A monitoring and traceability system for the transportation of agricultural product supply chains

Abstract

The present invention discloses a monitoring and traceability system for the transportation of agricultural product supply chains, specifically related to the field of supply chain transportation monitoring and traceability, including: quantitatively evaluating the damage resistance of each type of agricultural product in the supply chain to sliding, impact, and extrusion, training a sound recognition model based on the time-frequency domain characteristics of the labeled audio signals, collecting the cargo information and audio data of each link segment in the transportation route, and uploading them to the monitoring center; classifying and identifying the audio data through the sound recognition model, combining the damage resistance quantitative indicators, and calculating the damage assessment scores of each link segment; visually annotating the damage assessment results, sending abnormal signals to the corresponding link segments, adjusting the transportation density to reduce the damage risk, realizing the precise traceability of the transportation links with abnormal losses, and ensuring that the damage degree of the goods during transportation is controllable.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain transportation monitoring and traceability, and more specifically, the present invention relates to a monitoring and traceability system for the transportation of agricultural product supply chains. Background Art

[0002] During the transportation process of agricultural product supply chains, goods are often subjected to forces such as sliding, impact, and extrusion. These external forces will cause varying degrees of damage to the quality and appearance of agricultural products. Traditional damage monitoring methods rely on manual inspection or visual detection. These methods not only have a large workload, but also are difficult to achieve full-process monitoring, prone to missed inspections and misjudgments. At the same time, it is also impossible to accurately trace the transportation links with frequent sliding, impact, and extrusion damage, resulting in no judgment basis for targeted prevention and optimization of such damage during transportation.

[0003] With the rapid development of the Internet of Things and intelligent sensing technologies, sound signals can become an analysis basis capable of reflecting the external forces acting on goods during transportation. Sound analysis has the characteristics of high flexibility and strong detail recognition ability. Therefore, how to accurately identify different damage types and the transportation sections prone to damage in the transportation link through the analysis of sound signals, and implement a monitoring and traceability system for the transportation of agricultural product supply chains to meet the accurate traceability of the transportation link with abnormal losses and ensure that the damage degree of goods during transportation is controllable is an urgent problem to be solved.

[0004] To solve the above problems, a technical solution is provided as follows. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a monitoring and traceability system for the transportation of agricultural product supply chains to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A monitoring and traceability system for the transportation of agricultural product supply chains includes a damage resistance quantification module, a sound recognition model training module, a data acquisition and upload module, a sound recognition module, a link segment damage assessment module, and a damage traceability module;

[0008] The damage resistance quantification module respectively conducts damage resistance quantification evaluations of sliding, impact, and extrusion for each type of agricultural product category in the supply chain;

[0009] The sound recognition model training module labels the audio signals generated by the contact between the vehicle and the goods, and trains the sound recognition model based on the time-frequency domain characteristics of the sound signals after type labeling;

[0010] The data acquisition and upload module decomposes the supply chain transportation route into link segments, records the agricultural product category, quantity of goods, specifications of transportation vehicles, and the collected audio data of the goods in each link segment with the batch number of the goods as the monitoring dimension, and uploads the data to the transportation link monitoring center;

[0011] The sound recognition module classifies and recognizes the audio data in the transportation link monitoring center through a sound recognition model;

[0012] The link segment damage assessment module calculates the damage assessment score by calculating the frequencies of sliding, impact, and extrusion sounds in the audio slices of each link segment and combining the damage resistance quantization index values corresponding to the agricultural product categories to which the goods belong;

[0013] The damage traceability module visually marks the link segment damage of the transportation route and sends a transportation damage abnormal signal to the specific link segment to adjust the transportation density of the goods.

[0014] Furthermore, the specific steps for quantitatively evaluating the damage resistance of sliding, impact, and extrusion for each agricultural product category in the supply chain are as follows:

[0015] Obtain all agricultural product categories in the agricultural product supply chain. For each product category, select several test samples to form test sample groups A, B, and C, and conduct damage tests based on sliding, impact, and extrusion;

[0016] Select test sample group A, use a sliding friction test instrument to simulate sliding friction during transportation, gradually increase the friction force applied to the test sample until rupture damage appears on the surface of the test sample, and record the friction force reading of the instrument;

[0017] Select test sample group B to conduct a free fall experiment. Drop the test sample freely from different heights onto the surface of a mechanical sensor until rupture damage appears on the surface of the test sample, and record the sensor reading;

[0018] Select test sample group C, use a pressure loading device to gradually apply pressure to simulate the extrusion situation during transportation until rupture damage appears on the surface of the test sample, and record the applied pressure reading;

[0019] Calculate the mean value of the reading records of different test samples in the sliding, impact, and extrusion damage tests for each agricultural product category, perform unitless normalization processing on the mean value and map it to the interval expression of [0,1]. The result is used as the damage resistance quantization index value of sliding, impact, and extrusion for this agricultural product category.

