A big data real estate information processing system based on cloud computing
By obtaining the user's commuting information and historical browsing records, initial recommendations, high-quality and intended properties are selected, and target properties are recommended based on similarity. This solves the problem of inaccurate property recommendations in the existing technology and improves the satisfaction of user needs. And the recommended cost-effectiveness.
Patent Information
- Application Number
- CN202311207259.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-19
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
When recommending rental properties on existing real estate information platforms, they mainly rely on the user's company positioning and historical browsing records, making it difficult to push appropriate property information and cannot meet the real needs of users.
By obtaining the user's commuting information, confirm the circular target area, combine historical browsing information and search records, filter out the initial recommended, high-quality and intended properties, and recommend the target properties based on similarity.
It improves the accuracy of the real estate information platform recommends to users, meets the real needs of users, and recommends better and more cost-effective properties through screening and analysis of housing sources.
Smart Images

Figure CN117314689B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information processing technology, and in particular to a big data real estate information processing system based on cloud computing. Background Art
[0002] At present, the Internet is widely used. Various information aggregation platforms will display various information on the pages of the websites they set up for users to browse, which involves obtaining information as well as organizing and storing information. The real estate information platform connects with online and offline real estate information sources (such as different real estate agencies) to obtain relevant information about properties for sale, and classifies them in multiple dimensions, and displays them on the pages of the website so that users can quickly locate the properties they are interested in.
[0003] In the related art, the real estate information platforms currently on the market mainly recommend rental houses based on the user's company location, or recommend houses to users based on the user's historical browsing records. The above-mentioned house information processing method cannot push appropriate house information to users, and it is difficult to meet the real needs of users, and there is room for improvement. Summary of the invention
[0004] In view of the deficiencies in the prior art, the present invention provides a big data real estate information processing system based on cloud computing.
[0005] In a first aspect, the present application provides a method for processing big data real estate information based on cloud computing, comprising the following steps:
[0006] Acquire the user's commuting information, determine a circular target area based on the commuting information, and determine the listings within the circular target area as initial recommended listings;
[0007] Confirm high-quality housing sources based on the user's historical browsing information within the first preset condition, and confirm intended housing sources based on the user's historical browsing information within the second preset condition;
[0008] Confirming a screening housing candidate set based on the initial recommended housing sources, the high-quality housing sources and the intended housing sources, wherein the screening housing candidate set stores the housing intersection of the initial recommended housing sources, the high-quality housing sources and the intended housing sources;
[0009] Confirm the number of properties in the filtered property candidate set. When the number of properties exceeds a first preset number, obtain the user's historical search record and confirm the search keyword, confirm the similarity value of each property in the filtered property candidate set based on the search keyword, confirm the target property from the filtered property candidate set based on the similarity value, and recommend the target property to the user.
[0010] Preferably, the step of obtaining the user's commuting information, determining a circular target area based on the commuting information, and determining the housing sources within the circular target area as the initial recommended housing sources specifically includes:
[0011] Acquire the user's commuting information, including commuting tools and commuting time, to confirm the user's commuting distance;
[0012] When confirming that the company and commuting distance are reference data, obtain the circular target area, confirm the houses in the circular target area, and obtain the number of right turns from each house to the company, where the number of right turns is represented by the number of intersections where left turns are required from the house to the company;
[0013] The number of right turns is compared with a preset turning number range, and when the number of right turns is within the preset turning number range, the house is confirmed as an initially recommended house.
[0014] Preferably, the step of obtaining the user's commuting information, confirming a circular target area based on the commuting information, and confirming the housing sources in the circular target area as the initial recommended housing sources further includes confirming the preliminary recommended housing sources:
[0015] Obtaining basic information of the initially recommended housing source, wherein the basic information includes the time of sale and the occupancy rate;
[0016] Confirming the selling time of the initially recommended house source according to the sale start time of the initially recommended house source, dividing the selling time into a plurality of preset selling time intervals according to the selling time, determining the preset selling time interval in which the selling time is located, and further confirming the preset occupancy rate corresponding to the preset selling time interval;
[0017] When the occupancy rate of the initially recommended housing source is higher than the preset occupancy rate corresponding to the selling duration, the initially recommended housing source is set as the preliminary recommended housing source.
