Land recommendation service system and method based on big data

Abstract

The invention discloses a land recommendation service system and method based on big data, and relates to the technical field of land recommendation, and the system comprises a land type primary selection module, a user attention degree collection module, a key element analysis module, and an adaptation degree analysis and land recommendation module, which are used for receiving the type demands of user land use, the method comprises the following steps: preliminarily screening lands in a database according to type requirements, obtaining a primarily selected land set, setting an interactive weight distribution interface, obtaining the attention degree of a user to attention elements, respectively analyzing the adaptation degree of the attention elements to the user, and comprehensively analyzing the adaptation degree of the primarily selected land to the user according to the attention degree and the adaptation degree. According to the method, the primarily-selected land is regarded as a circular area with an actual influence range, the concept of land influence distance is introduced, the convenience degree of daily commuting of the user is reflected more truly, and time and energy are saved for the user through automatic evaluation and recommendation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of land promotion, in particular to a land promotion service system and method based on big data. BACKGROUND

[0002] The traditional land screening mode has long relied on straight-line distance as the core index, ignoring the spatial radiation capacity of the land itself. For example, in the assessment of traffic convenience, only the straight-line distance between the land and the subway station or bus station is considered, without considering the actual influence range formed by the land area. Although the land with larger area is slightly far away in straight-line distance, its coverage of the traffic station service radius is wider, and the traditional method is easy to misjudge its real accessibility. In addition, the assessment of surrounding supporting facilities also has similar problems, such as the coverage range of commercial land to residential areas, parking lots, the radiation radius of industrial land to industrial areas and logistics centers, etc., which are not included in the evaluation system through scientific quantitative means, resulting in deviation between land adaptation degree analysis and actual demand; in the traditional land promotion mode, the information transmission efficiency between supply and demand is low. Enterprises need to obtain land information through offline investigation, symposium or paper materials, and the information updating cycle is long and the coverage range is limited, which is difficult to meet the needs of the rapid changes of the market, and lacks deep information such as land real scene, surrounding supporting facilities and planning data, so that enterprises are difficult to make comprehensive investment research and judgment. At the same time, the individualized needs of enterprises cannot be fed back in time, resulting in the mismatch between land supply and market demand, affecting the efficiency of land resource allocation. SUMMARY

[0003] The purpose of the present application is to provide a land promotion service system and method based on big data to solve the problems raised in the background art.

[0004] In order to solve the above technical problems, the present application provides the following technical scheme: a land promotion service method based on big data, comprising the following steps: S1, receiving the type demand of the user land, preliminarily screening the land in the database according to the type demand, and obtaining a preliminary selected land set; S2, setting an interactive weight distribution interface to obtain the attention degree of the user to the concerned elements; S3, analyzing the adaptation degree of the concerned elements to the user respectively; S4, comprehensively analyzing the adaptation degree of the preliminary selected land to the user according to the attention degree and the adaptation degree, and promoting the preliminary selected land to the user in descending order of the adaptation degree.

[0005] Further, in step S1, the type requirement of the user land is received, including residential land, commercial land, industrial land and agricultural land, the maximum budget, minimum area and geographical position coordinates of the user land are received, the land in the database is preliminarily screened according to the type requirement, the maximum budget, the minimum area and the geographical position coordinates, and a set of preliminary selected lands {a1, a2, …, a m ,…,a M} is obtained; step S1 realizes efficient and accurate screening of land resources by integrating multi-dimensional requirements such as land type, budget, area and geographical position. This mechanism significantly improves the efficiency of land matching, quickly narrows down the candidate range through automated filtering function, and avoids the tedious process of manual comparison. At the same time, based on the spatial analysis ability of geographical coordinates, it ensures that the selected land blocks meet the development planning and location preference of the user specified area. The dual constraint mechanism of budget and area effectively controls the land cost and prevents the risk of overspending, ensuring the economy of resource utilization. Type screening supports the differentiated needs of users in different industries, whether it is residential development, commercial layout or agricultural production, and can quickly locate target land blocks through preset classification labels. In addition, the dynamically updated database system can respond to market changes in real time, ensuring that the screening results are always synchronized with the latest land supply information, providing reliable decision-making basis for users. Overall, this step significantly optimizes the land resource allocation process through systematic data processing and intelligent analysis, reduces the complexity of decision-making, and saves a lot of time and cost for users.

