Goods pledge and control system and method based on Internet of Things

Abstract

The invention discloses a cargo pledge and control system and method based on the Internet of Things, and relates to the technical field of cargo pledge supervision and relates to the technical field of cargo pledge and control, and the method specifically comprises the steps: 1, deploying multiple types of Internet of Things devices, synchronously collecting key data of pledged cargoes in different production scenes of an enterprise, and storing the key data in a database; extracting key characteristic parameters of the pledged goods; 2, standardizing the key characteristic parameters of the pledged goods, determining goods type classification dimensions, presetting movement scores, setting pledge movement risk coefficient values according to the actual value density of the goods, determining influence weights of different devices on the pledged goods, and finally constructing pledge risk assessment indexes, screening cargo types needing risk quantification; and step 3, calculating a core index for goods needing risk quantification, calculating a goods attribute risk score by fusing the core index, then dividing risk levels by combining historical data and industry supervision requirements, and executing response measures for different levels.

Description

Technical Field

[0001] This invention belongs to the field of cargo pledge supervision technology, specifically involving a cargo pledge control system and method based on the Internet of Things. Background Technology

[0002] In the field of supply chain finance, the security and efficiency of the supervision of goods pledged as a crucial financing method for enterprises have always been core concerns for the industry. Traditional goods pledge supervision models rely excessively on manual operations and the circulation of paper warehouse receipts, resulting in serious trust crises and efficiency bottlenecks. This exposes deep-seated flaws in the traditional model, such as ineffective risk control and ambiguous ownership of goods. Problems such as collusion between warehousing and financing parties to create false warehouse receipts, susceptibility of manual inspections to moral hazard, and delays in verifying the status of pledged goods lead financial institutions to face difficulties in monitoring, seizing, and disposing of goods, severely damaging the market's trust system.

[0003] Traditional regulatory models lack standardized risk quantification indicators and tiered response mechanisms, relying on manual risk assessment, which leads to problems such as delayed response and rigid measures. When collateral experiences abnormal movement, value fluctuations, or production anomalies, corresponding control measures cannot be triggered in real time, resulting in the spread and expansion of risks.

[0004] Therefore, there is an urgent need for an IoT-based method for cargo collateralization and control to solve the technical challenges in traditional cargo collateralization. Summary of the Invention

[0005] The purpose of this invention is to provide a cargo escort and control system and method based on the Internet of Things, which solves the technical problems of homogenized feature extraction, fragmented risk assessment, and delayed early warning response in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: IoT-based methods for cargo pledging and control include: Step 1: Deploy multiple types of IoT devices to simultaneously collect key data on pledged goods in different production scenarios of the enterprise, and extract key characteristic parameters of the pledged goods; Step 2: Standardize the key characteristic parameters of the pledged goods, determine the classification dimensions of the goods type and preset the movement score, set the pledge movement risk coefficient value based on the actual value density of the goods, determine the impact weight of different equipment on the pledged goods, and finally construct the pledge risk assessment index to screen the types of goods that need to be quantified for risk. Step 3: For goods requiring risk quantification, calculate core indicators, integrate the core indicators to calculate the risk score of the goods attributes, and then combine historical data and industry regulatory requirements to classify risk levels and implement response measures for different levels.

[0007] Furthermore, key data on pledged goods under different production scenarios of enterprises are collected simultaneously. The specific method is as follows: Based on the digital map of the warehouse / freight yard, a dedicated storage area for pledged goods is delineated and the physical boundary coordinates are extracted. UWB positioning tags collect the real-time coordinates (x, y, z) of the goods, weighing sensors collect the real-time weight, high-definition cameras combined with AI recognition record the appearance and stacking status, blockchain evidence storage terminal records the unique digital identity and ownership transfer record, near-infrared spectral sensors collect molecular spectral characteristics (λ1, λ2, ..., λn), and IoT locks record the opening and closing status of the containers. In the production workshop, smart meters record real-time energy consumption, equipment speed monitors collect speed, time recorders count the effective production time, and the MES system determines the daily production output, raw material purchase quantity, and finished product order quantity for the same type of goods.