[0018] Preferably, the preliminary recommended housing sources also include:
[0019] A change curve of the sale time-occupancy rate of the initially selected recommended housing source after the sale time is obtained, and the change curve is divided into several groups according to year, and a slope value set of the change curve in each year is obtained, including [k1, k2, k3...kn], where k1 represents the slope value corresponding to the first year of sale, k2 represents the slope value corresponding to the second year of sale, k3 represents the slope value corresponding to the third year of sale, and kn represents the slope value corresponding to the nth year of sale;
[0020] According to the calculation formula The average slope value ω is calculated, where k1′, k2′, k3′, …, kn′ represent the preset slope values corresponding to the first year, the second year, the third year, …, and the nth year of sales, respectively;
[0021] Comparing the average slope value ω of each of the preliminarily recommended properties with a preset average slope value;
[0022] When ω1<ω<ω2, the initially recommended housing source is confirmed as a high-quality housing source;
[0023] When ω>ω2, the preliminarily recommended housing source is confirmed as the intended housing source.
[0024] Preferably, the method of confirming high-quality housing sources based on the user's historical browsing information within the first preset condition and confirming intended housing sources based on the user's historical browsing information within the second preset condition includes:
[0025] Obtaining historical browsing information of a user on a real estate information platform, wherein the historical browsing information includes historical browsing of houses, historical browsing times and historical browsing duration;
[0026] According to the formula Calculate the intention coefficient β corresponding to each historically browsed property d , where b1 and b2 represent the weight coefficients corresponding to the number of historical browsing times and the historical browsing duration, respectively, n d It is represented by the historical browsing times of the d-th house, T d It represents the historical browsing time corresponding to the d-th house, and d represents the number corresponding to each historically browsed house, d = 1, 2, 3, ..., j;
[0027] Set the listings whose intention coefficients corresponding to the historically browsed listings are greater than the first preset intention coefficients as high-quality listings;
[0028] The houses whose intention coefficients corresponding to the historically browsed houses are greater than the second preset intention coefficient are set as intended houses, wherein the first preset intention coefficient is less than the second preset intention coefficient.
[0029] Preferably, before obtaining the user's historical search records and confirming the search keywords, the method further includes:
[0030] Confirm the label attributes of each house in the candidate set of screened houses, wherein the label attributes include house orientation, house decoration level, house floor, house area and house price.
[0031] Preferably, the determining of the similarity value of each house in the screened house candidate set based on the search keyword, determining a target house from the screened house candidate set based on the similarity value, and recommending the target house to the user specifically includes:
[0032] confirming a plurality of search keywords based on the user's historical search records, and setting the plurality of search keywords as a search keyword set;
[0033] Comparing each search keyword in the search keyword set with the label attribute of each house in the screened house candidate set to determine the similarity of each house in the screened house candidate set;
[0034] Directly push the properties in the candidate set of screened properties whose similarity is greater than a preset similarity threshold to the user as target properties;
[0035] When the houses in the screened house candidate set whose similarity is lower than the preset similarity threshold are pushed to the user as preset selected houses after a first preset time, the priority of house push is: target house>preset selected house.
[0036] In a second aspect, the present application provides a big data real estate information processing system based on cloud computing, comprising:
[0037] An initial recommended housing source confirmation module is used to obtain the user's commuting information, confirm a circular target area based on the commuting information, and confirm the housing sources within the circular target area as the initial recommended housing sources;
[0038] A module for confirming high-quality housing sources and intended housing sources, used to confirm high-quality housing sources based on the user's historical browsing information within a first preset condition, and to confirm intended housing sources based on the user's historical browsing information within a second preset condition;
[0039] A module for constructing a screening housing source candidate set, for confirming a screening housing source candidate set based on the initial recommended housing source, the high-quality housing source and the intended housing source, wherein the screening housing source candidate set stores the housing source intersection of the initial recommended housing source, the high-quality housing source and the intended housing source;
[0040] The target property recommendation module is used to confirm the number of properties in the screened property candidate set. When the number of properties exceeds a first preset number, the user's historical search records are obtained and the search keywords are confirmed. Based on the search keywords, the similarity values of each property in the screened property candidate set are confirmed, and based on the similarity values, the target property is confirmed from the screened property candidate set, and the target property is recommended to the user.
