Short-term-rental business management system and method based on long-term-rental apartment transportation management platform

Abstract

The invention belongs to the technical field of renting management, and particularly relates to a short-term renting service management system and method based on a long-term renting apartment transportation management platform, and the method comprises the steps: firstly enabling a vacant house resource recognition module to be connected into the long-term renting apartment transportation management platform, and obtaining the vacant house resource information; the short-term rental house source identification module calls a pre-constructed short-term rental house source AI analysis model according to the vacant house source information, analyzes and identifies the vacant house source information through the short-term rental house source AI analysis model, and outputs the short-term rental house source information; a short-term rental house source recommendation module obtains house rental preference characteristics of the resident after obtaining authorization of the resident, and performs matching with the short-term rental house source information according to the house rental preference characteristics, and outputs a short-term rental house source meeting a matching requirement; and finally, the short-term rental house source management module is used for pushing the short-term rental house sources meeting the matching requirements to the residents and executing short-term rental management. According to the invention, the problems of effective integration and flexible switching of an operation management platform of a long-term-rental apartment during short-term-rental service development in the prior art can be solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of housing rental management, and in particular to a short-term rental business management system and method based on a long-term rental apartment operation management platform. Background Art

[0002] In the field of operation and management of long-term rental apartments, its current situation presents many characteristics and challenges. Long-term rental apartments usually build their operation systems according to the long-term rental model. However, due to the dynamic changes in the market environment, such as fluctuations in market supply and demand, significant differences in seasonal consumer demand and other factors, it is inevitable that some houses will be idle and unrented for a long period of time, that is, vacant. Under the framework of the traditional long-term rental apartment operation and management model, there is a lack of efficient, flexible and systematic processing methods and mechanisms for such vacant houses. Enterprises can only passively wait for the emergence of long-term rental customers and find it difficult to actively and effectively activate these houses. This directly leads to idleness and waste of resources, resulting in the failure to fully utilize apartment resources, which in turn has a negative impact on the overall economic benefits of the enterprise, including reducing the speed of capital recovery, increasing the allocation of operating costs and other adverse consequences.

[0003] It is of great significance and value to carry out short-term rental business in the management of long-term rental apartments. For example, with the continuous growth of temporary housing demand such as tourism and business travel, the short-term rental market has shown a rapid development trend in recent years. For long-term rental apartments, if the short-term rental business can be effectively carried out, the originally vacant houses can be rented out in the short-term rental market, thereby greatly improving the utilization rate of the houses and converting idle resources into actual economic benefits. This will not only help increase the company's rental income and make up for the economic losses caused by vacancy, but also enhance the company's competitiveness and risk resistance in the market, optimize the company's resource allocation efficiency, promote the diversification and flexibility of the company's operations, and enable the company to better adapt to the dynamic changes and uncertainties in the market.

[0004] However, in the existing long-term rental apartment management model, there are many defects in the development of short-term rental business; specifically:

[0005] 1. The management model of long-term rental apartments and the operating model of the short-term rental market are separated from each other and operate independently, lacking an effective integration and connection mechanism between the two;

[0006] 2. The operation and management platforms of long-term rental apartments are mostly designed and built based on the long-term rental business processes and needs. They are difficult to directly apply to the management and operation of short-term rental business, and cannot achieve flexible and convenient switching from long-term rental mode to short-term rental mode.

[0007] Therefore, in the actual operation process, even if there is a possibility of matching short-term rental demand with vacant housing, the allocation and utilization of resources cannot be efficiently realized due to the disconnection of management models, which hinders the effective circulation and value creation of long-term rental apartment resources in the short-term rental market, making it difficult for apartment companies to fully tap the huge potential economic and social benefits of short-term rental business, limiting the further improvement of corporate operating efficiency and business expansion. Summary of the invention

[0008] The technical problem solved by the present invention is to provide a short-term rental business management system and method based on the long-term rental apartment operation management platform, so as to solve the problem of effective integration and flexible switching of the long-term rental apartment operation management platform in the prior art when carrying out short-term rental business.

