Apartment rental matching recommendation method and system based on multi-objective optimization

Abstract

The present invention relates to the technical field of apartment rental, and in particular to a method and system for apartment rental matching recommendation based on multi-objective optimization, including: determining the maximization of apartment price and the maximization of tenant satisfaction as optimization objectives; constructing an objective function of the optimization objectives, wherein the decision variables of the objective function include the current price of the apartment, the tenant's satisfaction score for the apartment, and the historical transaction information of the apartment; determining constraints; using a genetic algorithm to calculate the objective function to obtain an optimal solution; and generating a matching recommendation scheme for apartments and tenants based on the optimal solution. The present invention ensures that the interests of both the lessor and the tenant are fully considered by simultaneously optimizing the maximization of apartment price and the maximization of tenant satisfaction. The genetic algorithm can efficiently search for the optimal solution in a large range and improve the accuracy of matching.

Description

Technical Field

[0001] The present invention relates to the technical field of apartment rental, and in particular to a method and system for recommending apartment rental matching based on multi-objective optimization. Background Art

[0002] In the rental market, the interests of landlords and tenants are often in conflict. The landlord hopes to maximize the price of the apartment to obtain higher returns, while the tenant hopes to rent the most cost-effective apartment at the lowest price. This conflicting relationship makes the pricing and evaluation of apartments complicated.

[0003] First, the lessor needs to consider multiple factors when setting the price, including the location, facilities, decoration level, market supply and demand, etc. Apartments with good locations, complete facilities and new decoration can provide a better living experience and usually attract higher rents, so higher rents can be set.

[0004] However, when renting a house, tenants not only consider the price, but also hope to find an apartment that meets their living needs and has a high cost-effectiveness within a limited budget. Cost-effectiveness includes not only the conditions of the apartment itself, but also its superior location and complete facilities.

[0005] In order to maximize the interests of both parties, both the lessor and the tenant need to conduct reasonable evaluation and negotiation. The lessor can conduct market research to understand the rental level of similar apartments and set prices based on the characteristics of their own apartments. When looking for an apartment, the tenant should consider their own needs and budget. Information can be collected through online platforms, intermediary agencies and other channels to compare the conditions and prices of different apartments. In addition, tenants can also negotiate for more favorable conditions, such as reducing deposits, extending leases, etc.

[0006] In this process, how to satisfy both parties is a difficult point. Summary of the invention

[0007] (I) Purpose of the invention

[0008] The purpose of the present invention is to provide an apartment rental matching recommendation method and system based on multi-objective optimization that can improve the satisfaction of both the lessor and the tenant.

[0009] (II) Technical solution

[0010] To solve the above problems, the present invention provides an apartment rental matching recommendation method based on multi-objective optimization, comprising:

[0011] S1: Determine the maximization of apartment price and tenant satisfaction as optimization objectives;

[0012] S2: constructing an objective function of the optimization objective, wherein the decision variables of the objective function include the current price of the apartment, the tenant's satisfaction score for the apartment, and the historical transaction information of the apartment;

[0013] S3: Determine constraints;

[0014] S4: Calculate the objective function using a genetic algorithm to obtain an optimal solution;

[0015] S5: Generate a matching recommendation scheme for apartments and tenants based on the optimal solution.

[0016] In another aspect of the present invention, preferably, the historical transaction information of the apartment includes the historical transaction price of the apartment, the historical transaction volume of the apartment and the historical transaction time of the apartment.

[0017] In another aspect of the present invention, preferably, the objective function is:

[0018]

[0019] Among them, α, β and γ are weights, p i represents the current price of apartment i, s i represents the tenant's satisfaction score for apartment i, h ij represents the price of apartment i in the jth historical transaction, v ij represents the transaction volume of the same apartment as apartment i in the jth historical transaction, t ij represents the time of the jth historical transaction of apartment i, x i Indicates whether apartment i is selected, i = 1, 2, ..., N, N is the total number of apartments, and M is the number of historical transactions of the apartment.

[0020] In another aspect of the present invention, preferably, the constraint conditions include:

[0021]

[0022] Where B represents the maximum budget of the tenant, K represents the maximum number of apartments the tenant can choose, and t now represents the current time, and T represents the time threshold.

