Logistics supply chain intelligent management method and system based on Internet of Things

Abstract

The invention relates to a logistics supply chain intelligent management method and system based on the Internet of Things, and the method comprises the steps: obtaining the current supply chain information of transportation equipment, and determining a fixed stop position according to a historical supply chain information set and the current supply chain information; determining a stay degree according to the current supply chain information and a fixed stay position; determining a deviation degree according to current driving information in current supply chain information and planned supply route information in the current product transportation information; generating a monitoring frequency according to the stay degree and the deviation degree; and performing product state identification analysis on the monitoring video according to the monitoring frequency, and determining whether the product state is normal or not. The monitoring frequency is adjusted in real time during abnormal parking and yawing, the monitoring flexibility is improved, waste of monitoring resources is avoided, problems can be found in time under abnormal conditions, the quality of transported goods is effectively guaranteed, and the transported goods are prevented from being lost.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to an intelligent management method and system for a logistics supply chain based on the Internet of Things. Background Art

[0002] The Internet of Things uses sensors, RFID tags, GPS positioning and other devices to achieve real-time monitoring and tracking of goods, vehicles, warehouses and other links in the logistics supply chain. These devices can collect data in real time and transmit it to the central processing system through wireless networks, so that managers can keep track of the operating status of the supply chain at any time. Information sharing and collaboration between various nodes in the supply chain are achieved. Existing logistics supply chain intelligent management methods and systems usually monitor the video in the transport compartment in real time during transportation to monitor the status of the goods and detect the deterioration or loss of the goods. However, in the existing logistics supply chain intelligent management system, the frequency of video monitoring and analysis of goods in the transport compartment is usually fixed, which has certain limitations. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention proposes a logistics supply chain intelligent management method and system based on the Internet of Things.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A method for intelligent management of logistics supply chain based on the Internet of Things, the method comprising the following steps:

[0006] Acquire current supply chain information of the transport equipment, the current supply chain information including current driving information and current product transport information, the current driving information including driving track, current location, driving speed and driving direction, the current product transport information including transport equipment information, product information, planned supply route information and transport node information; wherein the transport equipment information includes the transport equipment license plate, transport equipment model and transport personnel information, the product information includes the product model, quantity and appearance, and the transport node information includes the starting point of the transport, the transfer point during the transport and the transport end point;

[0007] Obtain a historical supply chain information set, and determine a fixed stop location based on the historical supply chain information set and current supply chain information;

[0008] determining a stay degree according to the current supply chain information and the fixed stay location;

[0009] Determine the degree of deviation based on the driving track, current location and driving direction in the current driving information and the planned supply route information in the current product transportation information;

[0010] Generate a monitoring frequency according to the residence degree and deviation degree, monitoring frequency = α * deviation degree + β * residence degree + C, wherein α and β are deviation degree weight coefficient and residence degree weight coefficient respectively, C is a constant, and C ≥ 1, and the value of C can be set according to actual conditions; α + β = 1, in general, 1 ≥ α > β ≥ 0, in practical applications, the size of α and β is set according to actual needs, wherein the monitoring frequency can refer to analysis every few minutes;

[0011] Based on the monitoring equipment, the monitoring video inside the transportation equipment compartment is obtained in real time, and the product status recognition and analysis are performed on the monitoring video according to the monitoring frequency to determine whether the product status is normal. When the product status is abnormal, an abnormal prompt information is sent to the management end.

[0012] As a further technical solution of the present invention, the step of obtaining a historical supply chain information set and determining a fixed stop location according to the historical supply chain information set and current supply chain information includes:

[0013] Acquire a historical supply chain information set, and compare the current product transportation information in the current supply chain information with the historical product transportation information in the historical supply chain information set;

[0014] When the similarity between a certain historical product transportation information and the current product transportation information exceeds a preset similarity threshold, the corresponding historical supply chain information is obtained to obtain a subset of the historical supply chain information;

[0015] Obtain historical driving information in a historical supply chain information subset, and determine a fixed stop location based on analysis of the historical driving information in the historical supply chain information subset, wherein the fixed stop location refers to a location where each stop time exceeds a preset time threshold and the number of stops exceeds a preset number of times.

