Intelligent matching and scheduling algorithm based on different types of financial boxes

Abstract

The present application relates to a kind of based on different types of financial industry case flow, save intelligent matching scheduling algorithm, solve the technical problems of complexity response, cost control, operation efficiency and dynamic adaptability etc., by using step one, problem analysis and data preparation;Step two, build case vehicle scheduling model: based on vehicle driving speed constant, case loading and unloading time is ignored, each vehicle executes a scheduling task once etc.Assumptions;Build scheduling cost objective function, operation efficiency objective function;Step three, first search is carried out;Step four, second search is carried out;Step five, according to priority, complete vehicle allocation;Step six, simulation test and algorithm comparison;Step seven, scheduling algorithm combination and weight adjustment, the technical scheme of the problem is better solved, can be used in the scheduling of different types of case in financial industry.

Description

Technical Field

[0001] This invention relates to the field of financial technology, specifically to an intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry. Background Technology

[0002] In the daily operations of the financial industry, the circulation and storage of different types of cash boxes are crucial to ensuring the smooth operation of business. Cash boxes hold various financial assets such as cash and important documents, making their safe and efficient allocation paramount. However, the financial industry currently faces numerous challenges in cash box allocation, specifically in the following aspects: First, high allocation complexity. Financial business involves numerous branches and regions, and the circulation needs of different types of cash boxes are complex and diverse. For example, the allocation of cash boxes must strictly adhere to security regulations and quantity management requirements, while cash boxes for important documents have special requirements for confidentiality and timeliness. The cash box needs of different branches vary significantly in terms of time, quantity, and type, requiring comprehensive consideration of numerous factors in cash box allocation, increasing the difficulty and complexity of allocation. Second, cost control challenges. Traditional cash box allocation methods often lack systematicity and scientific rigor, failing to fully consider factors such as transportation costs and vehicle usage costs. On the one hand, unreasonable vehicle allocation leads to high empty load rates and circuitous transportation routes, increasing unnecessary transportation costs; on the other hand, failure to allocate vehicles reasonably according to cash box type and transportation needs results in wasted vehicle resources, further increasing operating costs. While pursuing efficient scheduling, effectively controlling costs has become a major challenge for financial institutions. Third, operational efficiency is low. With the continuous expansion of financial business, the scale of cash box turnover is increasing daily. Existing scheduling algorithms are increasingly showing efficiency problems when dealing with large-scale cash box scheduling. For example, scheduling methods based on simple priority rules struggle to fully consider the interplay of various factors when handling complex cash box scheduling tasks, resulting in suboptimal scheduling schemes, thus prolonging cash box turnover time and reducing overall operational efficiency. This not only affects the normal operation of financial business but may also negatively impact customer service quality. Fourth, there is a lack of dynamic adaptability. Financial business scenarios are constantly changing with market environment, policies, and regulations, and cash box scheduling needs also change dynamically accordingly. However, most current scheduling algorithms lack the ability to dynamically adapt to these changes and cannot adjust scheduling strategies in a timely manner according to actual conditions. In the event of emergencies or temporary changes in business needs, existing scheduling algorithms may fail to respond quickly and effectively, leading to scheduling chaos and affecting the stability and continuity of financial business.

[0003] In summary, existing cash box scheduling methods in the financial industry have shortcomings in terms of handling complexity, cost control, operational efficiency and dynamic adaptability, and traffic congestion, making it difficult to meet the growing business needs of the financial industry. Therefore, there is an urgent need to develop a cash box scheduling algorithm based on intelligent matching to improve scheduling efficiency, reduce costs, enhance adaptability to complex and ever-changing business scenarios, and reduce traffic congestion. Summary of the Invention

[0004] The technical problem this invention aims to solve is the inadequacy of existing technologies in terms of complexity handling, cost control, operational efficiency, and dynamic adaptability. It provides a novel intelligent matching and scheduling algorithm for the flow and storage of different types of cash boxes in the financial industry. This algorithm features improved scheduling efficiency and reduced costs.

