU and precision measurement circuit are woken up by a hardware interrupt signal. The MCU adjusts the sampling frequency and accuracy of each sensor according to the event type. After the vibration sensor and Hall sensor have collected data and transmitted it to the MCU, they return to sleep mode.
[0057] In practical applications, the built-in main control MCU of the smart sensor tag can perform preliminary processing on the raw data collected by the integrated sensors, such as jitter removal and sliding window mean calculation, to shield noise and reduce data volume. In this embodiment, the multidimensional environmental data collected by the smart sensor tag and obtained from the cloud is the multidimensional environmental data obtained after the smart sensor tag has performed preliminary processing on the raw multidimensional environmental data collected.
[0058] In this embodiment, the logistics information can be a waybill number, goods batch number, pallet ID, etc.
[0059] By linking multidimensional environmental data with logistics information, the environmental conditions of goods during transportation and warehousing can be monitored in real time, and corresponding adjustments can be made according to the characteristics of the goods. For example, for medicines that require refrigeration, temperature sensors monitor temperature changes during transportation in real time. Once the temperature exceeds the specified range, the system will immediately issue an alarm and take measures to ensure the quality of the medicines.
[0060] Step S102: Process the multidimensional environmental data using the event fragmentation method to obtain event feature data corresponding to each event fragment.
[0061] Event fragmentation refers to the cloud-based analysis of multidimensional environmental data uploaded by smart sensor tags. When the initiation conditions for a specific event type are met, event fragment creation begins, and the event fragment creation ends when the termination conditions for that event type are met, thus obtaining the event fragment corresponding to that event type. After the event fragment is generated, the cloud uses feature engineering (e.g., overheating amplitude, duration, vibration energy, etc.) to calculate a series of quantitative characteristics of the event fragment, obtaining event feature data for subsequent impact assessment.
[0062] Step S103: Based on the event feature data, determine the quality risk score of the item at the current moment.
[0063] In this embodiment, the item quality risk score is used to assess the quality status of goods in transit based on quantitative characteristics.
[0064] Step S104: Based on the current item quality risk score, assign responsibility weights to the responsibility relationships of each event segment and its associated responsible parties, and construct a responsibility attribution map.
[0065] In practical applications, various event fragments and their associated responsible parties can be linked based on event attribution association information to form a responsibility relationship.
[0066] Since the item quality risk score is determined based on the event feature data corresponding to the event segment, there is a corresponding relationship between the item quality risk score and the event segment. Based on this, the corresponding responsibility relationship consisting of the event segment and its associated responsible parties can be determined according to the item quality risk score at the current moment, and the responsibility weight can be assigned to the responsibility relationship according to the size of the item quality risk score at the current moment.
[0067] The higher the current quality risk score of the goods, the higher the risk of changes in the quality status of the goods in transit. In this case, a higher responsibility weight is assigned to the corresponding responsibility relationship. Conversely, the lower the current quality risk score of the goods, the lower the risk of changes in the quality status of the goods in transit. In this case, a lower responsibility weight is assigned to the corresponding responsibility relationship. This can form a network of responsibility attribution map with logistics information as the core, linking multiple event segments, and each event segment pointing to one or more responsible entities (and responsibility weights).
[0068] Step S105: Compare each event segment in the liability attribution map with the corresponding transportation contract terms to identify the breach event segment and the corresponding target responsible party.
[0069] The transportation contract terms record the transportation requirements, including: the temperature control range during transportation, the maximum allowed duration of a single door opening, the total allowed frequency of door openings per day, and the power outage tolerance time.
[0070] By comparing each event segment in the liability attribution map with the corresponding transportation contract terms—that is, by traversing all event segments associated with logistics information and comparing the event segments with the transportation contract terms—the breach event segments and their corresponding target responsible parties can be identified.
