Apartment rental matching recommendation method and system based on big data

Abstract

The present invention relates to the field of housing rental technology, and specifically to a big data-based apartment rental matching recommendation method and system, comprising: obtaining user information and room status information of all apartments, using big data technology to match the lease expiration time of the user's current apartment with the vacancy time of all apartments and matching the user's room condition demand information with the room condition supply information of all apartments; and recommending apartments to users based on the matching results. The present invention can quickly process and analyze user information and apartment room status information through big data technology, greatly improving the matching efficiency and reducing the time cost of users in finding suitable apartments. Not only the user's room condition demand information is taken into account, but also the user's lease expiration time is combined, so that the recommendation results are more in line with the user's actual situation and time requirements, improving user experience and satisfaction.

Description

Technical Field

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

[0002] In today's rapidly developing society, the rental market is active. With the accelerated pace of life and frequent changes in work locations, changing rentals has become a problem that many people have to face. In this context, an efficient and intelligent rental recommendation system is particularly important. However, although the existing rental recommendation system has solved some of the user's needs to a certain extent, it still has many shortcomings in practical applications.

[0003] First, information overload is a common problem. When users are looking for a new rental house, they are often faced with a huge amount of house information, including the type, location, price, supporting facilities, etc. Without an effective screening mechanism, it is difficult for users to quickly filter out the houses that meet their needs from this information. Information overload not only increases users' search costs, but also reduces the efficiency of renting houses.

[0004] Secondly, lack of personalization is another major flaw of existing rental recommendation systems. Traditional rental recommendation systems often use standardized recommendation algorithms, which usually recommend houses based on some common parameters, such as price, area, etc. However, each user's needs are unique, and they may have different preferences for the decoration style, surrounding environment, transportation convenience, etc. of the house. Standardized recommendation algorithms are difficult to meet the personalized needs of users, making it difficult for users to find houses that are truly suitable for them.

[0005] In addition, the lack of intelligent decision support is also a shortcoming of existing rental recommendation systems. Most recommendation systems lack deep learning of user behaviors and preferences and cannot provide intelligent decision support. Summary of the invention

[0006] (I) Purpose of the invention

[0007] The purpose of the present invention is to provide a big data-based apartment rental matching recommendation method and system that can improve recommendation satisfaction.

[0008] (II) Technical solution

[0009] In order to solve the above problems, the present invention provides an apartment rental matching recommendation method based on big data, the method comprising:

[0010] S1: Obtain user information and room status information of all apartments, wherein the user information includes the room condition demand information of the user and the lease expiration time of the user's current apartment, and the room status information of all apartments includes the room condition supply information of all apartments and the vacancy time of all apartments;

[0011] S2: using big data technology, matching the lease expiration time of the user's current apartment with the vacancy time of all the apartments and matching the user's housing condition demand information with the housing condition supply information of all the apartments;

[0012] S3: Recommend apartments to users based on the matching results.

[0013] In another aspect of the present invention, preferably, step S2 specifically includes:

[0014] S210: Filter out the apartments whose vacancy time is not later than the lease expiration time of the current apartment of the user from all the apartments and mark them as a target apartment set;

[0015] S220: Calculating the matching degree between the housing condition supply information of each apartment in the target apartment set and the housing condition demand information of the user;

[0016] Step S3 specifically includes:

[0017] The apartment with the highest calculated matching value is recommended to the user.

[0018] In another aspect of the present invention, preferably, the housing condition demand information of the user includes the desired apartment location, the desired apartment area, the desired apartment orientation, the desired apartment type, the desired apartment decoration and the desired apartment floor:

[0019] The housing condition supply information of each of the apartments includes the location of the apartment, the area of ​​the apartment, the orientation of the apartment, the apartment type, the decoration of the apartment and the floor of the apartment;

[0020] Step 220 specifically includes:

[0021] For each apartment, the location of the required apartment, the area of ​​the required apartment, the orientation of the required apartment, the apartment type of the required apartment, the decoration of the required apartment, the floor of the required apartment, the location of the supplied apartment, the area of ​​the supplied apartment, the orientation of the supplied apartment, the apartment type of the supplied apartment, the decoration of the supplied apartment and the floor of the supplied apartment are input into a preset housing matching degree calculation model to calculate the matching degree calculation value of each apartment;

[0022] All apartments in the target apartment set are sorted from high to low according to the obtained calculated matching degree values.