[0020] Furthermore, the specific steps for annotating the sound types of the audio signals generated by the contact between the vehicle and the goods and training the sound recognition model based on the time-frequency domain characteristics of the sound signals after type annotation are as follows:

[0021] Arrange acoustic sensors on the transport vehicle to collect audio data generated by the contact between the vehicle and the goods, and use signal processing algorithms to process the audio data to remove the running noise of the vehicle;

[0022] Intercept the sound segments containing sliding, impact and extrusion sounds in the denoised audio, and perform sound type annotation processing;

[0023] Use the short-time Fourier transform to perform time-frequency domain analysis on the signal, and extract the time-frequency domain characteristics of the sound signals of different types of sound segments. The time-frequency domain characteristics include amplitude, waveform shape, duration, change rate, frequency distribution and frequency peak;

[0024] Establish a sound recognition model during transportation, use the labeled time-frequency domain characteristics of the sound signals as the training data set, train and verify the sound recognition model through machine learning algorithms, and deploy the verified sound recognition model to the transportation link monitoring center.

[0025] Further, decompose the supply chain transportation route into link segments, and record the agricultural product category, quantity of goods, transport vehicle specifications and the collected audio data of the goods in each link segment with the batch number of the goods as the monitoring dimension. Uploading the data to the transportation link monitoring center specifically includes:

[0026] Mark the transportation transfer stations in all transportation routes within the supply chain as link nodes;

[0027] Taking the batch number of the goods as the monitoring dimension, obtain the actual transportation route of each batch of goods, and split the transportation route of the same batch of goods into link segments based on adjacent link nodes;

[0028] When the same batch of goods passes through a specific link segment, record the timestamps of entering and leaving the link segment, as well as the agricultural product category, quantity of goods and transport vehicle specification data of the goods transported in the link segment;

[0029] Real-time collect the audio data generated by the contact between the vehicle and the goods through the acoustic sensors on the transport vehicle, integrate all the data, establish a corresponding relationship with the batch number of the goods, and upload it to the transportation link monitoring center.

[0030] Further, the classification and recognition of the audio data in the transportation link monitoring center by the sound recognition model specifically includes:

[0031] Select the batch number of the goods that need to be monitored for transportation, and obtain the agricultural product category of the goods corresponding to the batch number, the timestamps of entering and leaving each link segment, and the collected complete audio data from the transportation link monitoring center;

[0032] Based on the timestamps of entering and leaving the link segment, divide the audio data into audio slices aligned with the passing time period of the link segment;

[0033] Extract the time-frequency domain features of the audio shards as the input recognition features of the sound recognition model, and select the main classification features corresponding to sliding, impact, and extrusion sounds from the input recognition features.

[0034] Obtain the quantitative index values of the damage resistance corresponding to sliding, impact, and extrusion for the agricultural product category to which the goods being transported belong.

[0035] Based on the quantitative index values of the damage resistance for various types of damage, regulate the classification decision sensitivity of the sound recognition model by controlling the expression of the input recognition features.

[0036] Obtain the final classification recognition output result of the sound recognition model after regulating the classification decision sensitivity, and record the occurrence times of sliding, impact, and extrusion sounds in the audio shards of each link segment.

[0037] Furthermore, regulating the classification decision sensitivity of the sound recognition model by controlling the expression of the input recognition features based on the quantitative index values of the damage resistance for various types of damage specifically includes:

[0038] Set the reference values of the quantitative index of the damage resistance for sliding, impact, and extrusion. If a certain quantitative index of the damage resistance of the agricultural product category to which the goods belong is greater than its corresponding reference value, mark that the goods have high damage resistance to this type of damage; otherwise, mark that the goods have low damage resistance to this type of damage.

