Goods on-time early warning method based on supply chain management system

Abstract

The invention discloses a goods in-time early warning method based on a supply chain management system, and the method comprises the steps: carrying out the quality evaluation of environment data collected by a sensor, processing and fusing goods information, and obtaining a comprehensive feature vector; a dynamic weight is set based on the feature vector, a dynamic shelf life prediction model is constructed, a jump compensation mechanism is introduced into the model, and when an emergency is detected, the early warning range is automatically adjusted, and the early warning precision is optimized; the method comprises the following steps: randomly extracting goods for shelf life detection, comparing with a model prediction result, dynamically updating an early warning range, and transmitting early warning information to a service end by utilizing a visual means, so as to realize accurate goods in-time early warning; according to the invention, the accuracy and real-time performance of early warning are significantly improved, the false alarm rate is reduced, the ability of the supply chain management system to deal with emergencies is enhanced, goods loss caused by environmental factors or emergencies can be effectively reduced, and the efficiency and response speed of supply chain management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of early warning of approaching expiration of goods, and particularly to an early warning method for approaching expiration of goods based on a supply chain management system. Background Art

[0002] With the rapid development of globalization and information technology, the supply chain management system has become a core component of modern logistics and production management. Especially in industries with strict shelf-life requirements such as food, medicine, and chemicals, this makes an accurate early warning system for approaching expiration of goods particularly important. Currently, traditional supply chain management systems often rely on static prediction of the goods life cycle, usually based on historical data and empirical rules for manual prediction. However, this method has significant limitations, especially when facing complex and changing environmental conditions, and it cannot provide sufficiently accurate and real-time warnings. In recent years, with the development of sensor technology, Internet of Things technology, and big data analysis methods, dynamically monitoring and analyzing environmental data of goods during transportation and storage has become an important means to improve the accuracy of predicting the shelf life of goods.

[0003] Currently, some shelf-life prediction methods based on environmental monitoring data have been proposed, mainly including the influence of environmental factors such as temperature, humidity, and gas concentration on the quality of goods. However, most of the existing technologies focus on static monitoring and prediction models, lacking the ability to dynamically respond to changes in environmental variables, resulting in poor accuracy and timeliness of prediction results. In addition, although sensors can collect data such as temperature and humidity in real time, due to the complexity of the interaction between environmental factors, most systems cannot fully capture the dynamic relationship between these variables and the quality of goods even under monitoring conditions. For example, a slight fluctuation in temperature or a change in humidity may have a significant impact on the quality of goods in a short period of time, but existing systems often have difficulty making effective adjustments under emergency or non-linear conditions, thus reducing the real-time performance and accuracy of the early warning system. Additionally, considering that goods may encounter emergencies such as vibrations during transportation, packaging damage, or equipment failures, which will also have a sudden impact on the shelf life of goods, and existing technologies usually ignore these interference factors of emergencies and lack a recovery and compensation mechanism, resulting in too slow processing efficiency after early warning and too large error range of early warning. Summary of the Invention

[0004] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a method for early warning of approaching expiration of goods based on a supply chain management system to solve the problems raised in the background art.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A method for early warning of approaching expiration of goods based on a supply chain management system, including:

[0007] Deploy different types of sensors in the production, warehousing, and transportation links of the supply chain respectively, obtain the environmental data in each sensor, conduct a quality assessment on the environmental data, and at the same time obtain the goods information from the supply chain management system, and merge the environmental data that has passed the quality assessment with the goods information to obtain a comprehensive feature vector of the goods;

[0008] Considering the influence of environmental data on the shelf life of goods, set dynamic weights for the comprehensive feature vector of the goods, and construct a dynamic shelf life prediction model with the comprehensive feature vector of the goods and the dynamic weights. Introduce an event-triggered jump compensation mechanism in the dynamic shelf life prediction model, and set the early warning range for approaching expiration of goods according to the event-triggered jump compensation mechanism;

[0009] Randomly select goods for shelf life detection, compare the prediction results of the dynamic shelf life prediction model with the detection results of the randomly selected goods' shelf life to obtain the model prediction error, update the early warning range for approaching expiration of goods according to the model prediction error, display each update result in a visual manner, and transmit it to the supply chain management system to achieve accurate early warning of approaching expiration of goods in the supply chain management system.