[0023] In another aspect of the present invention, preferably, step S2 specifically includes:

[0024] S211: Compare the vacancy time of all the apartments with the lease expiration time of the user's current apartment;

[0025] S2211: If the vacancy time of the apartment is later than the lease expiration time of the user's current apartment, the time matching value P of the apartment is time-a for:

[0026]

[0027] S2212: If the vacancy time of the apartment is not later than the lease expiration time of the user's current apartment, the time matching value P of the apartment is time-b for:

[0028]

[0029] Among them, α and β are coefficients, α<β, T vacant is the vacancy time of the apartment, T due The expiration date of the user's current apartment lease;

[0030] S231: Calculate the matching degree of each apartment's housing condition supply information and the user's housing condition demand information to obtain a matching degree calculation value of each apartment;

[0031] S241: Correcting the calculated matching value based on the time matching value of each apartment;

[0032] Step S3 specifically includes:

[0033] The apartment with the highest calculated corrected matching value is recommended to the user.

[0034] In another aspect of the present invention, preferably, the housing condition demand information of the user includes the desired apartment location, the desired apartment area, the desired apartment orientation, the desired apartment type, the desired apartment decoration and the desired apartment floor:

[0035] The housing condition supply information of each of the apartments includes the location of the apartment, the area of ​​the apartment, the orientation of the apartment, the apartment type, the decoration of the apartment and the floor of the apartment;

[0036] Step 231 specifically includes:

[0037] For each apartment, the required apartment location, the required apartment area, the required apartment orientation, the required apartment type, the required apartment decoration, the required apartment floor, the supplied apartment location, the supplied apartment area, the supplied apartment orientation, the supplied apartment type, the supplied apartment decoration and the supplied apartment floor are input into a preset house matching degree calculation model to calculate the matching degree calculation value of each apartment.

[0038] In another aspect of the present invention, preferably, the formula of the preset house matching degree calculation model is:

[0039]

[0040] Among them, MD represents the preset house matching degree, W pos represents the position weight, P pos Indicates the position matching degree, with a value range of 0-1; W area represents the area weight, P area Indicates the area matching degree, with a value range of 0-1; W dir represents the orientation weight, P dir Indicates the orientation matching degree, with a value range of 0-1; W type Represents the weight of the apartment type, P type Indicates the apartment type matching degree, with a value range of 0-1; W ren Represents the decoration weight, P ren Indicates the decoration matching degree, the value range is 0-1; W floor Represents the floor weight, P floor Indicates the floor matching degree, the value range is 0-1, I area-dir Indicates the interaction matching degree between area and orientation, I type-ren Indicates the interactive matching degree between apartment type and decoration, I pos-floor Indicates the interaction matching degree between location and floor.

[0041] In another aspect of the present invention, preferably,

[0042] The position matching degree is calculated using the following formula:

[0043]

[0044] Among them, P pos represents the location matching degree, d is the actual distance between the user's required apartment area and the supply apartment location; D max It is the set maximum distance threshold. If it exceeds the set maximum distance threshold, the matching degree is 0;

[0045] The area matching degree is calculated using the following formula:

[0046]

[0047] Among them, P area Indicates the area matching degree, A demand is the user's desired apartment location, A supply Indicates the area of ​​the apartment provided; A max is the maximum area threshold set;

[0048] The orientation matching degree is calculated using the following formula:

[0049]

[0050] Among them, P dir Indicates the orientation matching degree, dir demand Indicates the direction of the apartment required by the user, dir supply Indicates the orientation of the supply apartment;

[0051] The apartment type matching degree is calculated using the following formula:

[0052]

[0053] Among them, P type Indicates the apartment type matching degree, T demand represents the set of apartment types required by the user, T supply Represents the supply of apartment unit types;

[0054] The decoration matching degree is calculated using the following formula:

[0055]

[0056] Among them, P ren Indicates the decoration matching degree, ω i represents the weight of the i-th decoration feature, n represents the number of decoration features, d i is the mismatch degree of the i-th decoration feature;

[0057] The floor matching degree is calculated using the following formula:

[0058]

[0059] Among them, P floor Indicates the floor matching degree, F demand is the user's demand apartment floor, F supply Indicates the supply apartment floor; F max is the maximum floor difference threshold set.

[0060] In another aspect of the present invention, preferably, the interaction matching degree between the area and the orientation is calculated using the following formula:

[0061] I area-dir=P area ·f(P dir )

[0062] Among them, I area-dir represents the interaction matching degree between area and orientation, P area represents the area matching degree, f(P dir ) is the orientation matching degree P dir The function of represents the influence of orientation on overall satisfaction;

[0063] The interactive matching degree between the apartment type and the decoration is calculated using the following formula:

[0064] I type-ren =P type ·g(P ren )

[0065] Among them, I type-ren represents the interactive matching degree between apartment type and decoration, P type represents the apartment type matching degree, g(P ren ) is the decoration matching degree P ren The function of represents the impact of decoration on overall satisfaction;

[0066] The interaction matching degree between the position and the floor is calculated using the following formula:

[0067] I pos-floor =P pos ·h(P floor )

[0068] Among them, I pos-floor Represents the interaction matching degree between location and floor, P pos Indicates the position matching degree, h(P floor ) is the floor matching degree P floor A function that represents the impact of the floor on the overall satisfaction.

[0069] In another aspect of the present invention, preferably,

[0070] The f(P dir ) is calculated using the following formula:

[0071]

[0072] Among them, k dir represents the coefficient of control orientation influence;

[0073] The g(P ren ) is calculated using the following formula:

[0074]

[0075] Among them, kren represents the coefficient for controlling the impact of decoration;

[0076] The h(P floor ) is calculated using the following formula:

[0077]

[0078] Among them, k floor A coefficient that represents the influence of the control floor.

[0079] In another aspect of the present invention, preferably, a big data-based apartment rental matching recommendation system comprises:

[0080] An acquisition module, which is used to acquire user information and room status information of all apartments, wherein the user information includes the room status demand information of the user and the lease expiration time of the user's current apartment, and the room status information of all apartments includes the room status supply information of all apartments and the vacancy time of all apartments;

[0081] A matching module, which is used to match the lease expiration time of the user's current apartment with the vacancy time of all the apartments and to match the housing condition demand information of the user with the housing condition supply information of all the apartments by using big data technology;

[0082] The recommendation module is used to recommend apartments to users based on the matching results.

[0083] (III) Beneficial effects

[0084] The above technical solution of the present invention has the following beneficial technical effects:

[0085] The present invention can quickly process and analyze user information and apartment status information through big data technology, greatly improving the matching efficiency and reducing the time cost of users in finding suitable apartments. Not only the user's housing condition demand information is taken into account, but also the user's lease expiration time is combined, so that the recommendation results are more in line with the user's actual situation and time requirements, and the degree of personalization of the recommendation is improved. The configuration of apartment resources is optimized, the vacancy rate is reduced, and the efficiency of apartment use is improved. Users can quickly find suitable apartments according to their needs, improve user experience, and increase satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 It is an overall flow chart of an embodiment of the present invention. DETAILED DESCRIPTION

[0087] 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.

[0088] 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.

[0089] 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.