[0041] In a third aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute any one of the above-mentioned methods for processing big data real estate information based on cloud computing.
[0042] In summary, the present application includes at least one of the following beneficial technical effects:
[0043] 1. The present invention provides a real estate information processing method based on big data of cloud computing, which obtains the commuting information of the user to confirm the initial recommended housing source, confirms the high-quality housing source based on the historical browsing information of the user within the first preset condition, confirms the intended housing source based on the historical browsing information of the user within the second preset condition, and selects the screening housing source candidate set from the initial recommended housing source, the high-quality housing source and the intended housing source, and confirms the target housing source from the screening housing source candidate set based on the similarity and pushes it to the user, thereby effectively improving the accuracy of the real estate information platform in recommending suitable housing sources to the user, thereby effectively meeting the real needs of the user;
[0044] 2. By obtaining the basic information of the initially recommended properties, and comparing the sales launch time and occupancy rate of the initially recommended properties with the preset sales time and preset occupancy rate, the preliminary recommended properties are further confirmed, and the sales launch time-occupancy rate change curve of the preliminary recommended properties is analyzed, and the preliminary recommended properties are further divided into high-quality properties and intended properties, and the properties are further screened according to the basic information of the initially recommended properties, so as to recommend better and more cost-effective properties to users, thereby effectively meeting the real needs of users. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] Figure 1 It is a flow chart of a method for processing big data real estate information based on cloud computing according to an embodiment of the present application.
[0046] Figure 2 It is a system diagram of big data real estate information processing based on cloud computing in an embodiment of the present application. DETAILED DESCRIPTION
[0047] The following is combined with Figure 1-2 This application is described in further detail.
[0048] Example 1
[0049] The embodiment of the present application discloses a touch screen device testing method.
[0050] Reference Figure 1 , a big data real estate information processing method based on cloud computing, comprising the following steps:
[0051] S1. Obtain the user's commuting information, determine the circular target area based on the commuting information, and determine the housing sources in the circular target area as the initial recommended housing sources;
[0052] S2. Confirm high-quality housing sources based on the user's historical browsing information within the first preset condition, and confirm the intended housing sources based on the user's historical browsing information within the second preset condition;
[0053] S3. confirm and filter the candidate housing set based on the initial recommended housing sources, high-quality housing sources, and intended housing sources, where the candidate housing set contains the intersection of the initial recommended housing sources, high-quality housing sources, and intended housing sources;
[0054] S4. Confirm the number of properties in the candidate set of filtered properties. When the number of properties exceeds a first preset number, obtain the user's historical search record and confirm the search keywords. Based on the search keywords, confirm the similarity value of each property in the candidate set of filtered properties. Based on the similarity value, confirm the target property from the candidate set of filtered properties and recommend the target property to the user.
[0055] In step S1, the user's commuting information is obtained, a circular target area is determined based on the commuting information, and the housing sources in the circular target area are determined as the initial recommended housing sources, which specifically includes:
[0056] Obtain the user's commuting information, including commuting tools and commuting time, to confirm the user's commuting distance;
[0057] When confirming that the company and commuting distance are used as reference data, obtain the circular target area, confirm the properties within the circular target area, and obtain the number of right turns from each property to the company. The number of right turns is expressed as the number of intersections where left turns are required from the property to the company.
[0058] The number of right turns is compared with the preset turn number range. When the number of right turns is within the preset turn number range, the property is confirmed as the initial recommended property.
[0059] Specifically, in the embodiment of the present application, when the means of transportation is walking or non-motorized vehicles, it is set that the right turn does not need to wait for the traffic light, and when the means of transportation is a motor vehicle, the waiting time for the right turn is set to be shorter, and then by judging the number of right turns from each house source to the company, the commuting time is effectively saved, and another method for judging the number of right turns is also included:
[0060] The number of intersections from each property to the company is obtained. When the number of right turns exceeds two-thirds of the number of intersections, the property is confirmed as the initial recommended property.
