IoT-based full-lifecycle traceability digital shelf system

Abstract

The present invention proposes a full-life traceability digital shelf system for the Internet of Things, including: a multi-source heterogeneous sensor group deployed in raw material supply, production equipment, logistics vehicles and smart shelves. The multi-source heterogeneous sensor group includes: a vibration spectrum sensor set on the production equipment to collect equipment vibration waveform data bound to the raw material batch number in real time; a position sensor set on the logistics vehicle to synchronously record the GPS coordinates of the transportation trajectory and the corresponding time and space stamp; a pressure sensor array set on the smart shelf to detect the impact of ... 2 Grid-precision monitoring of product distribution patterns; blockchain causal evidence storage module. This invention utilizes the IoT's full-lifecycle traceability digital shelf system to precisely capture equipment vibration waveforms and link them to raw material batch numbers, enabling rapid tracing of quality issues back to the raw materials, improving production quality control. During logistics, high-precision spatiotemporal positioning and time synchronization accurately record transport trajectories, enabling comprehensive tracing of abnormal events and ensuring transparency of logistics information.

Description

Technical Field

[0001] The present invention relates to the technical field of digital shelf systems, and in particular to a full-lifecycle traceability digital shelf system for the Internet of Things. Background Art

[0002] In today's digital and intelligent business environment, the efficiency and transparency of commodity supply chain management are becoming increasingly critical. The rise of Internet of Things technology has provided new opportunities for optimizing all aspects of the supply chain. However, the current supply chain traceability system still has many limitations.

[0003] In contrast, the patent document with announcement number CN112926703B discloses a method, device, and system for processing product object display information. The system includes: multiple short-range communication tags located at multiple preset positions on a shelf, for storing first information, wherein the first information includes information associated with the short-range communication tag; a product object tag associated with a product object, for being set at a position on the shelf corresponding to the associated product object, wherein the product object tag is provided with a short-range communication card reader, and the first information stored in the short-range communication tag is read by the card reader; a server, for determining the position information of the product object associated with the product object tag on the shelf based on the received first information and pre-stored second information; the second information includes position information related to the short-range communication tag. Through the embodiments of the present application, it is possible to automatically obtain the actual display status of product objects on the shelves of physical stores.

[0004] Based on the aforementioned patent documents and existing technologies, traditional production equipment monitoring methods can often only obtain limited equipment status information, making it difficult to accurately and in real time collect subtle but important characteristics of equipment vibration. Furthermore, they lack effective binding to raw material batch numbers, making it difficult to quickly and accurately trace raw material batches and corresponding production process information when quality issues arise. In warehousing and sales, existing shelving systems can only simply count the number of goods and are unable to monitor their distribution with high precision, making real-time inventory management and accurate estimation difficult. Furthermore, the lack of a hierarchical data display and traceability mechanism for consumers and regulators makes it difficult for consumers to obtain comprehensive and intuitive product information, and regulators are unable to effectively conduct quality control and problem tracing.

[0005] In summary, existing technologies have many shortcomings in the traceability of goods throughout their entire life cycle. There is an urgent need for an IoT full-life cycle traceability digital shelf system that can integrate data from the entire production, logistics, warehousing and sales chain to achieve accurate traceability, reliable evidence storage and intelligent prediction. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to overcome the defects of the existing technology. The present invention proposes a full-life cycle traceability digital shelf system for the Internet of Things.

[0007] To solve the above technical problems, the technical solution adopted by the present invention is: a full-lifecycle traceability digital shelf system for the Internet of Things. The full-lifecycle traceability digital shelf system for the Internet of Things includes:

[0008] A multi-source heterogeneous sensor group is deployed at raw material supply, production equipment, logistics vehicles, and smart shelves. This includes: vibration spectrum sensors on production equipment; acquisition terminals with image recognition and NFC readers on raw material supply to collect equipment vibration waveform data tied to raw material batch numbers; location sensors on logistics vehicles to simultaneously record GPS coordinates and corresponding time and space stamps of transportation trajectories; and pressure sensor arrays on smart shelves to monitor product distribution with a 1cm² grid accuracy.

[0009] The blockchain causal evidence module includes:

[0010] The smart contract trigger unit automatically initiates a cross-chain verification request to a third-party testing agency when the vibration waveform data exceeds the device health threshold;

[0011] The spatiotemporal anchor ledger aligns production vibration data, logistics trajectory coordinates, and shelf pressure data according to the IEEE-1588v2 protocol to generate a joint hash value, which is stored as a time-stamped event chain unit.