[0006] Further, in step S2, an interactive weight allocation interface is used to guide the user to set attention levels for attention elements, including traffic convenience, surrounding supporting facilities and green intensity, the attention levels are divided into I levels, the higher the attention level, the higher the attention coefficient corresponding to the attention level, and the attention coefficient set is {b1, b2, …, b n ,…,b N}, the acquisition method of the attention coefficient is, for example: set four important levels, very important corresponding proportion 4, important corresponding proportion 3, general corresponding proportion 2, and unimportant corresponding proportion 1, then the attention coefficients {b1, b2, b3, b4} corresponding to the four attention levels are: very important b1=4 / (4+3+2+1), important b2=3 / (4+3+2+1), general b3=2 / (4+3+2+1), and unimportant b4=1 / (4+3+2+1); step S2 realizes the depth analysis and personalized matching of user demand through an interactive weight allocation interface. This mechanism allows users to dynamically adjust the priority of attention elements according to their own preferences, significantly enhancing the sense of participation and autonomy in the decision-making process. The system converts abstract subjective demands into quantifiable evaluation indicators through visual weight adjustment tools, making the relative importance of different elements more clear and intuitive. For example, business users can focus on traffic convenience, while residential users may pay more attention to green intensity. This differentiated weight setting effectively improves the accuracy of land evaluation. In addition, the standardized calculation method of the attention coefficient ensures the objectivity and fairness of the evaluation process, avoiding the bias that may be brought by traditional subjective judgment. Through the real-time feedback mechanism, users can immediately observe the impact of weight adjustment on the screening results, and repeatedly optimize until the optimal matching scheme is reached. This dynamic interactive mode not only improves the decision-making efficiency, but also enhances the user's trust in the system. Overall, this step provides highly customized land screening services for users through the combination of humanized design and scientific quantitative analysis, significantly improving the rationality and satisfaction of resource allocation.

