Homogeneous real estate space intelligent search method and system based on space partition

Abstract

The invention discloses a homogeneous real estate space intelligent search method and system based on space partition, and relates to the technical field of space data processing and intelligent search. According to the homogeneous real estate space intelligent search method and system based on space partition, the data of the target real estate area is obtained and preprocessed, so that the accuracy and integrity of the data are ensured; dividing the pre-processed area into a plurality of space subareas through a geographic information system, extracting homogeneous features through a clustering algorithm, and analyzing a peripheral matching adaptation degree index of each subarea in combination with geographic position preference of a user to form a homogeneous house resource set; and searching and matching the homogeneous house resource set through a collaborative filtering algorithm, generating a user recommended house resource list, calculating a matching degree index of house resources in each partition, setting a dynamic feedback mechanism, and sorting the recommended house resource list in real time, so as to improve the user satisfaction. Personalized housing resource recommendation is provided for the user, and the convenience and accuracy of real estate transaction are improved.

Description

Technical Field

[0001] The present invention relates to the field of spatial data processing and intelligent search technology, and in particular to a method and system for intelligent search of homogeneous real estate space based on spatial partitioning. Background Art

[0002] With the continuous advancement of urbanization, the scale of the real estate market continues to expand, and the types of properties and their related attribute information are becoming increasingly complex. The growth of urban population and the improvement of residents' living standards have diversified housing demand, and people's requirements for living environment and convenience of life have gradually increased. Traditional methods of obtaining and screening real estate information are difficult to meet the fast and accurate real estate needs of modern users. At the same time, with the rapid development of big data and artificial intelligence technology, intelligent and personalized real estate recommendation systems have become the key to improving user experience and market competitiveness.

[0003] Existing real estate search methods usually use simple keyword-based screening or coarse-grained geographic location matching, which is difficult to effectively process large amounts of multi-dimensional data. In addition, the lack of precise analysis based on spatial partitioning leads to low homogeneity of recommended results, making it difficult to meet the personalized needs of users. These methods have significant limitations in data processing and search efficiency, low recommendation accuracy, poor user experience, and are difficult to effectively respond to the complex needs of the modern real estate market. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present invention provides a method and system for intelligent search of homogeneous real estate space based on spatial partitioning, which solves the problems of the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a spatial intelligent search method for homogeneous real estate based on spatial partitioning, comprising the following steps: S1. obtaining target real estate area data and preprocessing the target real estate area data; S2. dividing the preprocessed target real estate area into several spatial partitions through a geographic information system, extracting the homogeneous characteristics of the real estate through a clustering algorithm, and analyzing them in combination with geographical location preferences, obtaining the surrounding supporting fitness index of each partition, incorporating the characteristics of each partition, and generating a homogeneous housing source set for each partition; S3. obtaining user housing source demand data, searching and matching the homogeneous housing source set in each partition through a collaborative filtering algorithm, obtaining the homogeneous housing source matching index in each partition, and generating a user recommended housing source list; S4. setting a dynamic feedback mechanism based on the homogeneous housing source matching index in each partition to sort the user recommended housing source list.

[0006] Furthermore, the target real estate area data includes: geographical location, building area, sales price, house structure, building type and surrounding supporting facilities information of urban village residences and commercial housing; the preprocessing process of the target real estate area data includes: deduplication of collected data, data format standardization, missing value completion and abnormal data filtering.

[0007] Furthermore, the specific process of extracting homogeneous characteristics of real estate through clustering algorithm and analyzing them in combination with geographical location preference is as follows: based on the pre-processed target real estate area data, the building area, room structure, building type, and sales price characteristics of the housing are clustered through the clustering algorithm to form a preliminary housing feature grouping; combined with geographical location preference, the surrounding supporting facilities of each group are analyzed to generate the surrounding supporting fitness index of each spatial partition, and the index is incorporated into the characteristic parameters of each spatial partition to generate a homogeneous housing source set for each partition.