[0005] To solve the above technical problems, the following technical solution is adopted:

[0006] An intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry includes the following steps:

[0007] Step 1, Problem Analysis and Data Preparation: Collect and organize the cash box data, including cash box number B. id (id∈{1,2,…,n}, where n is the total number of cash boxes), Cash box type weight Destination area Vehicle data, including vehicle number v j (j∈{1,2,…,m}, where m is the total number of vehicles), vehicle load capacity Restrictions, vehicle location area And regional data, including region number A k (k∈{1, 2, ..., p}, where p is the total number of regions), the distance matrix between regions d(A) i A j );

[0008] Step 2: Construct a cash box vehicle scheduling model: based on assumptions such as constant vehicle speed, negligible cash box loading and unloading time, and each vehicle executing one scheduling task at a time;

[0009] Define decision variable x ij If vehicle V j Assigned to transport cash box B i Then x ij =1, otherwise x ij =0(i∈{1,2,…,n},j∈{1,2,…,m});

[0010] Construct the scheduling cost objective function

[0011] Where C1 is the unit distance transportation cost coefficient. For vehicle V j The distance from the current area to the destination of the cash box, y j For vehicle V j The variable determining whether a vehicle participates in scheduling; C2 represents the fixed cost of vehicle participation in scheduling; the operational efficiency objective function. Where t ij For vehicle V j Transport cash box B i Time required;

[0012] Set vehicle load constraints Constraints on the allocation of cash boxes

[0013] Step 3, perform the first search: for each unassigned cash box B i Calculate V for each vehicle j The probability of being selected to ship this type of box

[0014] According to probability P ij Construct a roulette wheel and select from it using a random number to determine the transport box B. i Vehicle V j Repeat this process until all cash boxes have been allocated.

[0015] Step four, perform a second search: for each unassigned cash box B i Traverse all vehicles V j Calculate transportation costs

[0016] Choose the vehicle with the lowest cost V j Transport cash box B i Repeat this process until all cash boxes have been allocated;

[0017] Step 5: Allocate vehicles according to priority: Define priority rules, set the priority of emergency cash boxes to the highest, and determine the priority of non-emergency cash boxes based on the distance from the vehicle to the destination of the cash box; process emergency cash boxes first, allocate vehicles according to the distance priority principle, then process non-emergency cash boxes, and allocate vehicles according to the distance priority principle in the same way until all cash boxes are allocated.

[0018] Step 6, Simulation Experiment and Algorithm Comparison: Generate multiple sets of simulation data and set simulation experiment parameters;

[0019] Using scheduling cost and operational efficiency as performance evaluation metrics for the algorithms, we ran the first search, the second search, and the priority allocation of vehicles under the same simulation data and parameter settings, recorded the scheduling cost and operational efficiency of the corresponding algorithm combinations, and conducted comparative analysis.

[0020] Scheduling algorithm combination and weight adjustment: Based on the simulation test results, determine the merits of each algorithm under different scenarios, and select the best performing algorithm or algorithm combination for different types of cash box scheduling tasks;

[0021] We define weights w1, w2, and w3 to represent the weights of vehicles in the first search, second search, and priority allocation processes, respectively, in the overall scheduling, and w1 + w2 + w3 = 1. The weights are dynamically adjusted based on the merits of different scenarios.

[0022] The working principle of this invention is as follows: First, the algorithm collects data on cash boxes, vehicles, and areas to provide basic information for scheduling. Then, a cash box and vehicle scheduling model is constructed, assuming constant vehicle speeds, etc. Decision variables are defined, with scheduling cost and operational efficiency as objective functions, and constraints on vehicle load and cash box allocation are set. Next, three heuristic search algorithms are used: the first search calculates the vehicle selection probability inversely proportional to transportation cost and allocates cash boxes using a roulette wheel method; the second search selects the vehicle with the lowest cost for each cash box; and the priority-based algorithm packages scheduling instructions into data frames, sorts them by priority and length, and sends them. Simulation experiments are then conducted to compare algorithm performance. Finally, based on the experimental results, the algorithm combination and weights are adjusted to optimize scheduling.

[0023] In the above scheme, for optimization, the type of the shopping box in the shopping box data is further... This includes, but is not limited to, cash boxes and important document boxes.

[0024] Furthermore, in constructing the cash box vehicle scheduling model, the t in the operational efficiency objective function... ij Based on vehicle speed and distance The calculation yielded the result.

[0025] Furthermore, in the first search, the probability P ij The calculations make it more likely that vehicles with lower transportation costs will be selected to transport cash boxes.

[0026] Furthermore, in the second search, the transportation cost... ij The calculation comprehensively considers the unit distance transportation cost coefficient C1 and the distance from the vehicle to the destination of the cash box. And the fixed cost C2 for vehicles participating in dispatch.