[0090] Embodiment 1

[0091] A matching recommendation method for apartment rental based on big data. Figure 1 FIG. 1 shows an overall flow chart of an embodiment of the present invention, as shown in FIG. Figure 1 As shown, the method includes:

[0092] S1: Obtain user information and room status information of all apartments, where user information includes user's room condition demand information and the lease expiration time of the user's current apartment, and room status information of all apartments includes room condition supply information of all apartments and vacancy time of all apartments; collect detailed room condition demand information from users, such as the type of apartment desired by users (such as single room, one bedroom and one living room, two bedrooms and one living room, etc.), location preference, rental budget, whether furniture is needed, lease period, etc. At the same time, the lease expiration time of the user's current apartment will also be obtained, which is crucial for users to find a suitable moving and rental time window in the future. Real-time room status information of all apartments will also be obtained from the apartment management end, including apartment type, area, specific location, rent, vacancy time, etc. This information will serve as the basic data for subsequent matching.

[0093] S2: Using big data technology, the lease expiration date of the user's current apartment is matched with the vacancy time of all apartments, and the housing condition demand information of the user is matched with the housing condition supply information of all apartments; the specific matching method is not limited here.

[0094] In one embodiment of the present invention, further,

[0095] Step S2 specifically includes:

[0096] S210: Filter out the apartments whose vacancy time is not later than the lease expiration time of the user's current apartment from all the apartments and mark them as the target apartment set; in this step, the system will filter out all the apartments whose vacancy time is not later than the lease expiration time of the user's current apartment according to the lease expiration time of the user's current apartment. These apartments constitute the target apartment set, which means that these apartments are available for occupancy when the user needs to move.

[0097] S220: Calculate the matching degree of the housing supply information of each apartment in the target apartment set with the housing demand information of the user; after the target apartment set is screened, the system calculates the matching degree of each apartment in the set. The matching degree here is based on the similarity or conformity between the housing supply information of the apartment and the housing demand information of the user.

[0098] S3: Recommend an apartment to the user based on the matching results. Specifically, recommend an apartment with the highest calculated matching value to the user.

[0099] Furthermore, in this embodiment, the user's housing condition requirement information includes the required apartment location, required apartment area, required apartment orientation, required apartment type, required apartment decoration and required apartment floor:

[0100] The housing condition information of each apartment includes the location, area, orientation, type, decoration and floor level of the apartment.

[0101] For each apartment, the location of the required apartment, the area of ​​the required apartment, the orientation of the required apartment, the type of apartment, the decoration of the required apartment, the floor of the required apartment, the location of the supplied apartment, the area of ​​the supplied apartment, the orientation of the supplied apartment, the type of apartment, the decoration of the supplied apartment and the floor of the supplied apartment are input into a preset housing matching degree calculation model to calculate the matching degree calculation value of each apartment;

[0102] All apartments in the target apartment set are sorted from high to low according to the calculated matching values.

[0103] In another embodiment of the present invention, further,

[0104] Step S2 specifically includes:

[0105] S211: Compare the vacancy time of all apartments with the lease expiration time of the user's current apartment; perform time judgment on all apartments and calculate time matching values. Since the user needs to wait for the time to change the apartment when the apartment is vacant later, the vacancy time of all apartments is calculated according to the lease expiration time.

[0106] S2211: If the vacancy time of the apartment is later than the lease expiration time of the user's current apartment, the time matching value of the apartment is P time-a for:

[0107]

[0108] S2212: If the vacancy time of the apartment is not later than the expiration time of the current apartment lease of the user, the time matching value of the apartment is P time-b for:

[0109]

[0110] Among them, α and β are coefficients, α<β, T vacant is the vacancy time of the apartment, T due The expiration date of the user's current apartment lease;

[0111] S231: Calculate the matching degree of each apartment's housing condition supply information and the user's housing condition demand information to obtain a matching degree calculation value of each apartment;

[0112] S241: Correcting the calculated matching value based on the time matching value of each apartment;

[0113] The correction method may be to use the product of the corresponding time matching value and the matching calculation value as the corrected post-matching calculation value.

[0114] Step S3 specifically includes:

[0115] The apartment with the highest calculated corrected matching value is recommended to the user.