[0008] Furthermore, the specific process of obtaining the surrounding supporting facilities adaptability index of each zone is as follows: by obtaining the surrounding supporting facilities data in each spatial zone, an evaluation model is established according to the factors of traffic accessibility, educational resource coverage, commercial service convenience, and medical resource adequacy, and a quantitative score is given to the fit between supporting facilities and user needs; the score values ​​of each factor are weighted and summed according to the predetermined weights to generate the surrounding supporting facilities adaptability index of each spatial zone.

[0009] Furthermore, the specific process of searching and matching homogeneous housing sets in each partition through the collaborative filtering algorithm is as follows: based on the obtained user housing demand data, the feature weights of the housing sources preferred by the user are determined, and the similarity is calculated with the historical demand data of known users in the homogeneous housing set to construct a feature matching vector of user demand and historical data; the housing sources with high similarity to the current user demand are matched in the homogeneous housing set through the collaborative filtering algorithm, the matching index of each housing source and the current user demand is calculated, the homogeneous housing set in each partition is searched and matched, and a recommended housing list is output.

[0010] Furthermore, the specific process of obtaining the matching index of homogeneous housing resources in each partition is as follows: based on the list of housing resources matched by the collaborative filtering algorithm, the matching index between each housing resource and the current user demand is calculated one by one, and the matching score is obtained by comprehensively considering the weight of housing resource features and user preferences; the matching scores of all housing resources in each partition are weighted averaged to generate the matching index of homogeneous housing resources in each partition, which reflects the overall adaptability of the housing resource set in the partition to the current user demand.

[0011] Furthermore, a dynamic feedback mechanism is set up, and the specific process of sorting the user-recommended housing list is as follows: based on the user's browsing, clicking and feedback behavior on the recommended housing, the user's housing demand data is updated in real time, and the weights of the housing features preferred by the user are adjusted; combined with the matching index of homogeneous housing in each partition, a weighted sorting algorithm is used to dynamically adjust the user's recommended housing list.

[0012] A spatial intelligent search system for homogeneous real estate based on spatial partitioning comprises the following modules: a data acquisition module, a spatial partitioning module, a demand matching module and a feedback optimization module; the data acquisition module is used to acquire target real estate area data and pre-process the target real estate area data; the spatial partitioning module is used to divide the pre-processed target real estate area into a number of spatial partitions through a geographic information system, extract the homogeneous characteristics of the real estate through a clustering algorithm, and analyze it in combination with the geographical location preference, acquire the surrounding supporting adaptation index of each partition, incorporate the characteristics of each partition, and generate a homogeneous housing source set for each partition; the demand matching module is used to acquire user housing source demand data, search and match the homogeneous housing source set in each partition through a collaborative filtering algorithm, acquire the homogeneous housing source matching index in each partition, and generate a user recommended housing source list; the feedback optimization module is used to set a dynamic feedback mechanism based on the homogeneous housing source matching index in each partition, and sort the user recommended housing source list.

[0013] The present invention has the following beneficial effects: (1) This spatial intelligent search method for homogeneous real estate based on spatial partitioning ensures that the basic data for subsequent analysis is of high quality by accurately acquiring and preprocessing the target real estate area data, thereby improving the accuracy and reliability of the search results. The preprocessed target real estate area is divided into several spatial partitions through the geographic information system, and the homogeneous characteristics of real estate are extracted through the clustering algorithm. It can effectively identify and extract homogeneous real estate characteristics, so that houses with similar characteristics are classified into one category, thereby improving the accuracy of user selection in the same area. In addition, the analysis is combined with the geographical location preference to obtain the surrounding supporting fitness index of each partition, incorporate the characteristics of each partition, and generate a homogeneous housing source set for each partition, which can further improve the user experience and help users choose houses that suit their needs.

[0014] (2) The spatial partition-based homogeneous real estate space intelligent search system obtains user housing demand data, searches and matches the homogeneous housing collection in each partition through a collaborative filtering algorithm, obtains the matching index of homogeneous housing in each partition, and generates a user-recommended housing list, which significantly improves the relevance of the recommended housing and user satisfaction, thereby improving search efficiency. Based on the matching index of homogeneous housing in each partition, a dynamic feedback mechanism is set up to sort the user-recommended housing list, ensuring the continuous update and accuracy of the user-recommended housing list, thereby improving user experience and satisfaction.

