RFID and Internet of Things integrated logistics package tracking method, device and equipment and storage medium

Abstract

The invention relates to the field of logistics, in particular to a logistics package tracking method, device and equipment integrated with RFID and the Internet of Things and a storage medium. The RFID and Internet of Things integrated logistics package tracking method comprises the following steps that an information collection instruction is sent out regularly according to a preset data collection scheme so as to obtain continuously updated logistics transportation data, and the logistics transportation data comprises data information from an RFID electronic tag and a positioning system; the logistics transportation data are decoded and extracted to obtain key information, and the key information comprises an ID code and position information; and pre-constructing a parcel positioning model, and adopting the parcel positioning model to accurately predict the position of the parcel according to the key information. According to the method, the RFID technology and the Internet of Things technology are combined, the position information of the parcel can be continuously updated in the parcel transportation process, further calculation is conducted according to data through the parcel positioning model, and therefore more accurate position information is obtained.

Description

Technical Field

[0001] The present invention relates to the field of logistics, and in particular to a logistics package tracking method, device, equipment and storage medium integrating RFID and the Internet of Things. Background Art

[0002] With the rise of e-commerce and the growth of global trade, the logistics industry is experiencing rapid development. An effective cargo tracking system is essential to improving logistics efficiency, reducing losses and increasing customer satisfaction. The current industry mainly uses a barcode system for logistics tracking, which requires scanning barcodes at close range to obtain package information. The operation is inefficient and the barcodes are easily damaged and cannot be identified. In addition, since barcode scanning can only be performed at outlets, the tracking of package locations is also obviously insufficient. The location of packages during transportation cannot be accurately tracked.

[0003] It can be seen that the existing technology still needs to be improved and enhanced. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the object of the present invention is to provide a logistics package tracking method, device, equipment and storage medium integrating RFID and the Internet of Things, aiming to solve the technical problem of inaccurate location tracking of logistics packages in the prior art.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The first aspect of the present invention provides a logistics package tracking method integrating RFID and the Internet of Things, comprising the following steps: regularly issuing information collection instructions according to a preset data collection scheme to obtain continuously updated logistics transportation data, wherein the logistics transportation data includes data information from RFID electronic tags and a positioning system; decoding and extracting the logistics transportation data to obtain key information, wherein the key information includes an ID code and location information; pre-building a package positioning model, and using the package positioning model to accurately predict the location of the package based on the key information.

[0007] Optionally, in a first implementation method of the first aspect of the present invention, information collection instructions are periodically issued according to a preset plan to obtain continuously updated logistics and transportation data, and the logistics and transportation data include data information from RFID electronic tags and positioning systems. Specifically, the data collection plan is constructed, and the issuance frequency, nodes and types of information collection instructions are set. The types of information collection instructions include RFID electronic tag data acquisition instructions and positioning system data acquisition instructions; RFID electronic tag data acquisition instructions are issued according to the preset issuance frequency and nodes to obtain data information from RFID electronic tags; positioning system data acquisition instructions are issued according to the preset issuance frequency and nodes to obtain data information of the positioning system associated with the package.

[0008] Optionally, in a second implementation method of the first aspect of the present invention, the logistics transportation data is decoded and extracted to obtain key information, and the key information includes ID code and location information, specifically including: decoding the data information from the RFID electronic tag according to the coding rules, and performing data verification and error correction to obtain decoded data, extracting the ID code and the electronic tag reader number information from the decoded data, and the ID code and the electronic tag reader number information are used as the electronic tag reading location information; converting the data information from the positioning system to obtain locator data, and the locator data includes the locator number, the locator location information and the reader number information associated with the locator number; associating the electronic tag reading location information with the locator data to obtain the key information.

[0009] Optionally, in a third implementation method of the first aspect of the present invention, the package positioning model is pre-built and the package positioning model is used to accurately predict the location of the package based on the key information, specifically including: obtaining historical location data of the electronic tag, and preprocessing the historical location data of the electronic tag to obtain a model training set; using a convolutional graph neural network ConvGNN as a basic model, and using the model training set to train the convolutional graph neural network ConvGNN to obtain a package positioning model; and inputting the key information into the package positioning model to predict the precise location of the package.

[0010] Optionally, in a fourth implementation method of the first aspect of the present invention, the convolutional graph neural network ConvGNN is used as a basic model, and a model training set is used to train the convolutional graph neural network ConvGNN to obtain a package positioning model, specifically including: taking the convolutional graph neural network ConvGNN as a basic model, and using a model training set to train the convolutional graph neural network ConvGNN to obtain a preliminary model; setting an automatic iteration scheme, regularly obtaining the latest logistics and transportation data according to the automatic iteration scheme, and integrating the latest logistics and transportation data into the model training set to obtain a first training set; setting a valid time range for the data, removing the logistics and transportation data that does not meet the requirements in the first training set according to the valid time range, to obtain a second training set; using the second training set to train and iterate the preliminary model to obtain a continuously updated package positioning model.