[0010] As a preferred solution of the method for early warning of approaching expiration of goods based on the supply chain management system of the present invention, among them: Obtaining the environmental data in each sensor and conducting a quality assessment on the environmental data includes:

[0011] The quality assessment is expressed by the formula:

[0012]

[0013] where, v i is the current measured value v of the i-th sensor; is the average value of the measured values of the remaining sensors in the same area; δ i represents the threshold δ of the i-th sensor;

[0014] If the threshold δ does not exceed the thresholds of the other sensors in the same area, it indicates that the environmental data collected by the current sensor is normal. Otherwise, it indicates that the environmental data collected by the current sensor is abnormal. Synchronize the environmental data collected by the other sensors through timestamps. If there is a situation where the environmental data collected by the current sensor is missing during the data synchronization process, perform interpolation prediction based on the data of the other sensors in the same area.

[0015] As a preferred solution of the method for predicting approaching expiration of goods based on a supply chain management system according to the present invention, wherein: simultaneously obtain goods information from the supply chain management system, and merge the environmental data that has passed quality assessment with the goods information to obtain a comprehensive feature vector of the goods, including:

[0016] Represent the environmental data collected by the sensor in a normal state as the environmental data that has passed quality assessment. Simultaneously obtain goods information from the supply chain management system, and merge the environmental data that has passed quality assessment with the goods information to obtain a comprehensive feature vector of the goods.

[0017] As a preferred solution of the method for predicting approaching expiration of goods based on a supply chain management system according to the present invention, wherein: considering the influence of environmental data on the shelf life of goods, set dynamic weights for the comprehensive feature vector of the goods, including:

[0018] Considering that each piece of environmental data in the environmental data affects the shelf life of the goods, and the degrees of influence are different, assign a weight value that is updated over time to each piece of environmental data to obtain an assigned weight set.

[0019] As a preferred solution of the method for predicting approaching expiration of goods based on a supply chain management system according to the present invention, wherein: construct a dynamic shelf life prediction model with the comprehensive feature vector and dynamic weights of the goods, including:

[0020] Obtain the quality status of the goods at time t and initialize it. Set a discrete time step based on hours.

[0021] Based on the obtained assigned weight set and the comprehensive feature vector of the goods, obtain the quality decay process of the goods through a difference equation.

[0022] The difference equation Q(t + Δτ) is expressed as:

[0023] Q(t + Δτ) = Q(t) - Δτ × F(X(t), ω(t))

[0024] Among them, Q(t) represents the quality status of the goods at time t, and is initialized as Q(0) = Q0; Δτ represents the discrete time step, with the unit of hour; F(X(t), ω(t)) represents the attenuation function; X(t) is the comprehensive feature vector of the goods, and ω(t) is the set of allocated weights;

[0025] The attenuation function F(X(t), ω(t)) is expressed as:

[0026]

[0027] Among them, f i represents the i-th factor function, and N represents the specific environment.

[0028] As a preferred solution of the method for warning of approaching expiration of goods based on the supply chain management system described in the present invention, it further includes:

[0029] According to the obtained quality status Q(t) at time t, set the lower limit of quality safety Q low ;

[0030] When Q(t) ≤ Q low , it indicates that the goods have entered the approaching expiration state and are not suitable for transportation, and update the value of Q(t), and recalculate the difference equation Q(t + Δt);

[0031] Record the value of the difference equation updated each time, and mark the attenuation state of the goods quality corresponding to the difference equation.

[0032] As a preferred solution of the method for warning of approaching expiration of goods based on the supply chain management system described in the present invention, an event-triggered jump compensation mechanism is introduced in the dynamic shelf life prediction model, including:

[0033] If an unexpected event is detected, perform jump correction:

[0034] Q new (t) = Q(t) - ΔQ shock

[0035] Among them, Q new (t) represents the value of Q(t) after the jump, and ΔQ shock represents the severity of the unexpected event;

[0036] If a remedial measure is taken after the unexpected event occurs, define the unexpected event compensation term:

[0037] Q new (t) = Q new (t) + ΔQ recover

[0038] Among them, ΔQ recoverIndicates the effectiveness assessment of the remedial measures;

[0039] After the emergency is repaired, detect whether the value of Q new (t) changes. If it does not change, it means the environment has returned to normal, and update Q(t) to the current Q new (t) value.