[0015] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a flow chart of the method for intelligently searching homogeneous real estate space based on spatial partitioning.

[0017] Figure 2 This is a flow chart of the intelligent search system for homogeneous real estate space based on spatial partitioning of the present invention. DETAILED DESCRIPTION

[0018] The embodiments of the present application provide a method and system for intelligently searching homogeneous real estate spaces based on spatial partitioning, and solve the problems of low efficiency and insufficient matching degree of traditional real estate searches. Through intelligent spatial partitioning and a dynamic recommendation mechanism, personalized housing recommendations are provided.

[0019] The overall idea of ​​the problem in the embodiment of this application is as follows: Acquire target real estate area data and preprocess the target real estate area data.

[0020] The preprocessed target real estate area is divided into several spatial partitions through the geographic information system. The homogeneous characteristics of real estate are extracted through the clustering algorithm, and analyzed in combination with geographical location preferences to obtain the surrounding supporting fitness index of each partition, incorporate the characteristics of each partition, and generate a homogeneous housing source set for each partition.

[0021] Obtain user housing demand data, search and match homogeneous housing sets in each partition through collaborative filtering algorithm, obtain the matching index of homogeneous housing in each partition, and generate a user recommended housing list.

[0022] Based on the matching index of homogeneous properties in each partition, a dynamic feedback mechanism is set up to sort the user-recommended property list.

[0023] See also Figure 1The embodiment of the present invention provides a technical solution: a spatial intelligent search method for homogeneous real estate based on spatial partitioning, comprising the following steps: S1. obtaining target real estate area data and preprocessing the target real estate area data; S2. dividing the preprocessed target real estate area into a number of spatial partitions through a geographic information system, extracting the homogeneous characteristics of the real estate through a clustering algorithm, and analyzing them in combination with geographical location preferences, obtaining the surrounding supporting fitness index of each partition, incorporating the characteristics of each partition, and generating a homogeneous housing source set for each partition; S3. obtaining user housing source demand data, searching and matching the homogeneous housing source set in each partition through a collaborative filtering algorithm, obtaining the homogeneous housing source matching index in each partition, and generating a user recommended housing source list; S4. setting a dynamic feedback mechanism based on the homogeneous housing source matching index in each partition to sort the user recommended housing source list.

[0024] In this embodiment, a geographic information system (GIS) is a system for capturing, storing, analyzing and managing geospatial data, which can combine geographic information with attribute information and provide spatial analysis and visualization functions. GIS is used to spatially partition the target real estate area data. Through GIS, the system can intuitively divide different areas, making subsequent cluster analysis and user preference analysis more accurate, and can effectively identify homogeneous features and supporting facilities in related geographical locations. Clustering algorithm is an unsupervised learning method that divides a data set into several groups (clusters), so that the data points in the same group have a high similarity, while the data points in different groups have a low similarity. Clustering algorithm is used to extract homogeneous features of real estate. By clustering the building area, room structure, building type and sales price of the house source, the system can classify similar houses into one category, which is convenient for analyzing and matching user needs. Collaborative filtering algorithm: Collaborative filtering is a recommendation algorithm based on user behavior and preferences. By analyzing the interaction data between users and items, it predicts the user's preference for items that have not yet been exposed. Collaborative filtering algorithm is used to match user needs with a collection of homogeneous houses. The algorithm uses the historical demand data of known users to calculate the similarity with the current user's needs, thereby generating a personalized list of recommended properties for the user. The dynamic feedback mechanism is a system function that adjusts and optimizes the recommendation results in real time, and continuously updates the recommendation strategy based on user feedback information. The mechanism sorts the recommended property list based on the user's interactive behavior to improve the relevance of the recommendation and user satisfaction. This mechanism ensures that the system can adapt to changes in user needs in a timely manner and achieve more intelligent recommendations.