[0008] Furthermore, key characteristic parameters of the pledged goods are extracted, specifically using the following method: Key characteristic parameters of pledged goods include the number of abnormal movements, the magnitude of sudden drops in energy consumption, and the number of equipment malfunctions; Based on real-time coordinates from UWB positioning, the distance D between the goods and the center of the preset safety zone is calculated. The frequency of D exceeding the safety threshold is counted using a sliding window and recorded as the abnormal movement count Fd. The total value is determined by obtaining the unit market value through the commodity price platform, and the daily value volatility is calculated. The time period is divided into T periods. The unit capacity energy consumption Ea = E / Q is calculated using the energy consumption of smart meters E and the capacity Q of MES. The energy consumption drop is compared between the current value and the average value of Ea over the past n periods. The equipment utilization rate Od is determined by the ratio of the effective and planned production time of the time recorder. The number of times the rotation speed is lower than the preset threshold is counted as the equipment abnormality count Fs.

[0009] Furthermore, determine the classification dimensions for goods types and preset moving scores, specifically using the following method: The goods are classified according to their shape and packaging method. A movement score is preset based on the difficulty of moving the goods. The movement score value is greater than 0. The larger the value, the higher the difficulty of moving the goods. The goods are divided into simple goods that do not require fixed constraints and can be directly moved by a single person. The movement score is set as a1. For ordinary goods that require basic tools and can be moved by two or more people working together, the movement rating is set to a2. For difficult-to-move goods that require specialized equipment, the movement rating is set to a3. a1, a2, and a3 are all constant values, set according to historical data and actual requirements.

[0010] Furthermore, the pledge movement risk coefficient is set based on the actual value density of the goods. The specific method is as follows: Actual value density = total market value of goods / total volume of goods. Value density ranges are defined based on business experience, and risk coefficients are assigned to different value density ranges. The pledged movement risk coefficient is determined by integrating movement scoring and actual value density. The specific formula for the pledged movement risk coefficient is kf(i) = , where yd(i) represents the movement score of cargo type i, and jz(i) represents the risk coefficient corresponding to the value density interval to which cargo type i belongs.

[0011] Furthermore, the weighting of the impact of different equipment on the pledged goods is determined using the following method: Clearly define the type of pledged goods and the functions of different production equipment, determine whether the equipment directly participates in the production process of the pledged goods, and determine the weight of the equipment's influence on the goods based on the proportion of the processing time of different equipment in the goods processing stage to the total processing time.

[0012] Furthermore, we construct pledge risk assessment indicators and screen the types of goods that require risk quantification. The specific method is as follows: Based on the comprehensive basic anomaly indicators, the pledged movement risk coefficient, and the impact weight, the formula CI(i) is used. Set up pledge risk assessment indicators, where i represents the i-th type of goods, j represents the j-th type of equipment, and J represents the total number of equipment types. This represents the weight of the influence of the j-th type of equipment on the i-th type of goods; Collect CI(i) values ​​and actual risk events over a period of time g, mark the CI(i) values ​​corresponding to the risk events and statistically analyze the distribution intervals, and take the minimum CI(i) value covering 90% of the risk events as the threshold C(i); when the current CI(i) ≥ C(i), the risk of this type of goods needs to be quantified immediately, otherwise no quantification is required.

