A tobacco logistics monitoring system and method based on the Internet of Things

Abstract

The present invention discloses a tobacco logistics monitoring system and method based on the Internet of Things, which relates to the technical field of intelligent logistics, including judging the state of a package according to the features of a first image, sorting the package according to the state of the package, obtaining location information, matching the optimal route according to the location information, sending a route warning signal according to the first comparison result, transmitting the estimated arrival time and the deliveryman number to the terminal of the terminal warehouse, and evaluating the logistics efficiency according to the detection result. The present invention enables the location and state of the goods to be obtained in real time by real-time tracking of tobacco goods from the warehouse to the transport vehicle, automatically analyzes the state of the package by obtaining the image of the tobacco package and preprocessing it, improves the transportation integrity, sends a route warning signal in time, improves the transportation efficiency, and collects and analyzes a large amount of transportation data to detect and evaluate the delivered packages in proportion, thereby improving customer satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent logistics, and in particular to a tobacco logistics monitoring system and method based on the Internet of Things. Background Art

[0002] In recent years, IoT devices have been increasingly used in logistics monitoring, improving efficiency and reducing operating costs. Machine learning algorithms analyze large amounts of historical data to provide real-time forecasting and decision support. Logistics monitoring is achieving more accurate and efficient management of the cargo transportation process through continuous technological innovation and application.

[0003] At present, a tobacco logistics management platform based on the Internet of Things is disclosed in a Chinese invention patent with publication number CN 118246831 A. The invention provides a new monitoring solution for the environmental conditions of tobacco products during transportation by designing an environmental data acquisition module, and uses a signal conditioning component to realize efficient processing of environmental sensor acquisition signals. It can effectively eliminate noise even in complex interference environments, thereby improving signal clarity and accuracy. However, the relevant technology does not analyze multiple parameters, lacks comprehensiveness of data analysis, and does not plan logistics routes, which easily leads to waste of time and resources. Summary of the invention

[0004] The technical problem solved by the present invention is that the related technology does not analyze various parameters, lacks comprehensiveness of data analysis, and does not plan the logistics path, which easily leads to waste of time and resources.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, a tobacco logistics monitoring method based on the Internet of Things comprises the following steps:

[0006] Step S1, setting a first label of the warehouse, obtaining tobacco in the initial warehouse, setting a second label of the tobacco in the initial warehouse, wherein the first label and the second label recognize each other in a radio frequency non-contact manner;

[0007] Step S2, obtaining a tobacco packaging image, preprocessing the packaging image to obtain a first image, extracting features of the first image, judging the state of the packaging according to the features of the first image, and sorting the packaging according to the state of the packaging;

[0008] Step S3, setting a third tag on the transport vehicle, the third tag and the second tag are identified by radio frequency contactless, the sorted packages are loaded into the transport vehicle, the location information is obtained, and the optimal route is matched according to the location information;

[0009] Step S4, obtaining the position of the transport vehicle, comparing the position of the transport vehicle with the optimal route to obtain a first comparison result, and sending a route warning signal according to the first comparison result;

[0010] Step S5, obtain the transport vehicle speed and the delivery person number, calculate the estimated arrival time based on the transport vehicle speed, transmit the estimated arrival time and the delivery person number to the terminal of the final warehouse, inspect the delivered package according to the first ratio, obtain the inspection result, and evaluate the logistics efficiency based on the inspection result.

[0011] As a preferred solution of the tobacco logistics monitoring method based on the Internet of Things described in the present invention, step S1 includes the following sub-steps:

[0012] Step S11, obtaining a warehouse in the logistics chain, and setting a first label of the warehouse, wherein the first label is composed of a random code and a first feature code, wherein the random code is generated by an encoder, and the feature code is a combination of the longitude and latitude of the warehouse;

[0013] Step S12, obtaining the tobacco in the initial warehouse, setting a second label for the tobacco in the initial warehouse, wherein the second label consists of a random code and a second characteristic code, the random code is generated by an encoder, and the characteristic code consists of the tobacco production year, tobacco production month and tobacco production day, the first label and the second label recognize each other by radio frequency contactless means, and the initial warehouse is indicated as a warehouse for temporarily calling for tobacco.