[0040] As a preferred solution of the method for warning of approaching expiration of goods based on the supply chain management system described in the present invention, wherein: set the warning range for approaching expiration of goods according to the jump compensation mechanism triggered by the event, including:

[0041] According to the updated value of Q(t), set the first threshold, the second threshold and the third threshold. Each threshold corresponds to a different warning level, and the relationship between the thresholds is expressed as: β1 < β2 < β3;

[0042] When Q(t) approaches the first threshold β1, the prediction model issues a primary warning to prompt relevant personnel to pay attention to the current environment of the goods;

[0043] When Q(t) approaches the second threshold β2, the prediction model issues an intermediate warning to prompt relevant personnel to quickly promote the current goods;

[0044] When Q(t) approaches the third threshold β3, the prediction model issues a high-level warning to prompt relevant personnel to remove the goods from the shelves.

[0045] As a preferred solution of the method for warning of approaching expiration of goods based on the supply chain management system described in the present invention, wherein: randomly select goods for shelf life detection, and compare the prediction results of the dynamic shelf life prediction model with the detection results of the randomly selected goods' shelf life to obtain the model prediction error, including:

[0046] The model prediction error is achieved by minimizing the objective function, as follows:

[0047]

[0048] Among them, Q rs (t) is the quality status of the shelf life of randomly selected goods at time t, and Θ represents the internal model parameters of each factor function f i of.

[0049] As a preferred solution of the method for warning of approaching expiration of goods based on the supply chain management system described in the present invention, wherein: update the warning range for approaching expiration of goods according to the model prediction error, display each update result in a visual manner, and transmit it to the supply chain management system to achieve accurate warning of approaching expiration of goods in the supply chain management system, including:

[0050] The Q(t) update results of each model error and the classification warning information are respectively displayed in the form of curves and charts, and data intercommunication is carried out with the business end of the supply chain management system or the enterprise resource planning system (ERP) through an external RESTful API or other enterprise bus interfaces. At the same time, in the cloud database, the change records of Q(t) for each batch of goods and the jump information of all events are saved in real time.

[0051] Compared with the prior art, the beneficial effects of the invention are as follows:

[0052] 1. By introducing a dynamic weight adjustment mechanism and environmental data quality assessment, the present invention can monitor and adjust the approaching expiration prediction of goods in real time, making the warning results more accurate, avoiding the limitations of traditional static models that fail to cope with complex environmental changes, and the dynamic weight mechanism can adjust the weight in a timely manner according to changes in environmental conditions to ensure that the model continuously and accurately reflects the shelf life status of goods;

[0053] 2. An event-triggered jump compensation mechanism is introduced into the dynamic shelf life prediction model, enabling the supply chain management system to respond to emergencies during transportation in real time and adjust the warning range according to remedial measures, improving the flexibility of the supply chain management system to cope with unexpected environmental changes;

[0054] 3. By comparing the shelf life detection of randomly selected goods with the model prediction results, the warning range is dynamically updated, and information is transmitted to the supply chain management system through visualization means, enabling supply chain managers to make more refined management decisions based on the real-time updated warning information, improving the efficiency and response speed of goods management. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. Among them:

[0056] Figure 1 is the overall flowchart of the approaching expiration warning method for goods based on the supply chain management system according to an embodiment of the present invention;

[0057] Figure 2 is the comparison chart of the goods quality attenuation process of different models of the approaching expiration warning method for goods based on the supply chain management system according to an embodiment of the present invention;

[0058] Figure 3 is the comparison chart of the model error distribution (box type) of the approaching expiration warning method for goods based on the supply chain management system according to an embodiment of the present invention. Detailed implementation manners

[0059] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the detailed implementation manners of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0061] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that mutually excludes other embodiments.

[0062] The present invention will be described in detail in conjunction with the schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views showing the device structure will be enlarged locally not in accordance with the general scale, and the schematic diagrams are only examples and should not limit the protection scope of the present invention here. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0063] At the same time, in the description of the present invention, it should be noted that the orientation or positional relationships indicated by terms such as "upper, lower, inner, and outer" are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation to the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0064] Unless otherwise clearly defined and limited in the present invention, the terms "installed, connected, and coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can also be a mechanical connection, an electrical connection, or a direct connection, or can be indirectly connected through an intermediate medium, or can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0065] Embodiment 1

[0066] Reference Figure 1 , which is the first embodiment of the present invention. This embodiment provides a method for warning of approaching expiration of goods based on a supply chain management system, including:

[0067] S1. Different types of sensors are respectively arranged in the production, warehousing, and transportation links of the supply chain to obtain the environmental data in each sensor, evaluate the quality of the environmental data, and at the same time obtain the goods information from the supply chain management system, and merge the environmental data that has passed the quality evaluation with the goods information to obtain the comprehensive feature vector of the goods;