[0013] Furthermore, for goods requiring risk quantification, core indicators are calculated, and the risk score for the goods' attributes is calculated by integrating these core indicators. The specific method is as follows: Identify the core indicators for the types of goods that require risk quantification. These core indicators include identity matching degree, material consistency coefficient, and deviation index. Based on the blockchain-stored cargo ID and the opening / closing logs recorded by the IoT lock, a formula is used. Indicates the identity matching degree, where, This represents the number of unauthorized operations performed on goods of type i within a given time period. This represents the total number of operations performed on goods of type i within a given time period. The material consistency coefficient Cm is obtained by collecting the spectral characteristics (λ1, λ2, ..., λn) of the cargo at regular intervals using a near-infrared spectral sensor and comparing them with the standard spectral library (λ1s, λ2s, ..., λns) of the same type of cargo. Based on the ratio of the actual output of goods to the enterprise's finished goods order quantity in the current time period, the production matching degree Rp is determined, a reasonable matching range [a1, a2] is preset, and the deviation index Da(i) is set. ; Using the formula Sr(i)= A comprehensive risk score for cargo attributes is set, where Sr(i) represents the risk score for cargo attributes. This represents the weighting coefficient for material consistency. This represents the deviation weighting coefficient. + =1, the weighting coefficient is adjusted according to historical data and actual needs.

[0014] This invention also provides an IoT-based cargo pledging and control system, applied to an IoT-based cargo pledging and control method, comprising: The pledged goods data acquisition module collects key data of pledged goods in different production scenarios of enterprises by deploying multiple types of IoT devices, and extracts key characteristic parameters of pledged goods. The pledge risk assessment indicator construction module standardizes the key characteristic parameters of pledged goods, determines the classification dimensions of goods types and presets the mobility score, sets the pledge mobility risk coefficient value based on the actual value density of the goods, determines the impact weight of different equipment on pledged goods, and finally constructs pledge risk assessment indicators to screen the types of goods that need to be quantified for risk. The pledge and control measures response module calculates core indicators for goods requiring risk quantification, integrates these core indicators to calculate a risk score for the goods' attributes, and then combines historical data with industry regulatory requirements to classify risk levels and implement response measures for different levels.

[0015] In summary, due to the adoption of the above technical solutions, the beneficial effects of this invention are: 1. This invention improves the accuracy of risk warning by constructing a dynamic and differentiated risk assessment system. It classifies goods by form / packaging, presets movement scores, sets a pledge movement risk coefficient based on value density, and determines the impact weight based on the proportion of equipment processing time. Finally, it constructs a CI(i) assessment index that integrates basic anomaly indicators. Furthermore, it sets thresholds based on historical risk events to screen goods requiring quantification, avoiding the one-sidedness of traditional assessments that ignore the characteristics of goods and their connection to production. This allows for accurate identification of easily transferable high-value goods and equipment-related risks, reducing risk misjudgments and providing precise guidance for subsequent management, thus solving the problems of homogenization and fragmentation in traditional assessments. 2. This invention achieves efficient risk control by establishing a standardized risk quantification and tiered response mechanism. Risk scores are obtained by calculating core indicators such as identity matching degree and material consistency coefficient. Combined with historical data and regulatory requirements, high, medium, and low risk levels are classified, and corresponding measures such as mandatory locking, shortened data collection cycles, and routine monitoring are implemented. No manual risk level determination is required; differentiated responses can be triggered in real time, avoiding the problems of delayed responses and rigid measures in traditional regulatory approaches. This ensures timely risk control for high-risk goods while avoiding excessive control of medium- and low-risk goods, reducing risk, improving regulatory efficiency, and balancing the rights and interests of all parties involved in the pledge. 3. This invention selects identity matching degree, material consistency coefficient, and deviation index as core indicators to comprehensively assess cargo risk from three key dimensions: cargo operation authority, material authenticity, and production and order matching degree. This ensures the comprehensiveness and accuracy of risk assessment. By setting a cargo attribute risk scoring formula, each core indicator is calculated comprehensively according to different weight coefficients, taking into full account the impact of various factors on cargo risk, and obtaining a score that can comprehensively reflect the overall risk status of the cargo, providing a reliable basis for subsequent risk level classification. Attached Figure Description

[0016] 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 some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 The diagram illustrates the steps of the Internet of Things-based cargo material escort and control method of the present invention. Figure 2 The method steps of the present invention for screening the types of goods that require risk quantification are illustrated in the diagram. Figure 3 The diagram shows a module diagram of the cargo escort and control system based on the Internet of Things of the present invention. Detailed Implementation

[0018] 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.