[0014] As a preferred solution of the tobacco logistics monitoring method based on the Internet of Things described in the present invention, step S2 includes the following sub-steps:

[0015] Step S21, acquiring a tobacco packaging image, and preprocessing the packaging image to obtain a first image, wherein the preprocessing includes filtering and graying;

[0016] Step S22, extracting features of the first image, the features of the first image including surface features and shape features, the surface features including smoothness, wrinkles, depressions, holes, cracks and creases, and the shape features including bulges and flatness;

[0017] Step S23, judging the status of the packages according to the features of the first image, and sorting the packages according to the status of the packages.

[0018] As a preferred solution of the tobacco logistics monitoring method based on the Internet of Things described in the present invention, the judgment logic of the packaging status includes:

[0019] Calling a packaging database, inputting a packaging model, obtaining surface features and shape features corresponding to the packaging model, and combining the surface features and shape features corresponding to the packaging model into a standard feature vector group;

[0020] Acquiring features of the first image including surface features and shape features, and converting the features of the first image including the surface features and the shape features into a current feature vector group;

[0021] Calculate the similarity between the current feature vector group and the standard feature vector group, traverse the similarities, select the similarity with the largest value, obtain the standard feature vector group corresponding to the similarity with the largest value, set the standard feature vector group corresponding to the similarity with the largest value as a packaged state, and the expression of the packaged state is:

[0022] Surface features and morphological characteristics;

[0023] The smooth and flat packages are loaded onto the truck.

[0024] As a preferred solution of the tobacco logistics monitoring method based on the Internet of Things described in the present invention, the calculation expression of the similarity is:

[0025]

[0026] in, is the similarity, is the ratio of the size of the union of the current eigenvector group and the standard eigenvector group, is the current feature vector group, is the standard set of eigenvectors.

[0027] As a preferred solution of the tobacco logistics monitoring method based on the Internet of Things described in the present invention, step S3 includes the following sub-steps:

[0028] Step S61, setting a third tag of the transport vehicle, the third tag consisting of a random code and a third characteristic code, the random code is generated by an encoder, the third characteristic code is the license plate number of the transport vehicle, and the third tag is identified with the second tag by radio frequency contactless identification;

[0029] Step S62, loading the sorted packages into a transport vehicle, and obtaining location information, the location information including the initial warehouse location and the final warehouse location, the final warehouse indicating the destination to which the transport vehicle delivers the tobacco;

[0030] Step S62, matching the optimal route according to the location information.

[0031] As a preferred solution of the tobacco logistics monitoring method based on the Internet of Things described in the present invention, the matching logic of the optimal route includes:

[0032] Step S62, obtaining any route, obtaining traffic parameters based on big data, the traffic parameters including: road width, average daily road traffic volume and ground humidity, calculating the transportation difficulty according to the road width, average daily road traffic volume and ground humidity, the calculation expression of the transportation difficulty is:

[0033]

[0034] in, Due to the difficulty of transportation, is the number of traffic parameters, For the Traffic parameters, For the The coefficients corresponding to the traffic parameters.

[0035] The transport difficulties are traversed, a transport difficulty with the smallest value is selected, a route corresponding to the transport difficulty with the smallest value is obtained, and the route corresponding to the transport difficulty with the smallest value is set as the optimal route.

[0036] As a preferred solution of the tobacco logistics monitoring method based on the Internet of Things described in the present invention, step S4 includes the following sub-steps:

[0037] Step S41, obtaining the position of the transport vehicle, comparing the position of the transport vehicle with the optimal route, and obtaining a first comparison result, wherein the first comparison result is yaw and non-yaw;

[0038] Step S42, when the first comparison result is deviation, sending a line warning signal to the cab of the transport vehicle, until the first comparison result is no deviation, stopping sending the line warning signal.