[0016] As a further technical solution of the present invention, the step of determining the degree of stay according to the current supply chain information and the fixed stay location includes:

[0017] Determine a current stop location according to current driving information in the current supply chain information, wherein the current stop location refers to a location where the stay time exceeds a preset stop time threshold;

[0018] Comparing the current stay position with the fixed stay position to determine whether the current stay position is a fixed stay position;

[0019] When the current stay position is a fixed stay position, the current stay state is determined to be a normal stay state. At this time, the stay degree is determined to be W, W≥0, and is usually 0 or 1;

[0020] When the current stop position is not a fixed stop position, the current stop state is determined to be an abnormal stop state. At this time, the stop time of the transportation equipment at the current stop position is obtained in real time, and the stop degree is determined according to the stop time. The stop degree is positively correlated with the stop time, that is, the longer the stop time, the greater the stop degree.

[0021] As a further technical solution of the present invention, the step of determining the deviation degree based on the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information includes:

[0022] The deviation degree is determined according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information; wherein the deviation degree = A*deviation distance + B*deviation angle, A and B are weight coefficients of the deviation distance and the deviation angle respectively, A+B=1, usually, 0<A<B, and the specific size can be set according to the actual situation;

[0023] When the deviation is greater than the preset deviation threshold, the deviation is determined and a deviation prompt instruction is sent to the management end and the display end of the transportation equipment;

[0024] When the deviation is not greater than the preset deviation threshold, it is determined that there is no deviation and no deviation prompt instruction is generated.

[0025] As a further technical solution of the present invention, the step of calculating the deviation angle includes:

[0026] Set the current position of the transport equipment to P v =(x v ,y v ), the driving direction is the vector where dx v anddy v are the components of the direction vector on the x-axis and y-axis respectively;

[0027] The planned supply route consists of a series of planning points P1, P2, ..., P n Composition, by calculating P v To each planning point P i The distance from the current position of the transport equipment P is obtained v The nearest point P min , where P i The value of i in is 1, 2, ..., n;

[0028] Get P min The neighboring points include P min+1 and P min-1 , according to the P minThe formula for calculating the tangent direction vector with its adjacent points is as follows:

[0029]

[0030] or

[0031] Which one to choose depends on P min Which part of the route is it (starting point, end point or intermediate point). min If it is the start or end point of a route and there is no clear subsequent or previous point, you may need to use other methods (such as interpolation or curve fitting) to estimate the tangent direction;

[0032] Calculate the direction of travel of transport equipment and the direction of the tangent line at the nearest point The deviation angle θ between them is calculated as follows:

[0033]

[0034]

[0035] The calculated angle θ is between 0 and π (i.e., 0 and 180 degrees), which refers to the range of the angle. This range is based on the angle measurement method in mathematics, where:

[0036] 0 degrees means that the two direction vectors completely coincide, that is, the transport equipment is traveling along the tangent direction of the planned supply route.

[0037] π (or 180 degrees) means that the two direction vectors are completely opposite, that is, the direction of travel of the transportation equipment is completely opposite to the tangent direction of the planned supply route.

[0038] As a further technical solution of the present invention, the method for calculating the deviation distance is: calculating the straight-line distance between the current position of the transportation equipment and the nearest point on the planned supply route as the deviation distance; the actual driving path of the vehicle can also be considered to calculate the total length of the deviation path as the deviation distance.

[0039] Another object of the present invention is to provide a logistics supply chain intelligent management system based on the Internet of Things, the system comprising:

[0040] An information acquisition module is used to acquire current supply chain information of the transport equipment, wherein the current supply chain information includes current driving information and current product transport information, wherein the current driving information includes driving track, current location, driving speed and driving direction, and the current product transport information includes transport equipment information, product information, planned supply route information and transport node information; wherein the transport equipment information includes the transport equipment license plate, transport equipment model and transport personnel information, the product information includes the product model, quantity and appearance, and the transport node information includes the starting point of the transport, the transfer point during the transport and the transport end point;

[0041] A fixed location determination module is used to obtain a historical supply chain information set and determine a fixed stop location based on the historical supply chain information set and current supply chain information;