[0019] Example 1, such as Figure 1 , Figure 2 The IoT-based cargo pledging and control method shown includes the following steps: Step 1: Deploy multiple types of IoT devices to simultaneously collect key data on pledged goods in different production scenarios of the enterprise, and extract key characteristic parameters of the pledged goods; Based on digital maps of warehouses / freight yards (such as CAD drawings or laser scanning modeling data), dedicated storage areas (such as specific storage locations, shelves, or enclosed areas) are delineated for pledged goods. The physical boundary coordinates of these areas are extracted (such as the four corner coordinates of a rectangular area, or the center and radius of a circular area). Real-time coordinates (x, y, z) of the goods are collected via UWB positioning tags to monitor whether the goods are within a preset safe zone. Weighing sensors collect real-time weight data (W) of the goods to reflect changes in quantity. High-definition cameras combined with AI recognition technology record the appearance and stacking status of the goods, and a blockchain-based evidence storage terminal records the unique digital identity (ID) and ownership transfer records of the goods, ensuring the uniqueness of the pledged assets. Near-infrared spectral sensors collect the molecular spectral characteristics (λ1, λ2, ..., λn) of the goods to identify the purity of the material (such as the carbon content of steel or the content of effective ingredients in medicinal materials). IoT locks record the opening and closing status of the storage containers to mitigate the risk of unauthorized movement of goods. The real-time energy consumption of the enterprise's production workshop is recorded by smart meters; the speed of the equipment in the production workshop is collected by the equipment speed monitor; the time recorder counts the effective production time; and the production data collection, order management and process traceability capabilities of the MES system are used to determine the daily production output of the same type of pledged goods, the raw material purchase quantity and the finished product order quantity. Outliers are removed, and high-frequency fluctuating data (such as equipment speed and current) is smoothed by Kalman filtering to avoid instantaneous noise interference. For short-term data loss caused by equipment shutdown, linear interpolation is used to fill in the gaps to ensure data continuity. All data are mapped to the [0,1] interval by Min-Max normalization, and key characteristic parameters of pledged goods are extracted, including the number of abnormal movements, the magnitude of energy consumption drop, and the number of equipment anomalies. Based on the real-time coordinates (x, y, z) collected by UWB positioning tags, the spatial distance D between the goods and the center of the preset safety area (x0, y0, z0) is calculated. The frequency of D exceeding the safety threshold within the window is collected using a sliding window sampling method. The length of the sliding window is set based on the statistical patterns of past abnormal movement events (e.g., if 90% of abnormal movements last for more than 10 minutes, the window is set to 10 minutes), and recorded as the number of abnormal movements Fd, reflecting the frequency of abnormal movement of the goods. The safety threshold is set as the minimum buffer distance (e.g., 0.5 meters) for the outward expansion of the goods area boundary, ensuring that minor displacements of the goods during normal handling and stacking adjustments do not trigger false alarms. By connecting to a commodity price platform to obtain the unit market value of goods, the real-time total value of goods is calculated. The difference between the highest and lowest real-time total value of goods on a given day is calculated, and the ratio of this difference to the average real-time total value of goods is calculated to obtain the daily value volatility. Based on the total energy consumption E of smart meters and the actual production capacity (quantity of goods produced) Q of the MES system within different time periods (duration T), the unit production capacity energy consumption Ea within that time period is calculated, Ea = E / Q. By comparing the unit production capacity energy consumption Ea of the current time period with the average unit production capacity energy consumption of the past n time periods, the magnitude of the energy consumption drop is obtained. , ,in This represents the average energy consumption per unit of production capacity over the past n time periods; Based on the ratio of the effective production time to the planned production time of the time recorder, the equipment utilization rate Od is determined and calculated. The number of times the equipment speed is lower than the preset threshold is counted and recorded as the number of equipment abnormalities Fs.