[0027] Furthermore, in the priority-based heuristic algorithm, the emergency cash box priority principle ensures that emergency cash boxes are given priority in vehicle allocation during the scheduling process.

[0028] Furthermore, in the scheduling algorithm combination and weight adjustment steps, the dynamic adjustment of the weights w1, w2, and w3 is based on the scheduling cost and operating efficiency performance of each algorithm in different scenarios during the simulation experiment.

[0029] Furthermore, step five includes:

[0030] 1. Data Frame Generation and Attribute Definition

[0031] 1.1 Dispatch instructions are packaged into data frames, and each vehicle combination and its related dispatch information are packaged into a data frame F. k , where k∈{1,2,…,q}, and q is the total number of data frames;

[0032] 1.2 Define data frame attributes

[0033] Data frame length L(F) k ): Calculation method: L(F k ) = n k , where n k The number of vehicles contained in the k-th data frame; meaning: representing the number of vehicles in the same batch of box truck combinations;

[0034] Data frame transmission rate R(F) k ):

[0035] Calculation method: Assume data frame F k The vehicles in the project are expected to complete m k The scheduling task for each type of box requires time. k ,but Meaning: Represents the efficiency of scheduling and transferring vehicles using the same batch of funds, expressed as tasks / unit of time;

[0036] Data frame priority P(F) k ): Calculation method: For emergency cash boxes (such as cash boxes that need to be dispatched in a short time), P(F k P = 0.8; for ordinary cash boxes (such as cash boxes for important vouchers that are replenished regularly), P k =0.3; Meaning: Indicates the priority of the data frame, with a value range of [0, 1]. The larger the value, the higher the priority.

[0037] 2. Data Frame Sorting

[0038] 2.1 Priority sorting: First, sort all generated data frames according to priority P(F). k Sort the data in descending order to ensure that high-priority data frames are processed before low-priority data frames.

[0039] 2.2 Processing with the same priority: For data frames F with the same priority...i and F j (i.e., P(F) i )=P(F j According to the data frame length L(F) k The data frames are sorted in ascending order, meaning shorter frames are sent first, followed by longer frames. The sorting formula is as follows:

[0040] F k <F l if(P(F k )>P(F l ))or((P(F k )=P(F l ))and(L(F k )<L(F l )))

[0041] 3. Sending scheduling instructions

[0042] 3.1 Complete data frame generation and attribute calculation, traverse all vehicle combinations, and generate a data frame F for each combination. k And calculate its L(F) k ), R(F k ) and P(F k );

[0043] 3.2 Complete the sorting process by using the sorting formula to sort the data frame set {F}. k Sort by priority and length;

[0044] 3.3 Complete the sending of scheduling instructions. Send the data frames sequentially according to the sorted order to execute the scheduling task of the cash box.

[0045] The optimal solution mainly involves the combination of scheduling algorithms and weight adjustment. First, performance evaluations of the first and second search algorithms based on a roulette wheel, and the priority allocation algorithm, are conducted through simulation experiments, recording their scheduling costs and operational efficiency under different scenarios. Based on these experimental results, the superiority or inferiority of each algorithm in different scenarios is clarified. Then, based on the type of cash box scheduling task, such as urgency or non-urgency, cost sensitivity, etc., the most suitable algorithm or combination of algorithms is selected. Simultaneously, corresponding weights are assigned to each algorithm, with a total weight of 1, which is dynamically adjusted according to actual conditions to ensure optimal cash box scheduling performance under different business scenarios, achieving the best balance between scheduling costs and operational efficiency. Attached Figure Description

[0046] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0047] Figure 1 The algorithm flowchart in Example 1 is shown. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0049] Example 1

[0050] This embodiment provides an intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry, such as... Figure 1 It includes the following steps:

[0051] Step 1, Problem Analysis and Data Preparation: Collect and organize the cash box data, including cash box number B. id (id∈{1,2,…,n}, where n is the total number of cash boxes), Cash box type weight Destination area Vehicle data, including vehicle number V j (j∈{1,2,…,m}, where m is the total number of vehicles), vehicle load capacity Restrictions, vehicle location area And regional data, including region number A k (k∈{1, 2, ..., p}, where p is the total number of regions), the distance matrix between regions d(A) i A j );

[0052] Step 2: Construct a cash box vehicle scheduling model: based on assumptions such as constant vehicle speed, negligible cash box loading and unloading time, and each vehicle executing one scheduling task at a time;

