Transaction data processing method and system for deposit-free credit leasing

Abstract

The invention discloses a deposit-free credit lease transaction data processing method and system. The method comprises the following steps: obtaining lease transaction order information of a lease user; obtaining user credit information, analyzing the rental item information and the rental duration information, and determining system inventory information according to the rental item information; according to the user credit information, the lease item information, the lease duration information and the system inventory information, establishing a lease decision model under multiple constraint conditions, and determining an objective function of the model; calculating an optimal solution of the target function based on an improved particle swarm algorithm, and determining a lease strategy according to the optimal solution, including lease terms and a risk monitoring scheme; and drawing up an article lease contract according to the lease terms, sending the article lease contract to the lease user, and after the lease contract signed by the user is received, performing risk monitoring on a lease behavior according to a risk monitoring scheme. The method can accurately grasp user demands, flexibly adjust lease terms, effectively identify default risks, reduce loss and improve stock utilization rate.

Description

Technical Field

[0001] The present invention relates to the technical field of online leasing, and in particular to a transaction data processing method and system for deposit-free credit leasing. Background Art

[0002] With the rise of the sharing economy and leasing models, the leasing market is expanding rapidly. More and more consumers of electronic devices prefer to lease rather than buy. Consumers' recognition of credit is increasing, and users hope to obtain fair and reasonable terms during the leasing process. At the same time, leasing companies also hope to reduce risks through user credit information. With the advancement of technologies such as big data, artificial intelligence and blockchain, leasing companies are able to better collect and analyze user data, thereby making more accurate leasing decisions.

[0003] However, many leasing companies lack effective data integration mechanisms and are unable to effectively process and analyze data from different channels (such as user credit data, historical leasing data, inventory information, etc.). When allocating or managing inventory, they usually rely only on inventory systems and manual judgment, lacking intelligent analysis of user demand forecasts and inventory information. In terms of risk control, they are often based on fixed rules, lack flexibility and real-time performance, and are unable to cope with complex and changing market demands. In addition, most existing leasing terms and contracts are in fixed formats, without personalized adjustments based on the credit status of different users, the characteristics of the leased items, and the length of the lease, resulting in inflexible leasing conditions and inadequate risk control.

[0004] Therefore, the present invention proposes a transaction data processing method and system for deposit-free credit leasing, which not only considers user credit information, but also combines multiple factors such as rental item information, rental duration, inventory information, etc. to perform comprehensive data processing and analysis, establish a decision-making model under multiple constraints, improve the accuracy of leasing decisions, and enhance risk management capabilities. Summary of the invention

[0005] The present invention provides a transaction data processing method and system for deposit-free credit leasing, which is used to solve the technical problem that the existing online leasing risk management method does not fully consider the specific behavior and social relationships of users, resulting in the inability to accurately evaluate and manage the risk level of leasing users.

[0006] In order to solve the above problems, in a first aspect, the present invention provides a transaction data processing method for deposit-free credit leasing, comprising:

[0007] Obtain the rental transaction order information of the rental user;

[0008] Acquire user credit information corresponding to the rental user, parse the rental item information and rental duration information in the rental transaction order information, and determine the system inventory information of the rental item according to the rental item information;

[0009] Establishing a rental decision model under multiple constraints based on the user credit information, rental item information, rental duration information and system inventory information, and determining an objective function of the rental decision model;

[0010] Calculating the optimal solution of the objective function under the constraint conditions based on an improved particle swarm algorithm, and determining a leasing strategy according to the optimal solution, wherein the leasing strategy includes leasing terms and a risk monitoring plan;

[0011] An item rental contract is drawn up according to the rental terms and sent to the rental user. After receiving the rental contract signed by the user, risk monitoring of the rental behavior is performed according to the risk monitoring plan.

[0012] Furthermore, the leasing decision model includes a leasing item operating cost model, a leasing income model, and a default risk model;

[0013] The rental item operation cost model is used to determine the loss cost and delivery time cost of the rental item based on the rental item information, rental duration information and system inventory information;

[0014] The rental income model is used to determine the rental income amount of the rental item based on the user credit information, the rental item information and the rental duration information;

[0015] The default risk model is used to determine the default loss of the leased item based on the user credit information and the leased item information.