[0012] Trusted intelligent hub module, including:

[0013] The virtual inventory reverse engineering unit constructs physical constraint equations based on the gradient changes in shelf pressure distribution and outputs verifiable inventory quantities with zero-knowledge proof.

[0014] The causal enhancement prediction unit uses the LSTM-TCN model to predict demand. When the prediction error exceeds 5%, it reversely activates the holographic tracing module to obtain fault batch data and dynamically updates the model weight parameters through gradient backpropagation.

[0015] Holographic traceability execution engine module, including:

[0016] Edge computing nodes are deployed at smart shelf terminals to perform biometric binding and code scanning operations;

[0017] Hierarchical data reconstruction unit, dynamically assembling event chains based on access rights:

[0018] Consumers can display quality inspection reports and logistics trajectory heat maps;

[0019] Regulatory authority opens up vibration spectrum and temperature and humidity fluctuation coupled analysis views, and calls the space-time anchor ledger to restore the equipment abnormality timeline.

[0020] Preferably, the vibration spectrum sensor adopts a resonance peak detection method to collect vibration waveforms in the frequency range of 10 Hz-5 kHz, and binds it to the raw material batch number through the following formula: ;in, is the batch identification code, is the eigenfrequency matrix, is the time domain vibration waveform function, is the time domain vibration waveform function In the time interval Perform integral operation on is a hash function.

[0021] Preferably, the pressure sensing array is deployed with a 1 cm² grid accuracy, and adjacent sensor nodes are subjected to data fusion using Kalman filtering, and the pressure distribution function is:

[0022] ,in, For the The weight coefficient of each node, is the standard deviation of the Gaussian distribution, is the pressure distribution function, used to describe the plane coordinates The pressure distribution at the position, is the number of sensor nodes, For the The position of each sensor node in the plane coordinate, For the target point The distance difference between the sensors in the X-axis direction, The target point The distance difference between the sensors in the Y-axis direction is measured. The space-time positioning device synchronously records the GPS coordinates and the Beidou satellite timing signal, and the time synchronization error is less than 1ms.

[0023] Preferably, the IEEE-1588v2 protocol is used to align the clocks of each node and establish a space-time coordinate system conversion model. ,in is the drift coefficient, is the base time offset, is the spatial position compensation parameter, is the global time, is the local time, that is, the clock time of each node in the system, is the number of spatial position related parameters.

[0024] Preferably, the virtual inventory reverse calculation unit establishes a physical constraint equation of pressure gradient and inventory quantity, and establishes an integral equation of the time derivative of the shelf height distribution function and the pressure gradient through the physical constraint relationship between the pressure gradient vector and the commodity density, wherein the direction of the pressure gradient is orthogonal to the normal vector of the shelf surface.

[0025] Preferably, a zero-knowledge proof protocol is used to generate verifiable inventory, and the verification process includes checking the equivalence of linear homomorphic commitments between the secret parameter of the inventory and the verification coefficient over the prime field.

[0026] Preferably, the causal enhancement prediction unit includes a hybrid structure of a long short-term memory network and a temporal convolutional layer, wherein the temporal convolutional layer performs weighted sum calculation on the input data through the expansion coefficient and the number of convolution kernels, and triggers backtracking when the mean absolute error between the predicted value and the actual value exceeds 5% of the maximum actual value. The model weight is updated using a gradient descent algorithm with an L1 constraint, where the constraint strength increases linearly with the number of fault batches.

[0027] Preferably, the input of the long short-term memory network is multidimensional data including historical inventory, sales data and time series characteristics, and the information is selectively memorized and forgotten through a gating mechanism to capture long-term dependencies in the data.

[0028] Preferably, when generating a heat map of logistics trajectories for displaying consumer rights, the hierarchical data reconstruction unit adopts a kernel density estimation method to adaptively adjust the bandwidth according to the distribution of logistics trajectory points to intuitively display the density of the logistics trajectory.

[0029] Preferably, when the holographic traceability execution engine module receives a query request from the supervisory authority, in the process of calling the spatiotemporal anchor point account book to restore the equipment abnormality timeline, it combines the quantitative indicators of the equipment vibration spectrum abnormality and the equipment health equation to determine the time point when the equipment abnormality occurs and the remaining service life assessment, and sets reasonable thresholds for key indicators. When sensor data shows abnormalities, the system can immediately issue an early warning signal to remind relevant personnel to handle them in a timely manner;

[0030] According to the data analysis results, based on equipment status data and product quality traceability information.