[0116] Furthermore, the user's housing demand information includes the desired apartment location, the desired apartment area, the desired apartment orientation, the desired apartment type, the desired apartment decoration and the desired apartment floor:

[0117] The housing condition information of each apartment includes the location, area, orientation, type, decoration and floor level of the apartment.

[0118] For each apartment, the demand apartment location, demand apartment area, demand apartment orientation, demand apartment type, demand apartment decoration, demand apartment floor, supply apartment location, supply apartment area, supply apartment orientation, supply apartment type, supply apartment decoration and supply apartment floor are input into a preset house matching degree calculation model to calculate the matching degree calculation value of each apartment.

[0119] In the above two embodiments,

[0120] The formula for the preset housing matching calculation model is:

[0121]

[0122] Among them, MD represents the preset house matching degree, W pos represents the position weight, P pos Indicates the position matching degree, with a value range of 0-1; W area represents the area weight, P area Indicates the area matching degree, with a value range of 0-1; W dir represents the orientation weight, P dir Indicates the orientation matching degree, with a value range of 0-1; W type Represents the weight of the apartment type, P type Indicates the apartment type matching degree, with a value range of 0-1; W ren Represents the decoration weight, P ren Indicates the decoration matching degree, the value range is 0-1; W floor Represents the floor weight, P floor Indicates the floor matching degree, the value range is 0-1, I area-dir Indicates the interaction matching degree between area and orientation, I type-ren Indicates the interactive matching degree between apartment type and decoration, I pos-floor Indicates the interaction matching degree between location and floor.

[0123] By combining the matching of various dimensions such as location, area, orientation, apartment type, decoration and floor, a more comprehensive apartment matching evaluation can be provided. Users can adjust the corresponding weights according to their emphasis on different dimensions to obtain more personalized apartment recommendations. By considering the interaction between area and orientation, apartment type and decoration, and location and floor, the comprehensive needs of users can be better met and user satisfaction can be improved. A clear matching calculation formula can help users and apartment providers make more reasonable and scientific decisions. The formulated matching calculation provides a clear evaluation standard and enhances the transparency of the entire matching process. Through automated matching calculation, apartments can be quickly screened and sorted, improving search and recommendation efficiency. Highly matching recommendations can increase the possibility of user selection, thereby facilitating the conclusion of transactions. Weights and interaction coefficients can be dynamically adjusted according to market changes and user feedback to adapt to changing market needs.

[0124] Furthermore, the position matching degree is calculated using the following formula:

[0125]

[0126] Among them, P pos represents the location matching degree, d is the actual distance between the user's required apartment area and the supply apartment location; D maxIt is the set maximum distance threshold. If it exceeds the set maximum distance threshold, the matching degree is 0;

[0127] The area matching degree is calculated using the following formula:

[0128]

[0129] Among them, P area Indicates the area matching degree, A demand is the user's desired apartment location, A supply Indicates the area of ​​the apartment provided; A max is the maximum area threshold set;

[0130] The orientation match is calculated using the following formula:

[0131]

[0132] Among them, P dir Indicates the orientation matching degree, dir demand Indicates the direction of the apartment required by the user, dir supply Indicates the orientation of the supply apartment;

[0133] The apartment type matching degree is calculated using the following formula:

[0134]

[0135] Among them, P type Indicates the apartment type matching degree, T demand represents the set of apartment types required by the user, T supply Represents the supply of apartment unit types;

[0136] The decoration matching degree is calculated using the following formula:

[0137]

[0138] Among them, P ren Indicates the decoration matching degree, ω i represents the weight of the i-th decoration feature, n represents the number of decoration features, d i is the mismatch degree of the i-th decoration feature;

[0139] The floor matching degree is calculated using the following formula:

[0140]

[0141] Among them, P floor Indicates the floor matching degree, F demand is the user's demand apartment floor, F supply Indicates the supply apartment floor; F max is the maximum floor difference threshold set.