[0025] Specifically, the target real estate area data includes: the geographical location, building area, sales price, house structure, building type and surrounding supporting facilities information of urban village residences and commercial housing; the preprocessing process of the target real estate area data includes: deduplication of collected data, data format standardization, missing value completion and abnormal data filtering.

[0026] In this implementation plan, the target real estate area data refers to various information related to a specific real estate area, including urban village housing and commercial housing: these different types of housing sources differ in terms of policies, property attributes, and housing purchase qualifications, so they need to be classified and processed in the system analysis. Urban village housing includes urban village private houses: private self-built houses in the urban village area in the city center or surrounding areas. This type of housing is usually built by local villagers or small owners, and is mainly used for leasing; urban village small property houses: usually built on collective land, unable to obtain a complete property certificate, with a relatively low selling price, and are mostly located in the urban-rural fringe. Commercial housing includes ordinary commercial housing: housing sold in the ordinary market, with clear property rights, high prices, and mostly located in high-quality areas in the city. Apartment: a type of collective housing, a living form with complete living facilities but only occupying a part of the building. It is generally divided into residential apartments and serviced apartments. The geographical location of urban village housing and commercial housing: the geographical location is usually expressed in the form of latitude and longitude coordinates, specific addresses or area names, which can help locate the exact location of the housing source on the map. Geographic location is the basis for analyzing the value and selection of properties, and can affect the price of properties, transportation convenience, and the configuration of surrounding facilities. Floor area refers to the total floor area of ​​a property, including all available indoor space. Floor area is one of the main indicators that home buyers pay attention to, which directly affects the pricing of properties and the user's space requirements. Sales price: Sales price is the price at which a property is listed for sale, which is usually affected by market supply and demand. Function: Sales price is a key factor for users to evaluate the value of a property, and it is also one of the most important parameters in the recommendation system. Room structure: Room structure describes the layout type of a property, such as one-bedroom, two-bedroom, three-bedroom, etc., as well as the distribution of rooms. Room structure is directly related to the user's living needs and comfort, and is an important consideration for users when choosing a property. Building type: Building type refers to the nature of a property, such as different types of buildings such as residential, apartment, villa, etc. Building type affects users' selection preferences, and different types of buildings often have different market positioning and price ranges. Surrounding supporting facilities information: Surrounding supporting facilities information includes schools, hospitals, supermarkets, public transportation, and other service facilities near the property. The completeness of supporting facilities directly affects the user's satisfaction with the property. Good supporting facilities can often enhance the market appeal of the property. Preprocessing is the step of cleaning and organizing the data of the target real estate area, including: Deduplication: Detect and delete duplicates of the collected data to ensure the uniqueness of each piece of data. Deduplication can eliminate data redundancy, ensure the accuracy of the data set, and improve the effectiveness of subsequent analysis. Data format standardization: Convert data into a unified format and unit, such as converting all prices to the same currency and all areas to the same unit (square meters). Standardization can improve the consistency of data and facilitate subsequent analysis and comparison.Missing value filling: For missing data, fill it according to certain rules (such as mean filling, nearest neighbor filling, etc.) to avoid analysis bias caused by missing values. Filling missing values ​​can enhance the integrity of data and avoid errors caused by missing values ​​during data analysis. Abnormal data filtering: Identify and eliminate obviously unreasonable or erroneous data, such as negative sales prices or building areas. Abnormal data filtering can improve data quality and ensure the accuracy of subsequent model analysis.

[0027] Specifically, the specific process of extracting homogeneous characteristics of real estate through clustering algorithm and analyzing them in combination with geographical location preference is as follows: based on the pre-processed target real estate area data, the building area, room structure, building type, and sales price characteristics of the housing are clustered through the clustering algorithm to form a preliminary housing feature grouping; combined with geographical location preference, the surrounding supporting facilities of each group are analyzed to generate the surrounding supporting fitness index of each spatial partition, which is incorporated into the characteristic parameters of each spatial partition to generate a homogeneous housing source set for each partition.