[0011] Optionally, in a fifth implementation method of the first aspect of the present invention, the key information is input into a package positioning model to predict the precise location of the package, specifically comprising: obtaining the key information, and obtaining corresponding first geographic information from a GIS geographic information system based on the locator location information in the key information; preprocessing the first geographic information to obtain second geographic information; inputting the key information and the second geographic information into the package positioning model to predict the precise location of the package; obtaining weather forecast information, using a transportation time prediction model, and estimating the arrival time based on the key information, the precise location and the weather forecast information.

[0012] Optionally, in a sixth implementation method of the first aspect of the present invention, weather forecast information is obtained, and a transportation time prediction model is used to estimate the arrival time based on the key information, the precise location, and the weather forecast information, specifically including: calculating the city where the package is located based on the precise location, and obtaining first weather information related to the city where the package is located; obtaining a pre-established transportation route, calculating the remaining transit cities based on the transportation route and the city where the package is located, and obtaining second weather information based on the remaining transit cities; obtaining historical transportation data, the historical transportation data including historical transportation routes, transit cities, and transportation times, using historical transportation data and historical weather information to train a machine learning model to obtain a transportation time prediction model; inputting the pre-established transportation route, the city where the package is located, the first weather information, and the second weather information into the transportation time prediction model to obtain an estimated arrival time.

[0013] The second aspect of the present invention provides a logistics package tracking device integrating RFID and the Internet of Things, including: a data collection module, which is used to periodically issue information collection instructions according to a preset data collection plan to obtain continuously updated logistics transportation data, and the logistics transportation data includes data information from RFID electronic tags and positioning systems; a data extraction module, which is used to decode and extract the logistics transportation data to obtain key information, and the key information includes ID codes and location information; an accurate prediction module, which is used to pre-build a package positioning model, and use the package positioning model to accurately predict the location of the package according to the key information.

[0014] Optionally, in a first implementation method of the second aspect of the present invention, the data collection module includes: a first construction unit, used to construct a data collection plan, set the issuance frequency, node and type of information collection instructions, the types of information collection instructions include RFID electronic tag data acquisition instructions and positioning system data acquisition instructions; a first collection unit, used to issue RFID electronic tag data acquisition instructions according to a preset issuance frequency and node to obtain data information from the RFID electronic tag; a second collection unit, used to issue a positioning system data acquisition instruction according to a preset issuance frequency and node to obtain data information of the positioning system associated with the package.

[0015] Optionally, in a second implementation method of the second aspect of the present invention, the data extraction module includes: a decoding unit, which is used to decode the data information from the RFID electronic tag according to the coding rules, and perform data verification and error correction to obtain decoded data, and extract the ID code and the reader number information of the electronic tag from the decoded data, and the ID code and the reader number information of the electronic tag are used as the electronic tag reading position information; a conversion unit, which is used to convert the data information from the positioning system to obtain locator data, and the locator data includes the locator number, the locator position information and the reader number information associated with the locator number; an association unit, which is used to associate the electronic tag reading position information with the locator data to obtain the key information.

[0016] Optionally, in a third implementation of the second aspect of the present invention, the precise prediction module includes: a preprocessing submodule, used to obtain the electronic tag historical location data, and preprocess the electronic tag historical location data to obtain a model training set; a construction submodule, used to train the convolutional graph neural network ConvGNN using a model training set based on a convolutional graph neural network ConvGNN to obtain a package positioning model; and a prediction submodule, used to input the key information into the package positioning model to predict the precise location of the package.

[0017] Optionally, in a fourth implementation method of the second aspect of the present invention, the construction submodule includes: a second construction unit, used to take the convolutional graph neural network ConvGNN as a basic model, and use a model training set to train the convolutional graph neural network ConvGNN to obtain a preliminary model; an integration unit, used to set an automatic iteration scheme, regularly obtain the latest logistics and transportation data according to the automatic iteration scheme, and integrate the latest logistics and transportation data into the model training set to obtain a first training set; a removal unit, used to set a valid time range for the data, and remove the logistics and transportation data that does not meet the requirements in the first training set according to the valid time range to obtain a second training set; an iteration unit, used to use the second training set to train and iterate the preliminary model to obtain a continuously updated package positioning model.

[0018] Optionally, in a fifth implementation of the second aspect of the present invention, the prediction submodule includes: an acquisition unit, used to acquire key information, and acquire corresponding first geographic information from a GIS geographic information system according to the locator location information in the key information; a preprocessing unit, used to preprocess the first geographic information to obtain second geographic information; a calculation unit, used to input the key information and the second geographic information into a package positioning model to predict the precise location of the package; an arrival prediction unit, used to acquire weather forecast information, and adopt a transportation time prediction model to predict the arrival time according to the key information, the precise location and the weather forecast information.