[0042] A stay degree generating module, used for determining the stay degree according to the current supply chain information and the fixed stay location;

[0043] A deviation generation module, used to determine the deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information;

[0044] A monitoring frequency determination module, used for generating a monitoring frequency according to the stay degree and the deviation degree, wherein the monitoring frequency = α*deviation degree + β*stay degree + C, wherein α and β are the deviation degree weight coefficient and the stay degree weight coefficient respectively, and C is a constant;

[0045] The product status analysis module is used to obtain the monitoring video in the carriage of the transportation equipment in real time based on the monitoring equipment, and perform product status recognition analysis on the monitoring video according to the monitoring frequency to determine whether the product status is normal.

[0046] As a further technical solution of the present invention, the stay degree generating module includes:

[0047] A current stay position determination unit, configured to determine a current stay position according to current travel information in the current supply chain information, wherein the current stay position refers to a position where a stay time exceeds a preset stay time threshold;

[0048] a stop position comparison unit, used to compare the current stop position with the fixed stop position to determine whether the current stop position is a fixed stop position;

[0049] A normal state determination unit, used for determining that the current stay state is a normal stay state when the current stay position is a fixed stay position, and at this time determining that the stay degree is W;

[0050] The abnormal state determination unit is used to determine that the current stop state is an abnormal stop state when the current stop position is not a fixed stop position. At this time, the stop time of the transportation equipment at the current stop position is obtained in real time, and the stop degree is determined according to the stop time, and the stop degree is positively correlated with the stop time.

[0051] As a further technical solution of the present invention, the deviation generation module includes:

[0052] A deviation calculation unit, used to determine the deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information; wherein the deviation = A*deviation distance+B*deviation angle, A and B are weight coefficients of the deviation distance and the deviation angle respectively;

[0053] A deviation determination unit, used to determine the deviation when the deviation is greater than a preset deviation threshold, and send a deviation prompt instruction to the management terminal and the display terminal of the transportation equipment;

[0054] The non-deviation determination unit is used to determine that the vehicle is not yawed and not generate a yaw prompt instruction when the deviation is not greater than a preset deviation threshold.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides a logistics supply chain intelligent management method based on the Internet of Things, in which a fixed stop position is determined by a historical supply chain information set, and a stop degree is determined according to the current supply chain information and the fixed stop position, so as to realize an in-depth analysis of the parking state of the transportation equipment, and can effectively find out whether it is abnormally parked, and adjust the monitoring frequency according to the change of the stop degree; in the present invention, the deviation degree is determined according to the driving trajectory, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information, so as to realize real-time monitoring and analysis of the driving route of the transportation equipment during driving, and can effectively find out whether it is deviated, and generate a monitoring frequency according to the stop degree and deviation degree, and analyze the monitoring video based on the monitoring frequency. In the present invention, the real-time adjustment of the monitoring frequency is realized based on the stop degree and deviation degree when abnormal parking and deviation occur, which improves the flexibility of monitoring, avoids the waste of monitoring resources, and can timely find problems in abnormal situations, effectively ensure the quality of transported goods, and avoid the loss of transported goods. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of an intelligent management method for logistics supply chain based on the Internet of Things.

[0057] Figure 2 The present invention is a flowchart of the step of determining a fixed stop location in an intelligent management method for a logistics supply chain based on the Internet of Things.

[0058] Figure 3 The figure is a flowchart of the step of determining the dwelling degree in a logistics supply chain intelligent management method based on the Internet of Things.

[0059] Figure 4 A flowchart of the step of generating deviation in a logistics supply chain intelligent management method based on the Internet of Things.

[0060] Figure 5 This is a structural block diagram of a logistics supply chain intelligent management system based on the Internet of Things. DETAILED DESCRIPTION

[0061] The technical solution of this patent is further described in detail below in conjunction with specific implementation methods.