[0023] In another aspect of the present invention, preferably, the tenant's satisfaction score for the apartment is determined based on the location of the apartment, the area of ​​the apartment, the orientation of the apartment, the layout of the apartment, the decoration of the apartment and the floor of the apartment.

[0024] In another aspect of the present invention, preferably, the formula for the tenant's satisfaction score for the apartment is:

[0025]

[0026] Among them, s i represents the tenant's satisfaction score for apartment i; L i represents the tenant's rating of the location of apartment i, L max Indicates the maximum value of the position score; A i represents the area of ​​apartment i, A ideal Indicates the ideal area for tenants; i represents the tenant's rating of the orientation of apartment i; F i represents the floor of apartment i, F ideal Indicates the tenant's ideal floor, F max Indicates the maximum value of the floor, F min Indicates the minimum value of the floor; H i represents the tenant's rating of the apartment type of apartment i, H ideal Indicates the tenant's ideal apartment rating; D i represents the tenant's rating of the decoration of apartment i, D ideal Indicates tenant ideal decoration score.

[0027] In another aspect of the present invention, preferably, step S4 specifically includes:

[0028] S41: Initialization: setting the algorithm parameters, including population size, number of iterations, crossover rate, and mutation rate;

[0029] S42: Encoding: x i Encoded into binary representation;

[0030] S43: Fitness function: The fitness function is defined by using the fitness allocation method of multi-objective optimization;

[0031] S44: Iterative optimization: Generate new solutions through selection, crossover, and mutation operations, and evaluate the quality of the solutions according to the fitness function, and continuously iterate and optimize until the termination condition is met;

[0032] S45: Decoding: Decoding the optimal solution.

[0033] In another aspect of the present invention, preferably, the fitness allocation method for multi-objective optimization is a sorting method based on Pareto optimality.

[0034] In another aspect of the present invention, preferably, the termination condition is reaching a set maximum number of iterations.

[0035] In another aspect of the present invention, preferably, a system for recommending apartment rental matching based on multi-objective optimization comprises:

[0036] An optimization target determination module, which is used to determine the maximization of apartment price and the maximization of tenant satisfaction as optimization targets;

[0037] An objective function construction module, which is used to construct an objective function of the optimization objective, wherein the decision variables of the objective function include the current price of the apartment, the tenant's satisfaction score for the apartment, and the historical transaction information of the apartment;

[0038] A constraint condition determination module, which is used to determine the constraint condition;

[0039] A calculation module, which is used to calculate the objective function using a genetic algorithm to obtain an optimal solution;

[0040] A control module is used to generate a matching recommendation scheme for apartments and tenants based on the optimal solution.

[0041] (III) Beneficial effects

[0042] The above technical solution of the present invention has the following beneficial technical effects:

[0043] The present invention ensures that the interests of the lessor and the tenant are fully considered by optimizing the apartment price maximization and the tenant satisfaction maximization at the same time. The objective function includes the current price of the apartment, the tenant's satisfaction score for the apartment and the historical transaction information of the apartment as decision variables, so that the lessor can flexibly adjust the price according to the market situation and the tenant's needs. The tenant satisfaction score is used as one of the decision variables to ensure that the recommendation scheme can meet the tenant's personalized needs and preferences. The use of the apartment's historical transaction information can help evaluate market trends and tenant behavior, thereby providing more accurate price and satisfaction predictions. Genetic algorithms can efficiently search for the optimal solution in a large range and improve the accuracy of matching. By setting reasonable constraints, such as budget constraints, minimum satisfaction requirements, etc., the feasibility and practicality of the recommendation scheme can be ensured. Through automated matching recommendations, the time and cost of the lessor and the tenant to find a suitable apartment or tenant are reduced. In these ways, the apartment rental matching recommendation method based on multi-objective optimization can not only improve the lessor's income, but also ensure that the tenant obtains a highly satisfactory living experience, achieving a win-win situation for both parties. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is an overall flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0046] Obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0048] The present invention will be described in more detail below with reference to the accompanying drawings. In each of the accompanying drawings, the same elements are represented by similar reference numerals. For the sake of clarity, the various parts in the accompanying drawings are not drawn to scale.

