House property selection method and system based on big data
Through the peripheral characterization data processing of the target area and the analysis of the adjacent environmental assessment value, the hierarchy and priority ranking of real estate are achieved, which solves the problem that home buyers find it difficult to choose housing sources that meet their needs, and improves the reliability and comprehensiveness of home purchase decisions sex.
Patent Information
- Application Number
- CN202410981222.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
It is difficult for home buyers to accurately choose houses that meet their needs and expectations during the real estate selection process. Due to the complexity of factors such as geographical location, apartment size, price budget, and supporting facilities, the decision-making process is blind and random.
By processing the peripheral characterization data of the target area, obtaining environmental assessment behavior values, classifying levels, and processing the environmental assessment values and distances of adjacent areas within the same level, generating environmental assessment representation values of adjacent areas, realizing priority rankings for real estate and Secondary selection.
Through scientific real estate selection methods, the blindness and randomness of decision-making are reduced, the decision-making reliability of home buyers is improved, and the rationality and comprehensiveness of the house selection process are ensured.
Smart Images

Figure CN118941362A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of real estate recommendation, and in particular to a real estate recommendation method and system based on big data. Background Art
[0002] In the complex real estate market, different home buyers have different needs and preferences, such as geographical location, apartment size, price budget, supporting facilities, etc.
[0003] Through scientific recommendation methods, home buyers can systematically evaluate various factors, reduce blindness and randomness, and ensure a more rational and comprehensive decision-making process.
[0004] The property selection process involves a wide range of issues including purchasing needs, location, quality, supporting facilities, future planning, on-site viewing and comparison, etc. It is difficult for buyers to accurately choose a property that meets their needs and expectations.
[0005] Based on this, the present invention proposes a real estate recommendation method and system based on big data. Summary of the invention
[0006] The purpose of the present invention is to provide a real estate selection method and system based on big data. After processing the environmental impact assessment behavior value of the target area itself, the target area is graded, that is, the real estate corresponding to the target area is graded. On the basis of the grade division, the target areas adjacent to the target areas within the same grade are processed, that is, the adjacent environmental impact assessment value of the target area is obtained by processing the adjacent environmental impact assessment value and the environmental impact assessment distance length of the adjacent area, so as to identify the target area from the environmental status of the adjacent target area and complete the secondary selection of the target area, that is, the real estate is recommended through two screenings to solve the above-mentioned background problems.
[0007] The purpose of the present invention can be achieved through the following technical solutions:
[0008] A real estate recommendation method based on big data, comprising the following steps:
[0009] Divide the real estate into regions, obtain the target region corresponding to the real estate, obtain peripheral representation data of the target region, and obtain the environmental impact assessment behavior value of the target region based on the peripheral representation data of the target region;
[0010] Among them, the peripheral representation data include road risk base and road environment base;
[0011] Based on the environmental impact assessment behavior value of the target area, the target area corresponding to the property is identified in terms of grade status;
[0012] Among them, the level status of the target area includes a first-level housing selection signal, a second-level housing selection signal, and a third-level housing selection signal;
[0013] Obtain the adjacent target areas corresponding to the target area within the same level status, process all adjacent target areas to obtain the adjacent environmental assessment value and the environmental assessment distance length, obtain the adjacent environmental assessment characterization value of the target area based on the adjacent environmental assessment value and the environmental assessment distance length, and complete the priority ranking of the target area selection based on the adjacent environmental assessment characterization value.
[0014] As a further solution of the present invention: the process of obtaining the environmental assessment behavior value of the target area is as follows:
[0015] Record the road environment base number of the target area as H i;
[0016] Record the road risk base number of the target area as D i;
[0017] That is, through the formula Calculate to obtain the environmental assessment behavior value DH of the target area, where Ri is the perimeter dynamic base number.
[0018] As a further solution of the present invention: preset the limit values of the environmental assessment behavior value threshold of the target area as DH1 and DH2, where DH1 < DH2;
[0019] When DH < DH1, it means that the overall environmental assessment of the target area is poor, and a first-level housing selection signal of the target area is generated;
[0020] When DH1 ≤ DH < DH2, it means that the overall environmental assessment of the target area is medium, and a second-level housing selection signal of the target area is generated;
[0021] When DH ≥ DH2, it means that the overall environmental assessment of the target area is good, and a third-level housing selection signal of the target area is generated.