[0031] Compared with the existing technology, the beneficial effects of the present invention include: through the full-life traceability digital shelf system of the Internet of Things, in the production process, the vibration waveform of the equipment is accurately collected and bound to the batch number of the raw material, so that quality problems can be quickly traced back to the raw materials, thereby improving the level of production quality control; in logistics transportation, high-precision spatiotemporal positioning and time synchronization can accurately record the transportation trajectory, achieve comprehensive traceability of abnormal events, and ensure the transparency of logistics information; during warehousing and sales, the physical constraint equation is combined to calculate the inventory, improve the accuracy of inventory management, accurately predict demand, dynamically update the model weight, and improve the supply chain response speed, forming a complete and reliable product full life cycle traceability system, and comprehensively optimizing product supply chain management. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The disclosure of the present invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of the present invention. In the accompanying drawings, the same reference numerals are used to refer to the same components. Among them:

[0033] Figure 1 The flowchart of the full-lifecycle traceability digital shelf system of the Internet of Things proposed according to one embodiment of the present invention is schematically shown.

[0034] Figure 2 The figure schematically shows a logic decision diagram of a full-lifecycle traceability digital shelf system of the Internet of Things proposed according to one embodiment of the present invention. DETAILED DESCRIPTION

[0035] It is easy to understand that according to the technical solution of the present invention, without changing the essential spirit of the present invention, a person skilled in the art can propose a variety of interchangeable structural modes and implementation modes. Therefore, the following specific embodiments and drawings are only exemplary descriptions of the technical solution of the present invention and should not be regarded as the entire invention or as a limitation or restriction of the technical solution of the present invention.

[0036] According to one embodiment of the present invention, Figure 1-2 The IoT-based full-lifecycle traceability digital shelf system includes:

[0037] A multi-source heterogeneous sensor group is deployed in raw material supply, production equipment, logistics vehicles and smart shelves. Image recognition sensors are used to scan QR codes or barcodes on raw material packaging to obtain the origin, supplier name and unique identification code of the raw materials. Suppliers store the raw material composition analysis report in electronic document form in advance and write it into the NFC tag. The collection terminal obtains the composition data, including the proportion of the main ingredients, through the NFC reader to ensure that the raw material composition information enters the traceability system. With the help of NFC technology, the collection terminal reads the quality inspection report of the raw materials. IoT tracking devices are installed on the raw material transportation. The equipment collects the location information, transportation time and temperature and humidity parameters in the car during transportation in real time. At the same time, the location information is obtained through the Beidou positioning system. The transportation data will be transmitted to the traceability system at regular intervals and integrated with other raw material information.

[0038] The multi-source heterogeneous sensor system includes: vibration spectrum sensors installed on production equipment; acquisition terminals equipped with image recognition and NFC readers for raw material supply, which collect equipment vibration waveform data linked to raw material batch numbers; position sensors installed on logistics vehicles, which simultaneously record the GPS coordinates and corresponding time and space stamps of transportation trajectories; and pressure sensor arrays installed on smart shelves, which monitor the distribution of goods with a 1cm² grid accuracy.

[0039] Vibration spectrum sensors capture equipment vibration signals and convert them into waveform data using built-in algorithms. Logistics vehicles' position sensors utilize high-precision GPS modules, combined with satellite positioning technology, to track vehicle position changes in real time and simultaneously record timestamps to ensure accurate and time-consistent transport trajectory information. The smart shelf's pressure sensing array consists of multiple miniature pressure sensors arranged in a 1cm² grid, capable of meticulously sensing pressure variations at different locations on the shelf. During production, the vibration spectrum sensors are linked to raw material batch numbers to collect data, helping to quickly locate product quality issues caused by production equipment anomalies and trace them back to the corresponding raw material batch, improving production quality control. The simultaneous recording of logistics vehicle location and time provides complete transparency throughout the logistics transportation process, facilitating timely detection of delays and route deviations, and ensuring on-time and accurate delivery of goods. The smart shelf's high-precision pressure sensing array monitors merchandise placement and quantity changes in real time, providing accurate data support for inventory management.