[0016] Furthermore, the objective function of the leasing decision model is:

[0017] When the transportation time cost satisfies the rental duration information, the rental gross profit is determined according to the rental income amount and the loss cost;

[0018] The comprehensive profit is determined based on the gross profit of the lease and the breach loss, and maximizing the comprehensive profit is used as the objective function of the lease decision model, which is expressed as follows:

[0019] f tar =max[c1·g(X,W,T)-c2·N-c3(p·L)],

[0020] In the formula, f taris the objective function, c1, c2, c3 are weight coefficients respectively, g(·) is a calculation function based on user credit information X, rental item information W and rental duration information T, which is used to determine the rental income; N is the loss cost, p is the default probability, and L is the default loss.

[0021] Furthermore, the user credit information includes credit score data and maximum free deposit limit;

[0022] The rental item information includes the item's value information, quantity information, daily depreciation information, and rental location information;

[0023] The rental duration information includes the rental start time and rental days of the item;

[0024] The system inventory information includes the inventory quantity of items, reservation information, storage location and transportation price information.

[0025] Furthermore, the default probability p is determined according to the user's credit score and the maximum free deposit limit, and is expressed as follows:

[0026]

[0027] In the formula, β1, β2, and β3 are preset coefficients, E is the maximum free-deposit limit, S is the credit score, and Z is the user's basic information quantitative score.

[0028] Furthermore, the optimal solution of the objective function is calculated based on the improved particle swarm algorithm, including:

[0029] Initialize the particle swarm population and set the speed and position of the swarm particles;

[0030] Calculating the fitness of each particle according to the objective function;

[0031] Apply simulated annealing to each particle for local search and adjust the particle's velocity and position;

[0032] Iteratively update the position and velocity of each particle according to the individual optimal solution and the global optimal solution;

[0033] When the maximum number of iterations is reached, the global optimal solution of the objective function is obtained.

[0034] Furthermore, simulated annealing is applied to each particle for local search to adjust the particle's velocity and position, including:

[0035] Each particle decides whether to accept the new position based on the acceptance probability of simulated annealing, and the calculation formula of the acceptance probability is:

[0036]

[0037] Where T is the current temperature, indicating the activity of the search, and the temperature gradually decreases after each iteration; f(x i (t)) is the particle's current position x i (t), f(x i (t+1)) is the particle's new position x i Fitness at (t+1);

[0038] When f(x i (t+1))≤f(x i (t)) with acceptance probability P acc Accept the new position;

[0039] When f(x i (t+1))>f(x i (t)), accept the new position.

[0040] Furthermore, the particle velocity update formula is:

[0041] v i (t+1)=w·v i (t)+q1·r1·(pbest i -xi)+q2·r2·(gbest-x i )

[0042] The position update formula is:

[0043] x i (t+1)=x i (t)+v i (t+1)

[0044] Among them, v i (t) is the velocity of particle i at the tth iteration, pbest i is the best historical position of particle i, gbest is the position of the global optimal solution, r1 and r2 are random numbers between [0,1], w is the inertia weight, q1 and q2 are acceleration constants.

[0045] In a second aspect, the present invention further provides a transaction data processing system for deposit-free credit leasing, comprising:

[0046] The transaction information acquisition module is used to obtain the rental transaction order information of the rental user;

[0047] An analysis module, used to obtain user credit information corresponding to the rental user, parse the rental item information and rental duration information in the rental transaction order information, and determine the system inventory information of the rental item according to the rental item information;

[0048] A model building module, used to build a rental decision model under multiple constraints according to the user credit information, rental item information, rental duration information and system inventory information, and determine the objective function of the rental decision model;

[0049] A decision module, used to calculate the optimal solution of the objective function based on an improved particle swarm algorithm, and determine a lease strategy according to the optimal solution, wherein the lease strategy includes lease terms and a risk monitoring plan;

[0050] The scheme execution module is used to prepare an item rental contract according to the rental terms and send it to the rental user. After receiving the rental contract signed by the user, the risk monitoring of the rental behavior is carried out according to the risk monitoring scheme.

[0051] In a third aspect, the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, a transaction data processing method for deposit-free credit leasing as described in any of the above technical solutions is implemented.

[0052] Compared with the prior art, the advantages of the present invention are:

[0053] (1) By establishing a leasing decision model under multiple constraints and using big data analysis technology to make decisions based on user behavior and market trends, we can more accurately grasp market demand and optimize inventory management. At the same time, the flexibility of the leasing decision model allows us to adjust leasing terms and strategies in a timely manner according to market changes, user behavior and inventory conditions to maintain competitive advantages.