[0062] like Figure 1 As shown, an embodiment of the present invention provides a logistics supply chain intelligent management method based on the Internet of Things, and the method includes the following steps:

[0063] Step S100, obtaining the current supply chain information of the transport equipment, the current supply chain information including the current driving information and the current product transport information, the current driving information including the driving track, current position, driving speed and driving direction, the current product transport information including the transport equipment information, product information, planned supply route information and transport node information; wherein the transport equipment information includes the transport equipment license plate, transport equipment model and transport personnel information, the product information includes the product model, quantity and appearance (including color and shape), and the transport node information includes the starting point of the transport, the transfer point during the transport and the transport end point;

[0064] Step S200: Obtain a historical supply chain information set, and determine a fixed stop location based on the historical supply chain information set and current supply chain information;

[0065] Step S300, determining a stay degree according to the current supply chain information and the fixed stay location, where the stay degree may also be a stay abnormality degree;

[0066] Step S400, determining a degree of deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information;

[0067] Step S500, generating a monitoring frequency according to the residence degree and the deviation degree, monitoring frequency = α * deviation degree + β * residence degree + C, wherein α and β are the deviation degree weight coefficient and the residence degree weight coefficient respectively, C is a constant, and C ≥ 1, and the value of C can be set according to the actual situation; α + β = 1, in general, 1 ≥ α > β ≥ 0, in practical applications, the size of α and β is set according to actual needs, wherein the monitoring frequency can refer to analysis every few minutes;

[0068] Step S600: acquiring the monitoring video in the carriage of the transport equipment in real time based on the monitoring device, performing product status recognition and analysis on the monitoring video according to the monitoring frequency, determining whether the product status is normal, and sending abnormal prompt information to the management end when the product status is abnormal;

[0069] The step of performing product status recognition and analysis on the monitoring video according to the monitoring frequency is specifically as follows: according to the monitoring frequency, a deep learning model (such as YOLO, SSD, Faster R-CNN, etc.) is used to perform product status recognition and analysis on the monitoring video, and the status recognition and analysis includes position and posture analysis, damage detection, and abnormal behavior detection: wherein, position and posture analysis: judging whether the product is in the predetermined position and whether the posture is correct (such as whether the stacking is stable and without tilt), so as to judge whether there is position and posture abnormality. Damage detection: by comparing the appearance changes of the product in consecutive frames, possible damage or deformation is identified, so as to judge whether there is damage abnormality. Abnormal behavior detection: monitoring whether there are abnormal behaviors such as illegal entry of personnel and illegal movement of products in the carriage, so as to judge whether there is behavior abnormality. When at least one of position and posture abnormality, damage abnormality, and behavior abnormality occurs, the product status is judged to be abnormal. When none of position and posture abnormality, damage abnormality, and behavior abnormality occurs, the product status is judged to be normal.

[0070] In this embodiment, the present invention determines a fixed stop position through a historical supply chain information set, determines a stop degree based on the current supply chain information and the fixed stop position, and implements an in-depth analysis of the parking status of the transportation equipment, can effectively detect whether it is abnormal parking, and adjusts the monitoring frequency according to the change of the stop degree; the present invention determines the deviation degree based on the driving trajectory, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information, and implements real-time monitoring and analysis of the driving route of the transportation equipment during driving, and can effectively detect whether it is yawed, generates a monitoring frequency based on the stop degree and deviation, and analyzes the monitoring video based on the monitoring frequency. In the present invention, based on the stop degree and deviation, real-time adjustment of the monitoring frequency is implemented in the event of abnormal parking and yaw, which improves the flexibility of monitoring, avoids the waste of monitoring resources, and can timely discover problems in abnormal situations, effectively ensuring the quality of transported goods and avoiding the loss of transported goods.

[0071] See also Figure 2 As a preferred embodiment of the present invention, the step of obtaining a historical supply chain information set and determining a fixed stop location according to the historical supply chain information set and current supply chain information includes:

[0072] Step S201, obtaining a historical supply chain information set, and comparing the current product transportation information in the current supply chain information with the historical product transportation information in the historical supply chain information set;

[0073] Step S202: when the similarity between a certain historical product transportation information and the current product transportation information exceeds a preset similarity threshold, the corresponding historical supply chain information is obtained to obtain a subset of the historical supply chain information;

