Logistics supply chain intelligent early warning system based on Internet of Things

Abstract

The invention discloses a logistics supply chain intelligent early warning system based on the Internet of Things, and relates to the technical field of logistics supply, and the logistics supply chain intelligent early warning system based on the Internet of Things comprises a dispatching center which is used for processing a logistics request; and the early warning module is used for carrying out intelligent early warning on the logistics supply chain. Logistics supply chain information is collected through the data collection unit, the data cleaning unit can organize the collected logistics supply chain information, the organized information is substituted into the regression model module for calculation, the logistics supply chain cost is predicted and calculated through a formula, logistics supply chain operation can be evaluated through the evaluation unit, and the logistics supply chain cost can be evaluated. The system is used in cooperation with the data simulation unit to calculate the economic expenditure and income generated by the completion of the goods transaction, and can achieve the intelligent early warning of the logistics supply chain through the cooperation of the accounting unit, the evaluation unit and the comprehensive evaluation unit.

Description

Technical Field

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

[0002] Logistics supply chain is often referred to as the component of the supply chain. It is a broad concept that includes multiple links such as logistics, supplier management, inventory control, distribution management, etc. These activities ensure that products can move efficiently from producers to consumers.

[0003] An intelligent early warning system is needed when supplying products by logistics. Among them, the "Cost Forecasting Method Based on Automobile Warehouse and Distribution Logistics" disclosed with the publication number "CN115587832A" has solved the problems of large amount of data in EXCEL tables, long opening time, and high risk of data tampering, which often cause deviations in the measurement results, increase communication time among multiple units, and affect work efficiency.

[0004] However, there are still many defects in the actual use of logistics supply chains with similar structures, such as: the existing technology is not convenient for intelligent early warning of the logistics supply chain, and is not convenient for estimating and warning the profits and losses generated by the operation of the logistics supply chain, which leads to the logistics supply chain being prone to losses during operation, thereby causing the risk of a broken capital chain. The operating personnel do not make corresponding adjustments to the logistics supply chain in a timely manner, which reduces the intelligent effect of the use of the system and is not convenient for the system to be promoted and used. Therefore, it is necessary to design an intelligent early warning system for the logistics supply chain based on the Internet of Things. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a logistics supply chain intelligent early warning system based on the Internet of Things to solve the above problems.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: An intelligent early warning system for logistics supply chain based on the Internet of Things includes:

[0007] A dispatch center for processing logistics requests;

[0008] Early warning module for intelligent early warning of logistics supply chain;

[0009] A rule filtering module for filtering repeated logistics requests;

[0010] The dispatch center is connected to a data monitoring module for real-time monitoring of market logistics supply data;

[0011] The rule filtering module is connected to a statistical module for recording logistics supply.

[0012] Preferably, the dispatch center is connected to a server for storing data generated by the operation of the system, and is also connected to a storage center for logistics cargo dispatching. The dispatch center is also connected to a network integration module for real-time communication between the system and the Internet. The network integration module includes an intelligent gateway for communicating and interacting with the Internet. The intelligent gateway is connected to a communication module for communicating with the intelligent gateway via twisted pair cables and wireless signals. The communication module is connected to a calling module for real-time communication and control of internal devices of the system, and the calling module is connected to a collaborative unit for processing multiple tasks.

[0013] Preferably, the early warning module includes a data collection unit and a data statistics unit. The data collection unit is connected to a data cleaning unit to filter the collected logistics supply chain information. The data cleaning unit is connected to a regression model module to calculate the collected logistics supply chain information. The regression model module is connected to an evaluation unit to evaluate the profitability information of the logistics supply chain information. The data statistics unit is connected to a data simulation unit for simulating the scheduling logistics supply goods information. The data simulation unit is connected to a data verification module to calculate the scheduling logistics goods information. The data verification module is connected to an accounting unit to calculate the economic expenditure and income generated by completing the goods transaction. The evaluation unit and the accounting unit are connected to a comprehensive evaluation unit to comprehensively calculate the obtained profit information and loss information.