[0039] As a preferred solution of the tobacco logistics monitoring method based on the Internet of Things described in the present invention, step S5 includes the following sub-steps:

[0040] Step S51, obtaining the transport vehicle speed, the delivery person number and the distance of the optimal route, wherein the delivery person number is a natural number;

[0041] Step S52, calculating the ratio of the distance of the optimal route to the transportation speed, setting the ratio of the distance of the optimal route to the transportation speed as the estimated arrival time, and transmitting the estimated arrival time and the deliveryman number to the terminal of the terminal warehouse;

[0042] Step S53, inspect the delivered packages according to the first ratio, and obtain the inspection result, wherein the inspection result is the damaged quantity, obtain the total quantity of tobacco, calculate the ratio of the damaged quantity to the total quantity of tobacco, set the ratio of the damaged quantity to the total quantity of tobacco as the damage rate, and the calculation expression of the logistics efficiency is: logistics efficiency = 1-damage rate.

[0043] In the second aspect, a tobacco logistics monitoring system based on the Internet of Things includes a collection module, an analysis module, an early warning module and a display module;

[0044] The acquisition module is used to set a first label of the warehouse, a second label of the tobacco in the initial warehouse, and a third label of the transport vehicle, and obtain the tobacco in the initial warehouse, the packaging image of the tobacco, the location information, the speed of the transport vehicle, and the number of the delivery person;

[0045] The analysis module is used to pre-process the packaging image to obtain a first image, extract features of the first image, determine the status of the packaging according to the features of the first image, sort the packaging according to the status of the packaging, match the optimal route according to the position information, compare the position of the transport vehicle with the optimal route to obtain a first comparison result, calculate the estimated arrival time according to the speed of the transport vehicle, detect the delivered packaging according to the first ratio, obtain the detection result, and evaluate the logistics efficiency according to the detection result;

[0046] The warning module is used to send a line warning signal according to the first comparison result;

[0047] The display module is used to display the estimated arrival time, delivery person number and logistics efficiency.

[0048] The beneficial effects of the present invention are as follows: by setting warehouse labels, tobacco labels and transport vehicle labels, real-time tracking of tobacco goods from the warehouse to the transport vehicle is achieved; radio frequency contactless identification technology improves efficient communication between labels, so that the location and status of the goods can be acquired instantly; by acquiring images of tobacco packages and performing preprocessing, the status of the packages is automatically analyzed, and corresponding processing and sorting are performed according to the analysis results, thereby improving transportation safety and integrity; according to the matching of the location information of the transport vehicle and the optimal route, a route warning signal is issued in time so that corrective measures can be taken when the expected route is deviated, thereby improving the timeliness and efficiency of transportation; the delivered packages are detected and evaluated in proportion, thereby improving customer satisfaction; by collecting and analyzing a large amount of transportation data, real-time monitoring and decision support are provided; the use of machine learning algorithms can continuously optimize logistics operations, reduce the possibility of abnormal events, and improve management efficiency and decision-making accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1A basic flow chart of a tobacco logistics monitoring method based on the Internet of Things is provided as an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0051] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a tobacco logistics monitoring method based on the Internet of Things, comprising the following steps:

[0052] Step S1, setting a first label of the warehouse, obtaining tobacco in the initial warehouse, setting a second label of the tobacco in the initial warehouse, wherein the first label and the second label recognize each other in a radio frequency non-contact manner;

[0053] Step S2, obtaining a tobacco packaging image, preprocessing the packaging image to obtain a first image, extracting features of the first image, judging the state of the packaging according to the features of the first image, and sorting the packaging according to the state of the packaging;

[0054] Step S3, setting a third tag on the transport vehicle, the third tag and the second tag are identified by radio frequency contactless, the sorted packages are loaded into the transport vehicle, the location information is obtained, and the optimal route is matched according to the location information;

[0055] Step S4, obtaining the position of the transport vehicle, comparing the position of the transport vehicle with the optimal route to obtain a first comparison result, and sending a route warning signal according to the first comparison result;

[0056] Step S5, obtain the transport vehicle speed and the delivery person number, calculate the estimated arrival time based on the transport vehicle speed, transmit the estimated arrival time and the delivery person number to the terminal of the final warehouse, inspect the delivered package according to the first ratio, obtain the inspection result, and evaluate the logistics efficiency based on the inspection result.