[0071] In summary, this invention discloses a cold chain logistics monitoring method. It acquires multi-dimensional environmental data collected by smart sensor tags installed in the logistics unit to be monitored, associates this multi-dimensional environmental data with logistics information, processes the multi-dimensional environmental data using an event fragmentation method to obtain event feature data corresponding to each event fragment, determines the current-time goods quality risk score based on the event feature data, assigns responsibility weights to each event fragment and its associated responsible parties based on the magnitude of the current-time goods quality risk score, constructs a responsibility attribution graph, and compares each event fragment in the responsibility attribution graph with the corresponding transportation contract terms to identify breach of contract event fragments and their corresponding target responsible parties. This invention associates multi-dimensional environmental data of goods at each stage of cold chain logistics with logistics information. By processing the multi-dimensional environmental data into event fragments, it can acquire each event fragment and determine the current-time goods quality risk score accordingly. Simultaneously, by utilizing event attribution association information, it associates each event fragment with its associated responsible parties to construct a responsibility attribution graph, and then assigns responsibility weights to the corresponding responsibility relationships based on the current-time goods quality risk score. This effectively solves the problem of difficulty in tracing the source of problems caused by data fragmentation. By comparing the liability attribution map with the terms of the transportation contract, it is possible to quickly and accurately locate specific links and target responsible parties.
[0072] In one embodiment, step S101 may specifically include:
[0073] (1) Obtain the tag ID, logistics information and multi-dimensional environmental data collected by the smart sensor tag.
[0074] (2) Bind the tag ID to the logistics information to associate the multidimensional environmental data with the logistics information.
[0075] In practical applications, the tag ID and logistics information of the smart sensor tag can be obtained by scanning the device, and then the tag ID and logistics information can be uploaded to the cloud. Among them, the tag ID is the unique identifier of the smart sensor tag.
[0076] After obtaining the tag ID and logistics information of the smart sensor tag uploaded by the scanning device, as well as the multi-dimensional environmental data collected by the smart sensor tag, the cloud can associate the multi-dimensional environmental data with the logistics information by binding the tag ID with the logistics information.
[0077] In one embodiment, step S102 may specifically include:
[0078] (1) Monitor multidimensional environmental data based on multiple predefined event types.
[0079] This application predefines a series of event types that have a potential impact on the quality of goods (i.e., cargo), such as:
[0080] Over-temperature event: The temperature exceeds the threshold range agreed upon in the contract.
[0081] Severe vibration event: The vibration intensity exceeds the preset threshold.
[0082] Abnormal door opening events: Door opening behavior in non-designated locations or exceeding the allowed duration / frequency.
[0083] Long-term stationary event: The vehicle remains stationary for an extended period of time in a non-transfer station area.
[0084] Power outage event: Power outage due to sensor tag or cold operation.
[0085] (2) When the multidimensional environmental data is detected to meet the event start conditions corresponding to any event type, the corresponding event segment is created, and the event segment creation is terminated when the event end conditions corresponding to the same event type are met.
[0086] Taking an over-temperature event fragment as an example, the process of creating an over-temperature event fragment is as follows:
[0087] Starting conditions: The temperature is sampled N times (e.g., 3 times) and the values are higher or lower than the upper / lower limit of the allowable temperature range.
[0088] Termination condition: The temperature sample values recover to the allowable temperature range after M consecutive samplings (e.g., 5 times).
[0089] Recorded event segments: An over-temperature event segment must include at least: segment ID, associated waybill number, event type (over-temperature), start time, end time, over-temperature peak value, over-temperature average value, and responsible party (initially empty).
[0090] (3) After monitoring the multidimensional environmental data, an event fragment set consisting of multiple event fragments is obtained.
[0091] (4) Perform feature engineering calculations on each event segment in the event segment set to obtain the event feature data corresponding to each event segment.
[0092] Feature engineering refers to the process of calculating a series of quantitative features of an event fragment after it has been generated, for use in subsequent impact assessments.
[0093] The following is an example of event feature data obtained through feature engineering:
[0094] Over-temperature range: The average or maximum difference between the actual temperature and the threshold temperature during the over-temperature period.
[0095] Overheating duration: The duration of the event.
[0096] Overheat area: The integral of the portion of the temperature-time curve outside the threshold during the overheating period, which is proportional to the cumulative risk effect of cargo exposure to abnormal temperatures.