[0039] Based on the deviation ratio between the quantitative index values of the damage resistance of the agricultural product category to which the goods belong and the corresponding reference values, perform feature enhancement with an equal deviation ratio on the main classification features of the sound categories corresponding to the damage types with low damage resistance in the input recognition features. At the same time, perform feature dilution with an equal deviation ratio on the main classification features of the sound categories corresponding to the damage types with high damage resistance in the input recognition features.

[0040] Furthermore, calculating the damage assessment score by calculating the frequencies of sliding, impact, and extrusion sounds appearing in the audio shards of each link segment and combining with the quantitative index values of the damage resistance corresponding to the agricultural product category to which the goods belong specifically includes:

[0041] Based on the number of occurrences of sliding, impact, and extrusion sounds in the audio shards of each link segment and the passing time of the link segment, calculate the sound frequency, and combine with the quantitative index values of the damage resistance corresponding to the agricultural product category to which the goods belong. Calculate the damage assessment score through the damage assessment formula, and the damage assessment formula is specifically:

[0042] ;

[0043] In the formula, is the damage assessment score of the link segment, is the damage resistance quantification index value of the i-th type of damage, is the frequency of occurrence of the sound of the i-th type of damage, is the type of damage, and the value range is [1, 3].

[0044] Furthermore, for the visual annotation of link segment damage on the transportation route, sending a transportation damage abnormal signal to a specific link segment for adjusting the transportation density of goods specifically includes:

[0045] Based on the damage assessment score corresponding to each link segment, conduct visual annotation of link segment damage on the transportation route;

[0046] Set an abnormal threshold for the damage assessment score, screen the link segments with damage assessment scores greater than or equal to the abnormal threshold of the damage assessment score, send a transportation damage abnormal signal to the link node corresponding to this segment, and adjust the transportation density of goods at this node during subsequent transportation until the damage assessment score is less than the abnormal threshold of the damage assessment score.

[0047] The technical effects and advantages of a monitoring and traceability system for agricultural product supply chain transportation according to the present invention:

[0048] The transportation link is managed in segments, realizing fine-grained damage monitoring and data tracking, providing real-time feedback for the transportation process of each link segment, and effectively reducing the missed detection of damage caused by insufficient overall evaluation. The sound recognition model is trained with time-frequency domain features, can efficiently distinguish different types of damage sounds, and can flexibly adapt to various noise and interference conditions in the actual transportation environment, improving the classification accuracy and system stability. The data acquisition module monitors based on the batch number of goods, can record the transportation process of different batches of goods in detail, and ensure that the transportation status of each good can be traced back to the source. Through link segment damage assessment and damage traceability module, the system can accurately locate the specific link where the damage occurs, send abnormal signals in real time, guide the adjustment of transportation density, avoid excessive damage, thus ensuring the quality and safety of agricultural products and reducing transportation losses. Description of the Drawings

[0049] Figure 1 is a schematic structural diagram of a monitoring and traceability system for agricultural product supply chain transportation according to the present invention. Detailed Embodiments

[0050] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0051] Embodiment

[0052] Figure 1 There is provided a monitoring and traceability system for the transportation of agricultural product supply chains according to the present invention, including a damage resistance quantification module, a sound recognition model training module, a data collection and upload module, a sound recognition module, a link segment damage assessment module, and a damage traceability module;

[0053] The damage resistance quantification module respectively performs sliding, impact, and extrusion damage resistance quantification evaluations on each type of agricultural product category in the supply chain;

[0054] The sound recognition model training module labels the audio signals generated by the contact between the vehicle and the goods, and trains the sound recognition model based on the time-frequency domain features of the sound signals after type labeling;

[0055] The data collection and upload module decomposes the supply chain transportation route into link segments, records the agricultural product category to which the goods belong, the quantity of goods, the specifications of the transportation vehicle, and the collected audio data in each link segment with the batch number of the goods as the monitoring dimension, and uploads the data to the transportation link monitoring center;

[0056] The sound recognition module classifies and recognizes the audio data of the transportation link monitoring center through the sound recognition model;

[0057] The link segment damage assessment module calculates the damage assessment score by calculating the frequencies of the sliding, impact, and extrusion sounds appearing in the audio slices of each link segment and combining the damage resistance quantification index values corresponding to the agricultural product category to which the goods belong;

[0058] The damage traceability module visually labels the link segment damage of the transportation route and sends a transportation damage abnormal signal to the specific link segment to adjust the transportation density of the goods.

