Automatic luggage storing and taking safety optimization system based on Internet

Abstract

The invention belongs to the technical field of automatic luggage storage and taking, and particularly relates to an internet-based automatic luggage storage and taking safety optimization system, which comprises a safety transmission and pickup module, a luggage cabinet distribution module and a cabinet capacity arrangement module. According to the scheme, the passenger priority, the path cost and the cabinet vacancy rate are combined, the nearest and load-balanced cabinets are dynamically allocated through the deep Q network, the luggage access cost of passengers is reduced, the historical luggage size and time interval distribution are analyzed, the cabinet size proportion strategy table is generated, the storage cabinets are monitored in real time, personnel are dispatched in time, and the storage cabinets are quickly added. The peak demand is met; the defects of a traditional face recognition system are effectively overcome through multi-modal security authentication and a dynamic optimization mechanism, single face recognition is replaced with two-factor authentication combining OTP passwords and biological characteristics, and recognition failure caused by strong light and shielding is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic luggage storage and retrieval, and in particular to an Internet-based automatic luggage storage and retrieval security optimization system. Background Art

[0002] The Internet-based automatic luggage storage and retrieval security optimization system is a system that uses Internet of Things technology to realize automatic storage and retrieval of passenger luggage in airports.

[0003] Among the existing similar solutions, for example, CN112164186B is an online terminal building ATIS intelligent terminal check-in and baggage check-in method. This solution addresses the technical problem that the links that passengers have to go through before boarding are distributed in different areas of the terminal building, and passengers need to carry their luggage back and forth by themselves, causing great inconvenience. By scanning the QR code to bind the cabinet ID and passenger information, the third-party logistics personnel unlock the transportation after identity authentication, and the airport security personnel use a one-time password to open the box for verification. This technical means realizes the "door-to-door, zero waiting, zero burden" of luggage, allowing passengers to travel easily and improving the efficiency and experience of passengers' travel. However, the existing technology has the problem that failures of the ATIS intelligent terminal, cloud server or network may cause interruption of check-in and check-in services, resulting in loss of luggage tracking. There is also a technical problem that the cost of passengers storing and retrieving luggage during peak hours and the demand for expansion of luggage storage cabinets are not taken into account;

[0004] For example, CN114170735B is an unmanned supermarket locker based on face recognition. This solution addresses the technical problems of the existing face recognition lockers, in which the face recognition components are mostly fixed at a corresponding height during use. When the user is shorter, the face recognition components cannot recognize the user's face. At this time, the user cannot use the face recognition locker, thereby storing personal items, which is inconvenient to use, and the technical problem of difficulty in taking items due to the depth of the storage cavity. The lifting components (such as support plates, threaded columns, stepper motors, etc.) are automatically adjusted to the required height. The face recognition system is equipped with a sliding storage block in the storage cavity to adjust the height of the user. The user can push the items out of the storage cavity by rotating the rod and driving the chain. This technically enables users with shorter heights to be flush with the face recognition camera, thereby completing the recognition and operation. However, the existing technology has technical problems such as insufficient environmental adaptability of the face recognition system, reduced recognition rate in strong light, backlight or low light environments, high recognition failure rate when wearing a mask, glasses or partial occlusion, and sensitive data such as facial information, passenger ID card, flight information, luggage location, etc. may be intercepted or abused, leading to illegal opening of the box. Summary of the Invention

[0005] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an Internet-based automated luggage storage and retrieval security optimization system. In view of the problems in the prior art that ATIS intelligent terminals, cloud servers or network failures may cause interruptions in check-in and check-in services, resulting in loss of luggage tracking, and that the cost of passengers storing and retrieving luggage during peak hours and the demand for expansion of luggage storage cabinets are not considered, this solution combines passenger priority, path cost and cabinet idleness, dynamically allocates the nearest and load-balanced cabinets through a deep Q network, reduces the cost of passengers storing and retrieving luggage, analyzes historical luggage size and time period distribution, generates a cabinet size ratio strategy table, monitors storage cabinets in real time, and dispatches personnel in a timely manner to quickly add storage cabinets to meet peak demand. It provides a highly reliable, efficient and low-cost luggage storage and retrieval service. In response to the technical problems of existing technologies such as insufficient environmental adaptability of facial recognition systems, reduced recognition rates in strong light, backlight or low-light environments, high recognition failure rates when wearing masks, glasses or partial occlusion, and the possibility of facial information, passenger ID card, flight information, luggage location and other sensitive data being intercepted or abused, leading to illegal opening of luggage, this solution effectively solves the defects of traditional facial recognition systems through multimodal security authentication and dynamic optimization mechanisms, and adopts two-factor authentication combining OTP password and biometrics to replace single facial recognition, avoiding recognition failures caused by strong light and occlusion, which not only improves the authentication success rate in complex environments, but also reduces the risk of data interception through dynamic password encryption mechanism.