[0049] Embodiment 1

[0050] An apartment rental matching recommendation method based on multi-objective optimization. Figure 1 FIG. 1 shows an overall flow chart of an embodiment of the present invention, as shown in FIG. Figure 1 As shown, including:

[0051] S1: Identify the maximization of apartment price and tenant satisfaction as optimization goals; be able to balance the interests of the lessor and the tenant so that both parties can obtain satisfactory results in the leasing process; help to allocate apartment resources more efficiently and ensure that each tenant can obtain an apartment that matches their needs and budget.

[0052] S2: Construct an objective function of the optimization objective, wherein the decision variables of the objective function include the current price of the apartment, the tenant's satisfaction score for the apartment, and the historical transaction information of the apartment; by using price and satisfaction as decision variables, the objective function can find the optimal solution that can maximize the lessor's revenue and ensure tenant satisfaction. By using historical transaction information as a decision variable, more accurate and data-driven pricing decisions can be made based on historical data. By analyzing historical transaction information, potential risks such as high vacancy rates or frequent tenant changes can be predicted and avoided. The objective function can allocate apartment resources more effectively to ensure that each tenant can obtain an apartment that matches their needs and budget. The specific content of the apartment's historical transaction information is not limited here. In this embodiment, the apartment's historical transaction information includes the apartment's historical transaction price, the apartment's historical transaction volume, and the apartment's historical transaction time; the specific content of the objective function is also not limited here. In this embodiment, the objective function is:

[0053]

[0054] Among them, α, β and γ are weights, p i represents the current price of apartment i, s i represents the tenant's satisfaction score for apartment i, hij represents the price of apartment i in the jth historical transaction, v ij represents the transaction volume of the same apartment as apartment i in the jth historical transaction, t ij represents the time of the jth historical transaction of apartment i, x i Indicates whether apartment i is selected, i = 1, 2, ..., N, N is the total number of apartments, and M is the number of historical transactions of the apartment.

[0055] In the above, It means that the lessor starts from the current apartment price p i The benefits gained from By calculating the historical transaction price h of apartment i ij With the current price p i The average absolute difference between the historical transaction prices of apartments reflects the impact of the volatility of the apartment's historical transaction prices on the interests of the lessor. The impact of the historical transaction volume of the same apartment on the interests of the lessor is taken into account. That is, in the objective function, by adding the volatility of the historical transaction price and the historical transaction volume as considerations of the lessor's interests, the price volatility reflects the stability of the apartment price, while the historical transaction volume reflects the market demand for the apartment.

[0056] S3: Determine the constraints; the specific content of the constraints is not limited here, optional, budget constraints: ensure that the tenant's rental budget matches the apartment price to avoid exceeding the tenant's ability to pay. Quality standard constraints: ensure that the recommended apartments meet certain quality standards, such as safety, cleanliness and maintenance requirements. Geographical location constraints: limit the geographical location of the apartment based on the tenant's work location, school or other preferences. Living space constraints: ensure that the size of the apartment meets the living needs of the tenant's family. Facilities and service constraints: include requirements for internal and external facilities of the apartment, such as gyms, swimming pools, parking lots, etc. Lease term constraints: set a minimum or maximum lease term to accommodate the tenant's living plan. Tenant credit score constraints: limit recommended apartments based on the tenant's credit score to reduce the risk of the lessor. Legal and regulatory constraints: comply with local rental laws and regulations, such as rental contract requirements, rent control, etc. Market trend constraints: consider market rental trends to ensure that pricing is within a reasonable range. Environmental factor constraints: consider the environmental characteristics of the apartment, such as energy-saving standards, green building certification, etc. Community environment constraints: based on the tenant's preferences for the community environment, such as safety, quietness, etc. Pet policy constraints:

[0057] For apartments that allow pets, set relevant policies and conditions. Lease terms constraints: Clarify the terms in the lease contract, such as deposits, early termination clauses, etc. Constraints ensure the feasibility of the solution, that is, the recommended apartment and tenant matching plan is executable in the real world. By setting constraints, the lessor can avoid the financial risks caused by too high or too low prices. Constraints can help ensure that all rental plans comply with local laws and regulations and avoid legal disputes. Clear constraints increase the transparency of the optimization process, so that both lessors and tenants can clearly understand the basis for the decision. By meeting the specific needs and preferences of tenants, constraints help improve tenants' satisfaction with the recommended plans. Optionally, in this embodiment, the constraints include:

[0058]

[0059] Where B represents the maximum budget of the tenant, K represents the maximum number of apartments the tenant can choose, and t now represents the current time, T represents the time threshold, and T is used to limit the historical transaction time of the selected apartment to not be too long, so as to ensure that the historical transaction data considered has a certain timeliness.