[0019] Optionally, in a sixth implementation of the second aspect of the present invention, the arrival prediction unit includes: an acquisition subunit, used to calculate the city where the package is located based on the precise location, and obtain first weather information related to the city where the package is located; a training subunit, used to obtain a pre-established transportation route, calculate the remaining transit cities based on the transportation route and the city where the package is located, and obtain second weather information based on the remaining transit cities; an establishment subunit, used to obtain historical transportation data, the historical transportation data including historical transportation routes, transit cities and transportation time, use historical transportation data and historical weather information to train a machine learning model to obtain a transportation time prediction model; a calculation subunit, used to input the pre-established transportation route, the city where the package is located, the first weather information and the second weather information into the transportation time prediction model to obtain an estimated arrival time.

[0020] A third aspect of the present invention provides a logistics package tracking device integrating RFID and the Internet of Things, comprising a memory and at least one processor, wherein the memory stores computer-readable instructions; the at least one processor calls the computer-readable instructions in the memory to execute the various steps of the logistics package tracking method integrating RFID and the Internet of Things as described above.

[0021] A fourth aspect of the present invention provides a computer-readable storage medium having computer-readable instructions stored thereon, which, when executed by a processor, implement the various steps of the logistics package tracking method integrating RFID and the Internet of Things as described above.

[0022] Beneficial effects: The present invention provides a logistics package tracking method integrated with RFID and the Internet of Things. The logistics package tracking method integrated with RFID and the Internet of Things first obtains continuously updated logistics transportation data by periodically issuing information collection instructions through the system. The logistics transportation data includes data information from RFID electronic tags and positioning systems, ensuring the real-time performance of the data, and using RFID electronic tags to provide data information in batches, which is more efficient and provides more accurate information; then, the logistics transportation data is decoded and extracted to obtain key information, which includes ID code and location information; then, a package positioning model is pre-constructed, and the package positioning model is used to accurately predict the location of the package based on the key information. The present invention can continuously collect package location information during transportation through RFID technology, vehicle-mounted and network point positioning systems, and finally calculate through the package positioning model, so as to accurately locate and track the location of the package in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A first flow chart of a logistics package tracking method integrating RFID and the Internet of Things provided by an embodiment of the present invention;

[0024] Figure 2 A second flow chart of the logistics package tracking method integrating RFID and the Internet of Things provided by an embodiment of the present invention;

[0025] Figure 3 A third flow chart of the logistics package tracking method integrating RFID and the Internet of Things provided by an embodiment of the present invention;

[0026] Figure 4 A fourth flow chart of the logistics package tracking method integrating RFID and the Internet of Things provided by an embodiment of the present invention;

[0027] Figure 5 A fifth flow chart of the logistics package tracking method integrating RFID and the Internet of Things provided by an embodiment of the present invention;

[0028] Figure 6 A sixth flow chart of the logistics package tracking method integrating RFID and the Internet of Things provided by an embodiment of the present invention;

[0029] Figure 7 A seventh flow chart of the logistics package tracking method integrating RFID and the Internet of Things provided by an embodiment of the present invention;

[0030] Figure 8 A schematic diagram of the structure of a logistics package tracking device integrating RFID and the Internet of Things provided in an embodiment of the present invention;

[0031] Fig. 9 Another structural schematic diagram of a logistics package tracking device integrating RFID and the Internet of Things provided by an embodiment of the present invention;

[0032] Fig.10 A schematic diagram of the structure of a logistics package tracking device integrating RFID and the Internet of Things provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The present invention provides a logistics package tracking method, device, equipment and storage medium integrated with RFID and the Internet of Things. The present invention first periodically issues information collection instructions according to a preset data collection scheme to obtain continuously updated logistics transportation data, and the logistics transportation data includes data information from RFID electronic tags and positioning systems; then decodes and extracts the logistics transportation data to obtain key information including ID codes and location information; finally, by adopting a package positioning model, the location of the package is accurately predicted according to the key information. The present invention combines RFID and Internet of Things technologies to improve the convenience and efficiency of logistics data collection, and enables the location of packages to be tracked during automobile transportation, and analyzes and calculates the data in combination with the package positioning model to obtain more accurate location information.

[0034] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] For ease of understanding, the specific process of the embodiment of the present invention is described below. It should be noted that the relevant steps of obtaining user personal information in the present invention are all performed with the user's authorization.

[0036] See also Figure 1 The first embodiment of the logistics package tracking method integrating RFID and the Internet of Things in the embodiment of the present invention includes:

[0037] S101. Periodically issuing information collection instructions according to a preset data collection scheme to obtain continuously updated logistics and transportation data, the logistics and transportation data including data information from RFID electronic tags and positioning systems;

[0038] As an automatic identification technology, RFID technology has the advantages of non-contact, long-distance identification and batch reading compared to traditional barcode systems. When it is combined with Internet of Things technology, it can improve the efficiency of data collection and better track logistics packages.

[0039] Specifically, an RFID reader can be installed on the transport vehicle and associated with the vehicle-mounted locator. During the transportation process, the reader automatically collects the RFID electronic tag data of the package in the vehicle under the information collection instruction, and the positioning system simultaneously collects the location information of the vehicle. These data will be associated and sent to the system together, so that the location information of the package can be obtained in real time during the transportation process. Since RFID technology does not require manual scanning, automatic batch collection of data can be completed even when the vehicle is driving.