[0059] Respectively perform sliding, impact, and extrusion damage resistance quantification evaluations on each type of agricultural product category in the supply chain.

[0060] Obtain all agricultural product categories in the agricultural product supply chain, select several test samples to form test sample groups A, B, and C, and conduct damage tests based on sliding, impact, and extrusion. According to the characteristics of different agricultural products, at least three different agricultural product categories are respectively selected to ensure that the sample groups cover sufficient physical properties and appearance characteristics. At least three test samples are selected for each agricultural product category to form test sample groups A (sliding), B (impact), and C (extrusion). Each test sample is a representative actual transported good to ensure that the test results have practical application significance.

[0061] Select test sample group A and use a sliding friction test instrument to simulate sliding friction during transportation. During the simulation, the frictional force is gradually increased in increments of 0.5 N. Record the surface changes of the sample each time the frictional force increases until rupture damage appears on the surface of the test sample, and record the frictional force reading of the instrument.

[0062] Select test sample group B for a free fall experiment. Gradually increase the falling height from 0.5 m to 3 m, increasing by 0.5 m each time to ensure different impact forces are simulated. A mechanical sensor is used to measure the impact force of each impact, record the change in the impact force, and record the maximum reading of the impact force when cracks or damage appear on the surface of the test sample.

[0063] Select test sample group C and use a pressure loading device to gradually apply pressure to simulate the extrusion situation during transportation. The pressure loading device starts applying pressure from 0 N and increases by 5 N each time until rupture damage occurs on the surface of the test sample. Record the relationship between the pressure and the surface damage of the sample to ensure that the process of increasing pressure matches the extrusion forces that may be encountered during actual transportation.

[0064] Calculate the mean value of the reading records of different test samples in the sliding, impact, and extrusion damage tests for each type of agricultural product. Perform unitless normalization processing on the mean value and map it to the interval expression of [0,1]. The result is used as the quantitative index value of the sliding, impact, and extrusion damage resistance of this type of agricultural product.

[0065] Perform sound type annotation on the audio signals generated by the contact between the vehicle and the goods, and train a sound recognition model based on the time-frequency domain characteristics of the sound signals after type annotation.

[0066] Install multiple acoustic sensors on the transport vehicle. These sensors should be arranged in areas close to the goods to ensure that the audio signals generated when the goods come into contact with the vehicle can be clearly captured. The installed sensors should have high sensitivity and a wide frequency response range to cover different types of sounds such as sliding, impact, and extrusion. The audio data collected by these sensors usually contains multiple noise sources, and the running noise will affect the accuracy of the sound signal. Therefore, a signal processing algorithm is used to suppress the noise in the collected audio data, removing components unrelated to mechanical noise, engine noise, wind noise, etc. during the operation of the transport vehicle. Specifically, first select the no-load section during transportation for static noise estimation, then extract the spectral characteristics of the noise from these sections, and then subtract the noise spectrum from the spectrum of the original audio through spectral subtraction. After the above processing, the influence of vehicle operation and environmental noise on the audio can be removed, and the audio information related to the contact between the goods can be effectively retained.

[0067] In the denoised audio data, by analyzing the time-domain and frequency-domain characteristics of the audio signal, audio segments containing sliding, impact, and extrusion sounds are intercepted. Each segment needs to be manually or automatically labeled as the corresponding sound type according to the characteristics of the audio. The labeling process can be completed through manual labeling or semi-automatic labeling. When manually labeling, experts need to judge and label the sound type according to the time-frequency characteristics of the audio. For automatic labeling, a preliminary trained classification model can be used for pre-classification of the sounds, and then verified and corrected by experts. The labeled dataset will be used as the training dataset for the sound classification model, providing high-quality labeled samples for subsequent model training.

[0068] The short-time Fourier transform is used to perform time-frequency domain analysis on the signal, and the time-frequency domain characteristics of the sound signals of different types of sound segments are extracted. The time-frequency domain characteristics include amplitude, waveform shape, duration, rate of change, frequency distribution, and frequency peak.