[0142] The interaction degree between area and orientation is calculated using the following formula:

[0143] I area-dir =P area ·f(P dir )

[0144] Among them, I area-dir represents the interaction matching degree between area and orientation, P area represents the area matching degree, f(P dir ) is the orientation matching degree P dir The function of represents the influence of orientation on overall satisfaction;

[0145] The interactive matching degree between apartment type and decoration is calculated using the following formula:

[0146] I type-ren =P type ·g(P ren )

[0147] Among them, I type-ren represents the interactive matching degree between apartment type and decoration, P type represents the apartment type matching degree, g(P ren ) is the decoration matching degree P ren The function of represents the impact of decoration on overall satisfaction;

[0148] The interactive matching degree between location and floor is calculated using the following formula:

[0149] I pos-floor =P pos ·h(P floor )

[0150] Among them, I pos-floor Represents the interaction matching degree between location and floor, P pos Indicates the position matching degree, h(P floor ) is the floor matching degree P floor A function that represents the impact of the floor on the overall satisfaction.

[0151] f(P dir ) is calculated using the following formula:

[0152]

[0153] Among them, k dir represents the coefficient of control orientation influence;

[0154] g(P ren ) is calculated using the following formula:

[0155]

[0156] Among them, k ren represents the coefficient for controlling the impact of decoration;

[0157] h(P floor ) is calculated using the following formula:

[0158]

[0159] Among them, k floor A coefficient that represents the influence of the control floor.

[0160] The present invention can quickly process and analyze user information and apartment status information through big data technology, greatly improving the matching efficiency and reducing the time cost of users in finding suitable apartments. Not only the user's housing condition demand information is taken into account, but also the user's lease expiration time is combined, so that the recommendation results are more in line with the user's actual situation and time requirements, and the degree of personalization of the recommendation is improved. The configuration of apartment resources is optimized, the vacancy rate is reduced, and the efficiency of apartment use is improved. Users can quickly find suitable apartments according to their needs, improve user experience, and increase satisfaction.

[0161] Embodiment 2

[0162] An apartment rental matching recommendation system based on big data, characterized in that the system includes:

[0163] An acquisition module, which is used to acquire user information and room status information of all apartments, wherein the user information includes the room status demand information of the user and the lease expiration time of the user's current apartment, and the room status information of all apartments includes the room status supply information of all apartments and the vacancy time of all apartments;

[0164] A matching module, which uses big data technology to match the lease expiration time of the user's current apartment with the vacancy time of all apartments and to match the user's housing condition demand information with the housing condition supply information of all apartments;

[0165] The recommendation module is used to recommend apartments to users based on the matching results.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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 big data, characterized in that: The method comprises: S1: Obtain user information and room status information of all apartments, wherein the user information includes the room condition demand information of the user and the lease expiration time of the user's current apartment, and the room status information of all apartments includes the room condition supply information of all apartments and the vacancy time of all apartments; S2: using big data technology, matching the lease expiration time of the user's current apartment with the vacancy time of all the apartments and matching the user's housing condition demand information with the housing condition supply information of all the apartments; S3: Recommend apartments to users based on the matching results; Wherein, step S2 specifically includes: S210: Filter out the apartments whose vacancy time is not later than the lease expiration time of the current apartment of the user from all the apartments and mark them as a target apartment set; S220: Calculating the matching degree between the housing condition supply information of each apartment in the target apartment set and the housing condition demand information of the user; Step S3 specifically includes: Recommend the apartment with the highest calculated matching value to the user; The user's housing demand information includes the desired apartment location, desired apartment area, desired apartment orientation, desired apartment type, desired apartment decoration and desired apartment floor: The housing condition supply information of each of the apartments includes the location of the apartment, the area of ​​the apartment, the orientation of the apartment, the apartment type, the decoration of the apartment and the floor of the apartment; Step 220 specifically includes: For each apartment, the location of the required apartment, the area of ​​the required apartment, the orientation of the required apartment, the apartment type of the required apartment, the decoration of the required apartment, the floor of the required apartment, the location of the supplied apartment, the area of ​​the supplied apartment, the orientation of the supplied apartment, the apartment type of the supplied apartment, the decoration of the supplied apartment and the floor of the supplied apartment are input into a preset housing matching degree calculation model to calculate the matching degree calculation value of each apartment; Sort all apartments in the target apartment set from high to low according to the obtained calculated matching degree values; Step S2 specifically includes: S211: Compare the vacancy time of all the apartments with the lease expiration time of the user's current apartment; S2211: If the vacancy time of the apartment is later than the lease expiration time of the user's current apartment, the time matching value P of the apartment is time-a for: S2212: If the vacancy time of the apartment is not later than the lease expiration time of the user's current apartment, the time matching value P of the apartment is time-b for: Among them, α and β are coefficients, α<β, T vacant is the vacancy time of the apartment, T due The expiration date of the user's current apartment lease; S231: Calculate the matching degree of each apartment's housing condition supply information and the user's housing condition demand information to obtain a matching degree calculation value of each apartment; S241: Correcting the calculated matching value based on the time matching value of each apartment; Step S3 specifically includes: The apartment with the highest calculated corrected matching value is recommended to the user.