[0061] Furthermore, after step S1, it also includes confirming the preliminary recommended properties:
[0062] Obtain basic information of the initially recommended properties, including the launch time and occupancy rate;
[0063] Confirming the selling time of the initially recommended house source according to the sale start time of the initially recommended house source, dividing the selling time into a plurality of preset selling time intervals according to the selling time, determining the preset selling time interval in which the selling time is located, and further confirming the preset occupancy rate corresponding to the preset selling time interval;
[0064] When the occupancy rate of the initially recommended properties is higher than the preset occupancy rate corresponding to the sales duration, the initially recommended properties will be set as the preliminary recommended properties.
[0065] Furthermore, the preliminary recommended properties also include:
[0066] A change curve of the sale time-occupancy rate of the initially recommended housing sources after the sale time is obtained, and the change curve is divided into several groups by year, and a set of slope values of the change curve in each year is obtained, including [k1, k2, k3...kn], where k1 represents the slope value corresponding to the first year of sale, k2 represents the slope value corresponding to the second year of sale, k3 represents the slope value corresponding to the third year of sale, and kn represents the slope value corresponding to the nth year of sale;
[0067] According to the calculation formula The slope average value ω is calculated, where k1′, k2′, k3′, …, kn′ represent the preset slope values corresponding to the first year, second year, third year, …, and nth year of sales, respectively. The preset slope values of different years are calculated by averaging the slope values of the corresponding historical years;
[0068] Compare the average slope ω of each primary recommended house with the preset average slope;
[0069] When ω1<ω<ω2, the initially recommended housing sources are confirmed as high-quality housing sources;
[0070] When ω>ω2, the preliminarily recommended properties will be confirmed as intended properties.
[0071] Specifically, the slope of the curve of sale launch time-occupancy rate change is different in each year after the sale launch time. In the embodiment of the present application, the slope in the first two years after the sale launch time will show an upward trend, followed by a smooth trend for two years, and then a downward trend. Furthermore, the high-quality housing sources and intended housing sources confirmed by comparing the slope average value ω of the above-mentioned preliminary recommended housing sources with the preset slope average value are different from the high-quality housing sources and intended housing sources confirmed based on the user's historical browsing information within the first preset condition and the second preset condition as described below.
[0072] Among them, step S2 confirms high-quality housing sources based on the user's historical browsing information within the first preset condition, and confirms intended housing sources based on the user's historical browsing information within the second preset condition, including:
[0073] Obtain the user's historical browsing information of properties on the real estate information platform, including historical browsing properties, historical browsing times and historical browsing duration;
[0074] According to the formula Calculate the intention coefficient β corresponding to each historically browsed property d , where b1 and b2 represent the weight coefficients corresponding to the number of historical browsing times and the historical browsing duration, respectively, n d It is represented by the historical browsing times of the d-th house, T d It represents the historical browsing time corresponding to the d-th house, and d represents the number corresponding to each historically browsed house, d = 1, 2, 3, ..., j;
[0075] Set the listings whose intention coefficients corresponding to the historically browsed listings are greater than the first preset intention coefficients as high-quality listings;
[0076] The houses whose intention coefficients corresponding to the historically browsed houses are greater than the second preset intention coefficients are set as intended houses, wherein the first preset intention coefficient is less than the second preset intention coefficient.
[0077] Furthermore, before obtaining the user's historical search records and confirming the search keywords, it also includes:
[0078] Confirm and filter the label attributes of each house in the candidate set of houses. The label attributes include house orientation, house decoration degree, house floor, house area and house price. Among them, the house orientation includes house facing south, house facing southeast, house facing southwest, house facing east, house facing north, house facing northeast, house facing west and house facing northwest; the house decoration degree includes three levels: poor, average and satisfactory.
[0079] For example, the label attributes of a house are: the house faces south, the house decoration is satisfactory, it is on the 10th floor, it is 120 square meters, and it costs 15,000 per square meter.
[0080] Among them, in step S4, based on the search keywords, the similarity values of each house in the candidate set of screened houses are confirmed, and based on the similarity values, the target house is confirmed from the candidate set of screened houses, and the target house is recommended to the user, which specifically includes:
[0081] confirming multiple search keywords based on the user's historical search records, and setting the multiple search keywords as a search keyword set;
[0082] Compare each search keyword in the search keyword set with the label attributes of each listing in the screening listing candidate set to confirm the similarity of each listing in the screening listing candidate set;
[0083] For example, when the search keywords are south facing, average house decoration, and 15,000 per square meter, the similarity between the search keywords and the label attributes of the house is 40%.