[0040] The vibration spectrum sensor uses the resonance peak detection method to collect vibration waveforms in the frequency range of 10Hz-5kHz and binds them to the raw material batch number using the following formula: ;in, is the batch identification code, is the eigenfrequency matrix, is the time domain vibration waveform function, is the time domain vibration waveform function In the time interval Perform integral operation on is a hash function. The pressure sensing array is deployed with a 1cm² grid accuracy. Adjacent sensor nodes use Kalman filtering for data fusion. The pressure distribution function is:

[0041] ,in, For the The weight coefficient of each node, is the standard deviation of the Gaussian distribution, is the pressure distribution function, used to describe the plane coordinates The pressure distribution at the position, is the number of sensor nodes, For the The position of each sensor node in the plane coordinate, The target point The distance difference between the sensors in the X-axis direction, The target point The distance difference between the sensors in the Y-axis direction is measured. The space-time positioning device synchronously records the GPS coordinates and the Beidou satellite timing signal, and the time synchronization error is less than 1ms.

[0042] The blockchain causal evidence storage module includes: uploading raw material data to the chain, organizing raw material information, encrypting this data using encryption algorithms to ensure data security and integrity, and uploading the encrypted data to the blockchain's time-space anchor ledger through smart contracts;

[0043] Data association and traceability: When generating a joint hash value, raw material data, production vibration data, logistics trajectory coordinates, and shelf pressure data are included in the calculation scope. When full life cycle traceability is required, by accessing the spatiotemporal anchor ledger, data on the entire process of raw materials from supply to production, logistics, and sales can be quickly queried based on the joint hash value, truly realizing one-stop full life cycle query.

[0044] The smart contract trigger unit automatically initiates a cross-chain verification request to a third-party testing agency when the vibration waveform data exceeds the equipment health threshold. The smart contract pre-sets the equipment health threshold, which is determined based on the historical operating data of the equipment. Once the vibration waveform data exceeds the set threshold, the smart contract automatically sends a cross-chain verification request to a certified third-party testing agency through the communication protocol of the blockchain network. The request contains detailed equipment vibration data and related information, and automatically triggers cross-chain verification. It can conduct professional inspection and evaluation of abnormal equipment status in a timely manner to ensure that equipment problems are accurately diagnosed, avoid production interruptions or product quality problems caused by equipment failure, and at the same time, with the help of the credibility of third-party testing agencies, enhance the credibility and authority of the data.

[0045] The spatiotemporal anchor ledger aligns production vibration data, logistics trajectory coordinates, and shelf pressure data according to the IEEE-1588v2 protocol to generate a joint hash value, which is stored as an event chain unit with a time and space stamp.

[0046] Use IEEE-1588v2 protocol to align the clocks of each node and establish a space-time coordinate system conversion model ,in is the drift coefficient, is the base time offset, is the spatial position compensation parameter, is the global time, is the local time, that is, the clock time of each node in the system, is the number of spatial position related parameters.

[0047] Trusted intelligent hub module, including:

[0048] The virtual inventory inference unit constructs physical constraint equations based on the gradient of shelf pressure distribution and outputs verifiable inventory quantities with zero-knowledge proofs. This unit establishes physical constraint equations for pressure gradient and inventory quantities. Using the physical constraint relationship between the pressure gradient vector and product density, it establishes an integral equation for the time derivative of the shelf height distribution function and the pressure gradient, where the direction of the pressure gradient is orthogonal to the shelf surface normal vector. Verifiable inventory quantities are generated using a zero-knowledge proof protocol. The verification process includes a linear homomorphic commitment equivalence test between the secret inventory parameter and the verification coefficient over a prime number field. When constructing the physical constraint equations, the equations can accurately infer inventory based on shelf pressure, improving the efficiency and accuracy of inventory management. While protecting commercial secrets, the zero-knowledge proof protocol ensures the credibility of inventory data, meeting the requirements for inventory data verification in various scenarios.

[0049] The causal enhancement prediction unit uses an LSTM-TCN model for demand forecasting. When the prediction error exceeds 5%, the holographic tracing module is reversely activated to obtain faulty batch data and dynamically update the model weight parameters through gradient backpropagation. The causal enhancement prediction unit comprises a hybrid structure of a long short-term memory network and a temporal convolutional layer. The temporal convolutional layer calculates a weighted sum of the input data using the dilation coefficient and the number of convolution kernels. Backpropagation is triggered when the mean absolute error between the predicted and actual values ​​exceeds 5% of the maximum actual value. Model weights are updated using a gradient descent algorithm with an L1 constraint, where the constraint strength increases linearly with the number of faulty batches. The LSTM-TCN input is multidimensional data containing historical inventory levels, sales data, and time series features. A gating mechanism selectively memorizes and forgets information to capture long-term dependencies in the data. The LSTM-TCN model combines the LSTM network's ability to capture long-term dependencies with the temporal convolutional network's (TCN) ability to efficiently process time series data. During model training, iterative optimization is performed using a large amount of historical data to continuously adjust the model weight parameters. When the prediction error exceeds the set threshold, the reverse tracing mechanism interacts with the holographic tracing module to obtain detailed fault batch data, including equipment parameters and raw material information in the production process. Accurate demand forecasts help companies rationally arrange production and inventory and reduce operating costs. The reverse tracing and dynamic model update mechanism can adjust the model in a timely manner according to actual conditions, improve the accuracy of the prediction, and provide strong support for root cause analysis of the problem.