[0074] Among them, the similarity is composed of the weighted sum of transportation equipment similarity, product similarity, supply route similarity and transportation node similarity, similarity = a*transportation equipment similarity + b*product similarity + c*supply route similarity + d*transportation node similarity; a, b, c and d are weight coefficients of transportation equipment similarity, product similarity, supply route similarity and transportation node similarity respectively, a+b+c+d=1, and a, b, c and d are all greater than or equal to 0, and the specific size is set according to actual needs, among which, the calculation rule of transportation equipment similarity can be: respectively determine whether the transportation equipment license plate, transportation equipment model and transportation personnel information are the same, and assign values ​​according to whether they are the same. The size of the assigned value can be set according to the actual situation, and the transportation equipment similarity can be obtained; the calculation rule of product similarity can be: product model similarity: respectively determine the model of the product Whether they are the same, assign values ​​according to whether they are the same, and you can get the product model similarity; product quantity similarity: calculate the ratio between the product quantities of the two, assign values ​​according to the size of the ratio, and you can get the product quantity similarity, product similarity = product model similarity + product quantity similarity; the calculation rule for supply route similarity is: obtain the overlapping part between the supply routes of the two, and determine the supply route similarity according to the proportion of the overlapping part in the planned supply routes in the current supply chain information; the calculation rule for transportation node similarity is: obtain the same nodes of the transportation nodes of the two, and determine the transportation node similarity according to the proportion of the same nodes in the transportation nodes in the current supply chain information; in actual applications, the similarity can also be composed of the weighted sum of the supply route similarity and the transportation node similarity. The preset similarity threshold can be 90%, and the specific size can be adjusted and set according to actual conditions.

[0075] Step S203, obtain historical driving information in the historical supply chain information subset, and determine a fixed stop position based on the analysis of the historical driving information in the historical supply chain information subset. The fixed stop position refers to a position where the stay time each time exceeds a preset time threshold and the number of stays exceeds a preset number of times, the preset number of times is at least 1, and the preset time threshold can generally be 10 minutes, and the specific size can be set according to actual conditions.

[0076] This embodiment fully utilizes historical supply chain information and effectively improves the accuracy of determining fixed stop locations, thereby facilitating subsequent accurate analysis and determination.

[0077] See also Figure 3 As a preferred embodiment of the present invention, the step of determining the degree of stay according to the current supply chain information and the fixed stay location includes:

[0078] Step S301, determining the current stay position according to the current driving information in the current supply chain information, wherein the current stay position refers to a position where the stay time exceeds a preset stay time threshold, wherein the preset stay time threshold may generally be 10 minutes, and the specific value may be set according to the actual situation; when the current stay position does not exist at the current moment, the stay degree is 0;

[0079] Step S302: Compare the current stay position with the fixed stay position to determine whether the current stay position is a fixed stay position;

[0080] Step S303: when the current stay position is a fixed stay position, the current stay state is determined to be a normal stay state, and the stay degree is determined to be W, where W is a fixed value and can be 0 or 1, and usually W≥0;

[0081] Step S304: When the current stop position is not a fixed stop position, the current stop state is determined to be an abnormal stop state. At this time, the stop time of the transportation equipment at the current stop position is obtained in real time, and the stop degree is determined according to the stop time. The stop degree is positively correlated with the stop time, that is, the longer the stop time, the greater the stop degree.

[0082] See also Figure 4 As a preferred embodiment of the present invention, the step of determining the deviation degree based on the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information includes:

[0083] Step S401, determining the degree of deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information; wherein, the degree of deviation = A*deviation distance + B*deviation angle, A and B are weight coefficients of the deviation distance and the deviation angle respectively, A+B=1, usually, 0<A<B, and the specific value can be set according to the actual situation;

[0084] The step of calculating the deviation angle comprises:

[0085] Set the current position of the transport equipment to P v =(x v ,y v ), the driving direction is the vector where dx v anddy v are the components of the direction vector on the x-axis and y-axis respectively;

[0086] The planned route can usually be represented as a series of points or curves. To simplify, we can assume that the planned supply route consists of a series of planning points P1, P2, ..., Pn Composition, by calculating P v To each planning point P i The distance from the current position of the transport equipment P is obtained v The nearest point P min , where P i The value of i in is 1, 2, ..., n;