[0069] Using the time-frequency domain characteristics of the labeled sound signals as the training dataset, machine learning algorithms (such as support vector machine (SVM), random forest, convolutional neural network (CNN), etc.) are used to train the sound classification model. Through the training of the model, learn the rules to identify different sound types from the time-frequency domain characteristics and conduct verification. The verification of the model is carried out by comparing with the actual labeled dataset to ensure the accuracy and robustness of the model in practical applications. In the verification stage, the cross-validation method can be used to avoid overfitting and ensure the generalization ability of the model. The verified sound recognition model is deployed to the transportation link monitoring center for real-time monitoring and classification recognition of audio data during the transportation process.

[0070] The supply chain transportation route is decomposed into link segments, and the agricultural product category, quantity of goods, specifications of transportation vehicles, and collected audio data of the goods in each link segment are recorded with the batch number of the goods as the monitoring dimension, and the data is uploaded to the transportation link monitoring center.

[0071] Among all the transportation routes within the supply chain, all transfer stations and transportation nodes are first identified. These nodes include the transfer points where the goods move from one transportation link to another. Each transfer station will be marked as a link node, and these nodes are usually the locations where goods are transferred, changed vehicles, changed ships, or exchanged goods.

[0072] According to the batch number of the goods, the actual transportation route of each batch of goods is tracked and split into multiple link segments according to adjacent link nodes. Each link segment starts from one link node and ends at the next link node, representing a specific stage of the goods during transportation. Each batch of goods is identified by the batch number, and the path of each batch of goods during transportation is tracked in real time to ensure that the information of each link segment can be accurately recorded.

[0073] When the goods pass through each link segment, the system will record the timestamps of the goods entering and leaving the link segment in real time. The recorded timestamp information can accurately reflect the residence time of the goods in each link segment. In addition to the time information, detailed data on the agricultural product category to which the goods transported in this link segment belong, the quantity of goods, and the specifications of the transport vehicle also need to be recorded.

[0074] Real-time collect the audio data generated by the contact between the vehicle and the goods through the acoustic sensor on the transport vehicle, integrate all the data, establish a correspondence with the batch number of the goods, and upload it to the transport link monitoring center.

[0075] Classify and identify the audio data in the transport link monitoring center through the sound recognition model.

[0076] Select the batch number of the goods that need to be monitored for transportation, obtain the agricultural product category to which the goods of this batch belong (for example, fruits, vegetables, grains, etc.), the entry and exit timestamps of each link segment (that is, the time information when the goods enter and exit different link nodes), and the complete audio data collected through the acoustic sensor from the transport link monitoring center. All information is corresponding one by one according to the batch number of the goods to ensure that the obtained data and audio can accurately reflect the transportation process of this batch of goods.

[0077] By aligning the obtained audio data with the entry and exit timestamps of the link segment, the audio data can be divided into multiple time periods, and each time period corresponds to the passing period of the goods through different link segments. Specifically, according to the entry and exit times of the goods in each link segment, the collected complete audio data is divided into multiple audio slices.

[0078] Extract the time-frequency domain features of the audio slice as the input recognition features of the sound recognition model, and select the main classification features corresponding to sliding, impact, and extrusion sounds from the input recognition features.

[0079] Obtain the quantitative index values of the damage resistance of sliding, impact, and extrusion corresponding to the agricultural product category to which the goods for transportation monitoring belong.

[0080] Based on the quantitative index values of the damage resistance of various damages, through controlling the expression of the input recognition features, regulate the classification decision sensitivity of the sound recognition model. Specifically, use the quantitative index values of the damage resistance corresponding to the agricultural product category to enhance or weaken the input features, and indirectly achieve the dynamic regulation of the classification decision sensitivity of the sound recognition model.

[0081] Obtain the final classification recognition output result of the sound recognition model after the regulation of the classification decision sensitivity, and record the occurrence times of the three sounds of sliding, impact, and extrusion in the audio slices of each link segment.

[0082] Based on the damage resistance quantification index values for various types of damage, the sensitivity of the classification decision of the sound recognition model is regulated by controlling the expression of input recognition features.

[0083] Set the benchmark reference values for the quantification indexes of sliding, impact, and extrusion damage resistance (default set to 0.5). If a certain damage resistance quantification index in the agricultural product category to which the goods belong is greater than its corresponding benchmark reference value, mark that the goods have high damage resistance to this type of damage. Otherwise, mark that the goods have low damage resistance to this type of damage. For example, watermelons have high damage resistance to sliding damage and low damage resistance to impact and extrusion damage.