[0009] The basic solution provided by the present invention is a short-term rental business management system based on a long-term rental apartment operation and management platform, including a vacant housing source identification module, a short-term rental housing source identification module, a short-term rental housing source recommendation module, and a short-term rental housing source management module, wherein:

[0010] The vacant housing source identification module is used to access the long-term rental apartment operation management platform to obtain vacant housing source information;

[0011] The short-term rental housing source identification module is used to call a pre-built short-term rental housing source AI analysis model according to the vacant housing source information, analyze and identify the vacant housing source information through the short-term rental housing source AI analysis model, and output the short-term rental housing source information;

[0012] The short-term rental housing recommendation module is used to obtain the rental preference characteristics of the resident after obtaining the resident's authorization, and match the rental preference characteristics with the short-term rental housing information, and output the short-term rental housing that meets the matching requirements;

[0013] The short-term rental housing source management module is used to push short-term rental housing sources that meet the matching requirements to residents and perform short-term rental management.

[0014] Furthermore, the short-term rental housing source identification module includes a housing source information collection unit, a preprocessing unit, a short-term rental housing source AI analysis unit and a short-term rental display unit, wherein:

[0015] The housing source information collection unit is used to collect historical rental data and room type feature data of corresponding vacant housing sources from the long-term rental apartment operation management platform according to the vacant housing source information;

[0016] The preprocessing unit is used to perform preprocessing based on the collected historical rental data and room type feature data, and output the preprocessed collected data;

[0017] The short-term rental housing source AI analysis unit is based on the big data algorithm and the AI ​​analysis model to build a short-term rental housing source AI analysis model that integrates the big data algorithm and the AI ​​analysis model; the short-term rental housing source AI analysis unit is also used to call the big data algorithm in the short-term rental housing source AI analysis model to perform time series analysis and cluster analysis on the pre-processed collected data to generate analysis results, and use the AI ​​analysis model to perform short-term rental feature scoring on the analysis results, and output short-term rental housing source information;

[0018] The short-term rental display unit has a preset short-term rental housing source display table, and the short-term rental display unit is further used to import short-term rental housing source information into the preset short-term rental housing source display table for display.

[0019] Furthermore, the short-term rental housing source identification module further includes a housing source vacancy risk assessment unit and a dynamic update unit, wherein the housing source vacancy risk assessment unit is used to score the vacancy risk of the short-term rental housing source according to the change of the status of the short-term rental housing source, and re-import the score into the short-term rental housing source display table;

[0020] The dynamic updating unit is used to dynamically update and sort the short-term rental housing sources in the short-term rental housing source display table according to the vacancy risk according to the preset updating period and the short-term rental housing source status change period.

[0021] Furthermore, the short-term rental housing recommendation module includes a rental preference feature acquisition unit and an AI matching unit, wherein:

[0022] The rental preference feature acquisition unit is used to acquire the house source features in the user's historical rental information according to the user's authorization, and generate the resident's rental preference features; the rental preference feature acquisition unit is also used to generate a house source feature tendency map when the user's authorization is not obtained, acquire the user's click data in the house source feature tendency map, and generate the resident's rental preference features;

[0023] The AI ​​matching unit is used to obtain the residents' rental preference characteristics, input them into the trained AI matching model, and output short-term rental properties that meet the matching requirements.

[0024] Furthermore, the AI ​​matching model construction training matching process in the AI ​​matching unit is:

[0025] An AI matching model is built based on a deep learning neural network model, and the historical rental data of short-term rental properties in the short-term rental property display table in the long-term rental apartment operation and management platform is received. Sample data of tenants' rental preference characteristics and sample data of short-term rental property characteristics are extracted to generate training data.

[0026] Preprocess the training data, output the preprocessed training data, and annotate the preprocessed training data, retaining the short-term rental housing source characteristics corresponding to the tenants' rental preference characteristics. After the data annotation is completed, divide the training data into a training set and a test set according to a preset ratio;

[0027] The training set is input into the constructed AI matching model, the loss is calculated according to the preset loss function, and then the model parameters are updated using the optimization algorithm. After the preset number of update rounds and verification by the test set, the model parameters of the AI ​​matching model with the best performance are retained;

[0028] The resident rental preference features obtained by the rental preference feature acquisition unit are input into the trained AI matching model, and the short-term rental sources that meet the matching threshold are output.