[0087] The present invention is mainly aimed at planning supply routes in P min The point is smooth (i.e. not a sharp turn), obtain P min The neighboring points include P min+1 and P min-1 , according to the P min The formula for calculating the tangent direction vector with its adjacent points is as follows:

[0088]

[0089] or

[0090] Which one of the above formulas is chosen depends on P min Which part of the route is it (starting point, end point or intermediate point). min If it is the start or end point of a route and there is no clear subsequent or previous point, you may need to use other methods (such as interpolation or curve fitting) to estimate the tangent direction;

[0091] Calculate the direction of travel of transport equipment and the direction of the tangent line at the nearest point The deviation angle θ between them is calculated as follows:

[0092]

[0093]

[0094] The calculated angle θ is between 0 and π (i.e., 0 and 180 degrees), which refers to the range of the angle. This range is based on the angle measurement method in mathematics, where:

[0095] 0 degrees means that the two direction vectors completely coincide, that is, the transport equipment is traveling along the tangent direction of the planned supply route.

[0096] π (or 180 degrees) means that the two direction vectors are completely opposite, that is, the direction of travel of the transportation equipment is completely opposite to the tangent direction of the planned supply route.

[0097] The deviation distance may be calculated by calculating the straight-line distance between the current position of the transport equipment and the nearest point on the planned supply route as the deviation distance; or the actual driving path of the transport equipment may be considered to calculate the total length of the deviation path as the deviation distance.

[0098] Step S402: when the deviation is greater than a preset deviation threshold, the deviation is determined, and a deviation prompt instruction is sent to the management terminal and the display terminal of the transportation equipment; the preset deviation threshold may be 10, and the value of the preset deviation threshold may be set according to actual needs;

[0099] Step S403: When the deviation is not greater than the preset deviation threshold, it is determined that there is no deviation, and no deviation prompt instruction is generated.

[0100] See also Figure 5 Another object of the present invention is to provide a logistics supply chain intelligent management system based on the Internet of Things, the system comprising:

[0101] The information acquisition module 100 is used to acquire the current supply chain information of the transport equipment, wherein the current supply chain information includes the current driving information and the current product transport information, wherein the current driving information includes the driving track, the current position, the driving speed and the driving direction, and the current product transport information includes the transport equipment information, the product information, the planned supply route information and the transport node information; wherein the transport equipment information includes the transport equipment license plate, the transport equipment model and the transport personnel information, the product information includes the product model, quantity and appearance (including color and shape), and the transport node information includes the starting point of the transport, the transfer point during the transport and the transport end point;

[0102] A fixed location determination module 200 is used to obtain a historical supply chain information set and determine a fixed stop location based on the historical supply chain information set and current supply chain information;

[0103] A stay degree generating module 300, for determining a stay degree according to the current supply chain information and the fixed stay location;

[0104] The deviation generation module 400 is used to determine the deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information;

[0105] The monitoring frequency determination module 500 is used to generate a monitoring frequency according to the residence degree and the deviation degree, wherein the monitoring frequency = α*deviation degree + β*residence degree + C, wherein α and β are the deviation degree weight coefficient and the residence degree weight coefficient respectively, C is a constant, and C≥1, and the value of C can be set according to the actual situation; α+β=1, in general, 1≥α>β≥0, in practical applications, the size of α and β is set according to actual needs, wherein the monitoring frequency can refer to analysis every few minutes;

[0106] The product status analysis module 600 is used to obtain the monitoring video in the carriage of the transportation equipment in real time based on the monitoring equipment, and perform product status recognition analysis on the monitoring video according to the monitoring frequency to determine whether the product status is normal.