[0007] Further, in step S3, any preliminary selected land a m is analyzed, the score calculation method of traffic convenience is that the distance between the preliminary selected land a m and the nearest subway station is c m , the maximum subway consideration distance is c max , when c m ≥ c max , the subway convenience degree is 0; when c m < c max , the subway convenience degree is e (m_c) =(c max -c m +r) / c max , the distance between the preliminary selected land a m and the nearest bus station is d m , the maximum bus consideration distance is d max , when d m ≥ d max , the subway convenience degree is 0; when d m < d maxThe bus convenience degree is e (m_d) = (d max -d m +r) / d max , and then the traffic convenience score w1, w (m_1) is obtained c =f (m_c) *e d +f (m_d) *e c , wherein f d is a subway travel preference coefficient of the user, f c is a bus travel preference coefficient of the user, and the preference coefficient setting method is, for example, setting the options of preference, general, and dislike, wherein the preference corresponds to a parameter of 3, the general corresponds to a parameter of 2, and the dislike corresponds to a parameter of 1; when the user selects the preference subway travel and dislikes the bus travel, the subway travel preference coefficient f d of the user is 3 / (3+1), the bus travel preference coefficient f m of the user is 1 / (3+1), and r is a preliminary selected land influence distance; The area of the preliminary selected land a m is S (a_n) , the preliminary selected land is regarded as a circular land by considering the average user affected by the preliminary selected land, and the preliminary selected land influence distance is the radius of the circular land; The scoring method of the surrounding supporting facilities includes confirming the attention supporting facilities of the preliminary selected land, wherein the attention supporting facilities of the residential land include schools, hospitals, and shopping malls, the attention supporting facilities of the commercial land include residential areas, fitness areas, and parking lots, the attention supporting facilities of the industrial land include industrial areas, logistics centers, and hardware markets, and the attention supporting facilities of the agricultural land include agricultural product markets and agricultural stations; the distance between the attention supporting facilities g m and the preliminary selected land a (m_n) is h m , wherein n=1, 2, …, N, N is the number of the attention supporting facilities of the preliminary selected land a (a_n) , g m is the nth attention supporting facility of the preliminary selected land a n , and the surrounding supporting facility score w2 is calculated as follows: ; wherein P max is the attention degree of the user to the nth attention supporting facility, and h m is the maximum attention supporting facility consideration distance; The green area s m of the preliminary selected land a m is obtained, and the green intensity score w (m_3) of the preliminary selected land a m is calculated as follows: mStep S3 achieves precise analysis and scientific ranking of land value through a multi-dimensional quantitative evaluation system. This mechanism transforms factors such as transportation convenience, surrounding amenities, and greening intensity into quantifiable scoring indicators, significantly improving the objectivity and comprehensiveness of land selection. In terms of transportation assessment, combining subway and bus distance indicators with user travel preference coefficients ensures both the rigor of location accessibility analysis and flexible expression of personalized travel needs. Surrounding amenities scoring dynamically matches facilities of interest based on land use type (e.g., commercial land focuses on residential areas and parking lots), accurately reflecting the differentiated needs of different functional areas for amenities through a combination of distance decay models and user attention weights. Greening intensity scoring, with the proportion of green area as the core, intuitively reflects the ecological value of the plot, providing clear selection criteria for users who value environmental quality. Furthermore, all scores are based on real-time location data, ensuring a high degree of consistency between the evaluation results and real-world scenarios. This step, through multi-dimensional quantitative analysis and dynamic weight adjustment, effectively balances the economic, social, and ecological benefits of land resources, providing users with comprehensive decision support and significantly enhancing the scientific rigor and practicality of land selection.

[0008] Furthermore, in step S4, the initially selected land a... m The traffic convenience score is normalized to obtain an optimized traffic convenience score, W. (m_1) =w (m_1) / w (max_1) , where w (max_1) The highest score for transportation convenience among the initially selected land parcels; for initially selected land parcel a m The surrounding amenities scores were normalized to obtain an optimized surrounding amenities score W. (m_2) Optimize surrounding amenities rating W (m_2) =w (m_2) / w (max_2) , where w (max_2) The highest score for surrounding amenities among the shortlisted land parcels; for shortlisted land parcel a m The greening intensity score was normalized to obtain the optimized greening intensity score W. (m_3) Optimize the greening intensity score W (m_3) =w (m_3) / w (max_3) , where w (max_3) The highest greening intensity score is assigned to the initially selected land parcels. Then, based on the user's assigned level of interest in the selected elements, land parcel 'a' is calculated. m User fit Q m : ; Wherein β1 is the attention coefficient of the user to the traffic convenience, β2 is the attention coefficient of the user to the surrounding supporting, β3 is the attention coefficient of the user to the greening intensity, and β1, β2 and β3 are substituted into m=1, 2, …, M, and the adaptability of the M blocks of preliminary selected land to the user is calculated, and the preliminary selected land is recommended to the user in descending order of the adaptability; the differences in dimensions and numerical ranges between different indexes are eliminated by normalizing the scores of the three attention factors of traffic convenience, surrounding supporting and greening intensity, so that the scores can be compared fairly under the same standard. This operation enhances the objectivity and comparability of the score results, avoids the evaluation bias caused by the characteristics of the indexes, and then, the adaptability of each block of preliminary selected land to the user is calculated according to the attention coefficients corresponding to the attention levels set by the user for each attention factor. This way fully considers the individual needs of the user, integrates the subjective preferences of the user into the land evaluation system, makes the recommendation results more in line with the actual expectations of the user, and finally, the preliminary selected land is sorted and recommended to the user in descending order of the adaptability, providing the user with clear and intuitive land selection reference. The user can quickly focus on the land that best meets his needs according to the adaptability ranking, greatly saving the decision-making time and effort, improving the efficiency and accuracy of land screening, and truly realizing the precise matching of land resources and user needs.