[0029] Furthermore, the short-term rental house source management module includes a reservation unit, a check-in unit, a room change unit, a check-out settlement unit and a payment unit, wherein:

[0030] The reservation unit is used to generate short-term rental housing sources based on the matching results for residents to select housing sources and make reservations online;

[0031] The check-in unit is used for providing self-service check-in by intelligently reading a card reader containing the check-in information of the resident after the resident submits the check-in information online;

[0032] The room exchange unit is used to obtain the room exchange demand submitted online by the resident, match the short-term rental house sources that meet the resident's preferences according to the short-term rental house source display table, and generate a replacement house source;

[0033] The check-out settlement unit is used to allow residents to check out after the short-term lease expires, and provides online payment settlement;

[0034] The payment unit is used to integrate the payment platform and perform payment operations.

[0035] The short-term rental business management method based on the long-term rental apartment operation management platform is applied to the short-term rental business management system based on the long-term rental apartment operation management platform, including:

[0036] S1: Access the long-term rental apartment operation and management platform to obtain vacant housing information;

[0037] S2: The short-term rental housing AI analysis module is called and constructed based on the vacant housing information. The vacant housing is analyzed and identified through the short-term rental housing AI analysis model, and the short-term rental housing information is output;

[0038] S3: Obtain the tenant's rental preference characteristics by obtaining the tenant's authorization, match the rental preference characteristics with the short-term rental housing information, and output the short-term rental housing that meets the matching requirements;

[0039] S4: Push short-term rental properties that meet the matching requirements to residents and perform short-term rental management.

[0040] The principle and advantage of the present invention are that in the existing operation and management of long-term rental apartments, there is a problem that vacant housing resources cannot be well utilized. Therefore, in this solution, vacant housing resources in long-term rental apartments are first identified, and then the short-term rental housing source AI analysis model is called to filter out short-term rental housing source information from the vacant housing sources. The filtered short-term rental housing source information is a better choice for residents. By obtaining the rental preference characteristics of the residents, the rental preference characteristics are matched with the short-term rental housing source information to obtain short-term rental housing sources that meet the matching requirements and then push them to the residents.

[0041] Therefore, in this solution, the advantages are:

[0042] 1. Improve the utilization rate of vacant housing in long-term rental apartments and reduce vacancy periods; 2. Use intelligent screening and matching methods to reduce manual intervention and management costs; 3. Introduce short-term rental business in the operation and management of long-term rental apartments to achieve higher rental income for the company and attract short-term rental customers; 4. Improve residents' move-in experience by matching preference characteristics with housing characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a functional block diagram of an embodiment of the present invention;

[0044] Figure 2 The figure is a flowchart of an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following is further described in detail through specific implementation methods:

[0046] The embodiment is basically as follows Figure 1 and Figure 2 As shown: A short-term rental business management system based on a long-term rental apartment operation and management platform includes a vacant housing source identification module, a short-term rental housing source identification module, a short-term rental housing source recommendation module and a short-term rental housing source management module, wherein the vacant housing source identification module is connected to the long-term rental apartment operation and management platform to obtain vacant housing source information. In this embodiment, the judgment and identification method of vacant housing sources is:

[0047] 1. Water meter and electricity meter networking equipment: by cooperating with water meter and electricity meter networking equipment suppliers, regularly analyzing the changes in water meter and electricity meter data in each room, and setting water and electricity consumption thresholds for vacant houses, so as to determine whether the house is vacant;

[0048] 2. Through the reminder of lease expiration, mark and classify the properties that are about to expire. For example, the first-level warning properties are marked as soon as vacant properties, and the second-level warning properties are marked as potential vacant properties;

[0049] 3. Obtain door lock records through door lock devices, and extract the corresponding room number, tenant information, and event type from the door lock records. For example, for rooms without tenants, a period of time without door lock records is set and the room is judged as vacant. For rooms with tenants viewing the room, the unlocking method and time in the door lock records are analyzed.