[0107] As a preferred embodiment of the present invention, the stay degree generating module 300 includes:

[0108] A current stay position determination unit, used to determine a current stay position according to the current driving information in the current supply chain information, wherein the current stay position refers to a position where the stay time exceeds a preset stay time threshold, wherein the preset stay time threshold may generally be 10 minutes, and the specific value may be set according to actual conditions;

[0109] a stop position comparison unit, used to compare the current stop position with the fixed stop position to determine whether the current stop position is a fixed stop position;

[0110] A normal state determination unit, used for determining that the current stay state is a normal stay state when the current stay position is a fixed stay position, and at this time determining that the stay degree is W, W≥0, and is usually 0 or 1;

[0111] The abnormal state determination unit is used to determine that the current stop state is an abnormal stop state when the current stop position is not a fixed stop position. At this time, the stop time of the transportation equipment at the current stop position is obtained in real time, and the stop degree is determined according to the stop time. The stop degree is positively correlated with the stop time, that is, the longer the stop time, the greater the stop degree.

[0112] As a preferred embodiment of the present invention, the deviation generation module 400 includes:

[0113] A deviation calculation unit is used to determine the deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information; wherein, the deviation = A*deviation distance + B*deviation angle, A and B are weight coefficients of the deviation distance and the deviation angle respectively, A+B=1, usually, 0<A<B, and the specific size can be set according to the actual situation;

[0114] A deviation determination unit, used to determine the deviation when the deviation is greater than a preset deviation threshold, and send a deviation prompt instruction to the management terminal and the display terminal of the transportation equipment;

[0115] The non-deviation determination unit is used to determine that the vehicle is not yawed and not generate a yaw prompt instruction when the deviation is not greater than a preset deviation threshold.

[0116] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0117] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A logistics supply chain intelligent management method based on the Internet of Things, characterized in that: The method comprises the following steps: Acquire current supply chain information of the transport equipment, the current supply chain information including current driving information and current product transport information, the current driving information including driving track, current location, driving speed and driving direction, the current product transport information including transport equipment information, product information, planned supply route information and transport node information; Obtain a historical supply chain information set, and determine a fixed stop location based on the historical supply chain information set and current supply chain information; determining a stay degree according to the current supply chain information and the fixed stay location; Determine the degree of deviation based on the driving track, current location and driving direction in the current driving information and the planned supply route information in the current product transportation information; Generate a monitoring frequency according to the stay degree and the deviation degree, monitoring frequency = α*deviation degree + β*stay degree + C, wherein α and β are the deviation degree weight coefficient and the stay degree weight coefficient respectively, and C is a constant; Based on the monitoring device, the monitoring video inside the carriage of the transportation equipment is acquired in real time, and the product status recognition and analysis is performed on the monitoring video according to the monitoring frequency to determine whether the product status is normal.

2. According to the method of intelligent management of logistics supply chain based on Internet of Things in claim 1, it is characterized in that: The step of obtaining a historical supply chain information set and determining a fixed stop location according to the historical supply chain information set and current supply chain information includes: Acquire a historical supply chain information set, and compare the current product transportation information in the current supply chain information with the historical product transportation information in the historical supply chain information set; When the similarity between a certain historical product transportation information and the current product transportation information exceeds a preset similarity threshold, the corresponding historical supply chain information is obtained to obtain a subset of the historical supply chain information; Obtain historical driving information in a historical supply chain information subset, and determine a fixed stop location based on analysis of the historical driving information in the historical supply chain information subset, wherein the fixed stop location refers to a location where each stop time exceeds a preset time threshold and the number of stops exceeds a preset number of times.

3. According to the method of intelligent management of logistics supply chain based on Internet of Things in claim 2, it is characterized in that: The step of determining the degree of stay according to the current supply chain information and the fixed stay location comprises: Determine a current stop location according to current driving information in the current supply chain information, wherein the current stop location refers to a location where the stay time exceeds a preset stop time threshold; Comparing the current stay position with the fixed stay position to determine whether the current stay position is a fixed stay position; When the current stay position is a fixed stay position, the current stay state is determined to be a normal stay state, and the stay degree is determined to be W; When the current stop position is not a fixed stop position, the current stop state is determined to be an abnormal stop state. At this time, the stop time of the transportation equipment at the current stop position is obtained in real time, and the stop degree is determined according to the stop time. The stop degree is positively correlated with the stop time.