[0054] (2) Based on the improved particle swarm algorithm to calculate the optimal solution of the objective function, more attractive leasing terms can be formulated to improve user satisfaction and increase customer stickiness. Through personalized leasing terms and clear contract processes, the user experience can be improved and the user's trust in the platform can be enhanced.

[0055] (3) Through the analysis of user credit information and the implementation of risk monitoring solutions, potential default risks can be effectively identified and losses during the leasing process can be reduced. Through real-time monitoring and dynamic adjustments, efficient use of leased items can be ensured, inventory backlogs can be reduced, and overall operational efficiency can be improved.

[0056] (4) Clear leasing terms and contract content ensure the legality and transparency of the transaction and reduce legal risks.

[0057] In summary, the present invention can accurately grasp user needs and flexibly adjust lease terms, effectively identify default risks, reduce losses and improve inventory utilization, and clarify lease terms to ensure the legality and transparency of transactions and reduce legal risks. It takes into account factors such as decision-making efficiency, user experience, risk control and compliance, and has strong practical value in the field of item leasing. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A flow chart of a transaction data processing method for deposit-free credit leasing provided by the present invention;

[0059] Figure 2 A structural schematic diagram of a transaction data processing system for deposit-free credit leasing provided by the present invention;

[0060] Figure 3 The present invention provides a schematic structural diagram of an electronic device. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0062] This embodiment provides a method for processing transaction data of a deposit-free credit lease. Figure 1 As shown, Figure 1 It is a flowchart of the transaction data processing method of the deposit-free credit leasing, including:

[0063] Step S101: Acquire the rental transaction order information of the rental user;

[0064] Step S102: obtaining user credit information corresponding to the rental user, parsing the rental item information and rental duration information in the rental transaction order information, and determining the system inventory information of the rental item according to the rental item information;

[0065] Step S103: establishing a rental decision model under multiple constraints based on the user credit information, rental item information, rental duration information and system inventory information, and determining the objective function of the rental decision model;

[0066] Step S104: calculating the optimal solution of the objective function under the multiple constraints based on the improved particle swarm algorithm, and determining a leasing strategy according to the optimal solution, wherein the leasing strategy includes leasing terms and a risk monitoring plan;

[0067] Step S105: drafting an item rental contract according to the rental terms and sending it to the rental user; after receiving the rental contract signed by the user, performing risk monitoring on the rental behavior according to the risk monitoring plan.

[0068] The transaction data processing method for deposit-free credit leasing provided in this embodiment combines user credit information, leased item information, lease duration and inventory management, and adopts optimization algorithms and risk monitoring mechanisms to ensure that the leasing process is efficient, accurate and safe. The combination of deposit-free and refined risk management helps improve user experience and platform operation efficiency, ensures leasing safety while lowering user thresholds, and enhances market competitiveness.

[0069] As a preferred embodiment, the leasing decision model includes a leasing item operating cost model, a leasing income model and a default risk model;

[0070] The rental item operation cost model is used to determine the loss cost and delivery time cost of the rental item based on the rental item information, rental duration information and system inventory information;

[0071] The rental income model is used to determine the rental income amount of the rental item based on the user credit information, the rental item information and the rental duration information;

[0072] The default risk model is used to determine the default loss of the leased item based on the user credit information and the leased item information.

[0073] As a preferred embodiment, the objective function of the leasing decision model is:

[0074] When the transportation time cost satisfies the rental duration information, the rental gross profit is determined according to the rental income amount and the loss cost;

[0075] The comprehensive profit is determined based on the gross profit of the lease and the breach loss, and maximizing the comprehensive profit is used as the objective function of the lease decision model, which is expressed as follows:

[0076] f tar =max[c1·g(X,W,T)-c2·N-c3(p·L)],

[0077] In the formula, f tar is the objective function, c1, c2, c3 are weight coefficients respectively, g(·) is a calculation function based on user credit information X, rental item information W and rental duration information T, which is used to determine the rental income; N is the loss cost, p is the default probability, and L is the default loss.

[0078] As a preferred embodiment, the user credit information includes credit score data and a maximum free-deposit limit;

[0079] The rental item information includes the item's value information, quantity information, daily depreciation information, and rental location information;

[0080] The rental duration information includes the rental start time and rental days of the item;

[0081] The system inventory information includes the inventory quantity of items, reservation information, storage location and transportation price information.