[0009] A land recommendation service system based on big data, the system comprising: a land type preliminary selection module, a user attention degree collection module, a key factor analysis module and an adaptability analysis and land recommendation module; The land type preliminary selection module is used for receiving the type demand of the user for land, preliminarily screening the land in the database according to the type demand, and obtaining a preliminary selected land set; The user attention degree collection module is used for setting an interactive weight distribution interface and obtaining the attention degree of the user to the attention factors; The key factor analysis module is used for analyzing the adaptability of the attention factors to the user respectively; The adaptability analysis and land recommendation module is used for comprehensively analyzing the adaptability of the preliminary selected land to the user according to the attention degree and the adaptability, and recommending the preliminary selected land to the user in descending order of the adaptability.

[0010] Compared with the prior art, the beneficial effects achieved by the present application are: on the one hand, in the traditional land screening mode, only the straight-line distance is often simply considered, and the present method regards the preliminary selected land as a circular area with an actual influence range, and introduces the concept of land influence distance. Taking the traffic convenience evaluation as an example, not only the straight-line distance between the subway station, the bus station and the land is concerned, but also the influence range formed by the land area itself is combined. When the land area is larger, the range of the actual radiated traffic station is wider. This evaluation method can more truly reflect the convenience degree of user's daily commuting, avoid misjudgment of traffic conditions due to only looking at the straight-line distance, so as to make the traffic convenience score more practically valuable. On the one hand, a complete evaluation system is constructed from the three dimensions of traffic, supporting facilities and greening, and the effect of land influence distance is fully considered in the evaluation of each dimension. In terms of traffic, the accessibility of subway and bus is comprehensively considered, and a more reasonable traffic convenience score is calculated based on the land influence distance. In terms of supporting facilities, according to the characteristics of different land types, such as residential areas, fitness areas and parking lots for commercial land, industrial areas, logistics centers and hardware markets for industrial land, the actual coverage of these supporting facilities is evaluated based on the land influence distance. In terms of greening, the ratio of green area to total land area is calculated, and the land influence distance is combined to more scientifically evaluate the greening intensity of the land.

[0011] On the other hand, for the service provider, this method can quickly screen out the preliminary selected land set that meets the user's demand, reduce unnecessary manual intervention, and improve service efficiency. In the traditional land recommendation service, a large amount of manual communication and screening work is often required, and the present method greatly shortens the service cycle through automatic evaluation and recommendation, saving time and effort for users. BRIEF DESCRIPTION OF DRAWINGS

[0012] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation on the present application. In the drawings: Figure 1 is a structural diagram of a land recommendation service system based on big data according to the present application; Figure 2 is a flowchart of a land recommendation service method based on big data according to the present application. DETAILED DESCRIPTION

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0014] Referring to Figure 1 and Figure 2 , the application provides a technical solution: a land recommendation service method based on big data, comprising the following steps: S1, receiving the type demand of the user land, preliminarily screening the land in the database according to the type demand, and obtaining a preliminary selected land set; S2, setting an interactive weight distribution interface to obtain the attention degree of the user to the concerned elements; S3, respectively analyzing the adaptation degree of the concerned elements to the user; S4, comprehensively analyzing the adaptation degree of the preliminary selected land to the user according to the attention degree and the adaptation degree, and recommending the preliminary selected land to the user in descending order of the adaptation degree.