[0068] Specifically, sensors affected by environmental factors such as temperature, humidity, gas concentration (such as CO2, O2), and light intensity are arranged in the production and warehousing environments in the supply chain, and sensors affected by human factors such as integrated vibration and collision are arranged in the transportation link;

[0069] Specifically, each sensor has a unique number and is connected to the data platform of the supply chain management system by wireless or wired means;

[0070] It should be noted that considering that the sensors come from different manufacturers or the models between sensors are different, in order to avoid the distortion of a single data source obtained by a single sensor, it is necessary to evaluate the quality of the environmental data collected in each sensor;

[0071] Specifically, the quality evaluation can be expressed by a mathematical formula as:

[0072]

[0073] where v i is the current measured value v of the i-th sensor; is the average value of the measured values of the remaining sensors in the same area; δ i represents the threshold δ of the i-th sensor. If this δ exceeds 15% - 20% of the thresholds of the remaining sensors in the same area (the settings of the sensor thresholds can be adjusted according to the actual situation), it means that the environmental data collected by the current sensor is abnormal. Synchronize the environmental data collected by the remaining sensors through the time stamp. If there is a situation where the environmental data collected by the current sensor is missing during the data synchronization process, perform interpolation prediction based on the data of the remaining sensors in the same area;

[0074] It should be noted that both the time stamp and the interpolation prediction are the most common processing methods in data preprocessing, so they will not be elaborated;

[0075] Furthermore, the environmental data that has passed the quality evaluation is denoted as:

[0076] E(t) = [T(t), H(t), G(t), V(t), C(t), N1]

[0077] Among them, E(t) represents the environmental data at time t, T(t) represents the temperature at time t, H(t) represents the humidity at time t, G(t) represents the gas concentration at time t, V(t) represents the cumulative vibration amount at time t, and C(t) represents the collision intensity at time t; N1 represents the set of other environmental data, excluding the temperature, humidity, gas concentration, cumulative vibration amount, and collision intensity mentioned above;

[0078] Furthermore, obtain the packaging integrity, initial shelf-life benchmark value, etc. of the goods information from the supply chain management system, and merge the environmental data that has passed the quality assessment with the goods information to obtain the comprehensive feature vector of the goods;

[0079] Specifically, the comprehensive feature vector of the goods is expressed as:

[0080] X(t) = [E(t), I, P0, M]

[0081] Among them, X(t) represents the comprehensive feature vector of the goods at time t; I represents the packaging integrity of the goods, which is a percentage value; P0 represents the initial shelf-life benchmark value; M represents the set of other goods information, excluding the packaging integrity and initial shelf-life benchmark value of the goods mentioned above;

[0082] It should be noted that the obtained comprehensive feature vector of the goods can be regarded as the digital twin of each piece of goods in the supply chain to achieve a digital supply chain data management method. And by switching the application scenario, only the goods information needs to be swapped. For example, changing it to drug information or precision machinery information, etc., can meet the needs of the environmental data E(t), and thus the migration operation of supply chain data collection can be realized;

[0083] S2. Consider the problem of the impact of environmental data on the shelf life of goods, set dynamic weights for the comprehensive feature vector of the goods, and construct a dynamic shelf-life prediction model with the comprehensive feature vector of the goods and the dynamic weights. Introduce an event-triggered jump compensation mechanism into the dynamic shelf-life prediction model, and set the early warning range of the approaching expiration of the goods according to the event-triggered jump compensation mechanism;

[0084] It should be noted that since each environmental data in the environmental data E(t) can affect the shelf life of the goods, and the degree of influence is different, it is necessary to assign a weight value that is updated over time to each environmental data;

[0085] Specifically, the assigned weight value is denoted as:

[0086] ω(t) = [ω T (t), ωH (t), ω G (t), ω V (t), N2]

[0087] Among them, ω(t) represents the set of weights assigned at time t, ω T (t), ω H (t), ω G (t), ω V (t) respectively correspond to the weight values of temperature T(t), humidity H(t), gas concentration G(t), vibration accumulation V(t), and collision intensity C(t); N2 corresponds to N1 and represents the weight value of the other environmental data set N1;

[0088] Furthermore, obtain the quality state of the goods at time t, and perform initialization. Set the discrete time step based on hours, and based on the obtained assigned weight set ω(t) and the comprehensive feature vector X(t) of the goods, obtain the quality decay process of the goods through a difference equation;