[0097] Temperature recovery rate: The speed at which the temperature recovers to the normal range after an overheating event, reflecting the performance of the refrigeration equipment or the effectiveness of environmental intervention.
[0098] Vibration energy: The integral of the acceleration value during a vibration event reflects the severity of the turbulence.
[0099] Door opening frequency and duration per opening: The total number of times the door is opened and the average / longest duration per opening within a specific time window (e.g., 24 hours).
[0100] In one embodiment, step S103 may specifically include:
[0101] (1) Based on each event feature contained in each event feature data and combined with the basic risk coefficient, the event risk increment of the corresponding event segment is obtained.
[0102] The event risk increment is a function determined by the event feature vector, and its logic is as follows:
[0103] Event risk increment = base risk coefficient × f(characteristic 1, characteristic 2, ...);
[0104] Where f(feature1, feature2, ...) represents the individual event features contained in the event feature data.
[0105] For example, for a segment of an overheating event, the event feature data can include event features such as "overheated area" and "cargo thermal sensitivity coefficient." The cargo thermal sensitivity coefficient is a sensitivity parameter set according to cargo type (e.g., ice cream > vaccines > frozen meat), used to amplify or reduce the impact of the same event on different cargoes. The base risk coefficient is a global coefficient set according to event type, reflecting the baseline hazard weight of different event types (overheating, vibration, power outage, etc.) at the same intensity, and does not change with cargo type.
[0106] (2) Calculate the sum of the event risk increments of all newly added event segments for each event type within the time period from the previous moment to the current moment.
[0107] (3) For each event type, the item quality risk score at the previous moment is added to the sum of the event risk increments to obtain the item quality risk score at the current moment.
[0108] In this application, each waybill is assigned a base score upon shipment. During transit, for each event segment that occurs, a certain number of points are added based on the severity of the event.
[0109] The expression for the current item quality risk score is as follows:
[0110] Current item quality risk score = Previous item quality risk score + Σ(Event risk increment);
[0111] In the formula, Σ(event risk increment) represents the sum of the event risk increments of all newly added event segments of a certain event type within the time period from the previous moment to the current moment.
[0112] In one embodiment, step S104 may specifically include:
[0113] (1) Based on the event attribution association information, each event fragment is associated with the corresponding responsible party to establish a responsibility relationship.
[0114] Event attribution association information can be:
[0115] Spatiotemporal matching: Matching the time and location of an event segment with the planned routes and handover records of logistics information. Locations can be determined using GPS (Global Positioning System) or cell towers. For example, if a temperature exceedance event occurs and GPS indicates the vehicle is en route to carrier A, the event is initially attributed to carrier A.
[0116] Operational Association: Door opening and closing events are usually related to manual operation. If, during an abnormal door opening event, the system records an electronic signature action of "confirming unloading" by the driver, then that event segment is attributed to that driver.
[0117] Equipment fingerprinting: If the system can obtain the operating data of the chiller (such as compressor start-up and shutdown, defrosting cycle), it can associate the abnormal temperature with the equipment's own operating status and distinguish whether it is due to external causes or equipment failure.
[0118] (2) Under each event type, the responsibility weight is assigned to the corresponding responsibility relationship according to the size of the quality risk score of the item at the current moment, and the responsibility attribution map is constructed.
[0119] The higher the current quality risk score of the goods, the higher the risk of changes in the quality status of the goods in transit. In this case, a higher responsibility weight is assigned to the corresponding responsibility relationship. Conversely, the lower the current quality risk score of the goods, the lower the risk of changes in the quality status of the goods in transit. In this case, a lower responsibility weight is assigned to the corresponding responsibility relationship. This can form a network of responsibility attribution map with logistics information as the core, linking multiple event segments, and each event segment pointing to one or more responsible entities (and responsibility weights).
[0120] In one embodiment, step S105 may specifically include:
[0121] (1) Parameterize the terms of the transportation contract and establish a rule engine;
[0122] Parameterizing transportation contract terms refers to transforming key terms in a transportation service contract into configurable parameters, such as:
[0123] Temperature control range for transportation: [2.0, 8.0] (unit: degrees Celsius).
