Land investment attraction informatization platform

Abstract

The invention discloses a land investment attraction informatization platform, and relates to the technical field of investment attraction platforms, and the platform comprises the following steps: firstly, the platform comprehensively collects the historical selection and demand preference data of investors in the use process, and achieves the all-around understanding of the demands of each investor through data collection; according to the method, historical selection and demand preference data of investors are comprehensively collected and analyzed, and the investors are accurately divided into common demands and special demands by a platform according to an investment demand coefficient generated by feature extraction and machine learning. Common demand investors obtain standardized reports to meet the macroscopic demands of the common demand investors; the investors with special requirements obtain customized analysis, and the specific requirements are better met, so that the accuracy of investment decision making is improved. The accurate matching mechanism improves the investor satisfaction degree and the platform credibility, avoids resource waste, remarkably enhances the success rate and the market competitiveness of regional investment attraction, and establishes the good reputation of the platform.

Description

Technical Field

[0001] The present invention relates to the technical field of investment promotion platforms, and in particular to a land investment promotion information platform. Background Art

[0002] The land investment promotion information platform is a digital management system that uses information technology to provide support for land investment promotion. The platform integrates land resource data, policy information, investment promotion dynamics and demand matching functions. Through data collection, analysis and visualization, it helps governments or enterprises to efficiently publish and manage land investment promotion information, achieve accurate docking between supply and demand, improve the utilization rate of land resources and investment promotion efficiency, make the investment promotion process more transparent and convenient, and promote regional economic development. At the same time, the platform uses big data analysis to predict and evaluate land utilization rate, investment promotion trends, etc., generate data analysis reports, assist governments or enterprises in making scientific decisions, and improve the efficiency and quality of investment promotion.

[0003] The prior art has the following deficiencies:

[0004] Analysis reports generated based on average indicators usually use big data statistical analysis methods to extract average indicators that reflect overall characteristics by comprehensively processing various types of data in the land investment promotion area. Although this method can meet the needs of most investors, due to the problem of information "smoothing", the average indicator analysis method is difficult to accurately reflect individual differences and detailed characteristics, and thus cannot meet the needs of investors with special needs for transportation convenience, ecological conditions, and supporting facilities. For such investors, the results of averaging are difficult to accurately match their personalized needs, because the average indicator only reflects the overall level of the region, and combines the needs of transportation convenience, ecological conditions, supporting facilities, etc. into the overall analysis, and cannot focus on specific locations or subdivided conditions. For example, a company may be particularly concerned about the logistics convenience around the land or the distance from the highway, but the average indicator blurs these key characteristics, resulting in the analysis report failing to meet the company's requirements for transportation convenience.

[0005] If these investors continue to be provided with analysis reports based on average indicators, the following serious consequences may occur: Investors may make site selection decisions based on the "overall traffic convenience" or "supporting facilities level" in the report, but then find that the selected plot does not meet their actual needs (such as being far from the highway, or lacking key supporting facilities), resulting in increased logistics costs, reduced resource utilization efficiency, or even having to abandon the plot, resulting in waste of resources and increased costs. In addition, when investors realize that the report cannot meet their personalized needs, they may question the accuracy of the platform, thereby reducing their trust in the investment projects. For the government and investment agencies, this decline in trust may lead to the loss of high-quality investors, affect the overall effectiveness of investment promotion, and even damage the region's investment image, thereby triggering a long-term crisis of trust.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide an information platform for land investment promotion. By comprehensively collecting and analyzing investors' historical choices and demand preference data, the platform uses feature extraction and investment demand coefficients generated by machine learning to accurately divide investors into two categories: general needs and special needs. Investors with general needs obtain standardized reports to meet their macro needs; investors with special needs obtain customized analysis that better meets their specific requirements, thereby improving the accuracy of investment decisions. This precise matching mechanism improves investor satisfaction and platform trust, avoids waste of resources, and significantly enhances the success rate and market competitiveness of regional investment promotion, establishes a good reputation for the platform, and solves the problems in the above-mentioned background technology.

[0008] In order to achieve the above-mentioned purpose, the present invention provides the following technical solution: a land investment promotion information platform, comprising the following steps:

[0009] First, the platform comprehensively collects investors’ historical choices and demand preference data during use. Through data collection, it has a comprehensive understanding of each investor’s needs;

[0010] Extract features from the acquired investor historical selection and demand preference data, and use pre-learned machine learning models to intelligently evaluate investor needs based on the extracted features;

[0011] Based on the evaluation results of the machine learning model, investors are divided into general demand investors and special demand investors;

[0012] For ordinary investors, we will continue to use standardized analysis reports generated based on average indicators to help investors quickly understand the overall market picture and make wise investment decisions.

[0013] For investors with special needs, based on the average indicator report, we combine investors' historical choices and demand preferences to re-formulate personalized analysis reports, provide highly customized analysis, and meet the unique requirements of investors with special needs.