[0060] The specific content of the tenant's satisfaction rating for the apartment is not limited here. Optional: Location satisfaction: evaluate the tenant's satisfaction with the apartment's location, including the convenience of being close to the workplace, school, public transportation and living facilities. Spatial layout satisfaction: consider the tenant's preference for the interior spatial layout of the apartment, such as the size and layout of the bedroom, living room, kitchen and bathroom. Decoration and maintenance satisfaction: evaluate the tenant's satisfaction with the decoration quality and maintenance status of the apartment. Facility satisfaction: includes satisfaction with the internal and external facilities of the apartment, such as furniture, appliances, gym, swimming pool, etc. Community environment satisfaction: evaluate the tenant's satisfaction with the community environment, including security, greenery, noise level, etc. Price and value satisfaction: consider the tenant's satisfaction with whether the apartment price is consistent with the value they receive. Neighborhood relationship satisfaction: tenants' satisfaction with the neighborhood community and neighbor relations. Lease terms satisfaction: includes satisfaction with lease terms such as lease term, rent adjustment, and renewal policy. Privacy and quietness satisfaction: tenants' satisfaction with the privacy protection and quiet living environment provided by the apartment. Sustainability satisfaction: evaluates tenants' satisfaction with the environmental protection features and sustainability measures of the apartment. Satisfaction with pet friendliness: For tenants with pets, the satisfaction level of whether the apartment allows pets and the relevant regulations. Satisfaction with transportation convenience: The tenant’s satisfaction with the diversity and convenience of transportation to the apartment. Satisfaction with living convenience: Including satisfaction with living conveniences such as nearby shops, restaurants, and entertainment facilities. Satisfaction with safety: The tenant’s satisfaction with the apartment’s safety measures and emergency services. Satisfaction with personalized needs: Considering the personalized needs of tenants, such as workspaces, children’s play areas, etc. Service satisfaction: Including satisfaction with services such as property management and maintenance response. Long-term living satisfaction: The tenant’s satisfaction with the apartment as a long-term residence, including future appreciation potential, etc. With these optional satisfaction rating dimensions, the lessor can have a more comprehensive understanding of the tenants’ needs and preferences, thereby providing a more personalized apartment recommendation plan that meets the tenants’ expectations. This helps to improve the overall satisfaction of tenants, establish long-term rental relationships, and enhance the market competitiveness of the lessor.

[0061] In this embodiment, the tenant's satisfaction score for the apartment is determined based on the apartment's location, the apartment's area, the apartment's orientation, the apartment's layout, the apartment's decoration, and the apartment's floor;

[0062] The formula for tenants' satisfaction rating of an apartment is:

[0063]

[0064] Among them, s i represents the tenant's satisfaction score for apartment i; L i represents the tenant's rating of the location of apartment i, L max Indicates the maximum value of the position score; Ai represents the area of ​​apartment i, A ideal Indicates the ideal area for tenants; i represents the tenant's rating of the orientation of apartment i; F i represents the floor of apartment i, F ideal Indicates the tenant's ideal floor, F max Indicates the maximum value of the floor, F min Indicates the minimum value of the floor; H i represents the tenant's rating of the apartment type of apartment i, H ideal Indicates the tenant's ideal apartment rating; D i represents the tenant's rating of the decoration of apartment i, D ideal Represents the tenant's ideal decoration score. The above formula covers multiple key attributes of the apartment, including location, area, orientation, floor, unit type and decoration, providing tenants with a comprehensive evaluation tool. By standardizing the scores of each factor, consistency and comparability of the scores are ensured. The tenant's ideal area, ideal floor and ideal decoration scores are taken into account, so that the satisfaction score can reflect the tenant's personalized needs. The geometric mean is more balanced because it reduces the extreme impact of any one factor on the overall score.