[0040] S102. Decode and extract the logistics transportation data to obtain key information, the key information including ID code and location information;

[0041] The decoded RFID data can be integrated with other data in the logistics and transportation management system to form a complete logistics information chain. These data include the ID code, location information, transportation status, etc. of the package, which are crucial for logistics companies. By analyzing these data, companies can understand the bottlenecks and problems in the transportation process, optimize transportation routes and plans, and improve transportation efficiency and service quality. By decoding and extracting key information, the core data in the logistics and transportation process can be quickly located, reducing the need to process a large amount of non-critical data, thereby improving the overall data processing efficiency. The ID code is the unique number of the corresponding package in the RFID system, which is associated with a specific vehicle or transportation node through the ID code, which enables managers to easily track and identify each link in the logistics and transportation process.

[0042] S103. Pre-build a package positioning model, and use the package positioning model to accurately predict the location of the package based on the key information.

[0043] Using the package location model to predict the location of the package can further improve the accuracy of the package location, allowing customers and logistics companies to obtain the location of the package in real time. Specifically, customers can view the transportation status and predicted arrival time of the package in real time through mobile applications or web pages. This transparency reduces customer anxiety and increases trust in logistics companies. In addition, by predicting the location of the package, logistics companies can dispatch transportation vehicles more intelligently to ensure maximum vehicle efficiency and reduce idle driving and waiting time.

[0044] The RFID and Internet of Things integrated logistics package tracking method provided by the present invention realizes real-time tracking of packages during transportation by combining RFID technology and Internet of Things technology, solving the current problem that the package can only be tracked online to the point where it arrives at a network point, but the transportation location cannot be known in real time, allowing customers and enterprises to track the transportation of packages in a timely manner.

[0045] See also Figure 2 The second embodiment of the logistics package tracking method integrating RFID and the Internet of Things in the embodiment of the present invention includes:

[0046] S201. Build a data collection program, set the frequency, node and type of information collection instructions, the types of information collection instructions include RFID electronic tag data acquisition instructions and positioning system data acquisition instructions;

[0047] Specifically, different frequencies can be set for different types of packages. For example, for high-value items, a higher data acquisition frequency can be set, such as obtaining data every minute or every five minutes, to ensure real-time tracking and monitoring. For low-value items, a lower data acquisition frequency can be set, such as obtaining data once an hour or a day, to reduce system burden and energy consumption. In addition, it can also be set to obtain data after the transport vehicle arrives at a network point, transfer station or special geographical location (node). For example, when the package arrives at an important location or passes through a sensitive area, the company can obtain and process relevant information in a timely manner to ensure the safe delivery of the package.

[0048] When building a data collection plan, you need to set the frequency, nodes, and types of information collection instructions according to actual needs, and take corresponding measures to ensure data security, accuracy, and system stability.

[0049] S202. Issue an RFID electronic tag data acquisition instruction according to a preset frequency and node to obtain data information from the RFID electronic tag;

[0050] S203. Issue a positioning system data acquisition instruction according to the preset issuance frequency and node to obtain data information of the positioning system associated with the package.

[0051] By setting high-frequency data acquisition instructions, real-time tracking and monitoring of packages can be achieved. Real-time data can help companies promptly discover and deal with problems such as package delays, loss or errors, improve operational efficiency and customer satisfaction. The data provided by the positioning system can help companies understand the real-time location and status of packages, thereby optimizing resource allocation. For example, companies can reasonably dispatch vehicles and personnel based on the location and estimated arrival time of the package, reduce empty driving and waiting time, and reduce costs.

[0052] See also Figure 3 The third embodiment of the logistics package tracking method integrating RFID and the Internet of Things in the embodiment of the present invention includes:

[0053] S301. Decode the data information from the RFID electronic tag according to the coding rules, and perform data verification and error correction to obtain decoded data, extract the ID code and the reader number information of the electronic tag from the decoded data, and use the ID code and the reader number information of the electronic tag as the electronic tag reading position information;

[0054] RFID systems usually use specific coding rules to transmit data. Therefore, after receiving the radio frequency signal sent by the RFID tag, it is first converted into a digital signal, and then the digital signal is decoded according to the known coding rules. Due to the possible noise, interference or signal attenuation during the transmission process, the decoded data may contain errors. Therefore, data verification and error correction are required.

[0055] Verification usually involves checking the integrity of the data, such as using methods such as checksums or cyclic redundancy checks (CRCs). Checksums are implemented by performing a specific operation (such as addition) on each byte in the data and storing the result. The receiver can perform the same operation on the received data and compare the result with the checksum provided by the sender to verify the integrity of the data.

[0056] If there are errors in the data, these errors can be identified and corrected by error correction algorithms such as Hamming codes, convolutional codes, etc. Error correction algorithms usually add additional redundant information to the data so that errors can be detected and corrected at the receiving end.

[0057] S302. Converting the data information from the positioning system to obtain locator data, the locator data including the locator number, the locator position information, and the code reader number information associated with the locator number;

[0058] S303. Associate the electronic tag reading location information with the locator data to obtain the key information.