[0014] Preferably, the platform comprehensively collects the historical selection and demand preference data of investors during use. Through data collection, the specific steps to have a comprehensive understanding of the needs of each investor are as follows:

[0015] First, establish a comprehensive and efficient data collection mechanism to capture various behavioral data and preference information of investors in the process of using the platform;

[0016] During the data collection process, ensure the legality and compliance of data collection;

[0017] In order to effectively manage and quickly access the collected data, a unified data storage and management system should be established;

[0018] After data storage, the collected data is cleaned and preprocessed to improve data quality and ensure the accuracy of analysis results.

[0019] Preferably, feature extraction is performed on the acquired data on investors' historical choices and demand preferences, and the extracted features include the degree to which investors' attention is concentrated on a specific area and the frequency and complexity of investors' requests for personalized services to the platform. Within the detection window, the extracted degree to which investors' attention is concentrated on a specific area and the frequency and complexity of investors' requests for personalized services to the platform are analyzed to generate an investment area focus index and a personalized service request index, respectively. The investment area focus index and the personalized service request index are input into a pre-learned machine learning model, and an investment demand coefficient is generated through the machine learning model. Investors' needs are intelligently evaluated through the investment demand coefficient.

[0020] Preferably, the investment demand coefficient generated by analyzing the investor's historical selection and demand preference data obtained under the detection window is compared with a preset reference threshold of the investment demand coefficient to divide the investors. The specific steps are as follows:

[0021] If the investment demand coefficient is greater than or equal to the pre-set reference threshold of the investment demand coefficient, the investor is classified as a special demand investor;

[0022] If the investment demand coefficient is less than the pre-set investment demand coefficient reference threshold, the investor will be classified as an ordinary demand investor.

[0023] Preferably, for investors with special needs, based on the average indicator report, combined with investors' historical choices and demand preferences, a personalized analysis report is re-formulated to provide highly customized analysis to meet the unique requirements of investors with special needs. The specific steps are as follows:

[0024] First, generate a standardized analysis report based on regional average indicators R avg , this report provides the overall characteristics of the region, provides a reference for investors with general needs, and also provides a basis for subsequent customized reports;

[0025] We extract personalized features of investors with special needs, extract the special concerns of investors when selecting land, and generate a customized feature set. The expression is as follows:

[0026] F custom =g(H, A)

[0027] , where F custom is the investor's customized feature set, H represents the investor's historical selection record, A is the demand preference, and g is the feature extraction function;

[0028] The weight of personalized analysis is determined based on the investment demand coefficient IDC;

[0029] IDC≥IDC ref , then G=High

[0030] IDC <IDC ref , then G=Low

[0031] When the investment demand coefficient IDG is greater than or equal to the investment demand coefficient reference threshold IDC ref When the personalized analysis weight G is set to a high value (High), the personalized needs content is highlighted;

[0032] When the investment demand coefficient IDG is less than the investment demand coefficient reference threshold IDC ref When the personalized analysis weight G is set to a low value (Low), the impact of personalized needs is reduced;

[0033] According to the size of the investment demand coefficient, adjust the proportion of personalized analysis content in the final report to make the report content more in line with the actual demand intensity of investors;

[0034] Standardize the report R avg The feature set F customized to investors custom Integrate according to the weight G to generate the final personalized analysis report. The calculation expression is as follows:

[0035] R custom =R avg +G·F custom

[0036] , where R custom It is the final personalized analysis report;

[0037] After the personalized analysis report is generated, its content is verified for accuracy and applicability:

[0038] Validity = h(R custom ,T current )

[0039] , where Validity is the validity of the report, function h represents the verification process, T current It is the latest data status at the current time, which is used to compare the timeliness of report data;

[0040] If the verification does not meet the requirements, a re-update is triggered to ensure that the report provides accurate and up-to-date information for investors' decision-making.

[0041] Preferably, the specific steps of analyzing the concentration of investors' attention on a specific region and generating an investment region focus index are as follows:

[0042] Under the detection window, first calculate the basic attention intensity of investors to each region to reflect their interest in a specific region. The calculation expression is as follows:

[0043]

[0044] , where, BFI i，j is the basic attention intensity, that is, the basic attention intensity of investor i to region j, V i，j is the visit frequency, that is, the visit frequency of investor i to region j, W j is the weight of region j, D i，j is the time distance, i.e., the time interval from the last visit of investor i to region j, and C is a constant used to adjust the time distance;

[0045] In basic focus intensity (BFI) i，j On this basis, the depth of investors’ preference for different regions is calculated to reflect their level of focus in different regions. The calculation expression is as follows:

[0046]

[0047] , where DPF i，j is the regional preference depth, that is, the regional preference depth of investor i for region j, F i，j is the cumulative visit depth, that is, the cumulative visit depth of investor i to region j, T i，j is the specific behavior frequency, i.e., the specific behavior frequency of investor i towards region j, α is the preference index, which controls the influence weight of the cumulative visit depth, and γ is the preference depth index, which controls the sensitivity of the overall preference depth;