[0006] The technical solution adopted by the present invention is as follows: The present invention provides an Internet-based luggage automated storage and retrieval security optimization system, which includes a secure transmission and retrieval module, a luggage cabinet module, and a cabinet capacity arrangement module;

[0007] The secure transmission and retrieval module adopts a secure transmission and retrieval method to ensure the safe retrieval of luggage;

[0008] The luggage locker module uses a luggage locker matching method to intelligently allocate the optimal locker location. After the luggage is loaded into the locker, the specific locker location data is inserted into the passenger information, binding the corresponding relationship between the locker and the passenger. The passenger information includes check-in information, flight number, terminal, waiting room location, luggage size and passenger original priority.

[0009] The cabinet capacity arrangement module adopts a cabinet capacity arrangement method to optimize storage cabinet arrangement and cabinet capacity.

[0010] The secure transmission proxy module adopts a secure transmission proxy method, which specifically includes the following steps:

[0011] Step A1: Alternation between primary and secondary servers is used to handle service interruptions and implement server configuration. Specifically, a service cluster is deployed in the cloud. The service cluster includes a primary server and a backup server. The service cluster synchronizes passenger information in real time. In the event of a primary server failure, a virtual IP address is automatically used for switching. When the primary server goes down, the virtual IP address automatically drifts to the backup server.

[0012] Step A2: Intelligent retrieval. Specifically, the passenger sets a dynamic retrieval password when checking their luggage into the locker. The passenger is authorized in advance by the service cluster and the retrieval agent's biometrics are bound. When retrieving the luggage, the service cluster sends an OTP (One-Time Password) to the retrieval agent, who enters the OTP and has their biometrics verified.

[0013] Step A3: System linkage, specifically, setting an alarm threshold, detecting the cabinet vacancy rate each time luggage is put into the cabinet, and triggering an expansion warning when the cabinet vacancy rate is lower than the alarm threshold, prompting the dispatcher to dispatch additional luggage storage cabinets.

[0014] The luggage cabinet matching module adopts a luggage cabinet matching method, which specifically includes the following steps:

[0015] Step B1: Bluetooth positioning: Specifically, evenly deploy Bluetooth beacons in the terminal building and use RSSI triangulation to obtain the passenger's current location through the Bluetooth beacons;

[0016] Step B2: Data update, specifically, obtaining flight delay and gate change information from the application programming interfaces of major airlines in a polling manner and updating passenger information;

[0017] Step B3: Passenger priority evaluation is used to prioritize passengers. Specifically, the original weight is determined based on the passenger's original priority, and an incremental weight representing time urgency is calculated. Passengers on urgent flights with imminent departure times are given a higher priority weight. The formula used is as follows: ;

[0018] Where, Incremental weight representing time urgency, Indicates the remaining time until the flight takes off. represents the basic time weight, represents the exponential growth base, Indicates the critical time threshold;

[0019] The sum of the original weight and the incremental weight is used as the final weight for cabinet allocation;

[0020] Step B4: Load balancing: Create and maintain a list of locker vacancy rates based on the highest to lowest locker vacancy rates. Convert the terminal map layout into an undirected graph containing nodes and edges, with the passenger's current location, available locker locations, and boarding gates as nodes, and accessible routes as edges.

[0021] Step B5: Calculate the physical path cost. Specifically, use a graph search algorithm to find a path from the passenger's current location to all available storage cabinet locations on an undirected graph and evaluate the physical path cost. Calculate the mean of the storage cabinet occupancy rate, calculate the standard deviation of all cabinet occupancy rates and the mean, normalize the result of dividing the standard deviation by the mean, and obtain an occupancy balance score. Set a multi-objective reward function. The formula used is as follows: ;

[0022] Where, Indicates reward, represents the original weight, represents the physical path cost, represents the idle balance score, and All indicate rewarding contributions;

[0023] Step B6: Cabinet allocation decision, specifically, taking the final weight, the passenger's current location, the cabinet vacancy rate list, and the passenger information as states, allocating the passenger's luggage to any cabinet as an action, and a multi-objective reward function as a reward, and using a deep Q network for training iterations to obtain the optimal cabinet allocation.