[0124] Maximum allowed duration for a single door opening: 10 minutes.
[0125] Total number of times the door is allowed to be opened per day: 5 (unit: times).
[0126] Total number of times the door is allowed to be opened per day: 30 (unit: minutes).
[0127] The rules engine includes: transport temperature control range, maximum allowed duration of a single door opening, total allowed number of door openings per day, and total allowed number of door openings per day.
[0128] (2) Compare each event fragment in the liability attribution map with each clause rule in the rule engine to identify the breach of contract event and the corresponding target responsible party.
[0129] When goods are delivered and their status changes to "received", the cloud automatically triggers the liability assessment process. This process traverses each event segment in the liability attribution graph and compares each event segment with each clause and rule in the rule engine. Event segments that do not meet the clause and rule requirements are identified as breach of contract events, and the responsible party corresponding to the breach of contract event is identified as the target responsible party.
[0130] In one embodiment, after step S105, the cold chain logistics monitoring method may further include:
[0131] Based on the default event and the target responsible party, a judgment recommendation report containing tamper-proof evidence fingerprints is generated.
[0132] The liability assessment recommendation report includes any one or more of the following: liability allocation, claim recommendations, and evidence list.
[0133] For example, when the "overheating duration" of an event segment is 45 minutes, exceeding the contractually agreed "power outage tolerance time" of 30 minutes, the breach of contract event is identified as an overheating event segment.
[0134] When the "single duration" of an event segment is 15 minutes, exceeding the "maximum allowed single door opening time" of 10 minutes stipulated in the contract, the breach event is identified as an abnormal door opening event segment.
[0135] For each event that violates the contract terms, the system will mark it as a "breach event" and reference the relevant contract term number.
[0136] After the determination of liability is completed, the cloud automatically generates a determination of liability recommendation report, which is also known as the product quality traceability and claim recommendation report. The report may include any one or more of the following: liability division, claim recommendations, and evidence list.
[0137] Division of Responsibility: Based on the responsibility attribution map, the proportion of responsibility of each responsible party for the risk of product quality is indicated.
[0138] Evidence list: contains feature data, timestamps, and geographic location information of all event fragments, and performs hash calculations on the evidence list to generate a unique, tamper-proof "evidence fingerprint".
[0139] The liability assessment report may also include: the final product quality risk score, the risk score increase, a detailed list of all event segments, a list of breach of contract events and corresponding breach of contract clauses, etc.
[0140] In summary, this invention, by constructing a computable "event-impact-attribution" chain, shortens the manual investigation process, which previously required days or even weeks, to a second-level liability assessment report automatically generated by the system upon delivery of goods. Because it integrates multi-source information and performs logical attribution, its judgment results are more objective and accurate than relying solely on temperature curves. By automatically generating liability assessment reports containing tamper-proof evidence fingerprints, it provides both suppliers and buyers with a clear and credible basis for liability assessment, significantly reducing disputes and conflicts, accelerating the claims process, and lowering communication costs and legal risks for enterprises.
[0141] In one embodiment, the cold chain logistics monitoring method may further include:
[0142] Output the liability assessment recommendation report to the cold chain logistics management system;
[0143] Update the risk score in the credit file of the target responsible entity and perform corresponding operations based on the risk score.
[0144] In practical applications, the judgment recommendation report can be output to the cold chain logistics management system (such as the supplier management system or financial system) through API (Application Programming Interface) as the basis for paying freight and calculating KPI (Key Performance Indicator) performance.
[0145] When the risk score in the credit file of the target responsible entity is too high, a blacklist or demotion mechanism can be implemented, and an optimized supplier management strategy can be output.
[0146] The blacklist / demotion mechanism works as follows: The cloud establishes a long-term "quality credit file" for each cooperating carrier, driver, and vehicle, continuously accumulating their historical risk scores. For entities that frequently cause serious incidents, the system will automatically add them to the "watch list" or "blacklist," reducing their weight or directly blocking them when allocating waybills in the future.