[0022] As a further solution of the present invention: the process of obtaining the perimeter dynamic base number is as follows:
[0023] Obtain the population density of the target area and mark the population density as R1;
[0024] Obtain the vegetation coverage rate of the target area and mark the vegetation coverage rate as R2;
[0025] Obtain the police dispatch rate of the target area within the preset period and record the police dispatch rate of the target area within the preset period as R3;
[0026] Through the formula Calculate to obtain the perimeter dynamic base number Ri of the target area.
[0027] As a further solution of the present invention: the process of obtaining the road risk base number is as follows:
[0028] Get the number of lanes of the main road in the target area and record it as D1;
[0029] Obtain the number of road intersections on the main roads in the target area and record it as D2;
[0030] Obtain the road risk factor of the main roads in the target area, denoted as D3;
[0031] Calculated by the formula Calculate the road risk factor D of the target area;
[0032] The road risk factor of all main roads in the target area is summed and averaged to obtain the road risk base D i of the target area.
[0033] As a further solution of the present invention: the process of obtaining the road risk factor is:
[0034] The total number of road accidents on the main roads in the target area and the road accident frequency on the main roads in the target area are obtained, and processed to obtain the road risk factor.
[0035] As a further solution of the present invention: the process of obtaining the road environment base is:
[0036] Obtain the ambient dust ratio of the target area and mark it as H1;
[0037] Get the ambient noise ratio of the target area and mark it as H2;
[0038] Calculated by formula The road environment base Hi of the target area is obtained, where a1 and a2 are preset proportional coefficients, and hi is the dynamic value of the road quality.
[0039] As a further solution of the present invention: in the target area corresponding to the same room selection signal, an adjacent target area of any target area is obtained and marked to obtain a side adjacent area of the target area;
[0040] Obtain the environmental impact assessment behavior value of each adjacent area, recorded as the adjacent environmental impact assessment value HDj, where j is the number of adjacent areas, j=1,...,n;
[0041] Get the center point of the target area and the center point of any adjacent area, connect the center point of the target area with the center point of any adjacent area, and get the length of the environmental assessment distance, which is recorded as Lj;
[0042] By formula The neighboring environmental impact assessment characterization value of the target area is calculated.
[0043] As a further solution of the present invention: the neighboring environmental impact assessment characterization values corresponding to all target areas in the same house selection signal are arranged in order from large to small, and the property in the target area corresponding to the largest neighboring environmental impact assessment characterization value is selected as the first recommended property to complete the property selection.
[0044] As a further solution of the present invention: a real estate recommendation system based on big data, comprising:
[0045] A regional processing module, which is used to divide the real estate into regions, obtain the target region corresponding to the real estate, obtain the peripheral representation data of the target region, obtain the environmental impact assessment behavior value of the target region based on the peripheral representation data of the target region, and upload it to the cloud management and control platform;
[0046] Among them, the peripheral representation data include road risk base and road environment base;
[0047] An environmental assessment analysis module, wherein the environmental assessment analysis module receives the environmental assessment behavior value of the target area transmitted by the cloud management and control platform, identifies the level status of the target area corresponding to the real estate, and transmits the status identification signal to the cloud management and control platform;
[0048] The level status of the target area includes a first-level room selection signal, a second-level room selection signal, and a third-level room selection signal;
[0049] A multi-level recommendation module receives a status identification signal transmitted by a cloud management and control platform, obtains adjacent target areas corresponding to target areas in the same level of status, processes all adjacent target areas to obtain adjacent environmental impact assessment values and environmental impact assessment distance lengths, obtains adjacent environmental impact assessment representation values of the target areas according to the adjacent environmental impact assessment values and the environmental impact assessment distance lengths, and completes the priority sorting of target area recommendation based on the adjacent environmental impact assessment representation values.
[0050] Beneficial effects of the present invention:
[0051] (1) The present invention obtains the peripheral representation data of the target area corresponding to the real estate, that is, by processing the road risk base and the road environment base of the target area, the environmental impact assessment behavior value of the target area is obtained, and the target area is graded according to the environmental impact assessment behavior value of the target area, that is, by considering the environment, traffic status, public security and other dimensions of the real estate in the target area, the real estate in the target area is screened once, and the reliability is strong;
[0052] (2) After processing the environmental impact assessment behavior value of the target area itself, the present invention further processes the target areas adjacent to the target area within the same level on the basis of the level division, that is, by processing the adjacent environmental impact assessment value and the environmental impact assessment distance length of the adjacent area, the adjacent environmental impact assessment characterization value of the target area is obtained, thereby realizing the identification of the target area from the environmental status of the adjacent target area, and completing the secondary selection of the target area. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] The present invention will be further described below in conjunction with the accompanying drawings.