[0050] In this way, through the above method, vacant housing information can be obtained from the operating data of the long-term rental apartment operation management platform.

[0051] The short-term rental housing source identification module is used to call the pre-built short-term rental housing source AI analysis model according to the vacant housing source information, analyze and identify the vacant housing source information through the short-term rental housing source AI analysis model, and output the short-term rental housing source information; in this embodiment, the short-term rental housing source identification module includes a housing source information collection unit, a pre-processing unit, a short-term rental housing source AI analysis unit and a short-term rental display unit, wherein:

[0052] The housing information collection unit is used to collect historical rental data and room feature data of corresponding vacant housing from the long-term rental apartment operation management platform according to the vacant housing information; in this embodiment, the historical rental data includes occupancy rate data, rental fluctuation data, smart device usage, tenant evaluation, and seasonal demand data, and the room feature data includes room layout and structure, functional area configuration (such as bedroom configuration, living room configuration, kitchen configuration and bathroom configuration), decoration style, building facility details, etc.

[0053] The preprocessing unit is used to perform preprocessing based on the collected historical rental data and room type feature data, and output the preprocessed collected data; in this embodiment, the preprocessing includes data cleaning, data standardization, data normalization, etc., so that the preprocessed data can be easily input into the subsequent model for processing.

[0054] The short-term rental housing source AI analysis unit is based on the big data algorithm and the AI ​​model to build a short-term rental housing source AI analysis model that integrates the big data algorithm and the AI ​​model; the short-term rental housing source AI analysis unit is also used to call the big data algorithm in the short-term rental housing source AI analysis model to perform time series analysis and cluster analysis on the pre-processed collected data to generate analysis results, and use the AI ​​model to perform short-term rental feature scoring on the analysis results, and output short-term rental housing source information; in this embodiment, a big data algorithm is used to perform time series analysis or cluster analysis on the pre-processed collected data, and the analysis and processing method is determined according to actual needs. For example, when it is necessary to judge whether it is suitable for short-term rental based on the occupancy rate, time series analysis is performed, such as calculating a simple moving average to smooth the data and observe the trend. The process is:

[0055] Set the time series data to y t , the moving average window size is n, then:

[0056]

[0057] Therefore, according to the above expression, plotting the occupancy SMA t The curve of changes over time t can intuitively show the changing patterns of occupancy rate in different seasons or time periods, providing a basis for short-term rental pricing and promotion.

[0058] As for cluster analysis, it is necessary to make judgments based on the housing categories and group houses with similar room types into one category, so as to formulate unified short-term rental strategies for different types of houses.

[0059] The AI ​​analysis model then analyzes the data processed by the big data algorithm. In this solution, the AI ​​analysis model is implemented using a neural network model multi-layer perceptron. Specifically, after the big data algorithm time series analysis and cluster analysis, the extracted key features (such as occupancy rate trends, room type cluster category labels, etc.) are combined as the input of the AI ​​analysis model. The construction process of the AI ​​analysis model is as follows:

[0060] Assume that there are m features in total, the number of nodes in the input layer of the AI ​​analysis model is m, the hidden layer is set to two layers, and the number of nodes in the first hidden layer is:

[0061]

[0062] The number of nodes in the second hidden layer is set to:

[0063]

[0064] Then the ReLU activation function f(x)=max(0,x) is used to increase the nonlinear expression ability of the model; the number of nodes in the output layer is 1, and the Sigmoid activation function is used:

[0065]

[0066] The output value is the short-term rental feature score, which ranges from (0 to 1). The closer to 1, the more suitable it is for short-term rental.