[0082] As a specific embodiment, the constraint conditions of the objective function include at least:

[0083] 1. Inventory constraints:

[0084] Item inventory quantity ≥ quantity information of user's order;

[0085] This constraint ensures that when a rental platform rents out an item, there are enough items in stock to rent. If the stock is zero or negative, no rental can be made.

[0086] 2. Lease duration constraints:

[0087] The shortest rental duration is ≤ the rental duration ordered by the user

[0088] This constraint ensures that the rental duration is within an acceptable range to meet the customer's rental needs.

[0089] 3. Delivery time constraints:

[0090] Order time + maximum delivery time ≤ rental start time

[0091] This constraint ensures that the delivery time of items from the rental platform to the user is within the acceptable maximum delivery time to ensure user experience and service quality.

[0092] 4. Credit constraints:

[0093] User credit score ≥ minimum acceptable credit score for the value of the rental item

[0094] This constraint is used to ensure that, based on the value of the item, only users whose credit scores are above the preset credit score can rent the item, so as to reduce the risk of default.

[0095] It should be noted that in some embodiments, for users whose actual credit score is within a preset range from the lower limit of the credit score set for the rental item, they can also rent the item by paying a deposit corresponding to the proportion of the item, so as to improve user satisfaction. In this case, the income generated by the deposit needs to be taken into account when calculating the profit amount.

[0096] As a preferred embodiment, the default probability p is determined according to the user's credit score and the maximum free deposit limit, and is expressed as follows:

[0097]

[0098] In the formula, β1, β2, and β3 are preset coefficients, E is the maximum free-deposit limit, S is the credit score, and Z is the user's basic information quantitative score.

[0099] As a specific embodiment, the user's basic information quantitative score includes other factors that affect the probability of default, such as the number of rentals, user age, type of rental items, etc. The calculation complexity is relatively low, suitable for large-scale data sets, and has fast training and prediction speeds. It can not only give classification results, but also output the probability of default, which is convenient for decision making.

[0100] In order to further improve the accuracy of the particle swarm optimization algorithm and avoid falling into the local optimal solution, we combine the simulated annealing algorithm (SA) with the particle swarm optimization algorithm (PSO). By adding the simulated annealing mechanism to the local search phase of the particle swarm algorithm, the accuracy of the solution can be improved.

[0101] As a preferred embodiment, calculating the optimal solution of the objective function under the constraint conditions based on an improved particle swarm algorithm includes:

[0102] Initializing the particle swarm population under the constraints, and setting the speed and position of the swarm particles;

[0103] Calculating the fitness of each particle according to the objective function;

[0104] Apply simulated annealing to each particle for local search and adjust the particle's velocity and position;

[0105] Iteratively update the position and velocity of each particle according to the individual optimal solution and the global optimal solution;

[0106] When the maximum number of iterations is reached, the global optimal solution of the objective function is obtained.

[0107] By applying simulated annealing to each particle for local search through the above method, the quality of the solution can be further improved and the convergence speed can be enhanced. The improved particle swarm algorithm can effectively handle the optimization problem of complex objective functions under multiple constraints discussed in this embodiment and ensure the feasibility of the optimal solution.

[0108] As a preferred embodiment, simulated annealing is applied to each particle to perform local search and adjust the speed and position of the particle, including:

[0109] Each particle decides whether to accept the new position based on the acceptance probability of simulated annealing, and the calculation formula of the acceptance probability is:

[0110]

[0111] Where T is the current temperature, indicating the activity of the search, and the temperature gradually decreases after each iteration; f(x i (t)) is the particle's current position x i (t), f(x i (t+1)) is the particle's new position x i Fitness at (t+1);

[0112] When f(x i (t+1))≤f(x i (t)) with acceptance probability P acc Accept the new position;

[0113] When f(xi(t+1))>f(xi(t)), it is determined that the new position is accepted.

[0114] The meaning of the above method is: when the new solution is better than the original solution, then P acc close to 1, the new solution is almost always accepted. If the new solution is worse than the current solution by P acc It will still be greater than 0, which means that there is a non-zero probability of accepting a worse solution, which helps the algorithm escape from the local optimum.