[0084] The properties in the candidate set of screened properties whose similarity is greater than the preset similarity threshold are directly pushed to the user as target properties;
[0085] When the similarity of the filtered property candidate set is lower than the preset similarity threshold, the property is pushed to the user as the preset selected property after the first preset time, wherein the priority of property push is: target property > preset selected property.
[0086] Example 2
[0087] The embodiment of the present application also discloses a big data real estate information processing system based on cloud computing.
[0088] Reference Figure 2 , a big data real estate information processing system based on cloud computing, comprising:
[0089] An initial recommended housing source confirmation module is used to obtain the user's commuting information, confirm the circular target area based on the commuting information, and confirm the housing sources in the circular target area as the initial recommended housing sources;
[0090] A module for confirming high-quality housing sources and intended housing sources, used to confirm high-quality housing sources based on the user's historical browsing information within a first preset condition, and to confirm intended housing sources based on the user's historical browsing information within a second preset condition;
[0091] A module for constructing a candidate set of house selection, which is used to confirm the candidate set of house selection based on the initial recommended house selection, high-quality house selection and intended house selection. The candidate set of house selection stores the intersection of the initial recommended house selection, high-quality house selection and intended house selection.
[0092] The target property recommendation module is used to confirm the number of properties in the candidate set of filtered properties. When the number of properties exceeds a first preset number, the user's historical search records are obtained and the search keywords are confirmed. Based on the search keywords, the similarity values of each property in the candidate set of filtered properties are confirmed, and based on the similarity values, the target property is confirmed from the candidate set of filtered properties, and the target property is recommended to the user.
[0093] Among them, the initial recommended housing confirmation module includes a commuting information confirmation unit, a right turn number judgment unit and a comparison unit. The commuting information confirmation unit is used to confirm the user's commuting information, and then confirm the user's commuting distance. The commuting information includes commuting tools and commuting time; the right turn number judgment unit is used to obtain a circular target area with the company as the center and the commuting distance as the radius, and confirm the housing within the circular target area, and then confirm the number of right turns from each housing source to the company. The number of right turns is expressed as the number of intersections where left turns are required from the housing source to the company; the comparison unit is used to compare the number of right turns with the preset turn number range. When the number of right turns is within the preset turn number range, the housing source is confirmed as the initial recommended housing source.
[0094] Furthermore, the initial recommended housing source confirmation module also includes a preliminary recommended housing source confirmation unit, which is used to compare the sales launch time and occupancy rate of the initial recommended housing source with the preset sales time and preset occupancy rate, and then confirm the preliminary recommended housing source.
[0095] The preliminary recommended housing source confirmation unit also includes a calculation unit, which is used to obtain a change curve of the sale time-occupancy rate of the preliminary recommended housing source after the sale time, and divide the change curve into several groups according to years, and obtain a slope value set of the change curve in each year, including [k1, k2, k3...kn], where k1 represents the slope value corresponding to the first year of sale, k2 represents the slope value corresponding to the second year of sale, k3 represents the slope value corresponding to the third year of sale, and kn represents the slope value corresponding to the nth year of sale;
[0096] According to the calculation formula The average slope value ω is calculated, where k1′, k2′, k3′, …, kn′ represent the preset slope values corresponding to the first year, the second year, the third year, …, and the nth year of sales, respectively;
[0097] Compare the average slope ω of each primary recommended house with the preset average slope;
[0098] When ω1<ω<ω2, the initially recommended housing sources are confirmed as high-quality housing sources;
[0099] When ω>ω2, the preliminarily recommended properties will be confirmed as intended properties.