[0057] In this embodiment, preferably, by setting warehouse labels, tobacco labels and transport vehicle labels, real-time tracking of tobacco goods from the warehouse to the transport vehicle is achieved. Radio frequency contactless identification technology improves the efficient communication between labels, so that the location and status of the goods can be obtained in real time. By acquiring the image of the tobacco package and preprocessing it, the status of the package is automatically analyzed, and corresponding processing and sorting are performed according to the analysis results, thereby improving the safety and integrity of transportation. According to the matching of the location information of the transport vehicle and the optimal route, a route warning signal is issued in time to take corrective measures when deviating from the expected route, thereby improving the timeliness and efficiency of transportation, and performing proportional inspection and evaluation of the delivered packages to improve customer satisfaction. By collecting and analyzing a large amount of transportation data, real-time monitoring and decision support are provided. The use of machine learning algorithms can continuously optimize logistics operations, reduce the possibility of abnormal events, and improve management efficiency and decision-making accuracy.

[0058] The step S1 includes the following sub-steps:

[0059] Step S11, obtaining a warehouse in the logistics chain, and setting a first label of the warehouse, wherein the first label is composed of a random code and a first feature code, wherein the random code is generated by an encoder, and the feature code is a combination of the longitude and latitude of the warehouse;

[0060] Step S12, obtaining the tobacco in the initial warehouse, setting a second label for the tobacco in the initial warehouse, wherein the second label consists of a random code and a second characteristic code, the random code is generated by an encoder, and the characteristic code consists of the tobacco production year, tobacco production month and tobacco production day, the first label and the second label recognize each other by radio frequency contactless means, and the initial warehouse is indicated as a warehouse for temporarily calling for tobacco.

[0061] In this embodiment, preferably, by setting warehouse labels, tobacco labels and transport vehicle labels, real-time tracking of tobacco goods from the warehouse to the transport vehicle is achieved, and radio frequency contactless identification technology improves efficient communication between labels, so that the location and status of the goods can be obtained in real time.

[0062] The step S2 includes the following sub-steps:

[0063] Step S21, acquiring a tobacco packaging image, and preprocessing the packaging image to obtain a first image, wherein the preprocessing includes filtering and graying;

[0064] Step S22, extracting features of the first image, the features of the first image including surface features and shape features, the surface features including smoothness, wrinkles, depressions, holes, cracks and creases, and the shape features including bulges and flatness;

[0065] Step S23, judging the status of the packages according to the features of the first image, and sorting the packages according to the status of the packages.

[0066] The judgment logic of the packaging status includes:

[0067] Calling a packaging database, inputting a packaging model, obtaining surface features and shape features corresponding to the packaging model, and combining the surface features and shape features corresponding to the packaging model into a standard feature vector group;

[0068] Acquiring features of the first image including surface features and shape features, and converting the features of the first image including the surface features and the shape features into a current feature vector group;

[0069] Calculate the similarity between the current feature vector group and the standard feature vector group, traverse the similarities, select the similarity with the largest value, obtain the standard feature vector group corresponding to the similarity with the largest value, set the standard feature vector group corresponding to the similarity with the largest value as a packaged state, and the expression of the packaged state is:

[0070] Surface features and morphological characteristics;

[0071] The smooth and flat packages are loaded onto the truck.

[0072] The calculation expression of the similarity is:

[0073]

[0074] in, is the similarity, is the ratio of the size of the union of the current eigenvector group and the standard eigenvector group, is the current feature vector group, is the standard set of eigenvectors.