[0024] The cabinet capacity arrangement module adopts a cabinet capacity arrangement method, which specifically includes the following steps:

[0025] The dimensions of incoming luggage are measured and uploaded to the cloud. Based on the luggage size distribution patterns in different time periods, the K-means algorithm is used to divide luggage into size categories and peak time periods. Passenger storage needs are analyzed on the service cluster, and a cabinet adaptation strategy is developed. This strategy is used to guide adjustments to the storage cabinet capacity and structure, determine the proportions of different cabinet sizes, and adjust the position of cabinet partitions based on the strategy. The partitions are driven by stepper motors to move and adjust the space size within the cabinet.

[0026] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0027] (1) In view of the problem that the existing technology may cause the interruption of check-in and check-in services due to ATIS intelligent terminals, cloud servers or network failures, resulting in the loss of baggage tracking, and the technical problem of not considering the peak period, the cost of passengers storing and retrieving luggage, and the demand for expanding the capacity of luggage storage cabinets, this solution combines passenger priority, path cost and cabinet idle rate, and dynamically allocates the nearest and load-balanced cabinets through the deep Q network to reduce the cost of passengers storing and retrieving luggage. It analyzes the historical luggage size and time distribution, generates a cabinet size ratio strategy table, monitors the storage cabinets in real time, and dispatches personnel to quickly add storage cabinets in time to meet peak demand, thus achieving highly reliable, efficient and low-cost luggage storage and retrieval services;

[0028] (2) In view of the technical problems that the existing technology has, such as the lack of environmental adaptability of the face recognition system, the reduction of recognition rate in strong light, backlight or low light environment, the high recognition failure rate when wearing a mask, glasses or partial occlusion, and the possibility of interception or abuse of sensitive data such as facial information, passenger ID card, flight information, luggage location, etc., leading to illegal opening of the box, this solution effectively solves the defects of the traditional face recognition system through multimodal security authentication and dynamic optimization mechanism, and adopts two-factor authentication combining OTP password and biometrics to replace single facial recognition, avoiding recognition failure caused by strong light and occlusion, improving the authentication success rate in complex environments, and reducing the risk of data interception through dynamic password encryption mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A module connection diagram of an Internet-based luggage automated storage and retrieval security optimization system provided by the present invention;

[0030] Figure 2 A flowchart of a secure transmission proxy method;

[0031] Figure 3 Flowchart of the method for assigning luggage to a locker.

[0032] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0034] Example 1: See Figures 1 to 3This embodiment provides an Internet-based luggage automated storage and retrieval security optimization system, which includes a secure transmission and retrieval module, a luggage cabinet module, and a cabinet capacity arrangement module;

[0035] The secure transmission and retrieval module adopts a secure transmission and retrieval method to ensure the safe retrieval of luggage;

[0036] The luggage locker module uses a luggage locker matching method to intelligently allocate the optimal locker location. After the luggage is loaded into the locker, the specific locker location data is inserted into the passenger information, binding the corresponding relationship between the locker and the passenger. The passenger information includes check-in information, flight number, terminal, waiting room location, luggage size and passenger original priority.

[0037] The cabinet capacity arrangement module adopts a cabinet capacity arrangement method to optimize storage cabinet arrangement and cabinet capacity.

[0038] Example 2: See Figures 1 to 2 This embodiment is based on the above embodiment. The secure transmission substitution module adopts a secure transmission substitution method. The secure transmission substitution method specifically includes the following steps:

[0039] Step A1: Alternation between primary and secondary servers is used to handle service interruptions and implement server configuration. Specifically, a service cluster is deployed in the cloud. The service cluster includes a primary server and a backup server. The service cluster synchronizes passenger information in real time. In the event of a primary server failure, a virtual IP address is automatically used for switching. When the primary server goes down, the virtual IP address automatically drifts to the backup server.

[0040] Step A2: Intelligent retrieval. Specifically, the passenger sets a dynamic retrieval password when checking their luggage into the locker. The passenger is authorized in advance by the service cluster and the retrieval agent's biometrics are bound. When retrieving the luggage, the service cluster sends an OTP (One-Time Password) to the retrieval agent, who enters the OTP and has their biometrics verified.