[0048] Depth BFI based on regional preference i，j , calculate the concentration of investors' attention to each region to quantify whether they tend to prefer a specific region. The calculation expression is as follows:

[0049]

[0050] , where RCF i is the regional focus factor, i.e., the regional focus factor of investor i, S j is the market importance of region j, indicating the position of the region in the market, P i，jis the interaction depth coefficient, i.e., the interaction depth coefficient of investor i in region j, which indicates the interaction frequency and intensity of investors in this region. i，j is the geographical distance factor, i.e., the geographical distance factor between investor i and region j, which reflects the investor's preference for geographical location, δ is the concentration index, which is used to adjust the effect of distance on the regional concentration factor, and N is the total number of regions;

[0051] Based on the regional concentration factor RCF i , generate the investment area focus index, the calculation expression is as follows:

[0052]

[0053] , where IAFI is the investment area focus index, U j is the future development potential of region j, Z i，j is the long-term attention of investor i to region j, and θ is the sensitivity adjustment index.

[0054] Preferably, in the detection window, the frequency and complexity of the personalized service requests made by investors to the platform are analyzed, and the specific steps of generating the personalized service request index are as follows:

[0055] Under the detection window, the basic weight values ​​of the investor's request frequency and complexity within the monitoring window are defined, and the interaction term is introduced to capture the nonlinear relationship between frequency and complexity. The calculation expression is as follows:

[0056]

[0057] , where B i is the basic weight value, that is, the basic weight value of investor i, R f is the request frequency, W f is the weight coefficient of request frequency, W x is the weight coefficient of the request complexity, ω is the fine-tuning parameter, e is the natural base, C x is the request complexity;

[0058] In order to accurately calculate the request response efficiency index, parameters and nonlinear terms are introduced so that the index can specifically reflect the platform's response speed and processing accuracy to investor requests. The calculation expression is as follows:

[0059]

[0060] , where E i is the request response efficiency index, T ris the average processing time for the platform to respond to investor requests, reflecting the platform's response speed, ∈ is a small positive number, β is the response accuracy weight coefficient, A is the platform's actual response accuracy score for the request, is the adjustment coefficient, δ is the system constant;

[0061] In order to more accurately measure investors' preference for personalized needs, the request preference intensity coefficient is calculated by adding a combination of logarithms, exponents, and multiple powers. The calculation expression is as follows:

[0062]

[0063] , where P s is the request preference strength coefficient, τ is the adjustment parameter;

[0064] Based on the basic weight value B i , Request response efficiency index E i and the request preference strength coefficient P s , further adding nonlinear and interactive terms, we can more carefully characterize the complexity of investor needs and generate the final personalized service request index. The calculation expression is as follows:

[0065]

[0066] , where PSRI is the personalized service request index, η is the fine-tuning parameter, σ, k and λ are adjustment parameters, and σ is used to control the request preference intensity coefficient P s The weight in the personalized service request index, κ is used to control the comprehensive weight in the whole formula, and λ controls the sine function term sin(R f ·C x ) volatility in the final index.

[0067] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0068] The present invention comprehensively collects and analyzes investors' historical choices and demand preference data, and uses feature extraction and machine learning models to generate investment demand coefficients to accurately divide investors into two categories: general demand and special demand. For investors with general demand, the platform continues to provide standardized analysis reports generated based on average indicators to help them quickly understand the overall market situation in the region and meet their needs for macro indicators. For investors with special needs, the platform generates highly customized analysis reports based on their personalized needs, and adds detailed analysis of specific transportation nodes, ecological conditions, supporting facilities, etc. on the basis of standardized data. In this way, investors can obtain more accurate data support that better suits their needs, helping them make investment decisions that are more in line with expectations, and greatly improving investors' satisfaction and trust in the platform.

[0069] Through intelligent evaluation and demand division, the present invention allows the platform to effectively identify and meet the special needs of high-quality investors, avoiding waste of resources and investment errors caused by the "information smoothing" problem of average indicator reports. This precise demand matching mechanism helps to retain high-quality investors and prevent investors from leaving due to unmet needs. For the government and investment promotion agencies, this means that the success rate and quality of investment promotion will be significantly improved, which will help enhance the market attractiveness and economic competitiveness of the region. In addition, the precise matching mechanism can also improve the service quality and user experience of the platform, enable the platform to establish a good reputation and credibility in the market, and then form a positive brand effect, attract more investors to participate, and inject continuous impetus into the economic development of the region. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0071] Figure 1 This is a method flow chart of the land investment promotion information platform of the present invention. DETAILED DESCRIPTION

[0072] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0073] The present invention provides Figure 1 The land investment information platform shown includes the following steps:

[0074] First, the platform comprehensively collects investors’ historical choices and demand preference data during use. Through data collection, it has a comprehensive understanding of each investor’s needs;

[0075] The platform comprehensively collects investors' historical choices and demand preference data during use. Through data collection, the specific steps to have a comprehensive understanding of each investor's needs are as follows:

[0076] First, establish a comprehensive and efficient data collection mechanism to capture various behavioral data and preference information of investors in the process of using the platform;

[0077] This includes but is not limited to the plots viewed by investors, the areas of interest, the keywords searched, the reports downloaded, and any interactions with the platform. To this end, the platform should integrate data tracking tools at the technical level, such as behavioral analysis plug-ins for web pages and mobile applications, logging systems, etc. At the same time, it should ensure that the scope of data collection is wide, covering all possible touchpoints of investors on the platform, in order to obtain the most complete behavioral portrait;

[0078] During the data collection process, ensure the legality and compliance of data collection;

[0079] This means that when investors register or use the platform for the first time, they must be clearly informed that their data will be collected and used to improve services, and their consent must be obtained; the platform should provide a clear privacy policy and terms of use, explaining the purpose, scope and use of data collection; in addition, it is necessary to ensure the secure storage and transmission of data, use encryption technology to prevent data leakage, establish a sound permission management and security audit mechanism, and protect the privacy and rights of investors;

[0080] In order to effectively manage and quickly access the collected data, a unified data storage and management system should be established;

[0081] The architecture of a data warehouse or data lake can be used to store structured and unstructured data in a unified manner. The platform should design a reasonable data model to classify and label investors' behavior data, preference information, etc. to facilitate subsequent data analysis and feature extraction. At the same time, it is necessary to ensure high data availability and scalability to support large-scale data processing and real-time analysis needs.

[0082] After data storage, the collected data is cleaned and preprocessed to improve data quality and ensure the accuracy of analysis results;

[0083] Data cleaning includes operations such as removing duplicate data, correcting erroneous information, and processing missing values; preprocessing may involve steps such as data standardization, format conversion, and anonymization. Through these measures, the platform can eliminate noise and outliers in the data and improve the integrity and consistency of the data. This lays a solid foundation for subsequent feature extraction and intelligent analysis, making the full understanding of investor needs more reliable and accurate.

[0084] Extract features from the acquired investor historical selection and demand preference data, and use pre-learned machine learning models to intelligently evaluate investor needs based on the extracted features;

[0085] Extract features from the acquired data on investors' historical choices and demand preferences. The extracted features include the degree of concentration of investors' attention on a specific region and the frequency and complexity of investors' requests for personalized services on the platform. Under the detection window, analyze the extracted degree of concentration of investors' attention on a specific region and the frequency and complexity of investors' requests for personalized services on the platform to generate an investment region focus index and a personalized service request index, respectively. Input the investment region focus index and the personalized service request index into a pre-learned machine learning model, generate an investment demand coefficient through the machine learning model, and intelligently evaluate investors' needs through the investment demand coefficient.

[0086] A pre-trained machine learning model refers to a model that has been trained with a large amount of historical data, and has completed model parameter optimization and algorithm selection, and can accurately identify and evaluate investor needs. The model training process usually includes steps such as data collection, preprocessing, feature extraction, model training, testing and verification. In this process, the model uses a large amount of data containing characteristics such as investors' historical choices, preferences, and behavior records to "learn" the patterns and rules of different investor needs. Through this learning, the model can establish the relationship between investor behavior and demand, so that when it is put into actual use, it can quickly predict investors' demand preferences and output corresponding demand assessment results based on the input of new data (such as investment area focus index and personalized service request index). In this scenario, the pre-trained machine learning model can convert the input data features (i.e., investment area focus and personalized service request index) into investment demand coefficients as an intelligent basis for demand assessment.

[0087] The advantage of a pre-trained model is that after being trained with a large amount of data, it can already identify a variety of potential complex feature relationships, and has a high degree of predictive power and judgment on investor demand. Specifically, the model has the ability to automatically analyze and learn features through "pre-training", that is, without the need for manual intervention or parameter adjustment, it can automatically convert input data features such as the regional focus index and personalized service request index into high-level demand features such as the investment demand coefficient. This coefficient represents the intensity and preference direction of investors' demand, so that the platform can intelligently evaluate investor demand based on this result. The application of this pre-trained model greatly improves the efficiency and accuracy of the evaluation process. At the same time, through continuous updates and feedback optimization, the model can continuously enhance its understanding and adaptability to investor needs, providing technical support for the platform to achieve accurate demand forecasting and personalized services.