[0084] For the sound classification of low-resistance agricultural products for damage types such as impact, sliding, and extrusion, relatively strict classification rules are adopted, that is, the tolerance is reduced (sensitivity is increased to prevent missed recognition). For the sound classification of high-resistance agricultural products for damage types such as impact, sliding, and extrusion, relatively loose classification rules are adopted, that is, the tolerance is increased (sensitivity is reduced to prevent misrecognition).

[0085] The main features for the classification of sliding damage sounds are frequency distribution, amplitude, and waveform. Because the frequency distribution of sliding sounds is composed of higher frequency components, the amplitude is relatively stable, and the waveform is usually relatively regular, showing a stable repetitive pattern.

[0086] The main features for the classification of impact damage sounds are duration, amplitude, and frequency distribution. Because the duration of impact sounds is short, the impact sound will have a large instantaneous amplitude and the frequency spectrum of the impact sound is usually wide.

[0087] The main features for the classification of extrusion damage sounds are amplitude, duration, and frequency distribution. Because the amplitude of extrusion sounds is large, the duration is long, and it appears as a lower-frequency sound.

[0088] Based on the deviation ratio between the damage resistance quantification indexes of each agricultural product category to which the goods belong and the corresponding benchmark values, the main features of the sound categories corresponding to the damage types with low damage resistance in the input recognition features are enhanced with the same deviation ratio. At the same time, the main features of the sound categories corresponding to the damage types with high damage resistance in the input recognition features are diluted with the same deviation ratio.

[0089] Calculate the frequencies of the occurrences of sliding, impact, and extrusion sounds in the audio slices of each link segment, and combine with the damage resistance quantification index values corresponding to the agricultural product category to which the goods belong to calculate the damage assessment score.

[0090] Calculate the sound frequency based on the number of occurrences of sliding, impact, and extrusion sounds in the audio slices of each link segment and the passing time of the link segment, and combine with the damage resistance quantification index values corresponding to the agricultural product category to which the goods belong. Calculate the damage assessment score through the damage assessment formula. The specific damage assessment formula is:

[0091] ;

[0092] Wherein, is the damage assessment score of link segmentation, is the damage resistance quantification index value of the i-th type of damage, is the sound occurrence frequency of the i-th type of damage, is the type of damage, and the value range is [1, 3].

[0093] Perform visual annotation on the link segmentation damage of the transportation line, and send a transportation damage abnormal signal to the specific link segmentation to adjust the transportation density of the goods.

[0094] During transportation, the damage assessment score of each link segmentation is calculated based on the audio data and damage resistance quantification index obtained in the previous steps. The damage assessment score of each link segmentation reflects the degree of damage suffered by the goods within that segmentation. By corresponding the damage assessment score with the link segmentation, the damage risks of each link segmentation in the transportation line can be intuitively displayed. In the visual annotation, each link segmentation is assigned different colors or marks according to its damage assessment score. Link segments with greater damage are marked in red, and link segments with less damage are marked in green. This step enables managers to quickly identify which link segments in the transportation process have higher damage risks through visual means, facilitating subsequent monitoring and adjustment.

[0095] After completing the visual annotation of the damage assessment score, set an abnormal threshold for the damage assessment score. This abnormal threshold is obtained through multiple iterative fittings of the historical records of actual transportation damage based on regression analysis. When the damage assessment score of a certain link segmentation is greater than or equal to this abnormal threshold, it indicates that there is a relatively high damage risk in that segmentation, and immediate measures need to be taken. By screening the damage assessment scores of all link segments, find those link segments with higher risks, and send the corresponding abnormal signal to the link node corresponding to that segment. After receiving the abnormal signal, the link node will initiate subsequent emergency response mechanisms, including adjusting the transportation density of the goods at that node (calculated from the quantity of goods recorded by the transportation link monitoring center and the specifications of the transportation vehicle) to reduce potential damage to the goods. When the impact and sliding damage have a greater impact, increase the transportation density of the goods; when the extrusion damage has a greater impact, reduce the transportation density of the goods.

[0096] The above formulas are all dimensionless and take their numerical calculations. The formula is obtained by collecting a large amount of data and performing software simulation to obtain a formula closest to the actual situation. The preset parameters and threshold selection in the formula are set by those skilled in the art according to the actual situation.