[0020] Step 2: Standardize the key characteristic parameters of the pledged goods, determine the classification dimensions of the goods type and preset the movement score, set the pledge movement risk coefficient value based on the actual value density of the goods, determine the impact weight of different equipment on the pledged goods, and finally construct the pledge risk assessment index to screen the types of goods that need to be quantified for risk. Determine the number of abnormal movements of different types of goods, determine the magnitude of energy consumption drop and the number of equipment anomalies of different equipment in real time for each period of time, record them as basic anomaly indicators, and standardize the basic anomaly indicators. The core physical attributes and storage characteristics of different types of goods are clearly defined, and basic classification dimensions are divided into solid (including block and granular), liquid (including drum and tank storage), and gas (high-pressure tank / pipeline storage) by form and bulk (without fixed packaging, such as coal and ore), standard boxed (such as cardboard boxes and wooden boxes), and sealed container (such as steel drums and pressure vessels) by packaging method. Based on the difficulty of unauthorized movement of different types of goods, a movement score is preset. For example, goods that can be moved directly by a single person without fixed constraints (no locks / welded fixation) are recorded as simple goods with a movement score of 0.1. Goods that can be moved by two or more people with the help of basic tools are recorded as ordinary goods with a movement score of 0.5. Goods that require professional equipment to move are recorded as difficult goods with a movement score of 1. A movement score greater than 0 indicates that the higher the score, the more difficult the goods are to move. The actual value density is calculated based on the formula: Actual Value Density = Total Market Value of Goods / Total Volume of Goods. The actual value density can vary significantly (e.g., from 0.1 to 1 million RMB / cubic meter), requiring segmentation to avoid extreme values. Value density ranges are defined based on business experience (e.g., low, medium, and high value densities), and risk coefficients are assigned to each range. For example, the risk coefficient for a low value density range is 0.5, and for a high value density range it is 1.5. Considering the impact of transferability and value density on collateral security, the collateral mobility risk coefficient is determined by integrating mobility scoring and actual value density. The specific formula for the collateral mobility risk coefficient is kf(i) = , where yd(i) represents the mobility score of cargo type i, and jz(i) represents the risk coefficient corresponding to the value density interval of cargo type i. The cargo that is easy to transfer and has high value density is determined by pledging the mobility risk coefficient value. Clearly define the type of pledged goods and the functions of different production equipment, determine whether the equipment directly participates in the production process of the pledged goods, and determine the weight of the equipment's influence on the goods based on the proportion of the processing time of different equipment in the goods processing stage to the total processing time. The pledge risk assessment index is set by combining basic anomaly indicators, pledge movement risk coefficient, and impact weights. The specific formula is shown below: CI(i) = ; Where i represents the i-th type of goods, j represents the j-th type of equipment, and J represents the total number of equipment types. This represents the weight of the influence of the j-th type of equipment on the i-th type of goods; Collect the CI(i) values ​​of pledged goods and actual risk events (such as theft, replacement of pledged goods, and backlog of goods due to production abnormalities) within the past g time period. Mark the types of goods that have experienced risk events and their corresponding CI(i) values. Statistically analyze the CI(i) distribution range when risk events occur (e.g., 75% of risk events are concentrated in CI(i) ≥ 0.65). Based on the historical risk event distribution, select the minimum CI(i) value that covers 90% of risk events as the threshold C(i). If CI(i) is greater than or equal to C(i) in the current time period, it means that the location of goods of type i frequently crosses the boundary and risk quantification needs to be performed immediately. Otherwise, it is determined that goods of type i have not crossed the boundary and risk quantification is not required.