[0088] The continued increase in the concentration of investors' attention to a specific area may indeed indicate that they have special needs for the functionality of the plot; this concentration usually reflects that investors have highly customized preferences for certain functional needs in site selection, such as convenient transportation, high-quality ecological conditions or complete supporting facilities in a specific area; especially when the area has outstanding functional advantages (such as proximity to highways, beautiful natural environment, proximity to high-end commercial facilities, etc.), investors' continued attention to the area may indicate that these specific needs play an important role in their decision-making; the continued increase in regional concentration indicates that investors hope to establish projects in areas that can fully meet these functional needs to ensure better resource support during project operation or development; therefore, the platform can infer that investors may need more accurate and in-depth information on the functionality of the plot in order to evaluate whether the area does meet their special requirements for transportation, ecology and facilities;

[0089] Under the detection window, the specific steps for analyzing the concentration of investors' attention on a specific region and generating the investment region focus index are as follows:

[0090] Under the detection window, first calculate the basic attention intensity of investors to each region to reflect their interest in a specific region. The calculation expression is as follows:

[0091]

[0092] , where, BFI i，j is the basic attention intensity, that is, the basic attention intensity of investor i to region j, V i，j is the visit frequency, that is, the visit frequency of investor i to region j, W j is the weight of region j, D i，j is the time distance, i.e., the time interval from the last visit of investor i to region j, and C is a constant used to adjust the time distance to ensure that the denominator is not zero in the calculation process;

[0093] In basic focus intensity (BFI) i，j On this basis, the depth of investors’ preference for different regions is calculated to reflect their level of focus in different regions. The calculation expression is as follows:

[0094]

[0095] , where DPF i，j is the regional preference depth, that is, the regional preference depth of investor i for region j, F i，j is the cumulative visit depth, that is, the cumulative visit depth of investor i to region j, T i，jis the specific behavior frequency, i.e., the specific behavior frequency of investor i towards region j, α is the preference index, which controls the influence weight of the cumulative visit depth, and γ is the preference depth index, which controls the sensitivity of the overall preference depth;

[0096] The preference index α is used to control the cumulative visit depth F i，j Depth DPF for regional preference i，j It reflects the sensitivity of investors to visit depth, that is, the importance of factors such as the frequency and duration of regional visits. A larger preference index value will amplify the effect of visit depth, indicating that the frequency and duration of visits have a more significant impact on regional preference depth. By adjusting α, the platform can adjust the calculation results of DPF to make it more in line with the personalized needs of different investors in terms of frequency of attention, thereby helping to identify the real attention of investors to certain specific areas.

[0097] The preferred depth index γ is used to control the regional preferred depth DPF i，j Overall sensitivity in the calculation. It prefers deep DPF over the entire area i，j The value of γ is indexed to help highlight investors' concentrated attention on certain areas. Larger γ values ​​will amplify the impact of areas with higher preference depth, making highly focused areas more prominent in the overall evaluation. Conversely, smaller γ values ​​will smooth the DPF value and reduce the impact of the depth of preference for individual areas. Therefore, the role of γ is to increase or decrease the concentration of investors' attention depth, thereby helping the platform identify whether investors have a particularly concentrated interest in a specific area.

[0098] Depth BFI based on regional preference i，j , calculate the concentration of investors' attention to each region to quantify whether they tend to prefer a specific region. The calculation expression is as follows:

[0099]

[0100] , where RCF i is the regional focus factor, i.e., the regional focus factor of investor i, S j is the market importance of region j, indicating the position of the region in the market, P i，j is the interaction depth coefficient, i.e., the interaction depth coefficient of investor i in region j, which indicates the interaction frequency and intensity of investors in this region. i，j is the geographical distance factor, i.e., the geographical distance factor between investor i and region j, which reflects the investor's preference for geographical location, δ is the concentration index, which is used to adjust the effect of distance on the regional concentration factor, and N is the total number of regions;

[0101] Regional Concentration Factor (RCF) iRegional Concentration Factor (RCF) i Comprehensive regional preference depth BFI i，j , regional market importance, interaction depth, distance and other factors to assess whether investors prefer to focus on specific areas. Its role is to help the platform determine whether investors' attention to regions is scattered or concentrated in a few regions, and to identify whether investors have special functional needs for certain regions, thereby providing a basis for personalized site selection analysis and recommendations.

[0102] Based on the regional concentration factor RCF i , generate the investment area focus index, the calculation expression is as follows:

[0103]

[0104] , where IAFI is the investment area focus index, U j is the future development potential of region j, Z i，j is the long-term attention of investor i to region j, θ is the sensitivity adjustment index, which enhances or weakens the influence of the regional concentration factor;

[0105] Investors' long-term attention to a region can be calculated and measured through behavioral data such as the frequency of visits to the region, the interval between visits, and continuous interaction over a period of time. Specifically, the multiple visits of investors to the region are recorded, and weighted calculations are performed based on the frequency of visits, the regularity of the intervals, and the depth of visits (such as viewing detailed information, downloading related reports, etc.). The formula for long-term attention can be expressed as a weighted sum, in which higher visit frequencies, shorter visit intervals, and deeper interactive behaviors (such as data downloads) are given higher weights, thereby comprehensively reflecting investors' continued interest and deep attention to the region.