[0067] After the above AI analysis model is built, the historical rental data in the long-term rental apartment operation management platform is used for manual screening to generate sample data suitable for short-term rental. After preprocessing and big data algorithm processing, the sample data processed by the big data algorithm is divided into training set, validation set and test set according to 7:2:1. The training set is used to train the AI ​​analysis model. The mean square error loss function is used as the function, and the expression is:

[0068]

[0069] Where N represents the number of training samples. represents the real short-term rental feature score, Indicates the model predicts the short-term rental feature score;

[0070] Then set the AI ​​analysis model hyperparameters. After each round of model training, use the validation set to evaluate the model performance. After the maximum number of training rounds, for example 100, save the model parameters with the best performance.

[0071] Finally, the vacant housing data to be evaluated is preprocessed and processed by the big data algorithm, and then input into the trained AI analysis model to obtain the short-term rental feature score. In this embodiment, the housing sources are sorted or classified according to the scoring results, and the housing sources with a score greater than 0.7 are marked as high-quality short-term rental sources. The housing sources with a score of 0.5-0.7 are recommended after appropriate optimization, such as modification or fine-tuning of the decoration style; the housing sources with a score less than 0.5 are eliminated and not used as short-term rental sources.

[0072] A short-term rental housing display table is preset in the short-term rental display unit, and the short-term rental display unit is also used to import short-term rental housing information into the preset short-term rental housing display table for display; in this embodiment, the short-term rental housing display table includes three types of short-term rental housing, namely standard short-term rental housing, business short-term rental housing and tourist short-term rental housing, so as to cope with short-term rental needs in different scenarios, and in each type of short-term rental housing, the elements involved include: serial number, housing picture, housing title, housing location, room structure, area, number of occupants, short-term rental price, short-term rental duration requirements, facilities and services, surrounding facilities, transportation information, evaluation summary and score, etc., so that residents can understand the detailed information of the target short-term rental housing.

[0073] In addition, the short-term rental housing source identification module also includes a housing source vacancy risk assessment unit and a dynamic update unit. The housing source vacancy risk assessment unit is used to score the vacancy risk of the short-term rental housing source according to the change of the status of the short-term rental housing source, and re-import it into the short-term rental housing source display table; in this embodiment, the change of the status of the short-term rental housing source may include rent withdrawal, unsuccessful reservation of the resident, early check-out, and early warning due to long-term non-reservation, etc., which increases the risk of subsequent rental due to sudden vacancy of the short-term rental housing source. For this reason, the vacancy risk of the short-term rental housing source needs to be evaluated. In this solution, the factors affecting the vacancy risk include the historical average vacancy cycle, the seasonal adjustment factor, the recent booking cancellation rate, the market competition index and the price elasticity coefficient. Specifically, the historical average vacancy cycle refers to the average time experienced by the housing source each time it is vacant in the past period of time (for example, one year), and the calculation method is:

[0074]

[0075] Among them, t i represents the duration of the vacancy for the i-th time, and n is the number of vacancies in the past year;

[0076] The seasonal adjustment factor is determined by the impact of different seasons on short-term rental demand. For example, during the peak tourist season, when short-term rental demand is high, the seasonal adjustment factor (denoted by S) is set to be smaller, 0.5; during the off-season, when demand is low, the seasonal adjustment factor is larger, and is set to 1.5.

[0077] The recent booking cancellation rate is the percentage of orders that were canceled after successful booking of the property in the past period of time, for example, within three months, to the total number of booking orders. The expression is:

[0078]

[0079] Among them, m is the number of canceled orders, and M is the total number of pre-ordered orders;

[0080] The market competition index is expressed as the degree of competition between the property and similar short-term rental properties in the area where the property is located. The calculation formula is:

[0081]

[0082] Among them, Q represents the total number of short-term rental properties of the same type in the area, and q represents the ranking of the property;

[0083] The price elasticity coefficient indicates the degree of influence of short-term rental prices on demand, represented by E;

[0084] Therefore, based on the above-mentioned factors affecting vacancy risk, the vacancy risk calculation formula is constructed as follows:

[0085]

[0086] Among them, R represents the vacancy risk value. The larger the value, the higher the risk of vacancy faced by the house in the future.