[0147] In summary, the product quality risk score and credit profile in this invention provide shippers with a long-term, dynamic, and quantifiable carrier evaluation tool. This enables companies to make data-driven decisions, prioritizing high-quality service partners and eliminating substandard transportation capacity, thereby systematically improving the quality assurance capabilities of the entire supply chain.
[0148] This invention enables rapid response to abnormal events and precise identification of the responsible party. This feature effectively deters violations and encourages greater accountability among personnel at all stages of logistics, thereby directly reducing damage rates. Furthermore, improved claims efficiency accelerates cash flow. In the long run, implementing a merit-based supplier management mechanism can reduce overall logistics costs (including damage costs).
[0149] The system employs a modular design, encompassing modules for data acquisition, event fragmentation, attribution, and contract mapping. This design facilitates system expansion, enabling future integration with more types of sensors (such as light, humidity, and gas concentration sensors) or the adoption of more complex attribution logic. Furthermore, boundary condition handling during technical logic verification ensures the system's stability and reliability in complex real-world scenarios.
[0150] Corresponding to the above method embodiments, the present invention also discloses a cold chain logistics monitoring device.
[0151] See Figure 2 The present invention discloses a schematic diagram of a cold chain logistics monitoring device, which is applied in the cloud and may include:
[0152] The acquisition unit 201 is used to acquire multi-dimensional environmental data collected by smart sensor tags set in the logistics unit to be monitored, and to associate the multi-dimensional environmental data with logistics information;
[0153] In this embodiment, the logistics unit to be monitored refers to a container used to place goods such as food, medicine, and fresh produce in cold chain logistics, such as a pallet or insulated box.
[0154] In practical applications, one or more smart sensor tags are set on the logistics unit to be monitored. Each smart sensor tag integrates at least a temperature sensor, a vibration sensor, and a door opening / closing sensor (such as a Hall sensor or a light sensor). Therefore, it can collect multi-dimensional environmental data such as temperature, vibration, and door opening / closing of the logistics unit to be monitored.
[0155] The smart sensor tag adopts a hierarchical power consumption management strategy. The vibration sensor and Hall sensor are normally in a low-power sleep state and work by combining "duty cycle wake-up" (short periodic wake-up for regular sampling) and "event-triggered wake-up" (immediate wake-up and increased sampling frequency when a violent vibration or door opening signal is detected).
[0156] The smart sensor tag has a built-in microcontroller unit (MCU). When the low-power monitoring circuit in the vibration sensor detects vibration, and / or the low-power monitoring circuit in the Hall sensor detects a change in the magnetic field, the MCU and precision measurement circuit are woken up by a hardware interrupt signal. The MCU adjusts the sampling frequency and accuracy of each sensor according to the event type. After the vibration sensor and Hall sensor have collected data and transmitted it to the MCU, they return to sleep mode.
[0157] In practical applications, the built-in main control MCU of the smart sensor tag can perform preliminary processing on the raw data collected by the integrated sensors, such as jitter removal and sliding window mean calculation, to shield noise and reduce data volume. In this embodiment, the multidimensional environmental data collected by the smart sensor tag and obtained from the cloud is the multidimensional environmental data obtained after the smart sensor tag has performed preliminary processing on the raw multidimensional environmental data collected.
[0158] In this embodiment, the logistics information can be a waybill number, goods batch number, pallet ID, etc.
[0159] By linking multidimensional environmental data with logistics information, the environmental conditions of goods during transportation and warehousing can be monitored in real time, and corresponding adjustments can be made according to the characteristics of the goods. For example, for medicines that require refrigeration, temperature sensors monitor temperature changes during transportation in real time. Once the temperature exceeds the specified range, the system will immediately issue an alarm and take measures to ensure the quality of the medicines.
[0160] The fragmentation processing unit 202 is used to process the multidimensional environmental data using an event fragmentation method to obtain event feature data corresponding to each event fragment;
[0161] Event fragmentation refers to the cloud-based analysis of multidimensional environmental data uploaded by smart sensor tags. When the initiation conditions for a specific event type are met, event fragment creation begins, and the event fragment creation ends when the termination conditions for that event type are met, thus obtaining the event fragment corresponding to that event type. After the event fragment is generated, the cloud uses feature engineering (e.g., overheating amplitude, duration, vibration energy, etc.) to calculate a series of quantitative characteristics of the event fragment, obtaining event feature data for subsequent impact assessment.