[0106] Under the detection window, the larger the performance value of the investment area focus index generated by analyzing the concentration of investors' attention on a specific area, the more it usually indicates that the investor has special requirements for the functional needs of the plot. A higher focus index means that investors have a significant preference for a specific area when selecting a plot, indicating that they may have high requirements for the functional characteristics of the area, such as transportation convenience, ecological conditions, and supporting facilities, and hope to ensure that these characteristics can fully meet the needs of their project. On the contrary, if the focus index is low, it means that the investor's demand for the functionality of the plot is relatively broad, the dependence on a specific area is relatively small, and the functional needs of the plot are also relatively general.

[0107] When the frequency and complexity of personalized service requests made by investors on the platform continue to increase, it usually indicates that they have special functional requirements for the plots. This demand goes beyond the usual considerations of ordinary investors for plots, reflecting that investors have specific and detailed requirements for transportation convenience, ecological conditions and supporting facilities when selecting sites. High-frequency and complex requests may include inquiries about specific transportation nodes around the plots, detailed inspections of ecological protection areas or environmental quality, or customized evaluation requirements for high-end commercial and public facilities. These requests reveal that investors' functional requirements for plots are no longer limited to the overall situation covered by average indicators, but require more sophisticated feature matching to ensure that the plots can meet the unique conditions of operations, environmental protection, life services, etc. of specific projects. Therefore, frequent personalized requests are an important signal that investors have special functional requirements for plots, and the platform should provide in-depth and customized analysis and support for their needs.

[0108] Under the detection window, the frequency and complexity of investors' personalized service requests to the platform are analyzed. The specific steps for generating the personalized service request index are as follows:

[0109] Under the detection window, the basic weight values ​​of the investor's request frequency and complexity within the monitoring window are defined, and the interaction term is introduced to capture the nonlinear relationship between frequency and complexity. The calculation expression is as follows:

[0110]

[0111] , where B i is the basic weight value, that is, the basic weight value of investor i, R f is the request frequency, i.e., the total number of personalized service requests made by investors within the monitoring window, which reflects the intensity of investors’ demand for personalized services. f is the weight coefficient of request frequency, W x is the weight coefficient of the request complexity, ω is a fine-tuning parameter used to eliminate the impact of noise and outliers, ensuring that the index will not be zero or negative when the request frequency and complexity are extremely low, e is the natural base, and C x is the request complexity, which is used to quantify the complexity and degree of customization required for each request;

[0112] The weight coefficient W of the request frequency f Indicates that when calculating the basic weight value B i The platform attaches importance to the number of investor requests (i.e., frequency) when . The request frequency reflects the intensity of investors’ demand for personalized services, that is, how many times an investor makes requests within the monitoring window. By assigning a weight coefficient W to the request frequency f, the platform can control the influence of request frequency in the overall weight, so that high-frequency requests can get a larger weight in the calculation, highlighting investors who frequently put forward personalized needs. f The specific value of can be set according to the platform's attention to the request frequency. For example, if the platform believes that frequent requests mean higher demand specificity, \W f Set to a higher value.

[0113] The weight coefficient W of the request complexity x Used to measure the complexity of investor requests in the basic weight B i The complexity of the request reflects the specificity and depth of the personalized demand. The higher the complexity, the more detailed and unique the investor's demand is. By assigning a weight coefficient W to the complexity, x , we can give more weight to complex requests when calculating the basic weight, so that these requests get higher weights. x The specific value of can be adjusted according to the platform's strategy and resource configuration. For example, if the platform believes that complex requests require higher service and resource investment, a higher W can be assigned. x value to increase the impact of complex requirements in the calculation.

[0114] In order to accurately calculate the request response efficiency index, parameters and nonlinear terms are introduced so that the index can specifically reflect the platform's response speed and processing accuracy to investor requests. The calculation expression is as follows:

[0115]

[0116] , where E i is the request response efficiency index, which is used to measure the platform's response efficiency to the i-th investor's request, including response time and accuracy. r is the average processing time of the platform responding to investor requests, reflecting the platform's response speed, ∈ is a small positive number to prevent the denominator from being zero when the response time is extremely small, β is the response accuracy weight coefficient, A is the platform's actual response accuracy score for the request, is the adjustment coefficient, which is used to adjust the weight of complexity in the response efficiency index, and δ is the system constant;

[0117] The response accuracy weight coefficient β is a coefficient used to adjust the platform's emphasis on the accuracy of request responses. iWhen the platform pays attention to the response speed, it also pays attention to the accuracy of the response, and β is the weight of the accuracy. The higher the accuracy, the more accurately the needs of investors can be met, thereby improving the user experience. By adjusting the value of β, the platform can balance between response speed and accuracy: if the β value is large, it means that the platform pays more attention to the accuracy of the response, and the response accuracy has a greater impact on the efficiency index E. i If the β value is small, it means that the platform pays more attention to the response speed in this scenario.