[0054] Figure 1 It is a flow chart of a real estate recommendation method based on big data according to an embodiment of the present invention;
[0055] Figure 2 It is a flow chart of the classification of target area status in a real estate recommendation method based on big data in an embodiment of the present invention;
[0056] Figure 3 It is a flowchart of a real estate recommendation system based on big data in an embodiment of the present invention. DETAILED DESCRIPTION
[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0058] Example 1
[0059] See also Figure 1 As shown, the present invention is a real estate recommendation method based on big data, comprising the following steps:
[0060] Divide the real estate into regions, obtain the target region corresponding to the real estate, obtain peripheral representation data of the target region, and obtain the environmental impact assessment behavior value of the target region based on the peripheral representation data of the target region;
[0061] Among them, the peripheral representation data include road risk base and road environment base;
[0062] Based on the environmental impact assessment behavior value of the target area, the target area corresponding to the property is identified in terms of grade status;
[0063] The level status of the target area includes a first-level room selection signal, a second-level room selection signal, and a third-level room selection signal;
[0064] Obtain the adjacent target areas corresponding to the target area in the same level status, process all adjacent target areas to obtain the adjacent environmental impact assessment values and environmental impact assessment distance lengths, obtain the adjacent environmental impact assessment representation values of the target area based on the adjacent environmental impact assessment values and environmental impact assessment distance lengths, and complete the priority sorting of the target area selection based on the adjacent environmental impact assessment representation values.
[0065] Among them, the principles for dividing the target area include but are not limited to grid division or administrative area division;
[0066] Furthermore, it is also possible to divide by cell location.
[0067] Specific:
[0068] The process of obtaining the road risk base is as follows:
[0069] Get the number of lanes of the main road in the target area and record it as D1;
[0070] Obtain the number of road intersections on the main roads in the target area and record it as D2;
[0071] Obtain the road risk factor of the main roads in the target area, denoted as D3;
[0072] Calculated by the formula Calculate the road risk factor D of the target area;
[0073] Sum and average the road risk factors of all main roads in the target area to obtain the road risk base D i of the target area;
[0074] Among them, the main roads in the target area refer to roads with at least two lanes in both directions;
[0075] The process of obtaining road risk factors is as follows:
[0076] Obtain the total number of road accidents and road accident frequency on the main roads of the target area within a preset period;
[0077] The duration of the cycle includes but is not limited to 3 months, 6 months or 9 months, which is set by the staff based on experience;
[0078] The total number of road accidents on the main roads in the target area is recorded as g1;
[0079] The road accident frequency of the main roads in the target area is marked as g2;
[0080] Calculate by formula The road risk factor D3 is obtained, where θ is a preset proportional coefficient.
[0081] The process of obtaining the road environment base is as follows:
[0082] Obtain the ambient dust ratio of the target area and mark it as H1;
[0083] Get the ambient noise ratio of the target area and mark it as H2;
[0084] The target area is divided into several regional sub-units, and a dust monitoring device and a sound sensor are respectively set at the center of each regional sub-unit;
[0085] The environmental dust value of each regional sub-unit is obtained by using a dust monitoring instrument, and the environmental dust values of multiple regional sub-units are summed and averaged to obtain the total environmental dust value of the target area. The total environmental dust value of the target area is calculated by ratio with the total environmental dust value threshold to obtain the environmental dust ratio of the target area;
[0086] The environmental noise value of each regional sub-unit is obtained by a sound sensor, the environmental noise values of multiple regional sub-units are summed and averaged to obtain the total environmental noise value of the target area, and the total environmental noise value of the target area is calculated by ratio calculation with the total environmental noise value threshold to obtain the environmental noise ratio of the target area;
[0087] Calculate by formula Obtain the road environment base Hi of the target area, where a1 and a2 are preset proportional coefficients, and hi is the dynamic value of the road quality;
[0088] The process of obtaining the dynamic value of road quality is as follows:
[0089] The road surface roughness of the main road in the target area is marked as P1;
[0090] Mark the damage status of the main roads in the target area as P2;
[0091] The carrying capacity of the main roads in the target area is marked as P3;
[0092] The anti-skid capacity index of the main road in the target area is marked as P4;
[0093] Weighted processing is performed on the road surface smoothness, damage condition, load-bearing capacity and anti-skid capacity indicators of the main roads in the target area;
[0094] That is, the road quality value of the main road is obtained by the formula hi = P1 Xd1 + P2Xd2 + P3Xd3 + P4Xd4, where d1, d2, d3, and d4 represent the weight values of road surface flatness, damage condition, bearing capacity, and anti-skid ability indicators, respectively, d1+d2+d3+d4=1;
[0095] The road surface quality values of all main roads in the target area are summed and averaged to obtain the dynamic value hi of the road surface quality in the target area.