[0162] The quality risk score determination unit 203 is used to determine the quality risk score of the item at the current moment based on the event feature data.
[0163] In this embodiment, the item quality risk score is used to assess the quality status of goods in transit based on quantitative characteristics.
[0164] The graph construction unit 204 is used to assign responsibility weights to the responsibility relationships of each event segment and its associated responsible parties based on the magnitude of the item quality risk score at the current moment, and construct a responsibility attribution graph, wherein the responsibility relationships are determined based on event attribution association information.
[0165] In practical applications, various event fragments and their associated responsible parties can be linked based on event attribution association information to form a responsibility relationship.
[0166] Since the item quality risk score is determined based on the event feature data corresponding to the event segment, there is a corresponding relationship between the item quality risk score and the event segment. Based on this, the corresponding responsibility relationship consisting of the event segment and its associated responsible parties can be determined according to the item quality risk score at the current moment, and the responsibility weight can be assigned to the responsibility relationship according to the size of the item quality risk score at the current moment.
[0167] The higher the current quality risk score of the goods, the higher the risk of changes in the quality status of the goods in transit. In this case, a higher responsibility weight is assigned to the corresponding responsibility relationship. Conversely, the lower the current quality risk score of the goods, the lower the risk of changes in the quality status of the goods in transit. In this case, a lower responsibility weight is assigned to the corresponding responsibility relationship. This can form a network of responsibility attribution map with logistics information as the core, linking multiple event segments, and each event segment pointing to one or more responsible entities (and responsibility weights).
[0168] The breach of contract identification unit 205 is used to compare each event segment in the liability attribution map with the corresponding transportation contract terms to identify the breach of contract event segment and the corresponding target responsible party.
[0169] The transportation contract terms record the transportation requirements, including: the temperature control range during transportation, the maximum allowed duration of a single door opening, the total allowed frequency of door openings per day, and the power outage tolerance time.
[0170] By comparing each event segment in the liability attribution map with the corresponding transportation contract terms—that is, by traversing all event segments associated with logistics information and comparing the event segments with the transportation contract terms—the breach event segments and their corresponding target responsible parties can be identified.
[0171] In summary, this invention discloses a cold chain logistics monitoring device that acquires multi-dimensional environmental data collected by smart sensor tags installed in the logistics unit to be monitored, and associates this multi-dimensional environmental data with logistics information. The multi-dimensional environmental data is processed using an event fragmentation method to obtain event feature data corresponding to each event fragment. Based on the event feature data, the current-time item quality risk score is determined. Based on the magnitude of the current-time item quality risk score, responsibility weights are assigned to the responsibility relationships formed by each event fragment and its associated responsible parties, constructing a responsibility attribution graph. Each event fragment in the responsibility attribution graph is compared with the corresponding transportation contract terms to identify breach of contract event fragments and their corresponding target responsible parties. This invention associates multi-dimensional environmental data of goods at each stage of cold chain logistics with logistics information. By processing the multi-dimensional environmental data into event fragments, each event fragment can be obtained, and the current-time item quality risk score can be determined accordingly. Simultaneously, using event attribution association information, each event fragment is associated with its associated responsible parties, constructing a responsibility attribution graph. Then, based on the magnitude of the current-time item quality risk score, responsibility weights are assigned to the corresponding responsibility relationships. This effectively solves the problem of difficulty in tracing the source of problems caused by data fragmentation. By comparing the liability attribution map with the terms of the transportation contract, it is possible to quickly and accurately locate specific links and target responsible parties.
[0172] In one embodiment, the acquisition unit 201 is specifically used for:
[0173] Obtain the tag ID of the smart sensor tag, the logistics information, and the multidimensional environmental data collected by the smart sensor tag;
[0174] The tag ID is bound to the logistics information to associate the multidimensional environmental data with the logistics information.