[0118] Adjustment coefficient It is used to adjust the complexity of the request C x Request response efficiency index E i The higher the complexity of the request, the more resources and time the platform needs to handle it during the response process, which will affect efficiency. Can make the request complexity C x Request response efficiency index E i The influence of becomes more flexible and controllable. If the adjustment coefficient A larger value of indicates that complex requests will affect the request response efficiency index E. i The greater impact, resulting in a lower response efficiency index, reflects the difficulty of processing complex requests. A smaller value indicates that complex requests have relatively little impact on response efficiency, and the platform may have higher processing capabilities in this case.

[0119] In order to more accurately measure investors' preference for personalized needs, the request preference intensity coefficient is calculated by adding a combination of logarithms, exponents, and multiple powers. The calculation expression is as follows:

[0120]

[0121] , where P s is the request preference strength coefficient, τ is the adjustment parameter;

[0122] Based on the basic weight value B i , Request response efficiency index E i and the request preference strength coefficient P s , further adding nonlinear and interactive terms, we can more carefully characterize the complexity of investor needs and generate the final personalized service request index. The calculation expression is as follows:

[0123]

[0124] , where PSRI is the personalized service request index, η is the fine-tuning parameter, σ, κ and λ are adjustment parameters, and σ is used to control the request preference intensity coefficient Ps The weight in the personalized service request index is calculated by the request preference intensity coefficient P s Perform power operation, the value of σ can adjust the influence of preference intensity on the overall index. If the value of σ is large, the preference intensity coefficient P is requested. s The higher the proportion in the final index, the more influence the preference intensity of personalized demand has in the calculation. If σ is smaller, the request preference intensity coefficient P is weakened. s The contribution of κ to PSRI is used to control the comprehensive weight in the whole formula, that is, it affects the overall value and smoothness of the final index. By exponentially operating the whole expression, κ can amplify or reduce the result of the personalized service request index PSRI, thereby adjusting the range and sensitivity of the final index. A larger κ value will amplify the contribution of each indicator in the personalized service request index PSRI, making the index change more significant. A smaller κ value will make the personalized service request index PSRI less volatile and smoother overall. This parameter helps the platform control the stability of the final index, so that it can reflect significant differences without excessive fluctuations. λ controls the sine function term sin(R f ·C x ) Volatility in the final index. The sine term introduces a periodic fluctuation, which makes the personalized service request index PSRI show periodic fluctuations with changes in request frequency and complexity, while λ adjusts the amplitude and frequency of this fluctuation. A higher λ value will amplify the impact of the sine term, making PSRI more sensitive to changes in request frequency and complexity, thereby capturing subtle changes in investor demand. A lower λ value will reduce the impact of the sine term and reduce volatility. By controlling λ, the platform can flexibly adjust the degree of response of the personalized service request index PSRI to frequent changes in demand.

[0125] The fine-tuning parameter η is a parameter used to adjust the request preference strength coefficient P s The small constant ensures that when calculating the final personalized service request index PSRI, the index result will not be too low or affected by extreme values. Its role is to prevent the request preference intensity coefficient P from being too high when the request frequency or complexity is low. s The contribution to the overall index is too small, resulting in the personalized service request index PSRI being lower than the expected range. By adding the fine-tuning parameter η, it can be ensured that the index still maintains a certain basic value even when investor demand is low, improving the stability of the calculation and the reliability of the results.

[0126] Under the detection window, the larger the performance value of the personalized service request index generated by analyzing the frequency and complexity of personalized service requests made by investors to the platform, the higher the performance value is, which usually indicates that the investor has special needs for the functionality of the plot; this index is calculated by monitoring the frequency and complexity of personalized service requests made by investors on the platform. When the index value is high, it means that investors have repeatedly requested specific functional needs, such as transportation convenience, ecological conditions and detailed information on supporting facilities, which go beyond the scope of ordinary needs and reflect specific requirements for the plot; therefore, the larger the performance value is, the more it can indicate that investors need to meet special functional conditions for the plot; conversely, if the index value is low, it usually means that the investor's needs are more general and there are no special requirements for the functionality of the plot;

[0127] The machine learning model is not limited here, and any machine learning model that can perform a comprehensive analysis of the investment area focus index IAFI and the personalized service request index PSRI to generate the investment demand coefficient IDC is acceptable. To implement the technical solution of the present invention, the present invention provides a specific implementation method:

[0128] The formula for generating the investment demand coefficient IDC is as follows:

[0129]

[0130] , where f1 and f2 are the preset proportional coefficients of the investment area focus index IAFI and the personalized service request index PSRI, respectively, and both f1 and f2 are greater than 0;

[0131] It can be seen from the calculation expression of the investment demand coefficient that, under the detection window, the larger the performance value of the investment area focus index generated after analyzing the degree of concentration of investors' attention on a specific area, the larger the performance value of the personalized service request index generated after analyzing the frequency and complexity of investors' personalized service requests to the platform. The larger the performance value of the investment demand coefficient generated after analyzing the historical choices and demand preference data of investors obtained under the detection window, the greater the investor's special needs for the functionality of the plot. Otherwise, it means that the investor's needs are more general and there are no special requirements for the functionality of the plot.