[0089] Specifically, the difference equation is expressed as:

[0090] Q(t + Δτ) = Q(t) - Δτ × F(X(t), ω(t))

[0091] Among them, Q(t) represents the quality state of the goods at time t, and the initialization is Q(0) = Q0; Δτ represents the discrete time step, in hours; F(X(t), ω(t)) represents the decay function;

[0092] Even further, the decay function F(X(t), ω(t) is expressed as:

[0093]

[0094] Among them, f i represents the i-th factor function, and N represents the specific environment, such as the above-mentioned temperature T, humidity H, gas concentration G, etc.;

[0095] It should be noted that each factor function is non-linear or non-linearly represented. For example, the temperature factor uses the Arrhenius model, the humidity factor uses the exponential decay model, and the collision or vibration factor uses the piecewise linear model, etc.;

[0096] Even further, according to the obtained quality state Q(t) at time t, set the quality safety lower limit Q of the goods low , when Q(t) ≤ Q low , it indicates that the goods have entered the approaching expiration state and are not suitable for transportation, and update the value of Q(t), and recalculate the difference equation Q(t + Δτ);

[0097] Furthermore, record the values of the difference equation for each update and mark the decay status of the goods quality corresponding to the difference equation (such as the loss rate of goods, the number of customer returns, etc.);

[0098] It should be noted that recording each calculated value of the difference equation can trace the change trajectory of the sensor throughout the process from production to transportation of the goods;

[0099] It should be noted that in the actual supply chain, in addition to the daily stable environmental changes, sudden events (such as cold chain power failure, packaging damage, violent loading and unloading, etc.) will also cause discontinuous jumps or impacts on the shelf life of the goods; at the same time, in order to more finely warn of the approaching expiration risk of the goods, it is necessary to adopt multi-level thresholds for handling, rather than simply dividing them into two states of approaching expiration and not approaching expiration;

[0100] Further, on the basis of Q(t) in the dynamic shelf life prediction model, introduce an event-triggered jump compensation mechanism to perform jump correction when detecting sudden events (such as packaging damage, sudden temperature rise caused by temporary power failure, large vibration caused by violent loading and unloading of logistics, etc.);

[0101] Specifically, the jump correction is as follows:

[0102] Q new (t) = Q(t) - ΔQ shock

[0103] Wherein, Q new (t) represents the value of Q(t) after the jump, and ΔQ shock represents the severity of the sudden event;

[0104] Further, if remedial measures are taken after the sudden event occurs (such as rapid cooling, immediately replacing the damaged packaging), then define the sudden event compensation term:

[0105] Q new (t) = Q new (t) + ΔQ recover

[0106] Wherein, ΔQ recover represents the effectiveness evaluation of the remedial measures;

[0107] Further, after the sudden event is repaired, detect whether the value of Q new (t) changes. If it does not change, it means that the environment has returned to normal, and update Q(t) to the current value of Q new (t);

[0108] Furthermore, according to the updated value of Q(t), set the first threshold, the second threshold, and the third threshold, and each threshold corresponds to a different warning level;

[0109] Specifically, the first threshold, the second threshold, and the third threshold are respectively expressed as: β1 < β2 < β3;

[0110] When Q(t) is close to β1, the prediction model issues a primary warning to prompt relevant personnel to pay attention to the current environment of the commodity;

[0111] When Q(t) is close to β2, the prediction model issues an intermediate warning to prompt relevant personnel to quickly promote the current commodity;

[0112] When Q(t) is close to β3, the prediction model issues a high-level warning to prompt relevant personnel to remove the commodity from the shelves;

[0113] It should be noted that using threshold processing as the warning module of the supply chain management system can perform different levels of handling (such as commodity warehouse transfer, changing to a fast logistics channel, increasing the promotion intensity, etc.);

[0114] S3. Randomly select goods for shelf life detection, compare the prediction results of the dynamic shelf life prediction model with the detection results of the randomly selected goods' shelf life to obtain the model prediction error, update the warning range of approaching expiration of the goods according to the model prediction error, display each update result in a visual manner, and transmit it to the supply chain management system to achieve accurate warning of approaching expiration of goods in the supply chain management system;

[0115] Furthermore, the model prediction error is achieved by minimizing the objective function as follows:

[0116]

[0117] where Q rs (t) is the quality status of the shelf life of the randomly selected goods at time t, and Θ represents the internal model parameters of each factor function f i ;