[0014] Preferably, the rule filtering module includes a data receiving module for receiving and sending data, the data receiving module is connected to a feature extraction module for reading internal header information of the data, the feature extraction module is connected to a data verification module for verifying duplicate logistics information, and the data verification module is connected to a filtering module for filtering duplicate and malicious information.

[0015] Preferably, the data monitoring module includes: a network monitoring unit for monitoring market logistics supply information in different regions, the network monitoring unit is connected to a local monitoring unit for monitoring market logistics supply information in a designated region, the local monitoring unit is connected to a data fusion module for fusing market logistics information in different regions with market logistics supply information in a designated region, and the data monitoring module is data-connected to the statistical module.

[0016] Preferably, the rule filtering module is connected to a requesting end for requesting logistics supply information, and the requesting end includes but is not limited to a PC, a mobile terminal, and an integrated electronic device.

[0017] Preferably, the regression model module adopts a linear regression model, and the specific operating formula is: y=β0+β1x1+β2x2+....+β n x n +∈, where y is the logistics cost, x1, x2, ...., x n are independent variables, β0, β1, β2, ...., β n is the regression coefficient, ∈ is the error term.

[0018] Preferably, the linear regression model includes estimating regression coefficient calculation, wherein the regression coefficient calculation uses a method such as the least squares method to estimate the regression coefficient, through mathematical calculation:

[0019] Preferably, the data simulation unit simulates the scheduling logistics supply information using a direct cost accumulation algorithm, including the following steps:

[0020] S1. Calculation of shipped cost: multiply each shipment record by the unit price of the corresponding product and add up to get the total shipping cost;

[0021] S2. Calculation of unshipped inventory cost: multiply the current inventory quantity of each item in the inventory by its unit price, and add them up to get the total inventory value.

[0022] Beneficial Effects

[0023] The present invention provides an intelligent early warning system for logistics supply chain based on the Internet of Things. Compared with the prior art, it has the following beneficial effects:

[0024] 1. The intelligent early warning system for logistics supply chain based on the Internet of Things provided by the present invention collects logistics supply chain information through a data collection unit, organizes the collected logistics supply chain information through a data cleaning unit, substitutes the collected logistics supply chain information into the regression model module for calculation, and then calculates the logistics supply chain information through the formula The cost of the logistics supply chain can be predicted and estimated. The operation of the logistics supply chain can be evaluated through the evaluation unit, and the economic expenditure and income generated by completing the goods transaction can be calculated by cooperating with the data simulation unit. The function of intelligent early warning of the logistics supply chain can be realized by cooperating with the accounting unit, the evaluation unit and the comprehensive evaluation unit, thereby reducing the risk of capital chain rupture in the logistics supply chain, facilitating the calculation and early warning of the profits and losses of the logistics supply chain, thereby facilitating the operators to make corresponding adjustments, increasing the intelligent effect of the use of the system, and facilitating the promotion and use of the system.

[0025] 2. The IoT-based intelligent early warning system for logistics supply chain provided by the present invention can facilitate the transfer of logistics supply information sent by the requesting end through the data receiving module, and extract repeated information within the logistics supply information through the feature extraction module, wherein the feature extraction module adopts a difference comparison algorithm, which regards multiple requests as multiple texts, and finds the difference part by comparing line by line. When the feature extraction module extracts the abnormal logistics supply request information, it reduces the weight of the abnormal logistics supply information, and increases the weight of reasonable logistics supply information through the data verification module. The filtering module can filter the logistics supply request information with a weight below the minimum value, thereby realizing the function of improving the response speed of the system, avoiding the problem that the requesting end needs to occupy more logistics supply to meet the operator's erroneous request through repeated requests, and also shortens the response time of the system, which is convenient for the system to be promoted and used.