[0028] In this implementation scheme, clustering algorithm application: clustering the housing sources by K-means clustering. This step aims to divide the housing sources into multiple groups according to the similarity of their features. Feature selection: The following four features are mainly considered when clustering: Building area: the total area of ​​the housing source, in square meters. Room structure: the layout type of the house, such as one bedroom and one living room, two bedrooms and one living room, etc., usually encoded in numerical form. Building type: such as residential, villa, apartment, etc., using classification identification. Sales price: the market price of the housing source, usually in RMB. Clustering process: through the clustering algorithm, the housing source feature data set is divided into several groups to form a preliminary housing source feature grouping. The housing sources in each group have similar features. For example, a group may contain apartments with similar areas and price ranges. Combined with geographic location preferences: User preference collection: Obtain the user's geographic location preference data, which may include the user's desired area, distance from the workplace, and requirements for transportation convenience. Analyze the surrounding supporting facilities (such as schools, shopping malls, hospitals, etc.) of each group to ensure that the user's geographic location needs are taken into account. To this end, tools such as geographic information systems (GIS) are used to quantify the surrounding environment of each group. Generate a fitness index: Based on the user's geographical preferences, calculate the fitness index of each cluster group to reflect the degree of fit between the group's housing and the user's needs. Integrate characteristic parameters: Incorporate the generated fitness index into the characteristic parameters of each spatial partition to facilitate subsequent analysis and recommendations. For example, for a housing group containing multiple apartments, its distance from schools and shopping malls may be calculated to obtain a comprehensive fitness index. Generate homogeneous housing collections: Combine housing characteristics and their fitness index to form a homogeneous housing collection for each spatial partition. These collections will provide basic data for subsequent user recommendations.

[0029] Specifically, the specific process of obtaining the surrounding supporting facilities adaptability index of each zone is as follows: by obtaining the surrounding supporting facilities data in each spatial zone, an evaluation model is established according to the factors of transportation accessibility, educational resource coverage, commercial service convenience, and medical resource adequacy, and a quantitative score is given to the fit between supporting facilities and user needs; the score values ​​of each factor are weighted and summed according to the predetermined weight to generate the surrounding supporting facilities adaptability index of each spatial zone.

[0030] In this implementation plan, the surrounding supporting facilities data: obtain relevant facility information within each spatial partition, including transportation, education, commerce and medical resources. Specifically include: Transportation accessibility: measure the convenience of transportation facilities. Education resource coverage: reflect the distribution and number of educational facilities. Commercial service convenience: evaluate the accessibility and number of commercial facilities. Medical resource adequacy: indicates the distribution of medical facilities and their service capabilities. The surrounding supporting fitness index formula for each spatial partition is as follows; ; No. The surrounding supporting adaptability index of a spatial partition indicates the degree to which the partition meets user needs. The normalization factor is used to adjust the fitness index to keep it within a reasonable range and improve the comparability between different partitions. They represent the weight coefficients of traffic accessibility, educational resource coverage, commercial service convenience, and medical resource adequacy, respectively, reflecting the relative contributions of traffic, education, commerce, and medical care to the degree of adaptability, and satisfy . User arrives at The distance to a transportation hub. The maximum distance within the region used to normalize the transit accessibility score. No. The number of educational institutions. User arrives at Average distance to educational institutions. The number of b-th commercial service facilities. Represents the average distance for users to reach the bth commercial service facility. No. The number of medical institutions. User arrives at The average distance to medical institutions.

[0031] Specifically, the specific process of searching and matching homogeneous housing sets in each partition through the collaborative filtering algorithm is as follows: based on the obtained user housing demand data, determine the feature weights of the housing sources preferred by the user, and calculate the similarity with the historical demand data of known users in the homogeneous housing set, and construct a feature matching vector of user demand and historical data; match the housing sources with high similarity to the current user demand in the homogeneous housing set through the collaborative filtering algorithm, calculate the matching index of each housing source with the current user demand, search and match the homogeneous housing sets in each partition, and output a list of recommended housing sources.