[0118] It should be noted that if the model error is 0, it means that the dynamic shelf life prediction model is consistent with the actual shelf life of the goods. Otherwise, it means that the result of the dynamic shelf life prediction model is not ideal, and it is necessary to recheck the value of Q(t) in the jump compensation mechanism and correspondingly modify the warning division of threshold processing;

[0119] Specifically, the Q(t) update results of each model error and the classification warning information are respectively displayed in the form of curves and charts, and data intercommunication is carried out with the business end of the supply chain management system or the enterprise resource planning system (ERP) through the external RESTful API or other enterprise bus interfaces. At the same time, in the cloud database, in addition to recording the values of each difference equation, it is also necessary to save the change records of Q(t) for each batch of goods and the jump information of all events in real time, providing a basis for future goods analysis or responsibility tracing of each link.

[0120] Embodiment 2

[0121] Refer to Figure 2 and Figure 3 , which is the second embodiment of the present invention. This embodiment provides a method for warning of approaching expiration of goods based on a supply chain management system, including: comparing the solution of the present invention with the traditional solution through experimental methods to verify the beneficial effects of the solution of the present invention, and taking a small supply chain management system as an example for the experiment. The configuration of the experimental environment is as follows:

[0122] The test objects are fresh milk (shelf life of 7 days, storage conditions of 0 - 4°C) and chilled fresh meat (shelf life of 5 days, storage conditions of -2 - 2°C); considering the most common small supply chain management system, which consists of three links, corresponding sensors are deployed in each link, and the supply chain management system is based on the SAP ERP platform and integrates the MySQL database and the Tableau visualization tool; DS18B20 temperature sensors (accuracy of ±0.5°C) and SHT31 humidity sensors (accuracy of ±2%RH) are installed in the production link; AMS CCS811 gas sensors (CO2, VOC monitoring) and Bosch BMA400 vibration sensors (range of ±8g) are deployed in the warehousing link; ST LIS3DH three-axis accelerometers (collision monitoring) and LoRa wireless transmission modules are integrated in the transportation link;

[0123] The comparison solutions are as follows:

[0124] Traditional static model: Linear regression prediction based on historical data (only temperature and humidity as fixed weight factors); Dynamic weight model: Dynamically adjust the weights of environmental factors and introduce a jump compensation mechanism;

[0125] The experimental test process is as follows:

[0126] Data collection and preprocessing, simulating the full processes of production, warehousing (72 hours), and transportation (24 hours) for fresh milk and chilled fresh meat respectively; collecting environmental data every 5 minutes, and eliminating abnormal sensor data through the formula (setting the threshold δ > 15%); missing data is filled by cubic spline interpolation to generate the comprehensive feature vector X(t) of the goods;

[0127] Model training and prediction. The traditional model uses fixed weights (temperature weight 0.6, humidity 0.4), and the prediction formula is: Q(t) = Q0 - k×(T×0.6 + H×0.4), where k is the environmental impact factor; the dynamic model initializes the dynamic weight ω(t) and updates it once per hour; the attenuation function F(X(t), ω(t)) = ∑ i∈{T，H，G，…，N} ω i (t)×f i (X i (t)), where the temperature factor f T adopts the Arrhenius equation, and the humidity factor f H is exponential decay; simulate emergencies during transportation, that is, the cold chain power outage for 2 hours (the temperature rises to 8°C), triggering the jump compensation Q new (t) = Q(t) - ΔQ shock , and after repair, the compensation ΔQ recover = 0.8×ΔQ shock ;

[0128] Error calibration and visualization. Randomly select 10% of the goods for quality inspection, compare the actual shelf life with the predicted value, and take the minimum error of the objective function as the optimization goal; the warning thresholds are set as β1 = 20% (primary), β2 = 40% (intermediate), β1 = 60% (advanced), and the final test results are shown in Table 1;

[0129] Table 1 Comparison table of test data

[0130]