[0075] Preferably, in this embodiment, the transportation safety and integrity are improved by acquiring images of tobacco packages and performing preprocessing, automatically analyzing the status of the packages, and performing corresponding processing and sorting according to the analysis results.

[0076] The step S3 includes the following sub-steps:

[0077] Step S61, setting a third tag of the transport vehicle, the third tag consisting of a random code and a third characteristic code, the random code is generated by an encoder, the third characteristic code is the license plate number of the transport vehicle, and the third tag is identified with the second tag by radio frequency contactless identification;

[0078] Step S62, loading the sorted packages into a transport vehicle, and obtaining location information, the location information including the initial warehouse location and the final warehouse location, the final warehouse indicating the destination to which the transport vehicle delivers the tobacco;

[0079] Step S62, matching the optimal route according to the location information.

[0080] The matching logic of the optimal route includes:

[0081] Step S62, obtaining any route, obtaining traffic parameters based on big data, the traffic parameters including: road width, average daily road traffic volume and ground humidity, calculating the transportation difficulty according to the road width, average daily road traffic volume and ground humidity, the calculation expression of the transportation difficulty is:

[0082]

[0083] in, Due to the difficulty of transportation, is the number of traffic parameters, For the Traffic parameters, For the The coefficients corresponding to the traffic parameters.

[0084] The transport difficulties are traversed, a transport difficulty with the smallest value is selected, a route corresponding to the transport difficulty with the smallest value is obtained, and the route corresponding to the transport difficulty with the smallest value is set as the optimal route.

[0085] In this embodiment, preferably, the logistics transportation has economic and time benefits according to the matching of the location information of the transport vehicle and the optimal route.

[0086] The step S4 includes the following sub-steps:

[0087] Step S41, obtaining the position of the transport vehicle, comparing the position of the transport vehicle with the optimal route, and obtaining a first comparison result, wherein the first comparison result is yaw and non-yaw;

[0088] Step S42, when the first comparison result is deviation, sending a line warning signal to the cab of the transport vehicle, until the first comparison result is no deviation, stopping sending the line warning signal.

[0089] In this embodiment, it is preferred that a route warning signal is issued in a timely manner so that corrective measures can be taken when the expected route is deviated, thereby improving the timeliness and efficiency of transportation.

[0090] The step S5 includes the following sub-steps:

[0091] Step S51, obtaining the transport vehicle speed, the delivery person number and the distance of the optimal route, wherein the delivery person number is a natural number;

[0092] Step S52, calculating the ratio of the distance of the optimal route to the transportation speed, setting the ratio of the distance of the optimal route to the transportation speed as the estimated arrival time, and transmitting the estimated arrival time and the deliveryman number to the terminal of the terminal warehouse;

[0093] Step S53, inspect the delivered packages according to the first ratio, and obtain the inspection result, wherein the inspection result is the damaged quantity, obtain the total quantity of tobacco, calculate the ratio of the damaged quantity to the total quantity of tobacco, set the ratio of the damaged quantity to the total quantity of tobacco as the damage rate, and the calculation expression of the logistics efficiency is: logistics efficiency = 1-damage rate.

[0094] In this embodiment, it is preferred to perform proportional inspection and evaluation on the delivered packaging to improve customer satisfaction, and provide real-time monitoring and decision support by collecting and analyzing a large amount of transportation data.

[0095] By setting warehouse labels, tobacco labels and transport vehicle labels, real-time tracking of tobacco goods from warehouses to transport vehicles is achieved. Radio frequency contactless identification technology improves the efficient communication between labels, so that the location and status of goods can be obtained instantly. By acquiring images of tobacco packages and preprocessing them, the status of the packages is automatically analyzed, and corresponding processing and sorting are performed based on the analysis results, which improves transportation safety and integrity. According to the location information of the transport vehicle and the matching of the optimal route, route warning signals are issued in time so that corrective measures can be taken when the expected route is deviated, which improves the timeliness and efficiency of transportation. The delivered packages are inspected and evaluated in proportion to improve customer satisfaction. By collecting and analyzing a large amount of transportation data, real-time monitoring and decision support are provided. The use of machine learning algorithms can continuously optimize logistics operations, reduce the possibility of abnormal events, and improve management efficiency and decision-making accuracy.