[0032] In this implementation scheme, user demand weight setting: based on the user's housing demand data (building area, price, room type, location, etc.), extract and determine the weights of different features, that is, user preference weights. In this way, it can better reflect the user's emphasis on different housing features and ensure that the recommendation results are more in line with user needs. Feature matching vector construction: the system compares the user's demand with the historical demand data of other users in the homogeneous housing set, and calculates the similarity between the current user's demand and the historical demand based on the feature matching vector. This process usually uses a similarity algorithm to generate a vectorized representation that can reflect the similarity between the user and the historical demand data. Collaborative filtering algorithm matching: Use the collaborative filtering algorithm to filter out housing sources with high similarity to the current user's demand in the homogeneous housing set. Collaborative filtering analyzes the preference data of historical users with similar needs and infers the housing sources that may meet the current user's needs. Common collaborative filtering algorithms include user-based collaborative filtering (User-based CF) and item-based collaborative filtering (Item-based CF). This step can improve matching efficiency and recommendation accuracy. Matching index calculation: Calculate the matching index for each matching housing source. This index combines the user's feature weights and the matching of the house's features to quantify the degree of fit between each house and the user's needs. The higher the matching index, the more the house matches the user's needs. Recommendation list output: Output the recommended house list in descending order according to the matching index. This list provides users with the most suitable house recommendations in the current partition to improve the user's decision-making efficiency. This process can not only improve the personalization of the recommendation results through collaborative filtering, but also intelligently search and match the houses in each partition, making the system more accurate and applicable when recommending houses.

[0033] Specifically, the specific process of obtaining the matching index of homogeneous housing resources in each partition is as follows: based on the list of housing resources matched by the collaborative filtering algorithm, calculate the matching index between each housing resource and the current user demand one by one, and comprehensively consider the weight of housing resource feature and user preference to obtain the matching score; take the weighted average of the matching scores of all housing resources in each partition to generate the matching index of homogeneous housing resources in each partition, which reflects the overall adaptability of the housing resource set in the partition to the current user demand.

[0034] In this implementation plan, multiple weight adjustment coefficients are introduced to make it possible to calculate the matching degree between the house characteristics and user needs in a more detailed manner. The following is the matching degree index formula for homogeneous houses in each zone: ; :No. In the partition The matching index of a property indicates the overall fit between the property and user needs. : The number of listing features. :No. The user preference weight of each feature is used to adjust the relative influence of each feature on the matching degree. :No. Partition No. Listing No. A feature score is generated to quantify the conformity of the property features. :No. The adjustment coefficient of each feature is used to fine-tune the role of the feature in different matching scenarios. : Scoring index, used to control the nonlinear effect of scoring; when When , features with high scores have higher weights. Feature importance amplification factor, adjusts the gain effect of feature matching on the final index. User's The personalized preference value of a feature. The matching degree normalization coefficient keeps the final matching degree within a comparable range. : Distance adjustment factor, which controls the attenuation effect of distance on matching degree. :No. Partition No. The distance between a listing and the user is used to reflect the impact of geographic location on user matching.

[0035] Specifically, a dynamic feedback mechanism is set up, and the specific process of sorting the user-recommended housing list is as follows: based on the user's browsing, clicking and feedback behavior on the recommended housing, the user's housing demand data is updated in real time, and the weights of the user's preferred housing features are adjusted; combined with the matching index of homogeneous housing in each partition, a weighted sorting algorithm is used to dynamically adjust the user's recommended housing list.

[0036] In this implementation plan, user behavior data collection and update: The system continuously monitors users' browsing, clicking and feedback behaviors on recommended properties, and uses these behavior data as dynamic inputs of user needs. Behaviors such as number of views, click-through rate, and dwell time will be quantified and integrated to reflect users' potential preferences for property features. Adjust property feature weights: Based on the latest user behavior data, the system recalculates and updates the user's property feature weights. For example, if a user browses and clicks on properties with specific features (such as high transportation convenience or high-quality educational resources) many times, the system will increase the weight of the feature to better meet user preferences. Matching index comprehensive scoring: The system will combine the matching index of homogeneous properties in each partition to evaluate the fit between each recommended property and user needs in real time. The matching index is calculated based on a variety of factors (such as property location, price, facilities, etc.), providing basic data for sorting. Using the updated property feature weights and matching index as input, the weighted sorting algorithm is applied to dynamically adjust the recommended property list.