[0065] S4: Genetic algorithms are used to calculate the objective function and obtain the optimal solution. Genetic algorithms are good at global search in large-scale search spaces, which helps to find the global optimal solution or high-quality solution. Genetic algorithms do not rely on the specific form of the mathematical model of the problem, nor are they sensitive to the initial solution of the problem, and have good robustness. The algorithm can dynamically adjust parameters such as crossover rate and mutation rate according to the complexity of the problem to adapt to different optimization problems. Genetic algorithms can handle multi-objective optimization problems well, and consider multiple optimization goals at the same time by designing appropriate fitness functions and selection mechanisms. Through mutation operations, genetic algorithms can jump out of local optimal solutions and continue to search for possible global optimal solutions.

[0066] The specific content of using a genetic algorithm to calculate the objective function and obtain the optimal solution is not limited here. In this embodiment, step S4 specifically includes:

[0067] S41: Initialization: setting the algorithm parameters, including population size, number of iterations, crossover rate, and mutation rate;

[0068] S42: Encoding: x i Encoded into binary representation;

[0069] S43: Fitness function: The fitness function is defined by using the fitness allocation method of multi-objective optimization;

[0070] S44: Iterative optimization: Generate new solutions through selection, crossover, and mutation operations, and evaluate the quality of the solutions according to the fitness function, and continuously iterate and optimize until the termination condition is met;

[0071] S45: Decoding: Decoding the optimal solution.

[0072] S5: Generate a matching recommendation scheme for apartments and tenants based on the optimal solution.

[0073] Furthermore, in this embodiment, the fitness allocation method for multi-objective optimization is a Pareto optimal sorting method. The termination condition is reaching the set maximum number of iterations.

[0074] The present invention ensures that the interests of the lessor and the tenant are fully considered by optimizing the apartment price maximization and the tenant satisfaction maximization at the same time. The objective function includes the current price of the apartment, the tenant's satisfaction score for the apartment and the historical transaction information of the apartment as decision variables, so that the lessor can flexibly adjust the price according to the market situation and the tenant's needs. The tenant satisfaction score is used as one of the decision variables to ensure that the recommendation scheme can meet the tenant's personalized needs and preferences. The use of the apartment's historical transaction information can help evaluate market trends and tenant behavior, thereby providing more accurate price and satisfaction predictions. Genetic algorithms can efficiently search for the optimal solution in a large range and improve the accuracy of matching. By setting reasonable constraints, such as budget constraints, minimum satisfaction requirements, etc., the feasibility and practicality of the recommendation scheme can be ensured. Through automated matching recommendations, the time and cost of the lessor and the tenant to find a suitable apartment or tenant are reduced. In these ways, the apartment rental matching recommendation method based on multi-objective optimization can not only improve the lessor's income, but also ensure that the tenant obtains a highly satisfactory living experience, achieving a win-win situation for both parties.

[0075] Embodiment 2

[0076] An apartment rental matching recommendation system based on multi-objective optimization, the system comprising:

[0077] An optimization target determination module, which is used to determine the maximization of apartment price and the maximization of tenant satisfaction as optimization targets;

[0078] An objective function construction module, which is used to construct an objective function of the optimization objective, wherein the decision variables of the objective function include the current price of the apartment, the tenant's satisfaction score for the apartment, and the historical transaction information of the apartment;

[0079] A constraint condition determination module, which is used to determine the constraint condition;

[0080] A calculation module, which is used to calculate the objective function using a genetic algorithm to obtain an optimal solution;

[0081] A control module is used to generate a matching recommendation scheme for apartments and tenants based on the optimal solution.

[0082] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

[0083] The present invention has been described above with reference to the embodiments of the present invention. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. The scope of the present invention is defined by the appended claims and their equivalents. Without departing from the scope of the present invention, a person skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

[0084] Although the embodiments of the present invention have been described in detail, it should be understood that the various changes, substitutions, and alterations could be made hereto without departing from the spirit and scope of the invention.