[0096] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0097] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A tobacco logistics monitoring method based on the Internet of Things, characterized in that: The following steps are involved: Step S1, setting a first label of the warehouse, obtaining tobacco in the initial warehouse, setting a second label of the tobacco in the initial warehouse, wherein the first label and the second label recognize each other in a radio frequency non-contact manner; Step S2, obtaining a tobacco packaging image, preprocessing the packaging image to obtain a first image, extracting features of the first image, judging the state of the packaging according to the features of the first image, and sorting the packaging according to the state of the packaging; Step S3, setting a third tag on the transport vehicle, the third tag and the second tag are identified by radio frequency contactless, the sorted packages are loaded into the transport vehicle, the location information is obtained, and the optimal route is matched according to the location information; Step S4, obtaining the position of the transport vehicle, comparing the position of the transport vehicle with the optimal route to obtain a first comparison result, and sending a route warning signal according to the first comparison result; Step S5, obtain the transport vehicle speed and the delivery person number, calculate the estimated arrival time based on the transport vehicle speed, transmit the estimated arrival time and the delivery person number to the terminal of the final warehouse, inspect the delivered package according to the first ratio, obtain the inspection result, and evaluate the logistics efficiency based on the inspection result.

2. A tobacco logistics monitoring method based on the Internet of Things as claimed in claim 1, characterized in that: The step S1 includes the following sub-steps: Step S11, obtaining a warehouse in the logistics chain, and setting a first label of the warehouse, wherein the first label is composed of a random code and a first feature code, wherein the random code is generated by an encoder, and the feature code is a combination of the longitude and latitude of the warehouse; Step S12, obtaining the tobacco in the initial warehouse, setting a second label for the tobacco in the initial warehouse, wherein the second label consists of a random code and a second characteristic code, the random code is generated by an encoder, and the characteristic code consists of the tobacco production year, tobacco production month and tobacco production day, the first label and the second label recognize each other by radio frequency contactless means, and the initial warehouse is indicated as a warehouse for temporarily calling for tobacco.

3. The tobacco logistics monitoring method based on the Internet of Things according to claim 1, characterized in that: The step S2 includes the following sub-steps: Step S21, acquiring a tobacco packaging image, and preprocessing the packaging image to obtain a first image, wherein the preprocessing includes filtering and graying; Step S22, extracting features of the first image, the features of the first image including surface features and shape features, the surface features including smoothness, wrinkles, depressions, holes, cracks and creases, and the shape features including bulges and flatness; Step S23, judging the status of the packages according to the features of the first image, and sorting the packages according to the status of the packages.

4. A tobacco logistics monitoring method based on the Internet of Things as claimed in claim 3, characterized in that: The judgment logic of the packaging state includes: Calling a packaging database, inputting a packaging model, obtaining surface features and shape features corresponding to the packaging model, and combining the surface features and shape features corresponding to the packaging model into a standard feature vector group; Acquiring features of the first image including surface features and shape features, and converting the features of the first image including the surface features and the shape features into a current feature vector group; Calculate the similarity between the current feature vector group and the standard feature vector group, traverse the similarities, select the similarity with the largest value, obtain the standard feature vector group corresponding to the similarity with the largest value, set the standard feature vector group corresponding to the similarity with the largest value as a packaged state, and the expression of the packaged state is: Surface features and morphological characteristics; The smooth and flat packages are loaded onto the truck.

5. A tobacco logistics monitoring method based on the Internet of Things as claimed in claim 4, characterized in that: The calculation expression of the similarity is: V=1-J(x,y) Among them, V is the similarity, J(x,y) is the ratio of the size of the union of the current feature vector group and the standard feature vector group, x is the current feature vector group, and y is the standard feature vector group.