2. The method according to claim 1, characterized in that The user's housing demand information includes the desired apartment location, desired apartment area, desired apartment orientation, desired apartment type, desired apartment decoration and desired apartment floor: The housing condition supply information of each of the apartments includes the location of the apartment, the area of ​​the apartment, the orientation of the apartment, the apartment type, the decoration of the apartment and the floor of the apartment; Step 231 specifically includes: For each apartment, the required apartment location, the required apartment area, the required apartment orientation, the required apartment type, the required apartment decoration, the required apartment floor, the supplied apartment location, the supplied apartment area, the supplied apartment orientation, the supplied apartment type, the supplied apartment decoration and the supplied apartment floor are input into a preset house matching degree calculation model to calculate the matching degree calculation value of each apartment.

3. The method according to claim 1 or 2, characterized in that: The formula of the preset house matching calculation model is: Among them, MD represents the preset house matching degree, W pos represents the position weight, P pos Indicates the position matching degree, with a value range of 0-1; W area represents the area weight, P area Indicates the area matching degree, with a value range of 0-1; W dir represents the orientation weight, P dir Indicates the orientation matching degree, with a value range of 0-1; W type Represents the weight of the apartment type, P type Indicates the apartment type matching degree, with a value range of 0-1; W ren Represents the decoration weight, P ren Indicates the decoration matching degree, the value range is 0-1; W floor Represents the floor weight, P floor Indicates the floor matching degree, the value range is 0-1, I area-dir Indicates the interaction matching degree between area and orientation, I type-ren Indicates the interactive matching degree between apartment type and decoration, I pos-floor Indicates the interaction matching degree between location and floor.

4. The method according to claim 3, characterized in that The position matching degree is calculated using the following formula: Among them, P pos represents the location matching degree, d is the actual distance between the user's required apartment area and the supply apartment location; D max It is the set maximum distance threshold. If it exceeds the set maximum distance threshold, the matching degree is 0; The area matching degree is calculated using the following formula: Among them, P area Indicates the area matching degree, A demand is the user's desired apartment location, A supply Indicates the area of ​​the apartment provided; A max is the maximum area threshold set; The orientation matching degree is calculated using the following formula: Among them, P dir Indicates the orientation matching degree, dir demand Indicates the user's desired apartment orientation, dir supply Indicates the orientation of the supply apartment; The apartment type matching degree is calculated using the following formula: Among them, P type Indicates the apartment type matching degree, T demand represents the set of apartment types required by the user, T supply Represents the supply of apartment unit types; The decoration matching degree is calculated using the following formula: Among them, P ren Indicates the decoration matching degree, ω i represents the weight of the i-th decoration feature, n represents the number of decoration features, d i is the mismatch degree of the i-th decoration feature; The floor matching degree is calculated using the following formula: Among them, P floor Indicates the floor matching degree, F demand is the user's demand apartment floor, F supply Indicates the supply apartment floor; F max is the maximum floor difference threshold set.