[0026] 3. The intelligent early warning system for the logistics supply chain based on the Internet of Things provided by the present invention can monitor the logistics supply information of different regions in real time through the network through the network monitoring unit, and then monitor the internal logistics supply information of the designated area in real time through the local monitoring unit, and can fuse the logistics supply information of different regions with the logistics supply information of the designated area through the data fusion module, so as to facilitate operators to understand the market demand for logistics supply, and then can collect statistics on the call information of the storage center through the statistical module, and can remind operators in combination with the call information of the storage center, so as to facilitate operators to make timely responses to the congestion and high load of the logistics supply chain caused by a hot-selling product, thereby realizing the function of intelligent early warning of the logistics supply chain based on the Internet of Things. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the system principle of the present invention;

[0028] Figure 2 It is a schematic diagram of the early warning module of the present invention;

[0029] Figure 3 This is a schematic diagram of a rule filtering module of the present invention;

[0030] Figure 4 It is a schematic diagram of a data monitoring module of the present invention;

[0031] Figure 5 It is a schematic diagram of the network integration module of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] See also Figure 1-Figure 5 , two technical solutions are provided: The first implementation method:

[0034] An intelligent early warning system for logistics supply chain based on the Internet of Things, comprising:

[0035] A dispatch center for processing logistics requests;

[0036] Early warning module for intelligent early warning of logistics supply chain;

[0037] A rule filtering module for filtering repeated logistics requests;

[0038] The dispatch center is connected to a data monitoring module for real-time monitoring of market logistics supply data;

[0039] The rule filtering module is connected to a statistical module for recording logistics supply.

[0040] The dispatch center is connected to a server for storing data generated by the operation of the system, and is also connected to a storage center for logistics cargo dispatching. The dispatch center is also connected to a network integration module for real-time communication between the system and the Internet. The network integration module includes an intelligent gateway for communicating and interacting with the Internet. The intelligent gateway is connected to a communication module for communicating with the intelligent gateway through twisted pair cables and wireless signals. The communication module is connected to a calling module for real-time communication and control of internal devices of the system. The calling module is connected to a collaborative unit for processing multiple tasks.

[0041] The server can be used to store the data generated by the system operation and upload it to the cloud through the network, avoiding data loss caused by sudden system shutdown. The storage center can be used to store the logistics goods to be transported, and facilitate the subsequent transportation of the logistics goods, thereby achieving the function of the logistics supply chain. The communication module can be used in conjunction with the intelligent gateway to facilitate the remote control of the system through the Internet. The calling module can control the start and stop of the corresponding equipment according to the received instructions. Then, by cooperating with the collaborative unit, it can realize the processing of multiple instructions and call the corresponding equipment to run, realizing the function of operation and communication of the control device based on the Internet of Things;

[0042] The early warning module includes a data collection unit and a data statistics unit. The data collection unit is connected to a data cleaning unit to filter and process the collected logistics supply chain information. The data cleaning unit is connected to a regression model module to calculate the collected logistics supply chain information. The regression model module is connected to an evaluation unit to evaluate the profit information of the logistics supply chain information. The data statistics unit is connected to a data simulation unit for simulating the dispatching logistics supply goods information. The data simulation unit is connected to a data verification module to calculate the dispatching logistics goods information. The data verification module is connected to an accounting unit to calculate the economic expenditure and income generated by completing the goods transaction. The evaluation unit and the accounting unit are connected to a comprehensive evaluation unit to comprehensively calculate the obtained profit information and loss information.

[0043] The data collection unit collects logistics supply chain information, including but not limited to factors that may affect logistics costs, such as transportation distance, cargo weight, time, and fuel price. The data cleaning unit can organize the collected logistics supply chain information, clean up incomplete and abnormal values, and remove abnormal values ​​to ensure data quality.