[0131] As can be seen from Table 1, the traditional model cannot adapt to the dynamic environment due to fixed weights. For example, when the temperature rises suddenly during transportation, its prediction deviation reaches 18%, resulting in a warning accuracy rate of only 72%; through dynamic weight adjustment (the temperature weight rises from 0.6 to 0.8) in the present invention, the accuracy rate is increased to 94%. Especially in the cold chain power outage scenario, the jump compensation mechanism improves the error correction efficiency by 3 times (the error rate of the model of the present invention is 4% compared with 18% of the traditional static model), for reference Figure 2, at 100 hours of the goods quality test, the fitting accuracy of the goods quality decay trajectory can be significantly improved by adjusting the dynamic weight, which reflects that the jump compensation mechanism can effectively cope with emergencies; and the traditional model requires manual intervention to judge emergencies, and the response time is up to 4.2 hours; while the dynamic model of the present invention shortens the response time to 0.5 hours through real-time jump compensation, and automatically triggers hierarchical early warnings to avoid large-scale losses of goods; in addition, the traditional model has a misjudgment rate as high as 25% due to ignoring gas concentration (CO2 accelerating spoilage) and vibration accumulation (risk of package damage); while the present invention reduces the misjudgment rate to 5%, and separately, the dynamic weight model combined with random quality inspection feedback (objective function optimization) further reduces the model error rate from 9% to 4%, which is significantly better than the static model. Refer to Figure 3 , in the figure, the error distribution of the traditional model is wide (18±5%), showing a long-tail phenomenon; while the error of the model of the present invention is concentrated in (4±1.5%), and there are no abnormal points, which proves that the jump compensation in the solution of the present invention effectively suppresses the problem of error divergence; the traditional model relies on batch data synchronization (with a delay of 120 seconds) and cannot support real-time decision-making. The present invention compresses the delay to 30 seconds through interpolation prediction and LoRa wireless transmission, meeting the timeliness requirements of fresh food logistics;

[0132] Through the above tests, the significant advantages of the present invention in terms of early warning accuracy and error rate are verified, meeting the refined control requirements of the current goods supply chain.

[0133] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes. The solutions in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0134] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1 one process or multiple processes and / or blocksFigure 1 means for the functions specified in one or more boxes.

[0135] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions specified in one Figure 1 one or more processes and / or boxes Figure 1 or more boxes.

[0136] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one Figure 1 one or more processes and / or boxes Figure 1 or more boxes.

[0137] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0138] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A product expiration warning method based on a supply chain management system, characterized in that: include: Different types of sensors are deployed in the production, warehousing and transportation links of the supply chain to obtain environmental data from each sensor, conduct quality assessment on the environmental data, and obtain cargo information from the supply chain management system. The environmental data that has passed the quality assessment is combined with the cargo information to obtain a comprehensive feature vector of the cargo. Considering the impact of environmental data on the shelf life of goods, dynamic weights are set for the comprehensive feature vectors of the goods, and a dynamic shelf life prediction model is constructed based on the comprehensive feature vectors and dynamic weights of the goods. An event-triggered jump compensation mechanism is introduced into the dynamic shelf life prediction model, and an early warning range of the goods near expiration is set according to the event-triggered jump compensation mechanism. Goods are randomly selected for shelf life testing, and the prediction results of the dynamic shelf life prediction model are compared with the test results of the shelf life of randomly selected goods to obtain the model prediction error. The warning range of the goods approaching expiration is updated according to the model prediction error, and each updated result is displayed in a visual way and passed to the supply chain management system to achieve accurate warning of goods approaching expiration in the supply chain management system.

2. The method for early warning of goods expiration based on a supply chain management system according to claim 1, characterized in that: Obtain environmental data from each sensor and perform quality assessment on the environmental data, including: The quality assessment is expressed by the formula: Among them, v i is the current measurement value v of the i-th sensor; is the average value of the measurements of other sensors in the same area; i It is represented as the threshold δ of the i-th sensor; If the threshold δ does not exceed the thresholds of other sensors in the same area, it means that there is no abnormality in the environmental data collected by the current sensor. Otherwise, it means that there is an abnormality in the environmental data collected by the current sensor. The environmental data collected by other sensors are synchronized through timestamps. If the environmental data collected by the current sensor is missing during the data synchronization process, interpolation prediction is performed based on the data of other sensors in the same area.

3. The method for early warning of goods expiration based on a supply chain management system as claimed in claim 2, characterized in that: At the same time, the cargo information is obtained from the supply chain management system, and the environmental data that has passed the quality assessment is combined with the cargo information to obtain a comprehensive feature vector of the cargo, including: The environmental data collected by the sensor in a normal state is represented as environmental data that has passed quality assessment, and at the same time, cargo information is obtained from a supply chain management system, and the environmental data that has passed quality assessment is combined with the cargo information to obtain a comprehensive feature vector of the cargo.