[0053] Define decision variable x ij If vehicle V j Assigned to transport cash box B i Then x ij =1, otherwise x ij =0(i∈{1,2,…,n},j∈{1,2,…,m});

[0054] Construct the scheduling cost objective function

[0055] Where C1 is the unit distance transportation cost coefficient. For vehicle V j The distance from the current area to the destination of the cash box, y j For vehicle V j The variable determining whether a vehicle participates in scheduling; C2 represents the fixed cost of vehicle participation in scheduling; the operational efficiency objective function. Where tij For vehicle V j Transport cash box B i Time required;

[0056] Set vehicle load constraints Constraints on the allocation of cash boxes

[0057] Step 3, perform the first search: for each unassigned cash box B i Calculate V for each vehicle j The probability of being selected to ship this type of box

[0058] According to probability P ij Construct a roulette wheel and select from it using a random number to determine the transport box B. i Vehicle V j Repeat this process until all cash boxes have been allocated.

[0059] Step four, perform a second search: for each unassigned cash box B i Traverse all vehicles V j Calculate transportation costs

[0060] Choose the vehicle with the lowest cost V j Transport cash box B i Repeat this process until all cash boxes have been allocated;

[0061] Step 5: Allocate vehicles according to priority: Define priority rules, set the priority of emergency cash boxes to the highest, and determine the priority of non-emergency cash boxes based on the distance from the vehicle to the destination of the cash box; process emergency cash boxes first, allocate vehicles according to the distance priority principle, then process non-emergency cash boxes, and allocate vehicles according to the distance priority principle in the same way until all cash boxes are allocated.

[0062] Step 6, Simulation Experiment and Algorithm Comparison: Generate multiple sets of simulation data and set simulation experiment parameters;

[0063] Using scheduling cost and operational efficiency as performance evaluation metrics for the algorithms, we ran the first search, the second search, and the priority allocation of vehicles under the same simulation data and parameter settings, recorded the scheduling cost and operational efficiency of the corresponding algorithm combinations, and conducted comparative analysis.

[0064] Scheduling algorithm combination and weight adjustment: Based on the simulation test results, determine the merits of each algorithm under different scenarios, and select the best performing algorithm or algorithm combination for different types of cash box scheduling tasks;

[0065] We define weights w1, w2, and w3 to represent the weights of vehicles in the first search, second search, and priority allocation processes, respectively, in the overall scheduling, and w1 + w2 + w3 = 1. The weights are dynamically adjusted based on the merits of different scenarios.

[0066] This embodiment first collects data on cash boxes, vehicles, and areas to provide basic information for scheduling. Then, a cash box and vehicle scheduling model is constructed, assuming constant vehicle speeds, etc. Decision variables are defined, with scheduling cost and operational efficiency as objective functions, and constraints on vehicle load and cash box allocation are set. Next, three heuristic search algorithms are used: the first search calculates the vehicle selection probability inversely proportional to transportation cost and allocates cash boxes using a roulette wheel method; the second search selects the vehicle with the lowest cost for each cash box; and the priority-based algorithm packages scheduling instructions into data frames, sorts them by priority and length, and sends them. Simulation experiments are then conducted to compare algorithm performance. Finally, based on the experimental results, the algorithm combination and weights are adjusted to optimize scheduling.

[0067] Preferably, the type of the shopping box in the shopping box data This includes, but is not limited to, cash boxes and important document boxes.

[0068] Preferably, in constructing the cash box vehicle scheduling model, the objective function for operational efficiency includes t ij Based on vehicle speed and distance The calculation yielded the result.

[0069] Preferably, in the first search, the probability P ij The calculations make it more likely that vehicles with lower transportation costs will be selected to transport cash boxes.

[0070] Preferably, in the second search, the transportation cost is... ij The calculation comprehensively considers the unit distance transportation cost coefficient C1 and the distance from the vehicle to the destination of the cash box. And the fixed cost C2 for vehicles participating in dispatch.

[0071] Preferably, in the priority-based heuristic algorithm, the emergency cash box priority principle ensures that emergency cash boxes are given priority in vehicle allocation during the scheduling process.

[0072] Preferably, in the scheduling algorithm combination and weight adjustment step, the dynamic adjustment of the weights w1, w2, and w3 is based on the scheduling cost and operating efficiency performance of each algorithm in different scenarios during the simulation experiment.