4. According to the method of intelligent management of logistics supply chain based on Internet of Things in claim 1, it is characterized in that: The step of determining the degree of deviation based on the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information comprises: Determine the degree of deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information; wherein the degree of deviation = A*deviation distance + B*deviation angle, A and B are weight coefficients of the deviation distance and the deviation angle respectively; When the deviation is greater than the preset deviation threshold, the deviation is determined and a deviation prompt instruction is sent to the management end and the display end of the transportation equipment; When the deviation is not greater than the preset deviation threshold, it is determined that there is no deviation and no deviation prompt instruction is generated.

5. According to claim 4, a method for intelligent management of logistics supply chain based on the Internet of Things is characterized in that: The step of calculating the deviation angle comprises: Set the current position of the transport equipment to P v =(x v ,y v ), the driving direction is the vector where dx v anddy v are the components of the direction vector on the x-axis and y-axis respectively; The planned supply route consists of a series of planning points P1, P2, ..., P n Composition, by calculating P v To each planning point P i The distance from the current position of the transport equipment P is obtained v The nearest point P min ; Get P min The neighboring points include P min+1 and P min-1 , according to the P min The formula for calculating the tangent direction vector with its adjacent points is as follows: Calculate the direction of travel of transport equipment and the direction of the tangent line at the nearest point The deviation angle θ between them is calculated as follows:

6. The method for intelligent management of logistics supply chain based on the Internet of Things according to claim 5 is characterized in that: The method for calculating the deviation distance is: calculating the straight-line distance between the current position of the transportation equipment and the nearest point on the planned supply route as the deviation distance.

7. An intelligent management system for logistics supply chain based on the Internet of Things, characterized in that: The system comprises: An information acquisition module is used to acquire current supply chain information of the transport equipment, wherein the current supply chain information includes current driving information and current product transport information, wherein the current driving information includes driving track, current location, driving speed and driving direction, and the current product transport information includes transport equipment information, product information, planned supply route information and transport node information; A fixed location determination module is used to obtain a historical supply chain information set and determine a fixed stop location based on the historical supply chain information set and current supply chain information; A stay degree generating module, used for determining the stay degree according to the current supply chain information and the fixed stay location; A deviation generation module, used to determine the deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information; A monitoring frequency determination module, used for generating a monitoring frequency according to the stay degree and the deviation degree, wherein the monitoring frequency = α*deviation degree + β*stay degree + C, wherein α and β are the deviation degree weight coefficient and the stay degree weight coefficient respectively, and C is a constant; The product status analysis module is used to obtain the monitoring video in the carriage of the transportation equipment in real time based on the monitoring equipment, and perform product status recognition analysis on the monitoring video according to the monitoring frequency to determine whether the product status is normal.

8. According to claim 7, the intelligent management system for logistics supply chain based on the Internet of Things is characterized in that: The stay degree generation module comprises: A current stay position determination unit, configured to determine a current stay position according to current travel information in the current supply chain information, wherein the current stay position refers to a position where a stay time exceeds a preset stay time threshold; a stop position comparison unit, used to compare the current stop position with the fixed stop position to determine whether the current stop position is a fixed stop position; A normal state determination unit, used for determining that the current stay state is a normal stay state when the current stay position is a fixed stay position, and at this time determining that the stay degree is W; The abnormal state determination unit is used to determine that the current stop state is an abnormal stop state when the current stop position is not a fixed stop position. At this time, the stop time of the transportation equipment at the current stop position is obtained in real time, and the stop degree is determined according to the stop time, and the stop degree is positively correlated with the stop time.

9. The intelligent management system for logistics supply chain based on the Internet of Things according to claim 7 is characterized in that: The deviation generation module comprises: A deviation calculation unit, used to determine the deviation according to the driving track, current position and driving direction in the current driving information and the planned supply route information in the current product transportation information; wherein the deviation = A*deviation distance+B*deviation angle, A and B are weight coefficients of the deviation distance and the deviation angle respectively; A deviation determination unit, used to determine the deviation when the deviation is greater than a preset deviation threshold, and send a deviation prompt instruction to the management terminal and the display terminal of the transportation equipment; The non-deviation determination unit is used to determine that the vehicle is not yawed and not generate a yaw prompt instruction when the deviation is not greater than a preset deviation threshold.

Images