[0015] In step S1, the type demand of the user land is received, the type demand includes residential land, commercial land, industrial land and agricultural land, the maximum budget, the minimum area and the geographic position coordinates of the user land are received, the land in the database is preliminarily screened according to the type demand, the maximum budget, the minimum area and the geographic position coordinates, and a set of preliminary selected lands {a1, a2, …, a m ,…,a M} is obtained; step S1 realizes efficient and accurate screening of land resources by integrating multi-dimensional demands such as land type, budget, area and geographic position. This mechanism significantly improves the land matching efficiency, quickly narrows down the candidate range through automatic filtering function, and avoids the tedious process of manual comparison. At the same time, based on the spatial analysis ability of geographic coordinates, it ensures that the selected land meets the development planning and location preference of the user specified area. The dual constraint mechanism of budget and area effectively controls the land cost and prevents the risk of overspending, ensuring the economy of resource utilization. Type screening supports the differentiated needs of users in different industries, whether it is residential development, commercial layout or agricultural production, and target land blocks can be quickly located through preset classification labels. In addition, the dynamically updated database system can respond to market changes in real time, ensuring that the screening results are always synchronized with the latest land supply information, providing reliable decision-making basis for users. Overall, this step significantly optimizes the land resource allocation process through systematic data processing and intelligent analysis, reduces the complexity of decision-making, and saves a lot of time and cost for users.

[0016] In step S2, the user is guided to set the attention level of the concerned elements through the interactive weight distribution interface, the concerned elements include traffic convenience, surrounding supporting facilities and green intensity, the attention level is divided into I levels, the higher the attention level, the higher the attention coefficient corresponding to the attention level, and the attention coefficient set is {b1, b2, …, b n ,…,b N}, the acquisition method of the attention coefficient is, for example: set four important levels, very important corresponding proportion 4, important corresponding proportion 3, general corresponding proportion 2, and unimportant corresponding proportion 1, then the attention coefficients {b1, b2, b3, b4} corresponding to the four attention levels are: very important b1=4 / (4+3+2+1), important b2=3 / (4+3+2+1), general b3=2 / (4+3+2+1), and unimportant b4=1 / (4+3+2+1); step S2 realizes the depth analysis and personalized matching of user demand through an interactive weight allocation interface. This mechanism allows users to dynamically adjust the priority of attention elements according to their own preferences, significantly enhancing the participation and autonomy of the decision-making process. The system converts abstract subjective demands into quantifiable evaluation indicators through visual weight adjustment tools, making the relative importance of different elements more clear and intuitive. For example, business users can focus on traffic convenience, while residential users may pay more attention to green intensity. This differentiated weight setting effectively improves the accuracy of land evaluation. In addition, the standardized calculation method of the attention coefficient ensures the objectivity and fairness of the evaluation process, avoiding the bias that may be brought by traditional subjective judgment. Through the real-time feedback mechanism, users can immediately observe the impact of weight adjustment on the screening results, and repeatedly optimize until the optimal matching scheme is reached. This dynamic interactive mode not only improves the decision-making efficiency, but also enhances the user's trust in the system. Overall, this step combines humanized design and scientific quantitative analysis to provide highly customized land screening services for users, significantly improving the rationality and satisfaction of resource allocation.