[0059] By associating the electronic tag reading location information with the locator data, it can be ensured that the real-time data of the locator can be bound to the ID code and the reader number information of the electronic tag. During the package transportation process, the package will undergo multiple transfers, enter multiple outlets for distribution, and be transported by different vehicles. Different outlets and vehicles will have their own locators and readers. Therefore, each time the location information is sent to the system, it is necessary to include the time, ID code, electronic tag reader number, locator number, locator location information and other data to avoid data confusion.

[0060] See also Figure 4 The fourth embodiment of the logistics package tracking method integrating RFID and the Internet of Things in the embodiment of the present invention includes:

[0061] S401. Obtain the historical location data of the electronic tag, and pre-process the historical location data of the electronic tag to obtain a model training set;

[0062] By preprocessing the electronic tag historical location data, the format of the electronic tag historical location data can be unified, and erroneous or duplicate data therein can be removed, so that the data can be recognized by the model.

[0063] S402. Taking the convolutional graph neural network ConvGNN as the basic model, the convolutional graph neural network ConvGNN is trained using the model training set to obtain a package positioning model;

[0064] S403. Input the key information into the package positioning model to predict the precise location of the package.

[0065] ConvGNN significantly reduces the amount of computation in the network through local connections and parameter sharing. Local connections mean that each neural unit is only connected to some neural units in the previous layer, thereby reducing the complexity of the network. Parameter sharing allows the same set of parameters to be reused in different locations, further reducing the amount of computation. These features enable ConvGNN to give results faster when predicting the location of packages, improving the prediction speed.

[0066] Specifically, for example, during transportation, the vehicle will pass through different areas where the signal may be poor, causing the system to be unable to obtain the vehicle location information in a timely manner. For example, when passing through a tunnel, the data cannot be sent in time, or the positioning of the locator is not accurate enough, and there may be certain deviations. For another example, since data collection is carried out at intervals, the transport vehicle is in a state of continuous movement, so the location information viewed may be lagging. The use of the package positioning model can further predict the location of the package based on the existing data, thereby obtaining a more accurate location information.

[0067] See also Figure 5 The fifth embodiment of the logistics package tracking method integrating RFID and the Internet of Things in the embodiment of the present invention includes:

[0068] S501. Taking the convolutional graph neural network ConvGNN as the basic model, the convolutional graph neural network ConvGNN is trained using the model training set to obtain a preliminary model;

[0069] S502. Set an automatic iteration plan, regularly obtain the latest logistics and transportation data according to the automatic iteration plan, and integrate the latest logistics and transportation data into the model training set to obtain a first training set;

[0070] The automatic iteration solution can ensure that the data in the model training set is the latest and most accurate. Logistics and transportation data changes rapidly. Through regular updates, the model can better reflect the actual situation of current logistics and transportation. Regular integration of the latest logistics and transportation data can reduce model prediction errors caused by outdated or biased data. This helps to improve the accuracy of the model's prediction of logistics and transportation status. By regularly adding the latest data to the first training set and ultimately using it for model training, the model can be continuously optimized to promote the intelligent and automated development of the logistics industry.

[0071] S503. Set a valid time range for the data, remove the logistics and transportation data that do not meet the requirements in the first training set according to the valid time range, and obtain a second training set;

[0072] S504. Use the second training set to train and iterate the preliminary model to obtain a continuously updated package positioning model.

[0073] Specifically, for example, the logistics transportation data from one or two years ago can be removed from the first training set. With the continuous advancement of technology and the continuous updating of routes, the data from a few years ago may have been in line with the existing transportation environment and conditions. By removing outdated data, it can ensure that the constructed package positioning model is more in line with today's reality, making the prediction results more accurate.

[0074] Setting up an automatic iteration plan and regularly obtaining the latest logistics and transportation data based on the plan, and then integrating this data into the model training set can significantly improve the accuracy and efficiency of the logistics model, enhance the adaptability of the model, and promote the intelligent development of the logistics industry.

[0075] See also Figure 6 The sixth embodiment of the logistics package tracking method integrating RFID and the Internet of Things in the embodiment of the present invention includes:

[0076] S601. Obtain key information, and obtain corresponding first geographic information from the GIS geographic information system according to the locator location information in the key information;

[0077] In order to increase the accuracy of positioning, the first geographic information can be further introduced, which can reflect the geographic information of the location, such as basic altitude information, air pressure, etc. GIS can use the longitude and latitude and other location information provided by the locator to accurately mark the location of the target object on the map. By continuously obtaining the location information of the locator, GIS can track the movement trajectory of the target object in real time, providing strong support for dynamic monitoring.

[0078] S602. Preprocessing the first geographic information to obtain second geographic information;

[0079] S603. Input the key information and the second geographic information into the package positioning model to predict the precise location of the package;

[0080] S604. Obtain weather forecast information, use a transportation time prediction model, and estimate the arrival time based on the key information, precise location, and weather forecast information.