[0073] Preferably, step five includes:

[0074] 1. Data Frame Generation and Attribute Definition

[0075] 1.1 Dispatch instructions are packaged into data frames, and each vehicle combination and its related dispatch information are packaged into a data frame F. k , where k∈{1,2,…,q}, and q is the total number of data frames;

[0076] 1.2 Define data frame attributes

[0077] Data frame length L(F) k ): Calculation method: L(F k ) = n k , where n k The number of vehicles contained in the k-th data frame; meaning: representing the number of vehicles in the same batch of box truck combinations;

[0078] Data frame transmission rate R(F) k ):

[0079] Calculation method: Assume data frame F k The vehicles in the project are expected to complete m k The scheduling task for each type of box requires time. k ,but Meaning: Represents the efficiency of scheduling and transferring vehicles using the same batch of funds, expressed as tasks / unit of time;

[0080] Data frame priority P(F) k ): Calculation method: For emergency cash boxes (such as cash boxes that need to be dispatched in a short time), P(F k P = 0.8; for ordinary cash boxes (such as cash boxes for important vouchers that are replenished regularly), P k =0.3; Meaning: Indicates the priority of the data frame, with a value range of [0, 1]. The larger the value, the higher the priority.

[0081] 2. Data Frame Sorting

[0082] 2.1 Priority sorting: First, sort all generated data frames according to priority P(F). k Sort the data in descending order to ensure that high-priority data frames are processed before low-priority data frames.

[0083] 2.2 Processing with the same priority: For data frames F with the same priority... i and F j (i.e., P(F) i )=P(F j According to the data frame length L(F) k The data frames are sorted in ascending order, meaning shorter frames are sent first, followed by longer frames. The sorting formula is as follows:

[0084] F k <Fl if(P(F k )>P(F l ))or((P(F k )=P(F l ))and(L(F k )<L(F l )))

[0085] 3. Sending scheduling instructions

[0086] 3.1 Complete data frame generation and attribute calculation, traverse all vehicle combinations, and generate a data frame F for each combination. k And calculate its L(F) k ), R(F k ) and P(F k );

[0087] 3.2 Complete the sorting process by using the sorting formula to sort the data frame set {F}. k Sort by priority and length;

[0088] 3.3 Complete the sending of scheduling instructions. Send the data frames sequentially according to the sorted order to execute the scheduling task of the cash box.

[0089] The optimal solution mainly involves the combination of scheduling algorithms and weight adjustment. First, performance evaluations of the first and second search algorithms based on a roulette wheel, and the priority allocation algorithm, are conducted through simulation experiments, recording their scheduling costs and operational efficiency under different scenarios. Based on these experimental results, the superiority or inferiority of each algorithm in different scenarios is clarified. Then, based on the type of cash box scheduling task, such as urgency or non-urgency, cost sensitivity, etc., the most suitable algorithm or combination of algorithms is selected. Simultaneously, corresponding weights are assigned to each algorithm, with a total weight of 1, which is dynamically adjusted according to actual conditions to ensure optimal cash box scheduling performance under different business scenarios, achieving the best balance between scheduling costs and operational efficiency.

[0090] Specifically:

[0091] Suppose there exists a large financial institution with operations covering multiple cities and numerous branches. Every day, it needs to transfer a large number of different types of cash boxes, including cash boxes and boxes containing important documents, between different branches. The current scheduling method is inefficient and costly; therefore, it is decided to optimize it using the intelligent matching scheduling algorithm of this invention.

[0092] II. Data Preparation

[0093] Cargo box data:

[0094] Cash boxes: numbered B1, B2, and B3, weighing 50 kg, 60 kg, and 40 kg respectively, destined for branch A, branch B, and branch C respectively.

[0095] Important document cash boxes: numbered B4 and B5, weighing 20 kg and 30 kg respectively, destined for branch D and branch E respectively. Additionally, the cash boxes are marked as emergency cash boxes, and the important document cash boxes are marked as ordinary cash boxes.

[0096] Vehicle data:

[0097] Vehicle V1, with a maximum load capacity of 200 kg, is located in area X.

[0098] Vehicle V2, with a maximum load capacity of 150 kg, is located in region Y.