[0096] Process the road environment base number \(H_i\) of the target area and the road risk base number \(D_i\) of the target area, that is, through the formula Calculate the environmental impact assessment (EIA) behavior value \(DH\) of the target area, where \(R_i\) is the perimeter dynamic base number;
[0097] Preset the limit values of the EIA behavior value threshold of the target area as \(DH1\) and \(DH2\), where \(DH1 < DH2\);
[0098] Among them, the limit values \(DH1\) and \(DH2\) of the EIA behavior value threshold of the target area are empirical values, obtained according to experience:
[0099] In the actual obtaining process, there are many groups of road environment base numbers, road risk base numbers, perimeter dynamic base numbers and EIA behavior values. Process many groups of road environment base numbers, road risk base numbers, and perimeter dynamic base numbers to obtain the corresponding EIA behavior values of the target area. The staff identify the target area status level based on so many groups of EIA behavior values of the target area, so as to obtain a corresponding relationship between the EIA behavior value of the target area and the target area status level. Furthermore, deduce and divide the EIA behavior value threshold of the target area according to the target area status of the EIA behavior value of the target area, so as to obtain the limit values \(DH1\) and \(DH2\) of the EIA behavior value threshold of the target area. By comparing the limit values of the EIA behavior value threshold of the target area, the identification of the target area status level corresponding to the EIA behavior value of the target area is completed;
[0100] Refer to Figure 2 , when \(DH < DH1\), it means that the overall EIA of the target area is poor, and a first-level housing selection signal for the target area is generated;
[0101] When \(DH1\leq DH < DH2\), it means that the overall EIA of the target area is medium, and a second-level housing selection signal for the target area is generated;
[0102] When \(DH\geq DH2\), it means that the overall EIA of the target area is good, and a third-level housing selection signal for the target area is generated.
[0103] Among them, it should be noted that the higher the housing selection signal level of the target area, the better the environment and traffic conditions of the real estate in the target area. In the selection of the real estate corresponding to the target area, the real estate level of the target area corresponding to the third-level housing selection signal is higher than that of the target area corresponding to the second-level housing selection signal, and the real estate level of the target area corresponding to the second-level housing selection signal is higher than that of the target area corresponding to the first-level housing selection signal.
[0104] Among them, the process of obtaining the perimeter dynamic base number is as follows:
[0105] Obtain the population density of the target area and mark the population density as \(R1\);
[0106] Obtain the vegetation coverage rate of the target area and mark the vegetation coverage rate as R2;
[0107] Obtain the alarm rate of the target area within a preset period, and record the alarm rate of the target area within the preset period as R3;
[0108] The alarm rate of the target area within the preset period is the ratio of the number of alarms in the target area to the length of the preset period;
[0109] By formula The dynamic cardinality R i of the perimeter of the target area is calculated.
[0110] Through the above formula of the environmental impact assessment behavior value of the target area, we can know that:
[0111] The larger the dynamic cardinality of the perimeter of the target area, the higher the vegetation coverage rate of the target area, the better the air quality, the lower the population density, and the less crowded the living environment. At the same time, the lower the police response rate of the target area, the better the public security environment of the target area, and the larger the corresponding environmental assessment behavior value of the target area.
[0112] A low environmental dust ratio indicates that the road environment in the target area is well greened, and a low environmental noise ratio also indicates that the target area is far away from noise pollution. At the same time, a large dynamic value of road quality indicates that the main road in the target area is of good quality and high safety. The larger the road environment base value of the target area, the larger the corresponding environmental assessment behavior value of the target area.
[0113] The larger the road risk factor of the main road, the higher the frequency of road accidents in the target area, and the lower the safety of the target area. The lower the number of road intersections on the main road in the target area, the greater the probability of road accidents in the target area. The more lanes on the main road in the target area, the wider the road in the target area. The larger the road risk base, the smaller the corresponding environmental impact assessment behavior value of the target area.