[0081] GIS can integrate meteorological, geological and other multi-source data, combined with locator location information, to warn and assess potential disaster risks, and calculate the time it takes for vehicles to pass through the area through a transportation time prediction model combined with specific weather conditions, geographic location and vehicle conditions, thereby calculating the estimated arrival time. By comprehensively considering multiple on-site factors, a more accurate cargo arrival time can be predicted.

[0082] See also Figure 7 The seventh embodiment of the logistics package tracking method integrating RFID and the Internet of Things in the embodiment of the present invention includes:

[0083] S701. Calculate the city where the package is located according to the precise location, and obtain the first weather information related to the city where the package is located;

[0084] S702. Obtain a pre-established transport route, calculate the remaining transit cities based on the transport route and the city where the package is located, and obtain the second weather information based on the remaining transit cities;

[0085] Weather conditions can have a serious impact on the delivery of packages. For example, rainy days, sandstorms, and snowy days can have different effects on the speed of trucks. By obtaining weather information about the city where the package is currently located and the cities it will pass through in the future, the speed of the truck can be better predicted, thereby obtaining a more accurate estimated arrival time for the package.

[0086] S703. Obtain historical transportation data, including historical transportation routes, transit cities and transportation time, and use historical transportation data and historical weather information to train a machine learning model to obtain a transportation time prediction model;

[0087] Preferably, the historical transportation data may also include historical weather data. Weather data is closely related to historical transportation routes, transit cities and transportation time, and is also a key factor affecting transportation time. By training the machine learning model with the above multiple important influencing factors, a transportation time prediction model with better performance can be obtained.

[0088] S704. Input the pre-established transportation route, the city where the package is located, the first weather information and the second weather information into the transportation time estimation model to obtain the estimated arrival time.

[0089] By inputting the package's transportation route, the city where the package is located, the first weather information and the second weather information into the transportation time prediction model, the weather conditions that the package may encounter during transportation can be calculated, and the transportation time can be further calculated, thereby calculating the estimated arrival time. By combining multiple influencing factors for calculation, the data obtained has a higher reference value.

[0090] The above describes the logistics package tracking method integrating RFID and the Internet of Things in the embodiment of the present invention. The following describes the logistics package tracking device integrating RFID and the Internet of Things in the embodiment of the present invention. Figure 8 In one embodiment of the present invention, an embodiment of a logistics package tracking device integrating RFID and the Internet of Things includes:

[0091] The data collection module 10 is used to periodically issue information collection instructions according to a preset data collection plan to obtain continuously updated logistics and transportation data, wherein the logistics and transportation data includes data information from RFID electronic tags and positioning systems;

[0092] A data extraction module 20 is used to decode and extract the logistics transportation data to obtain key information, wherein the key information includes an ID code and location information;

[0093] The accurate prediction module 30 is used to pre-build a package positioning model, and use the package positioning model to accurately predict the location of the package based on the key information.

[0094] See also Fig. 9 In one embodiment of the present invention, an embodiment of a logistics package tracking device integrating RFID and the Internet of Things includes:

[0095] The data collection module 10 is used to periodically issue information collection instructions according to a preset data collection plan to obtain continuously updated logistics and transportation data, wherein the logistics and transportation data includes data information from RFID electronic tags and positioning systems;

[0096] A data extraction module 20 is used to decode and extract the logistics transportation data to obtain key information, wherein the key information includes an ID code and location information;

[0097] The accurate prediction module 30 is used to pre-build a package location model, and use the package location model to accurately predict the location of the package based on the key information;

[0098] In this embodiment, the data collection module 10 includes:

[0099] The first construction unit 11 is used to construct a data collection plan, set the frequency, nodes and types of information collection instructions, and the types of information collection instructions include RFID electronic tag data acquisition instructions and positioning system data acquisition instructions;

[0100] The first collection unit 12 is used to issue an RFID electronic tag data acquisition instruction according to a preset issuance frequency and node to obtain data information from the RFID electronic tag;

[0101] The second collection unit 13 is used to issue a positioning system data acquisition instruction according to a preset issuance frequency and node to obtain data information of the positioning system associated with the package;

[0102] In this embodiment, the data extraction module 20 includes:

[0103] The decoding unit 21 is used to decode the data information from the RFID electronic tag according to the coding rule, and perform data verification and error correction to obtain decoded data, and extract the ID code and the reader number information of the electronic tag from the decoded data, and the ID code and the reader number information of the electronic tag are used as the electronic tag reading position information;

[0104] A conversion unit 22, used for converting data information from the positioning system to obtain locator data, wherein the locator data includes a locator number, locator position information, and a code reader number information associated with the locator number;

[0105] An associating unit 23, used to associate the electronic tag read location information with the locator data to obtain the key information;

[0106] In this embodiment, the accurate prediction module 30 includes:

[0107] A preprocessing submodule 31 is used to obtain the historical location data of the electronic tag and preprocess the historical location data of the electronic tag to obtain a model training set;

[0108] A construction submodule 32 is used to train the convolutional graph neural network ConvGNN using a model training set based on the convolutional graph neural network ConvGNN to obtain a package positioning model;