[0021] Step 3: For goods requiring risk quantification, calculate core indicators, integrate the core indicators to calculate the risk score of the goods attributes, and then combine historical data and industry regulatory requirements to classify risk levels and implement response measures for different levels. Identify the core indicators for the types of goods that require risk quantification. These core indicators include identity matching degree, material consistency coefficient, and deviation index. Based on the ratio of the number of unauthorized identity operations to the total number of operations within a certain period determined from the goods ID stored on the blockchain and the switch logs recorded by the IoT lock, and using the formula represents the identity matching degree, where represents the number of unauthorized identity operations of goods of type i within the period, represents the total number of operations of goods of type i within the period; The spectral characteristics (λ1, λ2,..., λn) of the goods are collected by the near-infrared spectral sensor every other period, and the cosine similarity is calculated with the standard spectral library (λ1s, λ2s,..., λns) of this type of goods to obtain the material consistency coefficient Cm. The closer Cm is to 1, the more consistent the goods material is with the pledged agreement; Based on the ratio of the actual production volume of the goods in the current period to the enterprise's finished product order volume, the production matching degree Rp is determined. A reasonable range [a1, a2] of matching is preset. If Rp in the current period is less than a1, it indicates that the quantity of goods cannot meet the order demand. If Rp in the current period is greater than a2, it indicates that there may be a risk of overstocking. The deviation index Da(i)= is used to quantify the deviation degree of the production matching degree outside the reasonable range; The risk score of the goods attributes is comprehensively set, and the specific formula is as follows: Sr(i)= ; Among them, Sr(i) represents the risk score of the goods attributes, represents the material consistency weight coefficient, represents the deviation weight coefficient, + =1, and the weight coefficients are adjusted according to historical data and actual requirements; Based on the risk score Sr(i) of the goods attributes, combined with industry regulatory requirements and historical risk event handling experience, the risk level interval is defined; High risk: Sr(i)≥S1 (S1 is the high-risk threshold, determined by floating ΔS from the average value of Sr(i) corresponding to risk events within the past g duration), indicating that the goods have core risks such as inconsistent material, frequent unauthorized operations, or serious deviation in production matching; Medium risk: S2≤Sr(i)<S1 (S2 is the medium-risk threshold, taking the maximum value of Sr(i) in the historical period without risk events), indicating that the goods have a single-dimensional anomaly (such as slightly low identity matching degree, production matching degree close to the lower limit of the reasonable range); Low risk: Sr(i)<S2, indicating that the identity, material, and production status of the goods all meet the pledged agreement and there are no significant risk hazards; In case of high risk, the IoT lock will be forcibly locked immediately (prohibiting the opening and closing of the container). The system will push an alarm message containing the real-time coordinates (x, y, z) of the goods and the abnormal operation log to the supervisors. At the same time, the ownership transfer function of the blockchain evidence storage terminal will be frozen. The container can only be unlocked by manual authorization after the supervisors have verified the goods ID and collected spectral features on-site and confirmed that the risk has been eliminated. For medium-risk responses, shorten the sensor acquisition cycle (e.g., shorten the near-infrared spectral acquisition interval from T to T / 2), increase the frequency of abnormal behavior recognition by AI cameras (e.g., generate an appearance stacking status analysis report every 10 minutes); send risk warning letters to enterprises through the system, requiring them to provide feedback on the cause of the abnormality within T3 time (e.g., deviation in production matching degree may be due to order adjustments or temporary equipment maintenance), and provide supporting materials (e.g., new order contracts, equipment maintenance records). In a low-risk response, maintain regular monitoring frequency, synchronize Sr(i) and related indicators (identity matching degree, Cm, Rp) to the blockchain for evidence storage, and generate a daily staking security report for both staking and pledging parties to query.

[0022] Example 2, as follows Figure 3 The IoT-based cargo escrow and control system shown includes the following: The pledged goods data acquisition module collects key data of pledged goods in different production scenarios of enterprises by deploying multiple types of IoT devices, and extracts key characteristic parameters of pledged goods. The pledge risk assessment indicator construction module standardizes the key characteristic parameters of pledged goods, determines the classification dimensions of goods types and presets the mobility score, sets the pledge mobility risk coefficient value based on the actual value density of the goods, determines the impact weight of different equipment on pledged goods, and finally constructs pledge risk assessment indicators to screen the types of goods that need to be quantified for risk. The pledge and control measures response module calculates core indicators for goods requiring risk quantification, integrates these core indicators to calculate a risk score for the goods' attributes, and then combines historical data with industry regulatory requirements to classify risk levels and implement response measures for different levels.