[0100] Among them, the high-quality housing and intended housing confirmation module includes a housing history browsing information confirmation unit, an intention coefficient calculation unit and an intention coefficient comparison unit. The historical browsing information confirmation unit is used to obtain the user's historical browsing information of the housing on the real estate information platform. The historical browsing information includes historical browsing housing, historical browsing times and historical browsing time; the intention coefficient calculation unit is used to calculate the historical browsing time according to the formula Calculate the intention coefficient β corresponding to each historically browsed property d , where b1 and b2 represent the weight coefficients corresponding to the number of historical browsing times and the historical browsing duration, respectively, n d It is represented by the historical browsing times of the d-th house, T d is represented by the historical browsing time corresponding to the d-th house, d is represented by the number corresponding to each historically browsed house, d=1, 2, 3, ..., j; the intention coefficient comparison unit is used to set the house whose intention coefficient corresponding to each historically browsed house is greater than the first preset intention coefficient as a high-quality house;
[0101] The houses whose intention coefficients corresponding to the historically browsed houses are greater than the second preset intention coefficients are set as intended houses, wherein the first preset intention coefficient is less than the second preset intention coefficient.
[0102] The target housing source recommendation module includes a label attribute acquisition unit, a search keyword set confirmation unit and a comparison push unit. The label attribute acquisition unit is used to obtain the label attributes of each housing source in the screening housing source candidate set, and the label attributes include house orientation, house decoration degree, house floor, house area and house price; the search keyword set confirmation unit is used to confirm multiple search keywords based on the user's historical search records, and set the multiple search keywords as the search keyword set; the comparison push unit is used to compare each search keyword in the search keyword set with the label attributes of each housing source in the screening housing source candidate set, and confirm the similarity of each housing source in the screening housing source candidate set; the housing sources in the screening housing source candidate set whose similarity is greater than the preset similarity threshold are directly pushed to the user as target housing sources; when the housing sources in the screening housing source candidate set whose similarity is lower than the preset similarity threshold are pushed to the user as preset selected housing sources after the first preset time, the priority of housing source push is: target housing source>preset selected housing source.
[0103] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.
[0104] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0105] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.
Claims
1. A method for processing big data real estate information based on cloud computing, characterized in that: The following steps are involved: Acquire the user's commuting information, determine a circular target area based on the commuting information, and determine the housing sources within the circular target area as initial recommended housing sources; The obtaining of the user's commuting information, determining a circular target area based on the commuting information, and determining the housing sources within the circular target area as the initial recommended housing sources specifically includes: Acquire the user's commuting information, including commuting tools and commuting time, to confirm the user's commuting distance; When confirming that the company and commuting distance are reference data, obtain the circular target area, confirm the houses in the circular target area, and obtain the number of right turns from each house to the company, where the number of right turns is represented by the number of intersections where left turns are required from the house to the company; Compare the number of right turns with a preset turn number range, and when the number of right turns is within the preset turn number range, confirm the house as an initial recommended house; After obtaining the user's commuting information, confirming the circular target area based on the commuting information, and confirming the housing sources in the circular target area as the initial recommended housing sources, the method further includes confirming the preliminary recommended housing sources: Obtaining basic information of the initially recommended housing source, wherein the basic information includes the time of sale and the occupancy rate; Confirming the selling time of the initially recommended house source according to the sale start time of the initially recommended house source, dividing the selling time into a plurality of preset selling time intervals according to the selling time, determining the preset selling time interval in which the selling time is located, and further confirming the preset occupancy rate corresponding to the preset selling time interval; When the occupancy rate of the initially recommended house source is higher than the preset occupancy rate corresponding to the selling period, the initially recommended house source is set as the preliminary recommended house source; The preliminary recommended properties also include: A change curve of the sale time-occupancy rate of the initially selected recommended housing source after the sale time is obtained, and the change curve is divided into several groups according to year, and a slope value set of the change curve in each year is obtained, including [k1, k2, k3...kn], where k1 represents the slope value corresponding to the first year of sale, k2 represents the slope value corresponding to the second year of sale, k3 represents the slope value corresponding to the third year of sale, and kn represents the slope value corresponding to the nth year of sale; According to the calculation formula , calculate the average slope ,in, They represent the preset slope values corresponding to the first year, second year, third year, …, and nth year of sales respectively; Based on the average slope of each of the preliminary recommended properties Compare with the preset slope average; when , the preliminary recommended housing sources will be confirmed as high-quality housing sources; when , the preliminary recommended housing sources will be confirmed as intended housing sources; Confirm high-quality housing sources based on the user's historical browsing information within the first preset condition, and confirm intended housing sources based on the user's historical browsing information within the second preset condition; Confirming a screening housing candidate set based on the initial recommended housing sources, the high-quality housing sources and the intended housing sources, wherein the screening housing candidate set stores the housing intersection of the initial recommended housing sources, the high-quality housing sources and the intended housing sources; Confirm the number of properties in the filtered property candidate set. When the number of properties exceeds a first preset number, obtain the user's historical search record and confirm the search keyword, confirm the similarity value of each property in the filtered property candidate set based on the search keyword, confirm the target property from the filtered property candidate set based on the similarity value, and recommend the target property to the user.