[0017] In step S3, for any preliminary selected land a m , the traffic convenience score calculation method is as follows: through the positioning system, the distance between the preliminary selected land a m and the nearest subway station is c m , and the maximum subway consideration distance is c max . When c m ≥ c max , the subway convenience degree is 0; when c m < c max , the subway convenience degree is e (m_c) =(c max -c m +r) / c max . Through the positioning system, the distance between the preliminary selected land a m and the nearest bus station is d m , and the maximum bus consideration distance is d max . When d m ≥ d max , the subway convenience degree is 0; when d m < d max , the bus convenience degree is e(m_d) =(d max -d m +r) / d max This leads to a rating of transportation convenience, w1, w (m_1) =f c *e (m_c) +f d *e (m_d) The f c f represents the user's preference coefficient for subway travel. d The system assigns a preference coefficient to the user's preference for public transportation. The preference coefficient is set using, for example, by providing options for "like," "neutral," and "dislike," with a parameter of 3 for "like," 2 for "neutral," and 1 for "dislike." When a user selects "like subway travel" and "dislike bus travel," the user's preference coefficient for subway travel is f. c =3 / (3+1), the user's preference coefficient for public transportation f d =1 / (3+1), where r is the distance of influence of the initially selected land; Obtain the initial land selection a m The area is S m Considering the average user's impact from the initial land selection, if the initial land selection is regarded as a circular land, then the influence distance of the initial land selection is the radius of the circular land. The scoring method for surrounding amenities includes: confirming the amenities of interest for the initially selected land, which include: for residential land, schools, hospitals, and shopping malls; for commercial land, residential areas, fitness areas, and parking lots; for industrial land, industrial zones, logistics centers, and hardware markets; and for agricultural land, farmers' markets and agricultural stations; and then using a location system to retrieve the amenities' information. (a_n) and the initial land selection a m The distance between them is h (m_n) Where n = 1, 2, ..., N, and N is the initial land a. m Pay attention to the quantity of supporting equipment, g (a_n) For the initial selection of land a m For the nth featured facility, the score w2 of the surrounding facilities is calculated: ; Where P n h represents the user's level of attention to the nth associated item. max Distance should be considered for the most important supporting facilities; Obtain the initial land selection a m green area s m Calculate the initial land selection a m The greening intensity score w (m_3) =1-s m / S mStep S3 achieves precise analysis and scientific ranking of land value through a multi-dimensional quantitative evaluation system. This mechanism transforms factors such as transportation convenience, surrounding amenities, and greening intensity into quantifiable scoring indicators, significantly improving the objectivity and comprehensiveness of land selection. In terms of transportation assessment, combining subway and bus distance indicators with user travel preference coefficients ensures both the rigor of location accessibility analysis and flexible expression of personalized travel needs. Surrounding amenities scoring dynamically matches facilities of interest based on land use type (e.g., commercial land focuses on residential areas and parking lots), accurately reflecting the differentiated needs of different functional areas for amenities through a combination of distance decay models and user attention weights. Greening intensity scoring, with the proportion of green area as the core, intuitively reflects the ecological value of the plot, providing clear selection criteria for users who value environmental quality. Furthermore, all scores are based on real-time location data, ensuring a high degree of consistency between the evaluation results and real-world scenarios. This step, through multi-dimensional quantitative analysis and dynamic weight adjustment, effectively balances the economic, social, and ecological benefits of land resources, providing users with comprehensive decision support and significantly enhancing the scientific rigor and practicality of land selection.

[0018] In step S4, the initially selected land a m The traffic convenience score is normalized to obtain an optimized traffic convenience score, W. (m_1) =w (m_1) / w (max_1) , where w (max_1) The highest score for transportation convenience among the initially selected land parcels; for initially selected land parcel a m The surrounding amenities scores were normalized to obtain an optimized surrounding amenities score W. (m_2) Optimize surrounding amenities rating W (m_2) =w (m_2) / w (max_2) , where w (max_2) The highest score for surrounding amenities among the shortlisted land parcels; for shortlisted land parcel a m The greening intensity score was normalized to obtain the optimized greening intensity score W. (m_3) Optimize the greening intensity score W (m_3) =w (m_3) / w (max_3) , where w (max_3) The highest greening intensity score is assigned to the initially selected land parcels. Then, based on the user's assigned level of interest in the selected elements, land parcel 'a' is calculated. m User fit Q m : ; Where β1 represents the user's attention coefficient for transportation convenience, β2 represents the user's attention coefficient for surrounding amenities, and β3 represents the user's attention coefficient for greening intensity. Substituting these values ​​into m=1,2,…,M, the suitability of the M initially selected land parcels to the user is calculated. The initially selected land parcels are then recommended to the user in descending order of suitability. By normalizing the scores for the three key factors of transportation convenience, surrounding amenities, and greening intensity, differences in dimensions and numerical ranges between different indicators are eliminated, allowing for fair comparison of scores under the same standard. This operation enhances the objectivity and comparability of the scoring results, avoiding evaluation biases caused by the inherent characteristics of the indicators. Next, the suitability of each initially selected land parcel to the user is calculated based on the attention coefficient corresponding to the user's attention level for each key factor. This method fully considers the user's personalized needs, integrating the user's subjective preferences into the land evaluation system, making the recommended results more aligned with the user's actual expectations. Finally, the initially selected land parcels are ranked and recommended to the user in descending order of suitability, providing the user with a clear and intuitive reference for land selection. Users can quickly focus on the land that best suits their needs based on the suitability ranking, which greatly saves decision-making time and effort, improves the efficiency and accuracy of land screening, and truly achieves a precise match between land resources and user needs.