[0099] Regional data:

[0100] Given that points A, B, C, D, and E are located in different regions A1, A2, A3, A4, and A5 respectively, the distance matrix between regions is as follows:

[0101]

[0102] III. Constructing a Vehicle Dispatch Model for Cash Boxes

[0103] Assumptions: The vehicle speed is constant during travel. Traffic congestion and other unforeseen circumstances are not considered. The loading and unloading time of the cash box is negligible. Each vehicle can only execute one scheduling task at a time and returns to the initial area after completing the task.

[0104] Decision variable: Let x ij As a decision variable, if vehicle V j Assigned to transport cash box B i Then x ij =1; otherwise x ij =0.

[0105] Objective function:

[0106] Dispatch cost objective function: Assume that the unit distance transportation cost coefficient C1 = 1 and the fixed cost of vehicle participation in dispatching C2 = 100.

[0107] Operational efficiency objective function: calculated based on experience, estimating the travel speed and transportation time of each vehicle.

[0108] Constraints:

[0109] Vehicle load constraints: Ensure that the total weight of the boxes loaded on each vehicle does not exceed its load limit.

[0110] Cash box allocation constraint: Ensure that each cash box has one and only one vehicle responsible for transportation.

[0111] IV. Application of Heuristic Search Algorithms

[0112] Based on the first search algorithm: For cash box B1, calculate the selection probability of vehicles V1 and V2. The distance from vehicle V1 to point A is 50, and the transportation cost is 50×1+100=150; the distance from vehicle V2 to point A is 90, and the transportation cost is 90×1+100=190.

[0113] Calculate the selection probability of V1 V2's selection probability

[0114] Using the roulette wheel, let's assume V1 is selected to transport B1. Repeat this process to complete the allocation of all boxes.

[0115] Second search algorithm: For box B2, the transportation cost of vehicle V1 is calculated as 30×1+100=130, and the transportation cost of vehicle V2 is calculated as 110×1+100=210.

[0116] Select the option with the lowest cost, V1, to transport B2. Continue this process until all boxes are allocated.

[0117] Priority-based scheduling algorithm: Dispatch instructions for vehicle use are packaged into data frames. Data frames for dispatch instructions corresponding to cash deposit boxes are assigned high priority, while those corresponding to important voucher deposit boxes are assigned low priority.

[0118] For data frames with the same priority, they are sorted according to their data frame length (i.e., the number of vehicles). For example, if cash boxes B1 and B3 have the same priority, assuming that the data frame length corresponding to B1 is 1 (only one vehicle is needed for transportation) and the data frame length corresponding to B3 is 2 (two vehicles are needed for transportation), then the dispatch instruction data frame corresponding to B1 will be sent first.

[0119] V. Comparison of Simulation Experiments and Algorithms

[0120] Simulation test design: Using a computer simulation system, generate a large number of data combinations of cash boxes, vehicles and regions similar to those mentioned above, and set different test scenarios, such as different numbers of cash boxes, number of vehicles, and regional distribution.

[0121] Algorithm performance evaluation metrics:

[0122] Scheduling cost: Calculate the scheduling cost of each algorithm under different simulation data. For example, when using the first search algorithm, calculate the total transportation cost of all boxes.

[0123] Operational efficiency: Record the total time required for each algorithm to complete the scheduling of all cash boxes to evaluate operational efficiency.

[0124] Algorithm Comparison and Result Analysis: Under the same simulation data and parameter settings, the first, second, and priority-based scheduling algorithms were run respectively. It was found that the first search algorithm strikes a relatively good balance between cost and efficiency. The second search algorithm has lower cost in some scenarios, but its efficiency is slightly lower. The priority-based heuristic algorithm performs excellently in handling emergency cash boxes, responding quickly to scheduling needs.

[0125] VI. Scheduling Algorithm Combination and Weight Adjustment

[0126] Algorithm combination based on performance evaluation: Based on simulation results, for urgent cash box scheduling, a priority-based heuristic algorithm is preferred to ensure efficiency; for non-urgent and cost-sensitive scheduling tasks, the first search algorithm is used. For example, in this instance, the priority-based heuristic algorithm is used for cash box scheduling, while the first search algorithm is used for important voucher cash box scheduling.

[0127] Weight Adjustment: Define weight w1 、 w2 and w3 represent the weights of the first search algorithm, the second search algorithm, and the priority-based scheduling algorithm in the overall scheduling, respectively, and w1 + w2 + w3 = 1. In subsequent actual scheduling, based on changes in different business scenarios, such as an increase in emergency cash boxes during peak business periods, the weight w3 of the priority-based heuristic algorithm will be appropriately increased to optimize the overall scheduling effect.