[0085] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A method for recommending apartment rental matching based on multi-objective optimization, characterized in that: include: S1: Determine the maximization of apartment price and tenant satisfaction as optimization goals; S2: constructing an objective function of the optimization objective, wherein the decision variables of the objective function include the current price of the apartment, the tenant's satisfaction score for the apartment, and the historical transaction information of the apartment; S3: Determine constraints; S4: Calculate the objective function using a genetic algorithm to obtain an optimal solution; S5: Generate a matching recommendation scheme for apartments and tenants based on the optimal solution; The historical transaction information of the apartment includes the historical transaction price of the apartment, the historical transaction volume of the apartment and the historical transaction time of the apartment; The objective function is: Among them, α, β and γ are weights, p i represents the current price of apartment i, s i represents the tenant's satisfaction score for apartment i, h ij represents the price of apartment i in the jth historical transaction, v ij represents the transaction volume of the apartment identical to apartment i in the jth historical transaction, t ij represents the time of the jth historical transaction of apartment i, x i Indicates whether apartment i is selected, i = 1, 2, ..., N, N represents the total number of apartments, and M represents the number of historical transactions of the apartment; The constraints include: Where B represents the maximum budget of the tenant, K represents the maximum number of apartments the tenant can choose, and t now represents the current time, and T represents the time threshold.

2. The method according to claim 1, characterized in that The tenant's satisfaction score for the apartment is determined based on the apartment's location, apartment's area, apartment's orientation, apartment's layout, apartment's decoration and apartment's floor.

3. The method according to claim 2, characterized in that The formula for tenants' satisfaction rating of an apartment is: Among them, s i represents the tenant's satisfaction score for apartment i; L i represents the tenant's rating of the location of apartment i, L max Indicates the maximum value of the position score; A i represents the area of ​​apartment i, A ideal Indicates the ideal area for tenants; i represents the tenant's rating of the orientation of apartment i; F i represents the floor of apartment i, F ideal Indicates the tenant's ideal floor, F max Indicates the maximum value of the floor, F min Indicates the minimum value of the floor; H i represents the tenant's rating of the apartment type of apartment i, H ideal Indicates the tenant's ideal apartment rating; D i represents the tenant's rating of the decoration of apartment i, D ideal Indicates tenant ideal decoration score.

4. The method according to claim 3, characterized in that Step S4 specifically includes: S41: Initialization: setting the algorithm parameters, including population size, number of iterations, crossover rate, and mutation rate; S42: Encoding: x i Encoded into binary representation; S43: Fitness function: The fitness function is defined by using the fitness allocation method of multi-objective optimization; S44: Iterative optimization: Generate new solutions through selection, crossover, and mutation operations, and evaluate the quality of the solutions according to the fitness function, and continuously iterate and optimize until the termination condition is met; S45: Decoding: Decoding the optimal solution.

5. The method according to claim 4, characterized in that The fitness allocation method for multi-objective optimization is a sorting method based on Pareto optimality.

6. The method according to claim 5, characterized in that The termination condition is reaching the set maximum number of iterations.

7. An apartment rental matching recommendation system based on multi-objective optimization, characterized in that: The system comprises: An optimization target determination module, which is used to determine the maximization of apartment price and the maximization of tenant satisfaction as optimization targets; An objective function construction module, which is used to construct an objective function of the optimization objective, wherein the decision variables of the objective function include the current price of the apartment, the tenant's satisfaction score for the apartment, and the historical transaction information of the apartment; A constraint condition determination module, which is used to determine the constraint condition; A calculation module, which is used to calculate the objective function using a genetic algorithm to obtain an optimal solution; A control module, which is used to generate a matching recommendation scheme between apartments and tenants based on the optimal solution; The historical transaction information of the apartment includes the historical transaction price of the apartment, the historical transaction volume of the apartment and the historical transaction time of the apartment; The objective function is: Among them, α, β and γ are weights, p i represents the current price of apartment i, s i represents the tenant's satisfaction score for apartment i, h ij represents the price of apartment i in the jth historical transaction, v ij represents the transaction volume of the apartment identical to apartment i in the jth historical transaction, t ij represents the time of the jth historical transaction of apartment i, x i Indicates whether apartment i is selected, i = 1, 2, ..., N, N represents the total number of apartments, and M represents the number of historical transactions of the apartment; The constraints include: Where B represents the maximum budget of the tenant, K represents the maximum number of apartments the tenant can choose, and t now represents the current time, and T represents the time threshold.

Images