[0023] The above formulas are all dimensionless calculations, and the preset parameters in the formulas should be set by those skilled in the art according to the actual situation.

[0024] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

[0025] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to specific implementations. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A cargo material pledging and control method based on the Internet of Things, characterized in that, include: Step 1: Deploy multiple types of IoT devices to simultaneously collect key data on pledged goods in different production scenarios of the enterprise, and extract key characteristic parameters of the pledged goods; Step 2: Standardize the key characteristic parameters of the pledged goods, determine the classification dimensions of the goods type and preset the movement score, set the pledge movement risk coefficient value based on the actual value density of the goods, determine the impact weight of different equipment on the pledged goods, and finally construct the pledge risk assessment index to screen the types of goods that need to be quantified for risk. Step 3: For goods requiring risk quantification, calculate core indicators, integrate the core indicators to calculate the risk score of the goods attributes, and then combine historical data and industry regulatory requirements to classify risk levels and implement response measures for different levels.

2. The method for cargo material seizure and control based on the Internet of Things according to claim 1, characterized in that, The key data of pledged goods under different production scenarios of enterprises are collected synchronously. The specific method is as follows: Based on the digital map of the warehouse / freight yard, a dedicated storage area for pledged goods is delineated and the physical boundary coordinates are extracted. UWB positioning tags collect the real-time coordinates (x, y, z) of the goods, weighing sensors collect the real-time weight, high-definition cameras combined with AI recognition record the appearance and stacking status, blockchain evidence storage terminal records the unique digital identity and ownership transfer record, near-infrared spectral sensors collect molecular spectral characteristics (λ1, λ2, ..., λn), and IoT locks record the opening and closing status of the containers. In the production workshop, smart meters record real-time energy consumption, equipment speed monitors collect speed, time recorders count the effective production time, and the MES system determines the daily production output, raw material purchase quantity, and finished product order quantity for the same type of goods.

3. The method for cargo material seizure and control based on the Internet of Things according to claim 1, characterized in that, The specific method for extracting key characteristic parameters of pledged goods is as follows: Key characteristic parameters of pledged goods include the number of abnormal movements, the magnitude of sudden drops in energy consumption, and the number of equipment malfunctions; Based on real-time coordinates from UWB positioning, the distance D between the goods and the center of the preset safety zone is calculated. The frequency of D exceeding the safety threshold is counted using a sliding window and recorded as the abnormal movement count Fd. The total value is determined by obtaining the unit market value through the commodity price platform, and the daily value volatility is calculated. The time period is divided into T periods. The unit capacity energy consumption Ea = E / Q is calculated using the energy consumption of smart meters E and the capacity Q of MES. The energy consumption drop is compared between the current value and the average value of Ea over the past n periods. The equipment utilization rate Od is determined by the ratio of the effective and planned production time of the time recorder. The number of times the rotation speed is lower than the preset threshold is counted as the equipment abnormality count Fs.

4. The cargo material escrow control method based on the Internet of Things according to claim 1, characterized in that, The specific method for determining the cargo type classification dimensions and preset moving scores is as follows: The goods are classified according to their shape and packaging method. A movement score is preset based on the difficulty of moving the goods. The movement score value is greater than 0. The larger the value, the higher the difficulty of moving the goods. The goods are divided into simple goods that do not require fixed constraints and can be directly moved by a single person. The movement score is set as a1. For ordinary goods that require basic tools and can be moved by two or more people working together, the movement rating is set to a2. For difficult-to-move goods that require specialized equipment, the movement rating is set to a3. a1, a2, and a3 are all constant values, set according to historical data and actual requirements.