[0019] A land recommendation service system based on big data, the system includes: a land type preliminary selection module, a user attention collection module, a key element analysis module, and a suitability analysis and land recommendation module; The land type preliminary selection module is used to receive users' land use type requirements, and to perform preliminary screening of the land in the database according to the type requirements to obtain a preliminary land selection set. The user attention level collection module is used to set up an interactive weight allocation interface to obtain the user's attention level to the elements of interest. The key element analysis module analyzes the degree of user suitability of the elements of interest. The suitability analysis and land recommendation module is used to comprehensively analyze the suitability of the initially selected land to users based on the degree of attention and suitability, and recommend the initially selected land to users in descending order of suitability.

[0020] Example 1: When using this land screening system, in step S1, the user first inputs their land use requirements through the system interface, explicitly selecting residential land, setting a maximum budget of 50 million yuan, a minimum area requirement of 50,000 square meters, and defining the geographical coordinates of a certain area in the city. The system quickly filters through the database and provides a preliminary set of land parcels, covering multiple plots in the area that meet the basic conditions.

[0021] Next, in step S2, the developer uses an interactive weight allocation interface to set attention levels for transportation convenience, surrounding amenities, and green space intensity. Considering the importance of residential projects to residents' travel convenience and living amenities, the developer sets transportation convenience as "very important," surrounding amenities as "important," and green space intensity as "moderate." Based on these settings, the system generates corresponding attention coefficients for these factors.

[0022] Then, in step S3, the system performs a detailed analysis of each initially selected plot of land. For example, for a certain initially selected plot of land, it calculates the distance to the nearest subway station and bus station to assess its transportation convenience; it determines the distance to nearby schools, hospitals, shopping malls, and other amenities of interest and calculates the surrounding amenities score; and it calculates the green area to obtain the greening intensity score.

[0023] Finally, in step S4, the system normalizes the scores of each item, calculates the suitability of each piece of land by combining the attention coefficient, sorts them from high to low suitability, and recommends the land most suitable for the developer's needs to him, helping him to efficiently complete the land selection and promote the project.

[0024] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A land promotion service method based on big data, characterized in that: The method includes the following steps: S1. Receive the user's land use type requirements, and perform preliminary screening of the land in the database according to the type requirements to obtain a preliminary set of land. S2. Set up an interactive weight allocation interface to obtain the degree of attention users pay to the elements they are interested in; S3. Analyze the degree of user suitability of each key element; S4. Based on the level of attention and suitability, comprehensively analyze the suitability of the initial land selection to users, and recommend the initial land selection to users in descending order of suitability.

2. The land promotion service method based on big data according to claim 1, characterized in that: In step S1, the system receives the user's land use type requirements, which include residential land, commercial land, industrial land, and agricultural land. It also receives the user's maximum budget, minimum area, and geographic coordinates for the land. Based on the type requirements, maximum budget, minimum area, and geographic coordinates, the system performs a preliminary screening of the land in the database to obtain a preliminary set of land selections {a1, a2, ..., a...}. m ,…,a M } 3. The land recommendation service method based on big data according to claim 2, characterized in that: In step S2, the user is guided to set the attention level for the factors of interest through an interactive weight allocation interface. The factors of interest include: transportation convenience, surrounding facilities, and greening intensity. The attention level is divided into Level I, and the set of attention coefficients is {b1, b2, ..., b n ,…,b N } 4. The land recommendation service method based on big data according to claim 3, characterized in that: In step S3, for any initially selected land a m The analysis, specifically the method for calculating the traffic convenience score, uses a positioning system to obtain the initial land parcel a. m The distance to the nearest subway station is c m The maximum subway distance considered is c. max When c m ≥c max At that time, the convenience of the subway is 0; when c m <c max At that time, the convenience level of the subway was e. (m_c) =(c max -c m +r) / c max The initial land selection a was obtained through the positioning system. m The distance to the nearest bus stop is d m The maximum bus distance is set as d. max When d m ≥d max At that time, the convenience of the subway is 0; when d m <d max At that time, the convenience level of public transportation was e. (m_d) =(d max -d m +r) / d max This leads to a rating of transportation convenience, w1, w (m_1) =f c *e (m_c) +f d *e (m_d) The f c f represents the user's preference coefficient for subway travel. d Let r be the user's preference coefficient for public transportation, and r be the distance of influence of the initially selected land.