[0041] Step A3: System linkage, specifically, setting an alarm threshold, detecting the cabinet vacancy rate each time luggage is put into the cabinet, and triggering an expansion warning when the cabinet vacancy rate is lower than the alarm threshold, prompting the dispatcher to dispatch additional luggage storage cabinets.

[0042] Example 3: See Figures 1 to 3 This embodiment is based on the above embodiment. The luggage locker module adopts a luggage locker method, which specifically includes the following steps:

[0043] Step B1: Bluetooth positioning: Specifically, evenly deploy Bluetooth beacons in the terminal building and use RSSI triangulation to obtain the passenger's current location through the Bluetooth beacons;

[0044] Step B2: Data update, specifically, obtaining flight delay and gate change information from the application programming interfaces of major airlines in a polling manner and updating passenger information;

[0045] Step B3: Passenger priority evaluation is used to prioritize passengers. Specifically, the original weight is determined based on the passenger's original priority, and an incremental weight representing time urgency is calculated. Passengers on urgent flights with imminent departure times are given a higher priority weight. The formula used is as follows: ;

[0046] Where, Incremental weight representing time urgency, Indicates the remaining time until the flight takes off. represents the basic time weight, represents the exponential growth base, Indicates the critical time threshold;

[0047] The sum of the original weight and the incremental weight is used as the final weight for cabinet allocation;

[0048] Step B4: Load balancing: Create and maintain a list of locker vacancy rates based on the highest to lowest locker vacancy rates. Convert the terminal map layout into an undirected graph containing nodes and edges, with the passenger's current location, available locker locations, and boarding gates as nodes, and accessible routes as edges.

[0049] Step B5: Calculate the physical path cost. Specifically, use a graph search algorithm to find a path from the passenger's current location to all available storage cabinet locations on an undirected graph and evaluate the physical path cost. Calculate the mean of the storage cabinet occupancy rate, calculate the standard deviation of all cabinet occupancy rates and the mean, normalize the result of dividing the standard deviation by the mean, and obtain an occupancy balance score. Set a multi-objective reward function. The formula used is as follows: ;

[0050] Where, Indicates reward, represents the original weight, represents the physical path cost, represents the idle balance score, and All indicate rewarding contributions;

[0051] Step B6: Cabinet allocation decision, specifically, taking the final weight, the passenger's current location, the cabinet vacancy rate list, and the passenger information as states, allocating the passenger's luggage to any cabinet as an action, and a multi-objective reward function as a reward, and using a deep Q network for training iterations to obtain the optimal cabinet allocation.

[0052] Example 4: See Figures 1 to 3 This embodiment is based on the above embodiment. The cabinet capacity arrangement module adopts a cabinet capacity arrangement method, which specifically includes the following steps:

[0053] The dimensions of incoming luggage are measured and uploaded to the cloud. Based on the luggage size distribution patterns in different time periods, the K-means algorithm is used to divide luggage into size categories and peak time periods. Passenger storage needs are analyzed on the service cluster, and a cabinet adaptation strategy is developed. This strategy is used to guide adjustments to the storage cabinet capacity and structure, determine the proportions of different cabinet sizes, and adjust the position of cabinet partitions based on the strategy. The partitions are driven by stepper motors to move and adjust the space size within the cabinet.

[0054] Example 5: See Figures 1 to 3 This embodiment is based on the above embodiment. Specifically, formulating a cabinet adaptation strategy involves marking the size category of each piece of luggage based on the K-means clustering results, then counting the number of luggage of each size category in each time period, and calculating their percentage of the total. Finally, these percentage data are organized into an initial strategy table based on the correspondence between time periods and sizes. The table is stored in Redis in JSON format for fast query, and instructions are issued through the MQTT protocol to drive the stepper motor to dynamically adjust the partition position.

[0055] Example 6: See Figures 1 to 3 This embodiment is based on the above embodiment, and the different time periods are specifically represented as weekdays, holidays, and morning and evening peak hours.

[0056] Example 7: See Figures 1 to 3 This embodiment is based on the above embodiment. In step B3, =2.0, =1.05, =60 minutes.

[0057] Example 8: See Figures 1 to 3 This embodiment is based on the above embodiment. In step B3, the take-off time is imminent, specifically, the take-off time is less than 1 hour.

[0058] Example 9: See Figures 1 to 3 This embodiment is based on the above embodiment. The baggage size distribution pattern in different time periods is shown in the following figure: .