[0175] In one embodiment, the fragmentation processing unit 202 can specifically be used for:
[0176] The multidimensional environmental data is monitored based on multiple predefined event types;
[0177] When the multidimensional environmental data is detected to meet the event start condition corresponding to any event type, the creation of the corresponding event segment begins, and the creation of the event segment ends when the event end condition corresponding to the same event type is met.
[0178] After monitoring of the multidimensional environmental data is completed, a set of event fragments consisting of multiple event fragments is obtained;
[0179] Feature engineering calculations are performed on each event segment in the event segment set to obtain the event feature data corresponding to each event segment.
[0180] In one embodiment, the quality risk assessment unit 203 can be specifically used for:
[0181] Based on the event features contained in each of the event feature data, and combined with the basic risk coefficient, the event risk increment of the corresponding event segment is obtained;
[0182] Calculate the sum of the event risk increments for all newly added event segments of each event type within the time period from the previous moment to the current moment;
[0183] For each event type, the item quality risk score at the previous moment is added to the sum of the event risk increments to obtain the item quality risk score at the current moment.
[0184] In one embodiment, the map construction unit 204 can be specifically used for:
[0185] Based on event attribution association information, each event segment is associated with the corresponding responsible party to establish a responsibility relationship;
[0186] Under each event type, responsibility weights are assigned to the corresponding responsibility relationships based on the current item quality risk score, thereby constructing the responsibility attribution map.
[0187] In one embodiment, the default identification unit 205 can be specifically used for:
[0188] Parameterize transportation contract terms and establish a rule engine;
[0189] Each event fragment in the liability attribution graph is compared with each clause and rule in the rule engine to identify the breach event and the corresponding target responsible party.
[0190] In one embodiment, the cold chain logistics monitoring device may further include:
[0191] The report generation unit is used to generate a judgment recommendation report containing tamper-proof evidence fingerprints based on the default event and the target responsible party. The judgment recommendation report includes any one or more of the following: liability division, claim recommendations, and evidence list.
[0192] In one embodiment, the cold chain logistics monitoring device may further include:
[0193] The report output unit is used to output the judgment recommendation report to the cold chain logistics management system.
[0194] The update unit is used to update the risk score in the credit file of the target responsible entity and perform corresponding operations according to the magnitude of the risk score.
[0195] Corresponding to the above embodiments, the present invention also discloses a computer storage medium that stores at least one instruction, which, when executed by a processor, implements the steps shown in the embodiments of the cold chain logistics monitoring method.
[0196] Computer storage media can be tangible media that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device. Computer storage media can be machine-readable signal media or machine-readable storage media. Computer storage media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0197] Corresponding to the above embodiments, such as Figure 3 As shown, the present invention also provides a schematic diagram of the structure of an electronic device, which may include: a processor 1 and a memory 2;
[0198] The processor 1 and memory 2 communicate with each other via communication bus 3.
[0199] Processor 1, for executing at least one instruction;
[0200] Memory 2 is used to store at least one instruction;
[0201] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.
[0202] Memory 2 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.
[0203] The processor executes at least one instruction to implement the steps shown in the embodiment of the cold chain logistics monitoring method.
[0204] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0205] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.
[0206] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A cold chain logistics monitoring method, characterized in that, include: Acquire multidimensional environmental data collected by smart sensor tags installed in the logistics unit to be monitored, and associate the multidimensional environmental data with logistics information; The multidimensional environmental data is processed using an event fragmentation method to obtain event feature data corresponding to each event fragment; Based on the event characteristic data, determine the current item quality risk score; Based on the current item quality risk score, responsibility weights are assigned to the responsibility relationships of each event segment and its associated responsible parties, thus constructing a responsibility attribution map. The responsibility relationships are determined based on event attribution association information. Each event segment in the liability attribution map is compared with the corresponding transportation contract terms to identify the breach event segment and the corresponding target responsible party.