[0097] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0098] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0099] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0100] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or modules can be in an electrical, mechanical, or other form.

[0101] The module described as a separation component may or may not be physically separated. The component shown as a module may or may not be a physical module. It may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0102] In addition, in each embodiment of this application, each functional module can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0103] If the described function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The aforementioned storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0104] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claimed rights.

[0105] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A monitoring and traceability system for agricultural product supply chain transportation, including a damage resistance quantification module, a sound recognition model training module, a data acquisition and upload module, a sound recognition module, a link segment damage assessment module, and a damage traceability module; The damage resistance quantification module conducts quantitative evaluation of the damage resistance of sliding, impact and extrusion for each agricultural product category in the supply chain; The sound recognition model training module labels the sound type of the audio signal generated by the contact between the vehicle and the cargo, and trains the sound recognition model based on the time-frequency domain characteristics of the sound signal after type labeling; The data collection and upload module decomposes the supply chain transportation route into link segments, uses the batch number of the goods as the monitoring dimension to record the agricultural product category, quantity, transportation vehicle specifications and collected audio data of the goods in each link segment, and uploads the data to the transportation link monitoring center; The sound recognition module classifies and recognizes the audio data of the transport link monitoring center through the sound recognition model; The link segment damage assessment module calculates the damage assessment score by calculating the frequency of sliding, impact, and squeezing sounds in the audio segments of each link segment and combining the damage resistance quantitative index value corresponding to the agricultural product category to which the goods belong. The damage tracing module visually marks the damage of link segments on the transportation route and sends abnormal transportation damage signals to specific link segments to adjust the transportation density of goods.

2. A monitoring and traceability system for agricultural product supply chain transportation according to claim 1, characterized in that: The quantitative evaluation of the damage resistance of sliding, impact and extrusion for each type of agricultural product in the supply chain includes: Obtain all agricultural product categories in the agricultural product supply chain, select several test samples from each product category to form test sample groups A, B, and C, and conduct damage tests based on sliding, impact, and extrusion; Select test sample group A, use a sliding friction tester to simulate the sliding friction during transportation, gradually increase the friction force on the test sample until the test sample surface is cracked and damaged, and record the instrument friction force reading; Select test sample group B to conduct a free fall experiment. Let the test samples fall freely from different heights onto the surface of the mechanical sensor until the surface of the test samples is broken and damaged, and record the sensor readings; Select test sample group C, use a pressure loading device to gradually apply pressure to simulate the squeezing during transportation, until rupture damage appears on the surface of the test sample, and record the loading pressure reading; Calculate the mean of the reading records of different test samples of each agricultural product category in the sliding, impact and extrusion damage tests, normalize the mean to remove the unit and map it to the interval expression of [0,1]. The result is used as the quantitative index value of the sliding, impact and extrusion damage resistance of this agricultural product category.

3. A monitoring and traceability system for agricultural product supply chain transportation according to claim 2, characterized in that: The audio signal generated by the contact between the vehicle and the cargo is labeled with the sound type, and the sound recognition model is trained based on the time-frequency domain characteristics of the sound signal after type labeling. Specifically, the following steps are performed: Acoustic sensors are placed on transport vehicles to collect audio data generated by the contact between the vehicle and the cargo. The audio data is processed using signal processing algorithms to remove the operating noise of the vehicle. Extract the sound clips containing sliding, impact and squeezing sounds from the denoised audio, and label the sound types; Short-time Fourier transform is used to analyze the signal in the time and frequency domain to extract the time and frequency domain features of the sound signals of different types of sound clips. The time and frequency domain features include amplitude, waveform shape, duration, change rate, frequency distribution and frequency peak value. A sound recognition model for the transportation process is established. The labeled time-frequency domain features of the sound signal are used as the training data set. The sound recognition model is trained and verified through a machine learning algorithm. The verified sound recognition model is deployed to the transportation link monitoring center.