[0044] Substitute the collected logistics supply chain information into the regression model module for calculation, and then use the formula The cost of the logistics supply chain can be predicted and estimated. The operation of the logistics supply chain can be evaluated through the evaluation unit, and the economic expenditure and income generated by the completion of the goods transaction can be calculated by using it in conjunction with the data simulation unit. The intelligent early warning function of the logistics supply chain can be realized by using the accounting unit, evaluation unit, and comprehensive evaluation unit in conjunction with each other;

[0045] The rule filtering module includes a data receiving module for receiving and sending data, the data receiving module is connected to a feature extraction module for reading the internal header information of the data, the feature extraction module is connected to a data verification module for checking duplicate logistics information, and the data verification module is connected to a filtering module for filtering duplicate and malicious information;

[0046] The data receiving module can facilitate the transfer of logistics supply information sent by the requesting end, and the feature extraction module can extract the repeated information inside the logistics supply information. The feature extraction module adopts a difference comparison algorithm, which first formats the request to make it easier to compare, and then compares it line by line according to certain rules. Then, multiple requests are regarded as multiple texts, and the differences are found by comparing them line by line.

[0047] When the feature extraction module extracts abnormal logistics supply request information, it reduces the weight of the abnormal logistics supply information, and increases the weight of reasonable logistics supply information through the data verification module, so as to facilitate the subsequent filtering module to filter the logistics supply information. The filtering module can filter the logistics supply request information with a weight lower than the minimum value, thereby realizing the function of improving the system response speed;

[0048] The rule filtering module is connected to a requesting end for requesting logistics supply information, and the requesting end includes but is not limited to a PC, a mobile terminal, and an integrated electronic device;

[0049] The requesting end can transmit the logistics request information to the dispatching center through PC, mobile terminal, integrated electronic device and other devices, so that the dispatching center can dispatch the goods in the storage center for logistics distribution according to the requesting end;

[0050] The regression model module uses a linear regression model, and the specific operating formula is: y = β0 + β1x1 + β2x2 + .... + β n x n +∈, where y is the logistics cost, x1, x2, ...., x n are independent variables, β0, β1, β2, ...., β n is the regression coefficient, ∈ is the error term;

[0051] The linear regression model includes the estimation of regression coefficient calculation, in which the regression coefficient calculation uses the least squares method and other methods to estimate the regression coefficient. The goal of the least squares method is to minimize the sum of the squares of the difference between the actual logistics cost and the logistics cost predicted by the model. Through mathematical calculation: The smallest β0, β1, β2, .... βn, where m is the number of data samples, y i is the actual logistics cost, is the logistics cost predicted by the model, is the actual logistics cost, is the logistics cost predicted by the model;

[0052] The data simulation unit simulates the scheduling logistics supply information using a direct cost accumulation algorithm, including the following steps:

[0053] S1. Calculation of shipped cost: For each shipment record, multiply it by the unit price of the corresponding product, and add up to get the total shipment cost. Let Ci be the number of products shipped for the i-th time, and Pi be the unit price of the product. Then the single shipment cost is Ci*Pi, and the total shipment cost is the sum of all single shipment costs, that is, ∑(Ci*Pi);

[0054] S2. Calculation of unshipped inventory cost: multiply the current inventory quantity of each item in the inventory by its unit price, and add them up to get the total inventory value. Let li be the inventory quantity of the jth item, and Vj be the unit price of the item. Then the inventory value of the item is 1j*Vj. The inventory value of a household is the sum of the inventory values ​​of all items, that is, ∑(li*Vi).

[0055] The second implementation mode is mainly different from the first implementation mode in that: the data monitoring module includes: a network monitoring unit for monitoring market logistics supply information in different regions, the network monitoring unit is connected to a local monitoring unit for monitoring market logistics supply information in a designated region, the local monitoring unit is connected to a data fusion module for fusing market logistics information in different regions with market logistics supply information in a designated region, and the data monitoring module is connected to the statistical module data.

[0056] The network monitoring unit can be used to monitor the logistics supply information of different regions in real time through the network, and the local monitoring unit can be used to monitor the internal logistics supply information of the designated area in real time. The data fusion module can be used to fuse the logistics supply information of different regions with the logistics supply information of the designated area. The statistical module can be used to count the warehouse center call information, and the operator can be prompted in combination with the warehouse center call information, so that the operator can make timely responses to the congestion and high load of the logistics supply chain caused by a hot-selling product. The Internet of Things module can enable the system to have the function of real-time communication with the Internet, avoiding the need to use external communication equipment to convey system operation and communication.

[0057] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants 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.