[0050] Holographic traceability execution engine module, including:

[0051] Edge computing nodes are deployed at smart shelf terminals to perform biometric binding and scanning operations. Edge computing nodes can quickly and accurately identify biometric information and bind it to the product's identification code. The scanning operation uses QR code or RFID recognition technology to ensure fast reading and accurate transmission of product information.

[0052] The hierarchical data reconstruction unit dynamically assembles event chains based on access rights. When generating a heat map of logistics trajectories displayed by consumer rights, the hierarchical data reconstruction unit uses a kernel density estimation method to adaptively adjust the bandwidth according to the distribution of logistics trajectory points to intuitively display the density of logistics trajectories.

[0053] Consumers can display quality inspection reports and logistics trajectory heat maps. When generating the logistics trajectory heat map, a kernel density estimation method analyzes the spatial distribution of logistics trajectory points and automatically adjusts bandwidth parameters to accommodate variations in trajectory density across different regions. For the display of regulatory authority data, professional data analysis tools and a visualization interface are combined to present complex vibration spectra and temperature and humidity fluctuation data in intuitive charts. Quantitative indicators of equipment anomalies are derived through a comprehensive calculation of multiple characteristic parameters of the vibration spectrum.

[0054] The supervisory authority opens the vibration spectrum and temperature and humidity fluctuation coupled analysis view, and calls the spatiotemporal anchor account book to restore the equipment abnormality timeline. When the holographic traceability execution engine module receives the query request of the supervisory authority, it combines the quantitative indicators of the equipment vibration spectrum abnormality with the equipment health equation in the process of calling the spatiotemporal anchor account book to restore the equipment abnormality timeline, determines the time point when the equipment abnormality occurs and the remaining service life assessment, and sets reasonable thresholds for key indicators. When the sensor data is abnormal, the system can immediately issue an early warning signal to remind relevant personnel to deal with it in time;

[0055] According to the data analysis results, based on equipment status data and product quality traceability information.

[0056] The technical scope of the present invention is not limited to the contents of the above description. Those skilled in the art can make various deformations and modifications to the above embodiments without departing from the technical idea of ​​the present invention, and these deformations and modifications should all fall within the protection scope of the present invention.

Claims

1. The full life cycle traceability digital shelf system of the Internet of Things is characterized by: include: A multi-source heterogeneous sensor group is deployed in raw material supply, production equipment, logistics vehicles, and smart shelves. The multi-source heterogeneous sensor group includes: vibration spectrum sensors installed on production equipment; collection terminals with image recognition and NFC readers installed on raw material supply to collect equipment vibration waveform data tied to raw material batch numbers; and location sensors installed on logistics vehicles to synchronously record the GPS coordinates of the transportation trajectory and the corresponding time and space stamps. Smart shelves are equipped with pressure sensor arrays to monitor product distribution with a 1cm² grid accuracy. The blockchain causal evidence module includes: The smart contract trigger unit automatically initiates a cross-chain verification request to a third-party testing agency when the vibration waveform data exceeds the device health threshold; The spatiotemporal anchor ledger aligns production vibration data, logistics trajectory coordinates, and shelf pressure data according to the IEEE-1588v2 protocol to generate a joint hash value, which is stored as an event chain unit with a time and space stamp. Trusted intelligent hub module, including: The virtual inventory reverse engineering unit constructs physical constraint equations based on the gradient change of shelf pressure distribution and outputs verifiable inventory quantities with zero-knowledge proof; The causal enhancement prediction unit uses the LSTM-TCN model to predict demand. When the prediction error exceeds 5%, it reversely activates the holographic tracing module to obtain fault batch data and dynamically updates the model weight parameters through gradient backpropagation. Holographic traceability execution engine module, including: Edge computing nodes are deployed at smart shelf terminals to perform biometric binding and code scanning operations; Hierarchical data reconstruction unit, dynamically assembling event chains based on access rights: Consumers can display quality inspection reports and logistics trajectory heat maps; Regulatory authority opens up vibration spectrum and temperature and humidity fluctuation coupled analysis views, and calls the space-time anchor ledger to restore the equipment abnormality timeline.