[0109] A prediction submodule 33, used to input the key information into a package location model to predict the precise location of the package;

[0110] In this embodiment, the construction submodule 32 includes:

[0111] The second construction unit 321 is used to train the convolutional graph neural network ConvGNN using a model training set to obtain a preliminary model by taking the convolutional graph neural network ConvGNN as a basic model;

[0112] An integration unit 322 is used to set an automatic iteration scheme, regularly obtain the latest logistics and transportation data according to the automatic iteration scheme, and integrate the latest logistics and transportation data into the model training set to obtain a first training set;

[0113] A removal unit 323, used to set a valid time range for the data, and remove the logistics transportation data that does not meet the requirements in the first training set according to the valid time range to obtain a second training set;

[0114] An iteration unit 324, configured to train and iterate the preliminary model using the second training set to obtain a continuously updated package location model;

[0115] In this embodiment, the prediction submodule 33 includes:

[0116] The acquisition unit 331 is used to acquire key information and acquire corresponding first geographic information from a GIS geographic information system according to the locator position information in the key information;

[0117] A preprocessing unit 332, configured to preprocess the first geographic information to obtain second geographic information;

[0118] A calculation unit 333 is used to input the key information and the second geographic information into a package positioning model to predict the precise location of the package;

[0119] The arrival prediction unit 334 is used to obtain weather forecast information and use a transportation time prediction model to predict the arrival time based on the key information, the precise location and the weather forecast information;

[0120] In this embodiment, the arrival prediction unit 334 includes:

[0121] An acquisition subunit 3341 is used to calculate the city where the package is located according to the precise location, and acquire first weather information related to the city where the package is located;

[0122] The training subunit 3342 is used to obtain a pre-established transportation route, calculate the remaining passing cities according to the transportation route and the city where the package is located, and obtain the second weather information according to the remaining passing cities;

[0123] Establishing a subunit 3343 for acquiring historical transportation data, wherein the historical transportation data includes historical transportation routes, transit cities and transportation time, and using the historical transportation data and historical weather information to train a machine learning model to obtain a transportation time prediction model;

[0124] The calculation subunit 3344 is used to input the pre-established transportation route, the city where the package is located, the first weather information and the second weather information into the transportation time prediction model to obtain the estimated arrival time.

[0125] The above is a detailed description of the RFID and Internet of Things integrated logistics package tracking device in the embodiment of the present invention from the perspective of modular functional entities. The following is a detailed description of the RFID and Internet of Things integrated logistics package tracking device in the embodiment of the present invention from the perspective of hardware processing.

[0126] The RFID and IoT integrated logistics package tracking device of the present invention combines RFID technology with IoT technology to continuously obtain data information of electronic tags and positioning systems during package transportation, and finally accurately predicts the location of the package based on these data information through a package positioning model, thereby enabling real-time tracking of the package, so that the location tracking of the package is not limited to outlets, and both customers and enterprises can be informed of the delivery progress.

[0127] Fig.10The schematic diagram of the structure of a logistics package tracking device integrated with RFID and the Internet of Things provided in an embodiment of the present invention is shown. The logistics package tracking device 900 integrated with RFID and the Internet of Things may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 910 (for example, one or more processors) and a memory 920, and one or more storage media 930 (for example, one or more mass storage devices) storing application programs 933 or data 932. Among them, the memory 920 and the storage medium 930 may be temporary storage or permanent storage. The program stored in the storage medium 930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the logistics package tracking device 900 integrated with RFID and the Internet of Things. Furthermore, the processor 910 may be configured to communicate with the storage medium 930, and execute a series of instruction operations in the storage medium 930 on the logistics package tracking device 900 integrated with RFID and the Internet of Things, so as to implement the steps of the logistics package tracking method integrated with RFID and the Internet of Things provided in the above-mentioned method embodiments.

[0128] The RFID and IoT integrated logistics package tracking device 900 may also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input and output interfaces 960, and / or one or more operating systems 931, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that Fig.10 The structure of the logistics package tracking device integrated with RFID and the Internet of Things shown does not constitute a limitation of the logistics package tracking device integrated with RFID and the Internet of Things, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0129] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of a logistics package tracking method integrating RFID and the Internet of Things.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the equipment or device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0131] If the integrated unit is implemented in the form of a software functional unit 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 the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0132] It is understandable that those skilled in the art can make equivalent substitutions or changes based on the technical solution and inventive concept of the present invention, and all these changes or substitutions should fall within the protection scope of the claims attached to the present invention.

Claims

1. A logistics package tracking method integrating RFID and the Internet of Things, characterized in that: The steps include: Periodically issue information collection instructions according to a preset data collection plan to obtain continuously updated logistics and transportation data, wherein the logistics and transportation data includes data information from RFID electronic tags and positioning systems; Decoding and extracting the logistics transportation data to obtain key information, wherein the key information includes ID code and location information; A package positioning model is pre-built and used to accurately predict the location of the package based on the key information.