[0087] The dynamic update unit is used to dynamically update and sort the short-term rental properties in the short-term rental property display table according to the vacancy risk based on the preset update period and the short-term rental property status change period; in this embodiment, the preset update period is, for example, every day or every week, and the short-term rental properties with higher vacancy risk are displayed preferentially in the short-term rental property display table to increase the chance of being selected.

[0088] The short-term rental housing source recommendation module is used to obtain the rental preference characteristics of the resident after obtaining the resident's authorization, and match the rental preference characteristics with the short-term rental housing source information, and output the short-term rental housing sources that meet the matching requirements; in this embodiment, the short-term rental housing source recommendation module includes a rental preference feature acquisition unit and an AI matching unit, wherein:

[0089] The rental preference feature acquisition unit is used to acquire the house source features in the user's historical rental information according to the user's authorization, and generate the resident's rental preference features; the rental preference feature acquisition unit is also used to generate a house source feature tendency map when the user's authorization is not obtained, acquire the user's click data in the house source feature tendency map, and generate the resident's rental preference features;

[0090] In this embodiment, two methods are used to obtain the tenant's rental preference characteristics. The first method is to obtain the tenant's historical rental data in his / her mobile device by obtaining the tenant's authorization, and extract the tenant's rental preference characteristics from the historical rental data. The detailed implementation steps are as follows:

[0091] First, when the resident uses the short-term rental business management system in this solution for the first time, the purpose and use of obtaining the authorization of the mobile device are clearly explained to the user, so as to obtain the user's historical rental record data, and extract key information from the historical rental record data, including but not limited to the basic characteristics of the house, decoration and facility characteristics, location and surrounding characteristics, price and rental period characteristics, etc., and then calculate the frequency of occurrence of the characteristics to understand the user's preference, and then analyze the correlation between different characteristics through correlation analysis to obtain the characteristic combination preference of the resident when selecting a house, and obtain the comprehensive preference characteristics of the resident;

[0092] The second method is to obtain the rental preference characteristics of residents by setting a housing source feature tendency map when the user authorization is not obtained. Specifically, firstly, a housing source feature tendency map is designed. According to the common characteristics of short-term rental housing, such as decoration style, house type, location requirements, facility preferences, etc., specific option content is designed according to each feature category. For example, under the decoration style, it includes modern simplicity, European classical, American pastoral, Chinese tradition, Japanese fresh, Mediterranean style, industrial style, Nordic style, mixed style, etc.; then, the pictures containing these option contents are generated into a grid map, and interactive elements and guiding instructions are added, so that residents can click on the grid map to get the satisfactory answers they want. In this way, the click data of residents can be collected, and the feature preference calculation and analysis can be further performed to obtain the rental preference characteristics of residents.

[0093] The AI ​​matching unit is used to obtain the tenants' rental preference characteristics, input them into the trained AI matching model, and output short-term rental properties that meet the matching requirements; the AI ​​matching model construction training and matching process in the AI ​​matching unit is as follows:

[0094] An AI matching model is built based on a deep learning neural network model, and the historical rental data of short-term rental properties in the short-term rental property display table in the long-term rental apartment operation and management platform is received. Sample data of tenants' rental preference characteristics and sample data of short-term rental property characteristics are extracted to generate training data.

[0095] Preprocess the training data, output the preprocessed training data, and annotate the preprocessed training data, retaining the short-term rental housing source characteristics corresponding to the tenants' rental preference characteristics. After the data annotation is completed, divide the training data into a training set and a test set according to a preset ratio;

[0096] The training set is input into the constructed AI matching model, the loss is calculated according to the preset loss function, and then the model parameters are updated using the optimization algorithm. After the preset number of update rounds and verification by the test set, the model parameters of the AI ​​matching model with the best performance are retained;

[0097] Input the resident rental preference features obtained by the rental preference feature acquisition unit into the trained AI matching model, and output the short-term rental sources that meet the matching threshold;

[0098] In this embodiment, the construction and training process of the AI ​​matching model is consistent with the above-mentioned AI analysis model. Thus, the trained AI matching model inputs the residents' rental preference characteristics and matches them with the characteristics of the short-term rental sources in the AI ​​matching model. When the matching result is greater than a preset value, for example 80%, the short-term rental source is recommended to the residents as a recommended source.