2. The full life cycle traceability digital shelf system of the Internet of Things according to claim 1 is characterized in that: The vibration spectrum sensor uses the resonance peak detection method to collect vibration waveforms in the frequency range of 10Hz-5kHz and binds them to the raw material batch number using the following formula: ;in, is the batch identification code, is the eigenfrequency matrix, is the time domain vibration waveform function, is the time domain vibration waveform function In the time interval Perform integral operation on is a hash function.

3. The full life cycle traceability digital shelf system of the Internet of Things according to claim 2 is characterized in that: The pressure sensor array is deployed with a 1cm² grid accuracy. Adjacent sensor nodes use Kalman filtering for data fusion. The pressure distribution function is: ,in, For the The weight coefficient of each node, is the standard deviation of the Gaussian distribution, is the pressure distribution function, used to describe the plane coordinates The pressure distribution at the position, is the number of sensor nodes, For the The position of each sensor node in the plane coordinate, The target point The distance difference between the sensors in the X-axis direction, The target point The distance difference between the sensors in the Y-axis direction is measured. The space-time positioning device synchronously records the GPS coordinates and the Beidou satellite timing signal, and the time synchronization error is less than 1ms.

4. The full life cycle traceability digital shelf system of the Internet of Things according to claim 1 is characterized in that: Use IEEE-1588v2 protocol to align the clocks of each node and establish a space-time coordinate system conversion model ,in is the drift coefficient, is the base time offset, is the spatial position compensation parameter, is the global time, is the local time, that is, the clock time of each node in the system, is the number of spatial position related parameters.

5. The full life cycle traceability digital shelf system of the Internet of Things according to claim 1 is characterized in that: The virtual inventory reverse calculation unit establishes a physical constraint equation between pressure gradient and inventory quantity, and establishes an integral equation between the time derivative of the shelf height distribution function and the pressure gradient through the physical constraint relationship between the pressure gradient vector and the commodity density, wherein the direction of the pressure gradient is orthogonal to the normal vector of the shelf surface.

6. The full life cycle traceability digital shelf system of the Internet of Things according to claim 5 is characterized in that: A zero-knowledge proof protocol is used to generate verifiable inventory. The verification process includes checking the equivalence of the linear homomorphic commitment between the secret parameter of the inventory and the verification coefficient over the prime field.

7. The full life cycle traceability digital shelf system of the Internet of Things according to claim 1 is characterized in that: The causal enhancement prediction unit includes a hybrid structure of a long short-term memory network and a temporal convolutional layer, in which the temporal convolutional layer performs a weighted summation calculation on the input data using the expansion coefficient and the number of convolution kernels. When the mean absolute error between the predicted value and the actual value exceeds 5% of the maximum actual value, backtracking is triggered. The model weight is updated using a gradient descent algorithm with an L1 constraint, where the constraint strength increases linearly with the number of fault batches.

8. The full life cycle traceability digital shelf system of the Internet of Things according to claim 7 is characterized in that: The input of the long short-term memory network is multidimensional data including historical inventory, sales data and time series characteristics. The information is selectively memorized and forgotten through a gating mechanism to capture long-term dependencies in the data.

9. The full life cycle traceability digital shelf system of the Internet of Things according to claim 1 is characterized in that: When generating a logistics trajectory heat map for displaying consumer rights, the hierarchical data reconstruction unit adopts a kernel density estimation method to adaptively adjust the bandwidth according to the distribution of logistics trajectory points to intuitively display the density of the logistics trajectory.

10. The full life cycle traceability digital shelf system of the Internet of Things according to claim 1 is characterized in that: When the holographic traceability execution engine module receives a query request from the supervisory authority, it calls the spatiotemporal anchor point account book to restore the equipment abnormality timeline. It combines the quantitative indicators of the equipment vibration spectrum abnormality with the equipment health equation to determine the time point when the equipment abnormality occurs and the remaining service life assessment, and sets reasonable thresholds for key indicators. When sensor data shows abnormalities, the system can immediately issue an early warning signal to remind relevant personnel to deal with them in a timely manner. According to the data analysis results, based on equipment status data and product quality traceability information.

Images