2. The cold chain logistics monitoring method according to claim 1, characterized in that, The multidimensional environmental data is processed using an event fragmentation method to obtain event feature data corresponding to each event fragment, including: The multidimensional environmental data is monitored based on multiple predefined event types; When the multidimensional environmental data is detected to meet the event start condition corresponding to any event type, the creation of the corresponding event segment begins, and the creation of the event segment ends when the event end condition corresponding to the same event type is met. After monitoring of the multidimensional environmental data is completed, a set of event fragments consisting of multiple event fragments is obtained; Feature engineering calculations are performed on each event segment in the event segment set to obtain the event feature data corresponding to each event segment.
3. The cold chain logistics monitoring method according to claim 1, characterized in that, The process of determining the current item quality risk score based on the event feature data includes: Based on the event features contained in each of the event feature data, and combined with the basic risk coefficient, the event risk increment of the corresponding event segment is obtained; Calculate the sum of the event risk increments for all newly added event segments of each event type within the time period from the previous moment to the current moment; For each event type, the item quality risk score at the previous moment is added to the sum of the event risk increments to obtain the item quality risk score at the current moment.
4. The cold chain logistics monitoring method according to claim 1 or 3, characterized in that, Based on the current item quality risk score, responsibility weights are assigned to each event segment and its associated responsible parties to construct a responsibility attribution graph, including: Based on event attribution association information, each event segment is associated with the corresponding responsible party to establish a responsibility relationship; Under each event type, responsibility weights are assigned to the corresponding responsibility relationships based on the current item quality risk score, thereby constructing the responsibility attribution map.
5. The cold chain logistics monitoring method according to any one of claims 1 to 3, characterized in that, The step of comparing each event segment in the liability attribution map with the corresponding transportation contract terms to identify the breach event segment and the corresponding target liable party includes: Parameterize transportation contract terms and establish a rule engine; Each event fragment in the liability attribution graph is compared with each clause and rule in the rule engine to identify the breach event and the corresponding target responsible party.
6. The cold chain logistics monitoring method according to claim 1, characterized in that, Also includes: Based on the default event and the target responsible party, a liability determination report containing tamper-proof evidence fingerprints is generated. The liability determination report includes any one or more of the following: liability division, claim recommendations, and evidence list.
7. The cold chain logistics monitoring method according to claim 6, characterized in that, Also includes: The proposed liability assessment report will be output to the cold chain logistics management system. Update the risk score in the credit file of the target responsible entity, and perform corresponding operations based on the magnitude of the risk score.
8. The cold chain logistics monitoring method according to any one of claims 1 to 3, characterized in that, The process of acquiring multidimensional environmental data collected by smart sensor tags installed in the logistics unit to be monitored, and associating the multidimensional environmental data with logistics information, includes: Obtain the tag ID of the smart sensor tag, the logistics information, and the multidimensional environmental data collected by the smart sensor tag; The tag ID is bound to the logistics information to associate the multidimensional environmental data with the logistics information.
9. A cold chain logistics monitoring device, characterized in that, include: The acquisition unit is used to acquire multi-dimensional environmental data collected by smart sensor tags set in the logistics unit to be monitored, and to associate the multi-dimensional environmental data with logistics information; The fragmentation processing unit is used to process the multidimensional environmental data using an event fragmentation method to obtain event feature data corresponding to each event fragment; A quality risk score determination unit is used to determine the quality risk score of an item at the current moment based on the event feature data. The graph construction unit is used to assign responsibility weights to the responsibility relationships of each event segment and its associated responsible parties based on the magnitude of the item quality risk score at the current moment, thereby constructing a responsibility attribution graph. The responsibility relationships are determined based on event attribution association information. The breach of contract identification unit is used to compare each event segment in the liability attribution map with the corresponding transportation contract terms to identify the breach of contract event segment and the corresponding target responsible party.
10. A computer storage medium, characterized in that, The computer storage medium stores at least one instruction, which, when executed by a processor, implements the cold chain logistics monitoring method as described in any one of claims 1 to 8.
11. An electronic device, characterized in that, The electronic device includes: a memory and a processor; The memory is used to store at least one instruction; The processor is used to execute at least one instruction to implement the cold chain logistics monitoring method as described in any one of claims 1 to 8.