[0115] As a specific embodiment, after each local search, the temperature of simulated annealing is gradually reduced to reduce the probability of accepting a poor solution. The temperature update method is exponential decay, which is expressed as:

[0116] T new =η·T old

[0117] Among them, T new is the updated temperature, T old is the current temperature, η is the annealing factor, a constant less than 1, used to control the rate at which the temperature decreases. In the actual solution process, it is usually between 0.9 and 0.99. After each iteration, the temperature will decrease by this factor, that is, as time goes by, the algorithm is less and less likely to accept a worse solution, thus switching from global search to local search.

[0118] As a preferred embodiment, the particle speed update formula is:

[0119] v i (t+1)=w·v i (t)+q1·r1·(pbest i -xi)+q2·r2·(gbest-x i )

[0120] The position update formula is:

[0121] x i (t+1)=x i (t)+v i (t+1)

[0122] Among them, v i (t) is the velocity of particle i at the tth iteration, pbest i is the best historical position of particle i, gbest is the position of the global optimal solution, r1 and r2 are random numbers between [0,1], w is the inertia weight, q1 and q2 are acceleration constants.

[0123] The present invention is described in detail below through a specific numerical example.

[0124] Suppose a user logs in to the online rental platform and chooses that he needs a laptop computer with a rental period of 30 days.

[0125] The system automatically obtains the user's credit information based on the login information provided by the user. For example, if the user's credit score is 750, the corresponding maximum free deposit amount is 5,000 yuan. The laptop is worth 5,000 yuan; the current inventory is 50 units, and multiple warehouses can arrive before the rental start time. First determine the number of reservations, their respective transportation costs, and the daily loss cost of each laptop.

[0126] Based on the user's credit score, the user's rental price range is determined, the upper and lower income limits are determined, and based on the user's credit score of 750, the default probability is calculated to be 5% (assuming that the default probability corresponding to a score of 750 is 5%), and then the operating expenses and default losses are calculated based on the computer value and depreciation.

[0127] Next, the improved particle swarm algorithm is used to calculate the optimal solution of the objective function. The python code is as follows:

[0128] #Calculate default loss

[0129] defcalculate_default_loss(computer_value,default_probability):

[0130] return computer_value*default_probability

[0131] #Calculate rental income

[0132] defcalculate_rental_income(daily_rent,rental_days):

[0133] return daily_rent*rental_days

[0134] #Calculate rental gross profit

[0135] defcalculate_rental_profit(rental_income,loss_cost,transport_cost):

[0136] return rental_income-loss_cost-transport_cost

[0137] #Particle swarm algorithm objective function

[0138] def pso_target_function(x,daily_rent,rental_days,loss_cost,transport_cost,default_loss):

[0139] #x[0] is the daily rental fee, x[1] is the number of rental days

[0140] rental_income=calculate_rental_income(x[0],x[1])

[0141] rental_profit=calculate_rental_profit(rental_income,loss_cost,transport_cost)

[0142] net_profit=rental_profit-default_loss#Total profit taking into account default loss

[0143] return-net_profit#PSO is usually minimized, so it returns a negative profit, indicating maximization of profit

[0144] #Particle Swarm Optimization

[0145] for iteration in range(num_iterations):

[0146] # Update speed and position

[0147] for i in range(num_particles):

[0148] velocities[i] = velocities[i] + np.random.rand() * (personal_best_positions[i] - particles[i]) + np.random.rand() * (global_best_position - particles[i])

[0149] particles[i] = particles[i] + velocities[i]

[0150] # Update personal best solution

[0151] for i in range(num_particles):

[0152] score = pso_target_function(particles[i], daily_rent, rental_days, loss_cost, transport_cost, default_loss)

[0153] if score < personal_best_scores[i]:

[0154] personal_best_scores[i] = score

[0155] personal_best_positions[i] = particles[i]

[0156] # Update global best solution

[0157] min_score_idx = np.argmin(personal_best_scores)

[0158] if personal_best_scores[min_score_idx] < global_best_score:

[0159] global_best_score = personal_best_scores[min_score_idx]

[0160] global_best_position=personal_best_positions[min_score_idx]

[0161] return global_best_position

[0162] It can be seen from the above method that the present invention has significant advantages over the existing technology: by establishing a leasing decision-making model under multiple constraints and big data analysis, the market demand can be accurately grasped and the leasing terms can be flexibly adjusted; the leasing terms can be optimized using an improved particle swarm algorithm to improve user satisfaction and trust; user credit information can be analyzed and risk monitoring can be implemented to effectively identify default risks, reduce losses and improve inventory utilization; and clear leasing terms can ensure the legality and transparency of transactions and reduce legal risks.