[0099] Therefore, the short-term rental housing source management module is used to push short-term rental sources that meet the matching requirements to the residents and perform short-term rental management. The short-term rental housing source management module includes a reservation unit, a check-in unit, a room change unit, a check-out settlement unit, and a payment unit, among which:

[0100] The reservation unit is used to generate short-term rental houses based on the matching results for residents to select houses and make reservations online;

[0101] The check-in unit is used for residents to submit their check-in information online, and then intelligently read the card reader containing the resident's check-in information to provide self-service check-in;

[0102] The room exchange unit is used to obtain the room exchange requirements submitted by the residents online, match the short-term rental sources that meet the residents' preferences according to the short-term rental source display table, and generate replacement sources;

[0103] The check-out settlement unit is used for residents to check out after the short-term lease expires, and provides online payment settlement;

[0104] The payment unit is used to integrate the payment platform and perform payment operations.

[0105] In this embodiment, intelligent operation of short-term rental business management is realized through the reservation unit, check-in unit, room change unit, check-out settlement unit and payment unit, thereby reducing manual operation costs and improving short-term rental efficiency.

[0106] In another embodiment of the present embodiment, a short-term rental business management method based on a long-term rental apartment operation management platform is also included, which is applied to the short-term rental business management system based on the long-term rental apartment operation management platform, including:

[0107] S1: Access the long-term rental apartment operation and management platform to obtain vacant housing information;

[0108] S2: The short-term rental housing AI analysis module is called and constructed based on the vacant housing information. The vacant housing is analyzed and identified through the short-term rental housing AI analysis model, and the short-term rental housing information is output;

[0109] S3: Obtain the tenant's rental preference characteristics by obtaining the tenant's authorization, match the rental preference characteristics with the short-term rental housing information, and output the short-term rental housing that meets the matching requirements;

[0110] S4: Push short-term rental properties that meet the matching requirements to residents and perform short-term rental management.

[0111] The above are only embodiments of the present invention. Common knowledge such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A short-term rental business management system based on a long-term rental apartment operation management platform, characterized by: It includes vacant housing identification module, short-term rental housing identification module, short-term rental housing recommendation module and short-term rental housing management module, among which: The vacant housing source identification module is used to access the long-term rental apartment operation management platform to obtain vacant housing source information; The short-term rental housing source identification module is used to call a pre-built short-term rental housing source AI analysis model according to the vacant housing source information, analyze and identify the vacant housing source information through the short-term rental housing source AI analysis model, and output the short-term rental housing source information; The short-term rental housing recommendation module is used to obtain the rental preference characteristics of the resident after obtaining the resident's authorization, and match the rental preference characteristics with the short-term rental housing information, and output the short-term rental housing that meets the matching requirements; The short-term rental housing source management module is used to push short-term rental housing sources that meet the matching requirements to residents and perform short-term rental management.

2. The short-term rental business management system based on the long-term rental apartment operation management platform according to claim 1 is characterized by: The short-term rental housing source identification module includes a housing source information collection unit, a pre-processing unit, a short-term rental housing source AI analysis unit and a short-term rental display unit, wherein: The housing source information collection unit is used to collect historical rental data and room type feature data of corresponding vacant housing sources from the long-term rental apartment operation management platform according to the vacant housing source information; The preprocessing unit is used to perform preprocessing based on the collected historical rental data and room type feature data, and output the preprocessed collected data; The short-term rental housing source AI analysis unit is based on the big data algorithm and the AI ​​analysis model to build a short-term rental housing source AI analysis model that integrates the big data algorithm and the AI ​​analysis model; the short-term rental housing source AI analysis unit is also used to call the big data algorithm in the short-term rental housing source AI analysis model to perform time series analysis and cluster analysis on the pre-processed collected data to generate analysis results, and use the AI ​​analysis model to perform short-term rental feature scoring on the analysis results, and output short-term rental housing source information; The short-term rental display unit has a preset short-term rental housing source display table, and the short-term rental display unit is further used to import short-term rental housing source information into the preset short-term rental housing source display table for display.