5. The method according to claim 3, characterized in that: The interaction matching degree between the area and the orientation is calculated using the following formula: I area-dir =P area ·f(P dir ) Among them, I area-dir represents the interaction matching degree between area and orientation, P area represents the area matching degree, f(P dir ) is the orientation matching degree P dir The function of represents the influence of orientation on overall satisfaction; The interactive matching degree between the apartment type and the decoration is calculated using the following formula: I type-ren =P type ·g(P ren ) Among them, I type-ren represents the interactive matching degree between apartment type and decoration, P type represents the apartment type matching degree, g(P ren ) is the decoration matching degree P ren The function of represents the impact of decoration on overall satisfaction; The interaction matching degree between the position and the floor is calculated using the following formula: I pos-floor =P pos ·h(P floor ) Among them, I pos-floor Represents the interaction matching degree between location and floor, P pos Indicates the position matching degree, h(P floor ) is the floor matching degree P floor A function that represents the impact of the floor on the overall satisfaction.

6. The method according to claim 5, characterized in that The f(P dir ) is calculated using the following formula: Among them, k dir represents the coefficient of control orientation influence; The g(P ren ) is calculated using the following formula: Among them, k ren represents the coefficient for controlling the impact of decoration; The h(P floor ) is calculated using the following formula: Among them, k floor A coefficient that represents the influence of the control floor.

7. An apartment rental matching recommendation system based on big data, characterized in that: The system comprises: An acquisition module, which is used to acquire user information and room status information of all apartments, wherein the user information includes the room status demand information of the user and the lease expiration time of the user's current apartment, and the room status information of all apartments includes the room status supply information of all apartments and the vacancy time of all apartments; A matching module, which is used to match the lease expiration time of the user's current apartment with the vacancy time of all the apartments and to match the housing condition demand information of the user with the housing condition supply information of all the apartments by using big data technology; The recommendation module is used to recommend apartments to users based on the matching results; Wherein, step S2 specifically includes: S210: Filter out the apartments whose vacancy time is not later than the lease expiration time of the current apartment of the user from all the apartments and mark them as a target apartment set; S220: Calculating the matching degree between the housing condition supply information of each apartment in the target apartment set and the housing condition demand information of the user; Step S3 specifically includes: Recommend the apartment with the highest calculated matching value to the user; The user's housing demand information includes the desired apartment location, desired apartment area, desired apartment orientation, desired apartment type, desired apartment decoration and desired apartment floor: The housing condition supply information of each of the apartments includes the location of the apartment, the area of ​​the apartment, the orientation of the apartment, the apartment type, the decoration of the apartment and the floor of the apartment; Step 220 specifically includes: For each apartment, the location of the required apartment, the area of ​​the required apartment, the orientation of the required apartment, the apartment type of the required apartment, the decoration of the required apartment, the floor of the required apartment, the location of the supplied apartment, the area of ​​the supplied apartment, the orientation of the supplied apartment, the apartment type of the supplied apartment, the decoration of the supplied apartment and the floor of the supplied apartment are input into a preset housing matching degree calculation model to calculate the matching degree calculation value of each apartment; Sort all apartments in the target apartment set from high to low according to the obtained calculated matching degree values; Step S2 specifically includes: S211: Compare the vacancy time of all the apartments with the lease expiration time of the user's current apartment; S2211: If the vacancy time of the apartment is later than the lease expiration time of the user's current apartment, the time matching value P of the apartment is time-a for: S2212: If the vacancy time of the apartment is not later than the lease expiration time of the user's current apartment, the time matching value P of the apartment is time-b for: Among them, α and β are coefficients, α<β, T vacant is the vacancy time of the apartment, T due The expiration date of the user's current apartment lease; S231: Calculate the matching degree of each apartment's housing condition supply information and the user's housing condition demand information to obtain a matching degree calculation value of each apartment; S241: Correcting the calculated matching value based on the time matching value of each apartment; Step S3 specifically includes: The apartment with the highest calculated corrected matching value is recommended to the user.

Images