2. The method for processing big data real estate information based on cloud computing according to claim 1, characterized in that: The method of confirming high-quality housing sources based on the user's historical browsing information within the first preset condition and confirming intended housing sources based on the user's historical browsing information within the second preset condition includes: Obtaining historical browsing information of a user on a real estate information platform, wherein the historical browsing information includes historical browsing of houses, historical browsing times and historical browsing duration; According to the formula , calculate the intention coefficient corresponding to each historically browsed property , where b1 and b2 represent the weight coefficients corresponding to the number of historical browsing times and the historical browsing duration, respectively. It is represented by the historical browsing times of the d-th house. It is represented by the historical browsing time corresponding to the d-th house. Indicates the number corresponding to each historically browsed property. ; Set the listings whose intention coefficients corresponding to the historically browsed listings are greater than the first preset intention coefficients as high-quality listings; The houses whose intention coefficients corresponding to the historically browsed houses are greater than the second preset intention coefficient are set as intended houses, wherein the first preset intention coefficient is less than the second preset intention coefficient.
3. The method for processing big data real estate information based on cloud computing according to claim 2, characterized in that: Before obtaining the user's historical search records and confirming the search keywords, the method further includes: Confirm the label attributes of each house in the candidate set of screened houses, wherein the label attributes include house orientation, house decoration level, house floor, house area and house price.
4. The method for processing big data real estate information based on cloud computing according to claim 3 is characterized by: The determining of the similarity value of each house in the screened house candidate set based on the search keyword, determining a target house from the screened house candidate set based on the similarity value, and recommending the target house to the user specifically includes: confirming a plurality of search keywords based on the user's historical search records, and setting the plurality of search keywords as a search keyword set; Comparing each search keyword in the search keyword set with the label attribute of each house in the screened house candidate set to determine the similarity of each house in the screened house candidate set; Directly push the properties in the candidate set of screened properties whose similarity is greater than a preset similarity threshold to the user as target properties; When the houses in the screened house candidate set whose similarity is lower than the preset similarity threshold are pushed to the user as preset selected houses after a first preset time, the priority of house push is: target house>preset selected house.
5. A big data real estate information processing system based on cloud computing, applied to a big data real estate information processing method based on cloud computing according to claims 1-4, characterized in that: include: An initial recommended housing source confirmation module is used to obtain the user's commuting information, confirm a circular target area based on the commuting information, and confirm the housing sources within the circular target area as the initial recommended housing sources; A module for confirming high-quality housing sources and intended housing sources, used to confirm high-quality housing sources based on the user's historical browsing information within a first preset condition, and to confirm intended housing sources based on the user's historical browsing information within a second preset condition; A module for constructing a screening housing source candidate set, for confirming a screening housing source candidate set based on the initial recommended housing source, the high-quality housing source and the intended housing source, wherein the screening housing source candidate set stores the housing source intersection of the initial recommended housing source, the high-quality housing source and the intended housing source; The target property recommendation module is used to confirm the number of properties in the screened property candidate set. When the number of properties exceeds a first preset number, the user's historical search records are obtained and the search keywords are confirmed. Based on the search keywords, the similarity values of each property in the screened property candidate set are confirmed, and based on the similarity values, the target property is confirmed from the screened property candidate set, and the target property is recommended to the user.
6. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes a cloud computing-based big data real estate information processing method as described in any one of claims 1 to 4.
Citation Information
Cited By
House resource searching method and system based on big data
CN121980084A
Big data-based house searching method and system
CN121980084B