[0163] Specifically, after the lease contract is generated, the system will send the contract to the lease user via email, the lease platform or other forms. The contract will include the leased items, lease fees, lease duration, user responsibilities, etc. The lease user needs to read and sign the contract to confirm that they agree to the terms. Once the user signs, the contract officially takes effect. After the contract is signed, in order to ensure the smooth progress of the lease and minimize possible risks, the system will implement a risk monitoring plan. This usually includes:

[0164] 1. For rental users, the system will continuously monitor their credit status (such as payment status, item return status, etc.) and assess whether there is a risk of default.

[0165] 2. Use IoT devices to track the usage status of rented items. For example, rented electronic devices can be equipped with GPS or other sensors to monitor the location and status of items in real time.

[0166] 3. Expiration reminder and tracking: The system sets up an automatic reminder function for lease expiration, and if the item is not returned on time or there is a problem, the tracking and notification mechanism will be activated.

[0167] 4. Provide risk warnings based on user behavior patterns (such as delayed payment, frequent changes of address, etc.) and take countermeasures manually or automatically.

[0168] See also Figure 2 This embodiment also provides a transaction data processing system 200 for credit leasing without deposit, including:

[0169] The transaction information acquisition module 201 is used to obtain the rental transaction order information of the rental user;

[0170] The analysis module 202 is used to obtain the user credit information corresponding to the rental user, analyze the rental item information and rental duration information in the rental transaction order information, and determine the system inventory information of the rental item according to the rental item information;

[0171] A model building module 203 is used to build a rental decision model under multiple constraints based on the user credit information, rental item information, rental duration information and system inventory information, and determine the objective function of the rental decision model;

[0172] A decision module 204 is used to calculate the optimal solution of the objective function based on the improved particle swarm algorithm, and determine a lease strategy according to the optimal solution, wherein the lease strategy includes lease terms and risk monitoring solutions;

[0173] The solution execution module 205 is used to prepare an item rental contract according to the rental terms and send it to the rental user. After receiving the rental contract signed by the user, the risk monitoring of the rental behavior is performed according to the risk monitoring solution.

[0174] This embodiment further provides an electronic device 300 , which may be a computing device such as a mobile terminal, a desktop computer, a notebook, a palm computer, a server, etc. The electronic device includes a processor 301 , a memory 302 , and a display 303 .

[0175] In some embodiments, the memory 302 may be an internal storage unit of a computer device, such as a hard disk or memory of a computer device. In other embodiments, the memory 302 may also be an external storage device of a computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory 302 may also include both an internal storage unit of a computer device and an external storage device. The memory 302 is used to store application software and various types of data installed on the computer device, such as program codes for installing the computer device. The memory 302 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a transaction data processing method program 304 for a deposit-free credit lease is stored on the memory 302, and the transaction data processing method program 304 for a deposit-free credit lease can be executed by the processor 301, thereby realizing a transaction data processing method for a deposit-free credit lease in each embodiment of the present invention.

[0176] In some embodiments, the processor 301 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 302, such as executing a transaction data processing method program for deposit-free credit leasing.

[0177] In some embodiments, the display 303 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 303 is used to display information on the computer device and to display a visual user interface. The components 301-303 of the computer device communicate with each other through a system bus.

[0178] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A transaction data processing method for deposit-free credit leasing, characterized in that: include; Obtain the rental transaction order information of the rental user; Acquire user credit information corresponding to the rental user, parse the rental item information and rental duration information in the rental transaction order information, and determine the system inventory information of the rental item based on the rental item information; Establishing a rental decision model under multiple constraints based on the user credit information, rental item information, rental duration information and system inventory information, and determining an objective function of the rental decision model; Calculating the optimal solution of the objective function under the constraints based on an improved particle swarm algorithm, and determining a leasing strategy according to the optimal solution, wherein the leasing strategy includes leasing terms and a risk monitoring plan; An item rental contract is drawn up according to the rental terms and sent to the rental user. After receiving the rental contract signed by the user, risk monitoring of the rental behavior is performed according to the risk monitoring plan.

2. The transaction data processing method for deposit-free credit leasing according to claim 1 is characterized in that: The leasing decision model includes a leasing item operating cost model, a leasing income model and a default risk model; The rental item operation cost model is used to determine the loss cost and delivery time cost of the rental item based on the rental item information, rental duration information and system inventory information; The rental income model is used to determine the rental income amount of the rental item based on the user credit information, the rental item information and the rental duration information; The default risk model is used to determine the default loss of the leased item based on the user credit information and the leased item information.