[0037] A homogeneous real estate space intelligent search system based on spatial partitioning includes the following modules: a data acquisition module, a spatial partitioning module, a demand matching module, and a feedback optimization module; the data acquisition module is used to acquire target real estate area data and pre-process the target real estate area data; the spatial partitioning module is used to divide the pre-processed target real estate area into several spatial partitions through a geographic information system, extract the homogeneous characteristics of real estate through a clustering algorithm, and analyze it in combination with geographical location preferences to acquire the surrounding supporting adaptation index of each partition, incorporate the characteristics of each partition, and generate a homogeneous housing source set for each partition; the demand matching module is used to acquire user housing source demand data, search and match the homogeneous housing source set in each partition through a collaborative filtering algorithm, acquire the homogeneous housing source matching index in each partition, and generate a user recommended housing source list; the feedback optimization module is used to set a dynamic feedback mechanism based on the homogeneous housing source matching index in each partition, and sort the user recommended housing source list.

[0038] In this implementation plan, the data acquisition module: ensures the acquisition and preprocessing of high-quality target real estate area data to provide an accurate basis for subsequent analysis and matching. Spatial partitioning module: divides the region through geographic information system and clustering algorithm, extracts homogeneous features, analyzes geographic preferences, and generates a collection of houses that meet regional characteristics. Demand matching module: based on user housing demand data and collaborative filtering algorithm, accurately matches houses and generates personalized recommendation lists. Feedback optimization module: dynamically adjusts the recommendation list sorting according to user feedback, and continuously optimizes the recommendation results to improve matching and user satisfaction.

[0039] In summary, this application has at least the following effects: The spatial intelligent search method and system for homogeneous real estate based on spatial partitioning ensures the accuracy and completeness of the data by obtaining and preprocessing the data of the target real estate area; the preprocessed area is divided into multiple spatial partitions through the geographic information system, and the homogeneous features are extracted through the clustering algorithm. The surrounding supporting fitness index of each partition is analyzed in combination with the user's geographical location preference to form a homogeneous housing source set; the homogeneous housing source set is searched and matched through the collaborative filtering algorithm to generate a user-recommended housing source list, and the matching index of the housing sources in each partition is calculated. A dynamic feedback mechanism is set to sort the recommended housing source list in real time to improve user satisfaction. Provide users with personalized housing source recommendations to improve the convenience and accuracy of real estate transactions.

[0040] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0041] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0042] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0043] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0044] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0045] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A spatial intelligent search method for homogeneous real estate space based on spatial partitioning, characterized in that: The following steps are involved: S1. Obtain target real estate area data and pre-process the target real estate area data; S2. Divide the pre-processed target real estate area into several spatial partitions through the geographic information system, extract the homogeneous characteristics of real estate through the clustering algorithm, and analyze it in combination with the geographical location preference to obtain the surrounding supporting fitness index of each partition, incorporate the characteristics of each partition, and generate a homogeneous housing source set for each partition; S3. Obtain user housing demand data, search and match homogeneous housing sets in each partition through collaborative filtering algorithm, obtain the matching index of homogeneous housing in each partition, and generate a user recommended housing list; S4. Based on the matching index of homogeneous properties in each partition, a dynamic feedback mechanism is set up to sort the user-recommended property list.

2. The method for intelligently searching homogeneous real estate space based on spatial partitioning according to claim 1 is characterized by: The target real estate area data includes: geographical location, building area, sales price, house structure, building type and surrounding supporting facilities information of urban village housing and commercial housing; The preprocessing process of the target real estate area data includes: deduplication of the collected data, data format standardization, missing value filling and abnormal data filtering.