4. A monitoring and traceability system for agricultural product supply chain transportation according to claim 3, characterized in that: Decompose the supply chain transportation route into link segments, use the batch number of the goods as the monitoring dimension to record the agricultural product category, cargo quantity, transportation vehicle specifications and collected audio data of the goods in each link segment, and upload the data to the transportation link monitoring center. Specifically include: Mark the transport transfer stations in all transport routes in the supply chain as link nodes; Taking the batch number of goods as the monitoring dimension, the actual transportation route of each batch of goods is obtained, and the transportation route of the same batch of goods is split into link segments based on adjacent link nodes; When the same batch of goods passes through a specific link segment, the timestamps of entering and leaving the link segment, as well as the agricultural product category, quantity and transport vehicle specifications of the goods transported in the link segment are recorded; The acoustic sensors on the transport vehicle collect the audio data generated by the contact between the vehicle and the goods in real time. After all the data are integrated, a corresponding relationship with the batch number of the goods is established and uploaded to the transport link monitoring center.

5. A monitoring and traceability system for agricultural product supply chain transportation according to claim 4, characterized in that: The audio data of the transport link monitoring center is classified and identified through the sound recognition model, including: Select the batch number of goods that need to be monitored for transportation, and obtain the agricultural product category of the goods corresponding to the batch number, the entry and exit timestamps of each link segment, and the complete audio data collected from the transportation link monitoring center; Dividing the audio data into audio segments aligned with the link segment transit time periods based on the link segment ingress and egress timestamps; Extract the time-frequency domain features of the audio segments as input recognition features of the sound recognition model, and select the main classification features corresponding to the sliding, impacting, and squeezing sounds from the input recognition features; Obtain the sliding, impact, and extrusion damage resistance quantitative index values ​​corresponding to the agricultural product category to which the transport monitored goods belong; Based on the damage resistance quantitative index values ​​of various types of damage, the classification decision sensitivity of the sound recognition model is regulated by controlling the input recognition feature expression; The final classification and recognition output results of the sound recognition model after the classification decision sensitivity adjustment are obtained, and the number of occurrences of the three sounds of sliding, impact, and squeezing in the audio segments of each link segment is recorded.

6. A monitoring and traceability system for agricultural product supply chain transportation according to claim 5, characterized in that: Based on the damage resistance quantitative index values ​​of various types of damage, the classification decision sensitivity of the sound recognition model is regulated by controlling the input recognition feature expression. Specifically, the following are included: Set the benchmark reference values ​​of the quantitative indicators of sliding, impact and extrusion damage resistance. If the quantitative indicator of damage resistance of a certain agricultural product category to which the goods belong is greater than its corresponding benchmark reference value, the goods are marked as having high damage resistance to the damage type. Otherwise, the goods are marked as having low damage resistance to the damage type. Based on the deviation ratio of each damage resistance quantitative indicator of the agricultural product category to which the goods belong and the corresponding benchmark value, the classification main features of the sound category corresponding to the damage type with low damage resistance in the input recognition features are enhanced with equal deviation ratios. At the same time, the classification main features corresponding to the sound category of the damage type with high damage resistance in the input recognition features are diluted with equal deviation ratios.

7. A monitoring and traceability system for agricultural product supply chain transportation according to claim 6, characterized in that: By calculating the frequency of sliding, impact, and squeezing sounds in the audio segments of each link segment, combined with the damage resistance quantitative index value corresponding to the agricultural product category to which the goods belong, the damage assessment score is calculated specifically including: The sound frequency is calculated based on the number of times the sliding, impact, and squeezing sounds appear in the audio segments of each link segment and the travel time of the link segment. The damage assessment score is calculated using the damage assessment formula, combined with the damage resistance quantitative index value corresponding to the agricultural product category to which the goods belong. The damage assessment formula is as follows: ； In the formula, is the damage assessment score of the link segment, is the quantitative index value of damage resistance of the i-th damage, is the frequency of occurrence of the sound of the ith type of damage, is the damage type, and its value range is [1,3].

8. A monitoring and traceability system for agricultural product supply chain transportation according to claim 7, characterized in that: Visually mark the link segment damage of the transportation route and send the transportation damage abnormal signal to the specific link segment to adjust the transportation density of the goods. Specifically include: Based on the damage assessment score corresponding to each link segment, the link segment damage of the transportation line is visually marked; Set a damage assessment score abnormal threshold, filter link segments with damage assessment scores greater than or equal to the damage assessment score abnormal threshold, send a transport damage abnormal signal to the link node corresponding to the segment, and adjust the cargo transport density at the node for subsequent transportation until the damage assessment score is less than the damage assessment score abnormal threshold.

Images