[0114] Example 2
[0115] Based on the above embodiment, this embodiment solves how to select from the properties in multiple target areas when there are multiple properties in the target areas. The specific process is as follows:
[0116] This embodiment takes the three-level room selection signal as an example;
[0117] Mark the adjacent target areas of any target area in the three-level room selection signal to obtain the adjacent areas of the target area;
[0118] Obtain the environmental impact assessment behavior value of each adjacent area, recorded as the adjacent environmental impact assessment value HDj, where j is the number of adjacent areas, j=1,...,n;
[0119] Get the center point of the target area and the center point of any adjacent area, connect the center point of the target area with the center point of any adjacent area, and get the length of the environmental assessment distance, which is recorded as Lj;
[0120] By formula Calculate and obtain the neighboring environmental impact assessment characterization value of the target area;
[0121] Arrange the neighboring environmental impact assessment characterization values corresponding to all target areas in the three-level house selection signal in descending order, and select the property in the target area corresponding to the largest neighboring environmental impact assessment characterization value as the first recommended property, and the property in the target area corresponding to the second largest neighboring environmental impact assessment characterization value as the second recommended property, and so on, to complete the sorting of the target areas corresponding to the three-level house selection signal and the recommendation of the properties corresponding to the target areas.
[0122] The technical solution of the present invention is: after processing the environmental impact assessment behavior value of the target area itself, the level division of the target area is completed, that is, the level division of the real estate corresponding to the target area is realized, and on the basis of the level division, the target areas adjacent to the target area within the same level are processed, that is, the neighboring environmental impact assessment value and the environmental impact assessment distance length of the neighboring area are processed to obtain the neighboring environmental impact assessment characterization value of the target area, thereby realizing the identification of the target area from the environmental status of the adjacent target area and completing the secondary selection of the target area.
[0123] Example 3
[0124] See also Figure 3 As shown, the present invention is a real estate recommendation system based on big data, including a regional processing module, an environmental assessment analysis module, a multi-level recommendation module and a cloud management and control platform;
[0125] The regional processing module is used to divide the real estate into regions, obtain the target area corresponding to the real estate, obtain the peripheral representation data of the target area, obtain the environmental impact assessment behavior value of the target area based on the peripheral representation data of the target area, and upload it to the cloud management and control platform;
[0126] Among them, the peripheral representation data include road risk base and road environment base;
[0127] The environmental assessment analysis module receives the environmental assessment behavior value of the target area transmitted by the cloud management and control platform, identifies the level status of the target area corresponding to the real estate, and transmits the status identification signal to the cloud management and control platform;
[0128] The level status of the target area includes a first-level room selection signal, a second-level room selection signal, and a third-level room selection signal;
[0129] The multi-level recommendation module receives the status identification signal transmitted by the cloud management and control platform. The multi-level recommendation module obtains the adjacent target areas corresponding to the target areas in the same level of status, processes all adjacent target areas to obtain the adjacent environmental impact assessment values and environmental impact assessment distance lengths, obtains the adjacent environmental impact assessment representation values of the target areas according to the adjacent environmental impact assessment values and the environmental impact assessment distance lengths, and completes the priority sorting of the target area recommendation based on the adjacent environmental impact assessment representation values.
[0130] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.
Claims
1. A real estate recommendation method based on big data, characterized in that: It includes the following steps: Divide the property into regions to obtain the target region corresponding to the property, acquire the peripheral characterization data of the target region, and obtain the environmental assessment behavior value of the target region based on the peripheral characterization data of the target region; Among them, the peripheral characterization data includes the road risk base number and the road environment base number; Based on the environmental assessment behavior value of the target region, identify the grade status of the target region corresponding to the property; Among them, the grade status of the target region includes the first-level housing selection signal, the second-level housing selection signal, and the third-level housing selection signal; Acquire the adjacent target regions corresponding to the target region within the same grade status, process all adjacent target regions to obtain the adjacent environmental assessment value and the environmental assessment distance length, obtain the adjacent environmental assessment characterization value of the target region according to the adjacent environmental assessment value and the environmental assessment distance length, and complete the priority ranking of the target region selection based on the adjacent environmental assessment characterization value.
2. A real estate recommendation method based on big data according to claim 1, characterized in that: The acquisition process of the environmental assessment behavior value of the target region is as follows: Record the road environment base number of the target region as Hi; Record the road risk base number of the target region as Di; That is, through the formula The environmental impact assessment behavior value DH of the target area is calculated, where Ri is the dynamic base of the perimeter.