3. The method for intelligently searching homogeneous real estate space based on spatial partitioning according to claim 2 is characterized in that: The specific process of extracting homogeneous characteristics of real estate through clustering algorithms and analyzing them in combination with geographical location preferences is as follows: Based on the pre-processed target real estate area data, clustering algorithms are used to cluster the building area, room structure, building type, and sales price characteristics of the housing sources to form preliminary housing feature groupings; Combined with geographical location preferences, the surrounding supporting facilities of each group are analyzed to generate the surrounding supporting facilities suitability index for each spatial partition, and incorporated into the characteristic parameters of each spatial partition to generate a homogeneous housing set for each partition.

4. The method for intelligently searching homogeneous real estate space based on spatial partitioning according to claim 3 is characterized by: The specific process of obtaining the surrounding supporting fitness index of each partition is as follows: By obtaining the data of surrounding supporting facilities in each spatial zone, an evaluation model is established based on the factors of traffic accessibility, educational resource coverage, commercial service convenience, and medical resource adequacy, and a quantitative score is given on the fit between supporting facilities and user needs; The score values ​​of each factor are weighted and summed according to the predetermined weights to generate the surrounding supporting suitability index of each spatial partition.

5. The method for intelligently searching homogeneous real estate space based on spatial partitioning according to claim 4 is characterized in that: The specific process of searching and matching homogeneous housing sets in each partition through collaborative filtering algorithm is as follows: Based on the acquired user housing demand data, determine the weight of the user's preferred housing feature, calculate the similarity with the historical demand data of known users in the homogeneous housing set, and construct the feature matching vector of user demand and historical data; Through collaborative filtering algorithm, the homogeneous housing source set is matched with the housing sources with high similarity to the current user's needs, the matching index between each housing source and the current user's needs is calculated, the homogeneous housing source set in each partition is searched and matched, and a list of recommended housing sources is output.

6. The method for intelligently searching homogeneous real estate space based on spatial partitioning according to claim 5 is characterized by: The specific process of obtaining the matching index of homogeneous properties in each partition is as follows: Based on the list of properties matched by the collaborative filtering algorithm, the matching index between each property and the current user needs is calculated one by one, and the matching score is obtained by comprehensively considering the property feature weights and user preferences; The matching scores of all listings in each partition are weighted averaged to generate a matching index for homogeneous listings in each partition, which reflects the overall adaptability of the partition's listing set to current user needs.

7. The method for intelligently searching homogeneous real estate space based on spatial partitioning according to claim 6 is characterized by: The specific process of setting up a dynamic feedback mechanism and sorting the user-recommended housing list is as follows: Based on the user's browsing, clicking and feedback behavior on the recommended properties, the user's property demand data is updated in real time, and the weights of the property features preferred by the user are adjusted; Based on the matching index of homogeneous properties in each partition, a weighted sorting algorithm is used to dynamically adjust the user-recommended property list.

8. A spatial intelligent search system for homogeneous real estate based on spatial partitioning, applying a spatial intelligent search method for homogeneous real estate based on spatial partitioning as claimed in any one of claims 1 to 7, characterized in that: It includes the following modules: data acquisition module, space partition module, demand matching module, feedback optimization module; The data acquisition module is used to acquire target real estate area data and pre-process the target real estate area data; The spatial partitioning module is used to divide the pre-processed target real estate area into several spatial partitions through the geographic information system, extract the homogeneous characteristics of the real estate through the clustering algorithm, and analyze it in combination with the geographical location preference to obtain the surrounding supporting fitness index of each partition, incorporate the characteristics of each partition, and generate a homogeneous housing source set for each partition; The demand matching module is used to obtain user housing demand data, search and match homogeneous housing sets in each partition through a collaborative filtering algorithm, obtain the matching index of homogeneous housing in each partition, and generate a user recommended housing list; The feedback optimization module is used to set a dynamic feedback mechanism based on the matching index of homogeneous housing sources in each partition to sort the user-recommended housing source list.

Images