2. The logistics package tracking method integrating RFID and Internet of Things according to claim 1 is characterized in that: The information collection instructions are issued regularly according to the preset plan to obtain continuously updated logistics and transportation data, and the logistics and transportation data includes data information from RFID electronic tags and positioning systems, specifically including: Construct a data collection plan, set the frequency, nodes and types of information collection instructions, and the types of information collection instructions include RFID electronic tag data acquisition instructions and positioning system data acquisition instructions; Sending RFID electronic tag data acquisition instructions according to the preset issuance frequency and node to obtain data information from the RFID electronic tag; The positioning system data acquisition instruction is issued according to the preset issuance frequency and node to obtain the data information of the positioning system associated with the package.

3. The logistics package tracking method integrating RFID and Internet of Things according to claim 1 is characterized in that: The logistics transportation data is decoded and extracted to obtain key information, and the key information includes ID code and location information, specifically including: Decode the data information from the RFID electronic tag according to the coding rules, and perform data verification and error correction to obtain decoded data, extract the ID code and the reader number information of the electronic tag from the decoded data, and use the ID code and the reader number information of the electronic tag as the electronic tag reading position information; Converting data information from a positioning system to obtain locator data, wherein the locator data includes a locator number, locator position information, and a code reader number information associated with the locator number; The electronic tag read location information is associated with the locator data to obtain the key information.

4. The logistics package tracking method integrating RFID and Internet of Things according to claim 1 is characterized in that: The pre-construction of the package positioning model and the use of the package positioning model to accurately predict the location of the package according to the key information specifically include: Acquire historical location data of electronic tags, and preprocess the historical location data of electronic tags to obtain a model training set; Taking a convolutional graph neural network ConvGNN as a basic model, the convolutional graph neural network ConvGNN is trained using a model training set to obtain a package positioning model; The key information is input into the package location model to predict the precise location where the package will be obtained.

5. The logistics package tracking method integrating RFID and Internet of Things according to claim 4 is characterized in that: The convolutional graph neural network ConvGNN is used as a basic model, and a model training set is used to train the convolutional graph neural network ConvGNN to obtain a package positioning model, which specifically includes: Taking the convolutional graph neural network ConvGNN as the basic model, the convolutional graph neural network ConvGNN is trained using a model training set to obtain a preliminary model; An automatic iteration plan is set up, and the latest logistics and transportation data is regularly obtained according to the automatic iteration plan, and the latest logistics and transportation data is integrated into the model training set to obtain the first training set; Setting a valid time range for the data, and removing the logistics and transportation data that does not meet the requirements from the first training set according to the valid time range to obtain a second training set; The preliminary model is trained and iterated using the second training set to obtain a continuously updated package positioning model.

6. The logistics package tracking method integrating RFID and Internet of Things according to claim 4 is characterized in that: The step of inputting the key information into a package positioning model to predict the precise location of the package specifically includes: Acquire key information, and acquire corresponding first geographic information from a GIS geographic information system according to the locator position information in the key information; preprocessing the first geographic information to obtain second geographic information; Inputting the key information and the second geographic information into a package positioning model to predict the precise location of the package; Obtain weather forecast information, use a transportation time prediction model, and estimate the arrival time based on the key information, precise location, and weather forecast information.

7. The logistics package tracking method integrating RFID and Internet of Things according to claim 6 is characterized in that: The obtaining of weather forecast information, using a transportation time prediction model, and estimating the arrival time according to the key information, the precise location, and the weather forecast information specifically includes: Calculate the city where the package is located according to the precise location, and obtain first weather information related to the city where the package is located; Obtain a pre-established transportation route, calculate the remaining transit cities based on the transportation route and the city where the package is located, and obtain the second weather information based on the remaining transit cities; Obtain historical transportation data, wherein the historical transportation data includes historical transportation routes, transit cities, and transportation time, and use the historical transportation data and historical weather information to train a machine learning model to obtain a transportation time prediction model; The pre-established transportation route, the city where the package is located, the first weather information, and the second weather information are input into the transportation time estimation model to obtain the estimated arrival time.

8. A logistics package tracking device integrating RFID and the Internet of Things, characterized in that: include: A data collection module is used to periodically issue information collection instructions according to a preset data collection plan to obtain continuously updated logistics and transportation data, wherein the logistics and transportation data includes data information from RFID electronic tags and positioning systems; A data extraction module, used to decode and extract the logistics transportation data to obtain key information, wherein the key information includes ID code and location information; The accurate prediction module is used to pre-build a package positioning model, and use the package positioning model to accurately predict the location of the package based on the key information.

9. A logistics package tracking device integrating RFID and the Internet of Things, characterized in that: comprising a memory and at least one processor, wherein the memory has computer-readable instructions stored therein; The at least one processor calls the computer-readable instructions in the memory to execute the various steps of the logistics package tracking method integrating RFID and the Internet of Things as described in any one of claims 1-7.

10. A computer-readable storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by the processor, the steps of the logistics package tracking method integrating RFID and the Internet of Things as described in any one of claims 1 to 7 are implemented.

Images