4. The method for early warning of goods expiration based on a supply chain management system according to claim 2 or 3, characterized in that: Considering the impact of environmental data on the shelf life of goods, dynamic weights are set for the comprehensive feature vectors of the goods, including: Considering that each environmental data has an impact on the shelf life of the goods, and the degree of impact is different, a weight value updated over time is assigned to each environmental data to obtain an assigned weight set.

5. The method for early warning of product expiration based on a supply chain management system as claimed in claim 4, characterized in that: A dynamic shelf life prediction model is constructed based on the comprehensive feature vector and dynamic weight of the goods, including: Get the quality status of the goods at time t, initialize it, set the discrete time step based on hours; Based on the obtained assigned weight set and the comprehensive characteristic vector of the goods, the mass decay process of the goods is obtained through the difference equation; The difference equation Q(t+Δτ) is expressed as: Q(t+Δτ)=Q(t)-Δτ×F(X(t),ω(t)) Among them, Q(t) represents the quality status of the goods at time t, which is initialized to Q(0) = Q0; Δτ represents the discrete time step, in hours; F(X(t), ω(t)) represents the decay function; X(t) is the comprehensive feature vector of the goods, and ω(t) is the assigned weight set; The attenuation function F(X(t),ω(t)) is expressed as: Among them, f i It is represented as the i-th factor function, and N represents the specific environment.

6. The method for early warning of product expiration based on a supply chain management system as claimed in claim 5, characterized in that: Also includes: According to the quality status Q(t) obtained at time t, set the quality safety lower limit Q of the goods low ; When Q(t)≤Q low When , it indicates that the goods have reached the expiration date and are not suitable for transportation. The value of Q(t) is updated and the differential equation Q(t+Δτ) is recalculated. The value of each updated differential equation is recorded, and the decay state of the differential equation corresponding to the mass of the goods is marked.

7. The method for early warning of product expiration based on a supply chain management system as claimed in claim 5, characterized in that: An event-triggered jump compensation mechanism is introduced into the dynamic shelf life prediction model, including: If an emergency is detected, a jump correction is performed: Q new (t)=Q(t)-ΔQ shock Among them, Q new (t) represents the Q(t) value after the jump, ΔQ shock It is expressed as the severity of the emergency; If remedial measures are taken after an emergency occurs, the emergency compensation item is defined: Q new (t)=Q new (t)+ΔQ recover Among them, ΔQ recover expressed as an assessment of the effectiveness of remedial measures; If the emergency is repaired, the Q new (t) value changes. If it does not change, it means that the environment has returned to normal, and Q(t) is updated to the current Q new The value of (t).

8. The method for early warning of product expiration based on a supply chain management system as claimed in claim 7, characterized in that: The warning range of the goods approaching expiration date is set according to the jump compensation mechanism triggered by the event, including: According to the updated value of Q(t), the first threshold, the second threshold and the third threshold are set, each threshold corresponds to a different warning level, and the relationship between the thresholds is expressed as: β1<β2<β3; When Q(t) approaches the first threshold β1, the prediction model issues a primary warning, prompting relevant personnel to pay attention to the current environment of the product; When Q(t) approaches the second threshold β2, the prediction model issues an intermediate warning, prompting relevant personnel to quickly promote the current product; When Q(t) approaches the third threshold β3, the prediction model issues an advanced warning, prompting relevant personnel to remove the product from the shelves.

9. The method for early warning of goods near expiration based on a supply chain management system according to claim 1 or 8, characterized in that: Randomly select goods for shelf life testing, compare the prediction results of the dynamic shelf life prediction model with the test results of the shelf life of randomly selected goods, and obtain the model prediction error, including: The model prediction error is achieved by minimizing the objective function, as follows: Among them, Q rs (t) is the quality status of the shelf life of the goods randomly selected at time t, Θ is represented by the function of each factor f i The internal model parameters.

10. The method for early warning of product expiration based on a supply chain management system according to claim 8, characterized in that: The warning range of the goods near expiration is updated according to the prediction error of the model, and each update result is displayed in a visual manner and transmitted to the supply chain management system to achieve accurate warning of the goods near expiration in the supply chain management system, including: The Q(t) update results of each model error and the graded warning information are displayed in the form of curves and charts, and data is exchanged with the business end of the supply chain management system or the enterprise resource planning system (ERP) through the external RESTful API or other enterprise bus interface. At the same time, the Q(t) change records of each batch of goods and the jump information of all events are saved in real time in the cloud database.

Images