[0128] Although the illustrative specific embodiments of the present invention have been described above to enable those skilled in the art to understand the invention, the invention is not limited to the scope of the specific embodiments. For those skilled in the art, all inventions utilizing the concept of the present invention are protected as long as various variations are within the spirit and scope of the invention as defined and determined by the appended claims.

Claims

1. A smart matching and scheduling algorithm based on the flow and storage of different types of boxes in the financial industry, characterized by, Includes the following steps: Step 1, Problem Analysis and Data Preparation: Collect and organize cash box data, including cash box numbers. ( , (Total number of boxes) and box type ,weight Destination area Vehicle data, including vehicle number ( , (Total number of vehicles) and maximum vehicle load capacity The area where the vehicle is located ; And regional data, including area codes. ( , (Total number of regions), inter-region distance matrix ; Step 2, construct a cash container vehicle scheduling model: based on the assumptions that the vehicle speed is constant, the cash container loading and unloading time is negligible, and each vehicle executes one scheduling task at a time; Define decision variables If the vehicle Distributed shipping boxes ,but ,otherwise ( , ); Construct the scheduling cost objective function ； in This is the unit distance transportation cost coefficient. For vehicles The distance from the current location to the destination of the cash box. For vehicles Whether or not a variable participates in scheduling Fixed costs for vehicle participation in dispatching; operational efficiency objective function ,in For vehicles Transport cash box Time required; Set vehicle load constraints ( ) and cash box allocation constraints ( ); Step 3, perform the first search: for each unassigned cash box Calculate each vehicle The probability of being selected to ship this type of box ; According to probability Construct a roulette wheel and select the appropriate cash box by using a random number. vehicles Repeat this process until all cash boxes have been allocated; Step four, perform a second search: for each unassigned cash box Traverse all vehicles Calculate transportation costs ; Choose the vehicle with the lowest cost. Transport cash box Repeat this process until all cash boxes have been allocated; Step 5: Allocate vehicles according to priority: Define priority rules, set the priority of emergency cash boxes to the highest, and determine the priority of non-emergency cash boxes based on the distance from the vehicle to the destination of the cash box; process emergency cash boxes first, allocate vehicles according to the distance priority principle, then process non-emergency cash boxes, and allocate vehicles according to the distance priority principle in the same way until all cash boxes are allocated. Step 6, Simulation Experiment and Algorithm Comparison: Generate multiple sets of simulation data and set simulation experiment parameters; Using scheduling cost and operational efficiency as performance evaluation metrics for the algorithms, we ran the first search, the second search, and the priority allocation of vehicles under the same simulation data and parameter settings, recorded the scheduling cost and operational efficiency of the corresponding algorithm combinations, and conducted comparative analysis. Step 7, Scheduling Algorithm Combination and Weight Adjustment: Determine the merits of each algorithm under different scenarios based on the simulation test results, and select the best performing algorithm or algorithm combination for different types of cash box scheduling tasks; Define weights , , These represent the weights of the first search, second search, and priority allocation vehicles in the integrated scheduling, respectively. The weights of superiority and inferiority are dynamically adjusted in different scenarios.

2. The intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry as described in claim 1, is characterized in that, The type of the cash box in the cash box data This includes cash boxes and important document boxes.

3. The intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry as described in claim 1, is characterized in that... In constructing the vehicle dispatching model for cash boxes, the objective function for operational efficiency includes... Based on vehicle speed and distance The calculation yielded the result.

4. The intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry as described in claim 1, is characterized in that... In the first search, the probability The calculations make it more likely that vehicles with lower transportation costs will be selected to transport cash boxes.

5. The intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry according to claim 1, characterized in that, In the second search, the transportation cost The calculation comprehensively considers the unit distance transportation cost coefficient. Distance from the vehicle to the destination of the cash box and the fixed costs of vehicle dispatching .

6. The intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry according to claim 1, characterized in that, In the priority-based heuristic algorithm, the emergency cash box priority principle ensures that emergency cash boxes are given priority in vehicle allocation during the scheduling process.

7. The intelligent matching and scheduling algorithm for the circulation and storage of different types of cash boxes in the financial industry according to claim 1, characterized in that, In the scheduling algorithm combination and weight adjustment steps, the weights , , The dynamic adjustment is based on the scheduling cost and running efficiency performance of each algorithm in different scenarios in the simulation test.

Images