[0059] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0060] While 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 these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

[0061] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. An Internet-based luggage automated storage and retrieval security optimization system, characterized by: It includes a safe transmission and pickup module, a luggage cabinet module, and a cabinet capacity arrangement module; The secure transmission and retrieval module adopts a secure transmission and retrieval method to ensure the safe retrieval of luggage; The luggage locker module uses a luggage locker matching method to intelligently allocate the optimal locker location. After the luggage is loaded into the locker, the specific locker location data is inserted into the passenger information, binding the corresponding relationship between the locker and the passenger. The passenger information includes check-in information, flight number, terminal, waiting room location, luggage size and passenger original priority. The cabinet capacity arrangement module adopts a cabinet capacity arrangement method to optimize storage cabinet arrangement and cabinet capacity.

2. The Internet-based automated luggage storage and retrieval security optimization system according to claim 1, characterized in that: The secure transmission and substitution method specifically includes the following steps: Step A1: Alternation between primary and secondary servers is used to handle service interruptions and implement server configuration. Specifically, a service cluster is deployed in the cloud. The service cluster includes a primary server and a backup server. The service cluster synchronizes passenger information in real time. In the event of a primary server failure, a virtual IP address is automatically used for switching. When the primary server goes down, the virtual IP address automatically drifts to the backup server. Step A2: Intelligent luggage collection. Specifically, the passenger sets a dynamic luggage collection password when checking their luggage into the locker. The passenger is authorized in advance by the service cluster and binds the biometrics of the person who collects the luggage. When collecting the luggage, the service cluster sends an OTP password to the person who collects the luggage. The person enters the OTP password and verifies the biometrics. Step A3: System linkage, specifically, setting an alarm threshold, detecting the cabinet vacancy rate each time luggage is put into the cabinet, and triggering an expansion warning when the cabinet vacancy rate is lower than the alarm threshold, prompting the dispatcher to dispatch additional luggage storage cabinets.

3. The Internet-based automated luggage storage and retrieval security optimization system according to claim 2, characterized in that: The luggage locker matching method specifically includes the following steps: Step B1: Bluetooth positioning: Specifically, evenly deploy Bluetooth beacons in the terminal building and use RSSI triangulation to obtain the passenger's current location through the Bluetooth beacons; Step B2: Data update, specifically, obtaining flight delay and gate change information from the application programming interfaces of major airlines in a polling manner and updating passenger information; Step B3: Passenger priority evaluation is used to prioritize passengers. Specifically, referring to the original priority of the passenger, the original weight is determined, and the incremental weight representing the time urgency is calculated. The formula used is as follows: ； Where, Incremental weight representing time urgency, Indicates the remaining time until the flight takes off. represents the basic time weight, represents the exponential growth base, Indicates the critical time threshold; The sum of the original weight and the incremental weight is used as the final weight for cabinet allocation; Step B4: Load balancing: sort the cabinets in descending order of their idleness, create and maintain a list of cabinet idleness rates, and convert the terminal map layout into an undirected graph containing nodes and edges; Step B5: Calculate the physical path cost. Specifically, use a graph search algorithm to find a path from the passenger's current location to all available storage cabinet locations on an undirected graph and evaluate the physical path cost. Calculate the mean of the storage cabinet occupancy rate, calculate the standard deviation of all cabinet occupancy rates and the mean, normalize the result of dividing the standard deviation by the mean, and obtain an occupancy balance score. Set a multi-objective reward function. The formula used is as follows: ； Where, Indicates reward, represents the original weight, represents the physical path cost, represents the idle balance score, and All indicate rewarding contributions; Step B6: Cabinet allocation decision, specifically, taking the final weight, the passenger's current location, the cabinet vacancy rate list, and the passenger information as states, allocating the passenger's luggage to any cabinet as an action, and a multi-objective reward function as a reward, and using a deep Q network for training iterations to obtain the optimal cabinet allocation.

4. The Internet-based automated luggage storage and retrieval security optimization system according to claim 3, characterized in that: The cabinet capacity arrangement method specifically includes the following steps: The dimensions of incoming luggage are measured and uploaded to the cloud. Based on the luggage size distribution patterns in different time periods, the K-means algorithm is used to divide luggage into size categories and peak time periods. Passenger storage needs are analyzed on the service cluster, and a cabinet adaptation strategy is developed. This strategy is used to guide adjustments to the storage cabinet capacity and structure, determine the proportions of different cabinet sizes, and adjust the position of cabinet partitions based on the strategy. The partitions are driven by stepper motors to move and adjust the space size within the cabinet.

Images