[0058] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent early warning system for logistics supply chain based on the Internet of Things, characterized in that: include: A dispatch center for processing logistics requests; Early warning module for intelligent early warning of logistics supply chain; A rule filtering module for filtering repeated logistics requests; The dispatch center is connected to a data monitoring module for real-time monitoring of market logistics supply data; The rule filtering module is connected to a statistical module for recording logistics supply.

2. According to the IoT-based logistics supply chain intelligent early warning system of claim 1, it is characterized by: The dispatch center is connected to a server for storing data generated by the operation of the system, and is also connected to a storage center for logistics cargo dispatching. The dispatch center is also connected to a network integration module for real-time communication between the system and the Internet. The network integration module includes an intelligent gateway for communicating and interacting with the Internet. The intelligent gateway is connected to a communication module for communicating with the intelligent gateway via twisted pair cables and wireless signals. The communication module is connected to a calling module for real-time communication and control of internal devices of the system, and the calling module is connected to a collaborative unit for processing multiple tasks.

3. According to the IoT-based logistics supply chain intelligent early warning system of claim 1, it is characterized by: The early warning module includes a data collection unit and a data statistics unit. The data collection unit is connected to a data cleaning unit to filter and process the collected logistics supply chain information. The data cleaning unit is connected to a regression model module to calculate the collected logistics supply chain information. The regression model module is connected to an evaluation unit to evaluate the profitability information of the logistics supply chain information. The data statistics unit is connected to a data simulation unit for simulating the scheduling logistics supply goods information. The data simulation unit is connected to a data verification module to calculate the scheduling logistics goods information. The data verification module is connected to an accounting unit to calculate the economic expenditure and income generated by completing the goods transaction. The evaluation unit and the accounting unit are connected to a comprehensive evaluation unit to comprehensively calculate the obtained profit information and loss information.

4. According to claim 1, the intelligent early warning system for logistics supply chain based on the Internet of Things is characterized by: The rule filtering module includes a data receiving module for receiving and sending data, the data receiving module is connected to a feature extraction module for reading internal header information of the data, the feature extraction module is connected to a data verification module for verifying duplicate logistics information, and the data verification module is connected to a filtering module for filtering duplicate and malicious information.

5. According to the IoT-based logistics supply chain intelligent early warning system of claim 1, it is characterized by: The data monitoring module includes: a network monitoring unit for monitoring market logistics supply information in different regions, the network monitoring unit is connected to a local monitoring unit for monitoring market logistics supply information in a designated region, the local monitoring unit is connected to a data fusion module for fusing market logistics information in different regions with market logistics supply information in a designated region, and the data monitoring module is data-connected to a statistical module.

6. According to claim 1, the intelligent early warning system for logistics supply chain based on the Internet of Things is characterized by: The rule filtering module is connected to a request end for requesting logistics supply information, and the request end includes but is not limited to a PC, a mobile terminal, and an integrated electronic device.

7. According to claim 1, the intelligent early warning system for logistics supply chain based on the Internet of Things is characterized by: The regression model module adopts a linear regression model, and the specific operating formula is: y = β0 + β1x1 + β2x2 + .... + β n x n +∈, where y is the logistics cost, x1, x2, ...., x n are independent variables, β0, β1, β2, ...., β n is the regression coefficient, ∈ is the error term.

8. According to claim 7, the intelligent early warning system for logistics supply chain based on the Internet of Things is characterized by: The linear regression model includes an estimated regression coefficient calculation, wherein the regression coefficient calculation uses a method such as the least squares method to estimate the regression coefficient, through mathematical calculation:

9. The intelligent early warning system for logistics supply chain based on the Internet of Things according to claim 1 is characterized by: The data simulation unit simulates the scheduling logistics supply information using a direct cost accumulation algorithm, including the following steps: S1. Calculation of shipped cost: multiply each shipment record by the unit price of the corresponding product and add up to get the total shipping cost; S2. Calculation of unshipped inventory cost: multiply the current inventory quantity of each item in the inventory by its unit price, and add them up to get the total inventory value.

Images