3. The short-term rental business management system based on the long-term rental apartment operation management platform according to claim 2 is characterized by: The short-term rental housing source identification module also includes a housing source vacancy risk assessment unit and a dynamic update unit. The housing source vacancy risk assessment unit is used to score the vacancy risk of the short-term rental housing source according to the change of the status of the short-term rental housing source, and re-import it into the short-term rental housing source display table; The dynamic updating unit is used to dynamically update and sort the short-term rental housing sources in the short-term rental housing source display table according to the vacancy risk according to the preset updating period and the short-term rental housing source status change period.

4. The short-term rental business management system based on the long-term rental apartment operation management platform according to claim 3 is characterized by: The short-term rental housing recommendation module includes a rental preference feature acquisition unit and an AI matching unit, wherein: The rental preference feature acquisition unit is used to acquire the house source features in the user's historical rental information according to the user's authorization, and generate the resident's rental preference features; the rental preference feature acquisition unit is also used to generate a house source feature tendency map when the user's authorization is not obtained, acquire the user's click data in the house source feature tendency map, and generate the resident's rental preference features; The AI ​​matching unit is used to obtain the residents' rental preference characteristics, input them into the trained AI matching model, and output short-term rental properties that meet the matching requirements.

5. The short-term rental business management system based on the long-term rental apartment operation management platform according to claim 4 is characterized by: The AI ​​matching model construction training matching process in the AI ​​matching unit is as follows: An AI matching model is built based on a deep learning neural network model, and the historical rental data of short-term rental properties in the short-term rental property display table in the long-term rental apartment operation and management platform is received. Sample data of tenants' rental preference characteristics and sample data of short-term rental property characteristics are extracted to generate training data. Preprocess the training data, output the preprocessed training data, and annotate the preprocessed training data, retaining the short-term rental housing source characteristics corresponding to the tenants' rental preference characteristics. After the data annotation is completed, divide the training data into a training set and a test set according to a preset ratio; The training set is input into the constructed AI matching model, the loss is calculated according to the preset loss function, and then the model parameters are updated using the optimization algorithm. After the preset number of update rounds and verification by the test set, the model parameters of the AI ​​matching model with the best performance are retained; The resident rental preference features obtained by the rental preference feature acquisition unit are input into the trained AI matching model, and the short-term rental sources that meet the matching threshold are output.

6. The short-term rental business management system based on the long-term rental apartment operation management platform according to claim 5 is characterized by: The short-term rental house source management module includes a reservation unit, a check-in unit, a room change unit, a check-out settlement unit and a payment unit, wherein: The reservation unit is used to generate short-term rental housing sources based on the matching results for residents to select housing sources and make reservations online; The check-in unit is used for providing self-service check-in by intelligently reading a card reader containing the check-in information of the resident after the resident submits the check-in information online; The room exchange unit is used to obtain the room exchange demand submitted online by the resident, match the short-term rental house sources that meet the resident's preferences according to the short-term rental house source display table, and generate a replacement house source; The check-out settlement unit is used to allow residents to check out after the short-term lease expires, and provides online payment settlement; The payment unit is used to integrate the payment platform and perform payment operations.

7. A short-term rental business management method based on a long-term rental apartment operation and management platform is applied to the above-mentioned short-term rental business management system based on a long-term rental apartment operation and management platform, and is characterized by: include: S1: Access the long-term rental apartment operation and management platform to obtain vacant housing information; S2: The short-term rental housing AI analysis module is called and constructed based on the vacant housing information. The vacant housing is analyzed and identified through the short-term rental housing AI analysis model, and the short-term rental housing information is output; S3: Obtain the tenant's rental preference characteristics by obtaining the tenant's authorization, match the rental preference characteristics with the short-term rental housing information, and output the short-term rental housing that meets the matching requirements; S4: Push short-term rental properties that meet the matching requirements to residents and perform short-term rental management.

Images