6. The tobacco logistics monitoring method based on the Internet of Things according to claim 1, characterized in that: The step S3 includes the following sub-steps: Step S61, setting a third tag of the transport vehicle, the third tag consisting of a random code and a third characteristic code, the random code is generated by an encoder, the third characteristic code is the license plate number of the transport vehicle, and the third tag is identified with the second tag by radio frequency contactless identification; Step S62, loading the sorted packages into a transport vehicle, and obtaining location information, the location information including the initial warehouse location and the final warehouse location, the final warehouse indicating the destination to which the transport vehicle delivers the tobacco; Step S62, matching the optimal route according to the location information.

7. A tobacco logistics monitoring method based on the Internet of Things as claimed in claim 6, characterized in that: The matching logic of the optimal line includes: Step S62, obtaining any route, obtaining traffic parameters based on big data, the traffic parameters including: road width, average daily road traffic volume and ground humidity, calculating the transportation difficulty according to the road width, average daily road traffic volume and ground humidity, the calculation expression of the transportation difficulty is: Where m is the transportation difficulty, n is the number of traffic parameters, and n i is the i-th traffic parameter, C i is the coefficient corresponding to the i-th traffic parameter; The transport difficulties are traversed, a transport difficulty with the smallest value is selected, a route corresponding to the transport difficulty with the smallest value is obtained, and the route corresponding to the transport difficulty with the smallest value is set as the optimal route.

8. The tobacco logistics monitoring method based on the Internet of Things according to claim 1, characterized in that: The step S4 includes the following sub-steps: Step S41, obtaining the position of the transport vehicle, comparing the position of the transport vehicle with the optimal route, and obtaining a first comparison result, wherein the first comparison result is yaw and no yaw; Step S42, when the first comparison result is deviation, sending a line warning signal to the cab of the transport vehicle, until the first comparison result is no deviation, stopping sending the line warning signal.

9. The tobacco logistics monitoring method based on the Internet of Things according to claim 1, characterized in that: The step S5 includes the following sub-steps: Step S51, obtaining the transport vehicle speed, the delivery person number and the distance of the optimal route, wherein the delivery person number is a natural number; Step S52, calculating the ratio of the distance of the optimal route to the speed of the transport vehicle, setting the ratio of the distance of the optimal route to the speed of the transport vehicle as the estimated arrival time, and transmitting the estimated arrival time and the delivery person number to the terminal of the terminal warehouse; Step S53, inspect the delivered packages according to the first ratio, and obtain the inspection result, wherein the inspection result is the damaged quantity, obtain the total quantity of tobacco, calculate the ratio of the damaged quantity to the total quantity of tobacco, and set the ratio of the damaged quantity to the total quantity of tobacco as the damage rate. The calculation expression of the logistics efficiency is: logistics efficiency = 1-damage rate.

10. A tobacco logistics monitoring system based on the Internet of Things, characterized in that: It includes acquisition module, analysis module, warning module and display module; The acquisition module is used to set a first label of the warehouse, a second label of the tobacco in the initial warehouse, and a third label of the transport vehicle, and obtain the tobacco in the initial warehouse, the packaging image of the tobacco, the location information, the speed of the transport vehicle, and the number of the delivery person; The analysis module is used to preprocess the packaging image to obtain a first image, extract features of the first image, determine the status of the packaging according to the features of the first image, sort the packaging according to the status of the packaging, match the optimal route according to the position information, compare the position of the transport vehicle with the optimal route to obtain a first comparison result, calculate the estimated arrival time according to the speed of the transport vehicle, detect the delivered packaging according to the first ratio, obtain the detection result, and evaluate the logistics efficiency according to the detection result; The warning module is used to send a line warning signal according to the first comparison result; The display module is used to display the estimated arrival time, delivery person number and logistics efficiency.

Images