5. The land recommendation service method based on big data according to claim 4, characterized in that: Obtain the initial land selection a m The area is S m Considering the average user's impact from the initial land selection, and treating the initial land selection as a circular plot of land, the influence distance of the initial land selection is equal to the radius of the circular plot of land.

6. The land recommendation service method based on big data according to claim 5, characterized in that: The scoring method for surrounding amenities includes: confirming the amenities of interest for the initially selected land, which include: for residential land, schools, hospitals, and shopping malls; for commercial land, residential areas, fitness areas, and parking lots; for industrial land, industrial parks, logistics centers, and hardware markets; and for agricultural land, farmers' markets and agricultural stations; and then using a location system to retrieve the amenities' information. (a_n） and the initial land selection a m The distance between them is h (m_n) Where n = 1, 2, ..., N, and N is the initial land a m Pay attention to the quantity of supporting equipment, g (a_n) For the initial selection of land a m The score w2 of the surrounding amenities is calculated for the nth amenities that are of interest.

7. The land recommendation service method based on big data according to claim 5, characterized in that: Obtain the initial land selection a m green area s m Calculate the initial land selection a m The greening intensity score w (m_3) =1-s m / S m .

8. A land recommendation service method based on big data according to claim 6, characterized in that: In step S4, the initially selected land a m The traffic convenience score is normalized to obtain an optimized traffic convenience score, W. (m_1) =w (m_1) / w (max_1) , where w (max_1) The highest score for transportation convenience among the initially selected land parcels; for initially selected land parcel a m The surrounding amenities scores were normalized to obtain an optimized surrounding amenities score W. (m_2) Optimize surrounding amenities rating W (m_2) =w (m_2) / w (max_2) , where w (max_2) The highest score for surrounding amenities among the shortlisted land parcels; for shortlisted land parcel a m The greening intensity score was normalized to obtain the optimized greening intensity score W. (m_3) Optimize the greening intensity score W (m_3) =w (m_3) / w (max_3) , where w (max_3) The highest greening intensity score is assigned to the initially selected land parcels. Then, based on the user's assigned level of interest in the selected elements, land parcel 'a' is calculated. m User fit Q m Substitute each value into m=1,2,…,M to calculate the suitability of the M initially selected land parcels to the user, and recommend the initially selected land parcels to the user in descending order of suitability.

9. A land promotion service system based on big data, wherein the system is applied to the land promotion service method based on big data as described in any one of claims 1-8, characterized in that: The system includes: a land type preliminary selection module, a user attention collection module, a key element analysis module, and a suitability analysis and land recommendation module. The land type preliminary selection module is used to receive users' land use type requirements, and to perform preliminary screening of the land in the database according to the type requirements to obtain a preliminary land selection set. The user attention level collection module is used to set up an interactive weight allocation interface to obtain the user's attention level to the elements of interest. The key element analysis module analyzes the degree of user suitability of the elements of interest. The suitability analysis and land recommendation module is used to comprehensively analyze the suitability of the initially selected land to users based on the degree of attention and suitability, and recommend the initially selected land to users in descending order of suitability.

Images