3. A real estate recommendation method based on big data according to claim 2, characterized in that: Preset the limit values of the environmental assessment behavior value threshold of the target region as DH1 and DH2, where DH1 < DH2; When DH < DH1, it indicates that the overall environmental assessment of the target region is poor, and generate the first-level housing selection signal of the target region; When DH1 ≤ DH < DH2, it indicates that the overall environmental assessment of the target region is medium, and generate the second-level housing selection signal of the target region; When DH ≥ DH2, it indicates that the overall environmental assessment of the target region is good, and generate the third-level housing selection signal of the target region.
4. The real estate recommendation method based on big data according to claim 2 is characterized in that: The acquisition process of the perimeter dynamic base number is as follows: Acquire the population density of the target region and mark it as R1; Acquire the vegetation coverage rate of the target region and mark it as R2; Acquire the police dispatch rate of the target region within the preset period, and record the police dispatch rate of the target region within the preset period as R3; By formula The dynamic cardinality R i of the perimeter of the target area is calculated.
5. The real estate recommendation method based on big data according to claim 2 is characterized in that: The acquisition process of the road risk base number is as follows: Acquire the number of lanes of the main road in the target region and record it as D1; Acquire the number of road intersections of the main road in the target region and record it as D2; Acquire the road risk factor of the main road in the target region and record it as D3; Calculated by the formula Calculate the road risk factor D of the target area; Sum up and take the average of the road risk factors of all main roads in the target region to obtain the road risk base number Di of the target region.
6. A real estate recommendation method based on big data according to claim 5, characterized in that: The acquisition process of the road risk factor is as follows: Acquire the total number of road accidents on the main road in the target region and the road accident frequency on the main road in the target region, and process them to obtain the road risk factor.
7. The real estate recommendation method based on big data according to claim 2, characterized in that: The acquisition process of the road environment base number is as follows: Acquire the environmental dust ratio of the target region and mark it as H1; Acquire the environmental noise ratio of the target region and mark it as H2; Calculated by formula The road environment base Hi of the target area is obtained, where a1 and a2 are preset proportional coefficients, and hi is the dynamic value of the road quality.
8. The real estate recommendation method based on big data according to claim 1, characterized in that: Within the target regions corresponding to the same housing selection signal, acquire and mark any adjacent target region of a target region to obtain the adjacent region of the target region; Acquire the environmental assessment behavior value of each adjacent region, record it as the adjacent environmental assessment value HDj, where j is the number of adjacent regions, j = 1,..., n; Acquire the center point of the target region and the center point of any adjacent region, connect the center point of the target region with the center point of any adjacent region to obtain the environmental assessment distance length, and record it as Lj; By formula The neighboring environmental impact assessment characterization value of the target area is calculated.
9. A real estate recommendation method based on big data according to claim 8, characterized in that: Arrange the neighboring environmental assessment characterization values corresponding to all target areas in the same house selection signal in descending order, and select the property in the target area corresponding to the largest neighboring environmental assessment characterization value as the first recommended property to complete the property selection.
10. A real estate recommendation system based on big data, characterized in that: include: A regional processing module, which is used to divide the real estate into regions, obtain the target region corresponding to the real estate, obtain the peripheral representation data of the target region, obtain the environmental impact assessment behavior value of the target region based on the peripheral representation data of the target region, and upload it to the cloud management and control platform; Among them, the peripheral representation data include road risk base and road environment base; An environmental assessment analysis module, wherein the environmental assessment analysis module receives the environmental assessment behavior value of the target area transmitted by the cloud management and control platform, identifies the level status of the target area corresponding to the real estate, and transmits the status identification signal to the cloud management and control platform; The level status of the target area includes a first-level room selection signal, a second-level room selection signal, and a third-level room selection signal; A multi-level recommendation module receives a status identification signal transmitted by a cloud management and control platform, obtains adjacent target areas corresponding to target areas in the same level of status, processes all adjacent target areas to obtain adjacent environmental impact assessment values and environmental impact assessment distance lengths, obtains adjacent environmental impact assessment representation values of the target areas according to the adjacent environmental impact assessment values and the environmental impact assessment distance lengths, and completes the priority sorting of target area recommendation based on the adjacent environmental impact assessment representation values.
Citation Information
Patent Citations
Method of generation, analysis and evaluation of equipped urban residential districts
CN113127950A
Urban residential building livability evaluation method and system based on multi-source data
CN117973668A
Method And Apparatus for Recommending Commercial Real Estate Investment
KR102332624B1