3. The transaction data processing method for deposit-free credit leasing according to claim 2 is characterized in that: The objective function of the leasing decision model is: When the transportation time cost satisfies the rental duration information, the rental gross profit is determined according to the rental income amount and the loss cost; The comprehensive profit is determined based on the gross profit of the lease and the breach loss, and maximizing the comprehensive profit is used as the objective function of the lease decision model, which is expressed as follows: f tar =max[c1·g(X,W,T)-c2·N-c3(p·L)], In the formula, f tar is the objective function, c1, c2, c3 are weight coefficients respectively, g(·) is a calculation function based on user credit information X, rental item information W and rental duration information T, which is used to determine the rental income; N is the loss cost, p is the default probability, and L is the default loss.

4. The transaction data processing method for deposit-free credit leasing according to claim 3 is characterized in that: The user credit information includes credit score data and maximum free-deposit limit; The rental item information includes the item's value information, quantity information, daily depreciation information, and rental location information; The rental duration information includes the rental start time and rental days of the item; The system inventory information includes the inventory quantity of items, reservation information, storage location and transportation price information.

5. The transaction data processing method for deposit-free credit leasing according to claim 3 is characterized in that: The default probability p is determined according to the user's credit score and the maximum free deposit limit, and is expressed as follows: In the formula, β1, β2, and β3 are preset coefficients, E is the maximum free-deposit limit, S is the credit score, and Z is the user's basic information quantitative score.

6. The transaction data processing method for deposit-free credit leasing according to claim 1 is characterized in that: Calculating the optimal solution of the objective function under the constraint conditions based on the improved particle swarm algorithm includes: Initializing the particle swarm population under the constraints, and setting the speed and position of the swarm particles; Calculating the fitness of each particle according to the objective function; Apply simulated annealing to each particle for local search and adjust the particle's velocity and position; Iteratively update the position and velocity of each particle according to the individual optimal solution and the global optimal solution; When the maximum number of iterations is reached, the global optimal solution of the objective function is obtained.

7. The transaction data processing method for deposit-free credit leasing according to claim 6 is characterized in that: Apply simulated annealing to each particle to perform a local search and adjust the particle's velocity and position, including: Each particle decides whether to accept the new position based on the acceptance probability of simulated annealing, and the calculation formula of the acceptance probability is: Where T is the current temperature, indicating the activity of the search, and the temperature gradually decreases after each iteration; f(x i (t)) is the particle's current position x i (t), f(x i (t+1)) is the particle's new position x i Fitness at (t+1); When f(x i (t+1))≤f(x i (t)) with acceptance probability P acc Accept the new position; When f(x i (t+1))>f(x i (t)), accept the new position.

8. The transaction data processing method for deposit-free credit leasing according to claim 6 is characterized in that: The particle velocity update formula is: v i (t+1)=w·v i (t)+q1·r1·(pbest i -xi)+q2·r2·(gbest-x i ) The position update formula is: x i (t+1)=x i (t)+v i (t+1) Among them, v i (t) is the velocity of particle i at the tth iteration, pbest i is the best historical position of particle i, gbest is the position of the global optimal solution, r1 and r2 are random numbers between [0,1], w is the inertia weight, q1 and q2 are acceleration constants.

9. A transaction data processing system for credit leasing without deposit, characterized in that: include: The transaction information acquisition module is used to obtain the rental transaction order information of the rental user; An analysis module, used to obtain user credit information corresponding to the rental user, parse the rental item information and rental duration information in the rental transaction order information, and determine the system inventory information of the rental item according to the rental item information; A model building module, used to build a rental decision model under multiple constraints according to the user credit information, rental item information, rental duration information and system inventory information, and determine the objective function of the rental decision model; A decision module, used to calculate the optimal solution of the objective function based on an improved particle swarm algorithm, and determine a lease strategy according to the optimal solution, wherein the lease strategy includes lease terms and a risk monitoring plan; The solution execution module is used to prepare an item rental contract according to the rental terms and send it to the rental user. After receiving the rental contract signed by the user, the risk monitoring of the rental behavior is carried out according to the risk monitoring solution.

10. An electronic device, characterized in that: It comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the transaction data processing method for deposit-free credit leasing as described in any one of claims 1-8 is implemented.

Images