5. The method for cargo material seizure and control based on the Internet of Things according to claim 1, characterized in that, The collateral mobility risk coefficient is set based on the actual value density of the goods. The specific method is as follows: Actual value density = total market value of goods / total volume of goods. Value density ranges are defined based on business experience, and risk coefficients are assigned to different value density ranges. The pledged movement risk coefficient is determined by integrating movement scoring and actual value density. The specific formula for the pledged movement risk coefficient is kf(i) = , where yd(i) represents the movement score of cargo type i, and jz(i) represents the risk coefficient corresponding to the value density interval to which cargo type i belongs.

6. The cargo material escrow control method based on the Internet of Things according to claim 1, characterized in that, The specific method for determining the impact weight of different devices on pledged goods is as follows: Clearly define the type of pledged goods and the functions of different production equipment, determine whether the equipment directly participates in the production process of the pledged goods, and determine the weight of the equipment's influence on the goods based on the proportion of the processing time of different equipment in the goods processing stage to the total processing time.

7. The method for cargo material seizure and control based on the Internet of Things according to claim 1, characterized in that, Construct pledge risk assessment indicators and screen the types of goods that require risk quantification. The specific method is as follows: Based on the comprehensive basic anomaly indicators, the pledged movement risk coefficient, and the impact weight, the formula CI(i) is used. Set up pledge risk assessment indicators, where i represents the i-th type of goods, j represents the j-th type of equipment, and J represents the total number of equipment types. This represents the weight of the influence of the j-th type of equipment on the i-th type of goods; Collect CI(i) values ​​and actual risk events over a period of time g, mark the CI(i) values ​​corresponding to the risk events and statistically analyze the distribution intervals, and take the minimum CI(i) value covering 90% of the risk events as the threshold C(i); when the current CI(i) ≥ C(i), the risk of this type of goods needs to be quantified immediately, otherwise no quantification is required.

8. The method for cargo material seizure and control based on the Internet of Things according to claim 1, characterized in that, For goods requiring risk quantification, core indicators are calculated, and the risk score for the goods' attributes is calculated by integrating these core indicators. The specific method is as follows: Identify the core indicators for the types of goods that require risk quantification. These core indicators include identity matching degree, material consistency coefficient, and deviation index. Based on the blockchain-stored cargo ID and the opening / closing logs recorded by the IoT lock, a formula is used. Indicates the identity matching degree, where, This represents the number of unauthorized operations performed on goods of type i within a given time period. This represents the total number of operations performed on goods of type i within a given time period. The material consistency coefficient Cm is obtained by collecting the spectral characteristics (λ1, λ2, ..., λn) of the cargo at regular intervals using a near-infrared spectral sensor and comparing them with the standard spectral library (λ1s, λ2s, ..., λns) of the same type of cargo. Based on the ratio of the actual output of goods to the enterprise's finished goods order quantity in the current time period, the production matching degree Rp is determined, a reasonable matching range [a1, a2] is preset, and the deviation index Da(i) is set. ; Using the formula Sr(i)= A comprehensive risk score for cargo attributes is set, where Sr(i) represents the risk score for cargo attributes. This represents the weighting coefficient for material consistency. This represents the deviation weighting coefficient. + =1, the weighting coefficient is adjusted according to historical data and actual needs.

9. A cargo material escort and control system based on the Internet of Things (IoT), applied to the cargo material escort and control method based on the IoT as described in any one of claims 1-8, characterized in that, include: The pledged goods data acquisition module collects key data of pledged goods in different production scenarios of enterprises by deploying multiple types of IoT devices, and extracts key characteristic parameters of pledged goods. The pledge risk assessment indicator construction module standardizes the key characteristic parameters of pledged goods, determines the classification dimensions of goods types and presets the mobility score, sets the pledge mobility risk coefficient value based on the actual value density of the goods, determines the impact weight of different equipment on pledged goods, and finally constructs pledge risk assessment indicators to screen the types of goods that need to be quantified for risk. The pledge and control measures response module calculates core indicators for goods requiring risk quantification, integrates these core indicators to calculate a risk score for the goods' attributes, and then combines historical data with industry regulatory requirements to classify risk levels and implement response measures for different levels.

Images