[0132] Based on the evaluation results of the machine learning model, investors are divided into general demand investors and special demand investors;

[0133] The investment demand coefficient generated by analyzing the historical selection and demand preference data of investors obtained under the detection window is compared with the pre-set reference threshold of the investment demand coefficient to divide investors. The specific steps are as follows:

[0134] If the investment demand coefficient is greater than or equal to the pre-set reference threshold of the investment demand coefficient, the investor is classified as a special demand investor;

[0135] If the investment demand coefficient is less than the pre-set reference threshold of the investment demand coefficient, the investor is classified as a general demand investor;

[0136] Investors with general needs refer to those who have a wide range of standardized requirements for land selection. They mainly focus on the overall conditions of the land, such as macro indicators such as price, basic supporting facilities, and transportation convenience. Investors with special needs have more specific and unique site selection requirements, and usually focus on specific functional characteristics, such as the special transportation conditions of a plot of land (such as the specific distance from the highway), the uniqueness of the surrounding ecological environment (such as air quality, water source protection, etc.), or special supporting facilities (such as high-end commercial and educational resources).

[0137] For ordinary investors, we will continue to use standardized analysis reports generated based on average indicators to help investors quickly understand the overall market picture and make wise investment decisions.

[0138] The report covers the overall characteristics of the land investment area, such as average traffic convenience, ecological environment quality, supporting facilities level, etc. By providing these systematic data support and decision-making references, the platform can meet the needs of ordinary investors for macro information, help them make investment decisions quickly, and improve user experience and satisfaction.

[0139] For investors with special needs, based on the average indicator report, we combine the investors' historical choices and demand preferences to re-formulate personalized analysis reports, provide highly customized analysis, and meet the unique requirements of investors with special needs;

[0140] For investors with special needs, based on the average indicator report, combined with investors' historical choices and demand preferences, we re-formulate personalized analysis reports to provide highly customized analysis to meet the unique requirements of investors with special needs. The specific steps are as follows:

[0141] First, generate a standardized analysis report based on regional average indicators R avg , this report provides the overall characteristics of the region, provides a reference for investors with general needs, and also provides a basis for subsequent customized reports;

[0142] We extract personalized features of investors with special needs, extract the special concerns of investors when selecting land, and generate a customized feature set. The expression is as follows:

[0143] F custom =g(H, A)

[0144] , where Fcustom is a customized feature set for investors, H represents the investor’s historical selection record (such as the land parcels of interest in the past and location preferences), A is the demand preference (such as attention to specific conditions such as transportation and supporting facilities), and g is the feature extraction function;

[0145] A customized feature set refers to a set of features generated based on investors' historical choices and demand preferences. This feature set contains specific elements that can reflect investors' personalized needs, such as preferences for specific transportation nodes, requirements for the ecological environment, and attention to supporting facilities. A customized feature set can provide the platform with in-depth information about investors' unique needs, enabling the platform to better meet investors' needs in subsequent analysis reports, rather than relying solely on average indicator data for the region. It helps the platform identify the details that investors value in decision-making so that it can generate more targeted analysis reports that meet their needs.

[0146] The feature extraction function is an algorithm or method for extracting useful features from investors' historical data and demand preferences. The role of the feature extraction function is to convert massive amounts of raw data into specific and actionable features. For example, through data mining, cluster analysis or association rules and other technologies, the key factors that investors pay attention to in site selection are extracted. The core role of the feature extraction function is to screen out key information that affects the analysis report, construct a feature set that reflects the personalized needs of investors, and lay the foundation for generating customized reports. Through this extraction process, the platform can automatically identify the unique needs of investors from massive data and improve the accuracy and personalization of services.

[0147] The weight of personalized analysis is determined based on the investment demand coefficient IDC;

[0148] IDC≥IDC ref , then G=High

[0149] IDC <IDC ref , then G=Low

[0150] When the investment demand coefficient IDC is greater than or equal to the investment demand coefficient reference threshold IDC ref When the personalized analysis weight G is set to a high value (High), the personalized needs content is highlighted;

[0151] When the investment demand coefficient IDC is less than the investment demand coefficient reference threshold IDC ref When the personalized analysis weight G is set to a low value (Low), the impact of personalized needs is reduced;

[0152] According to the size of the investment demand coefficient, adjust the proportion of personalized analysis content in the final report to make the report content more in line with the actual demand intensity of investors;

[0153] Standardize the report R avg The feature set F customized to investors custom The final personalized analysis report is generated by integrating according to the weight G. The report contains basic regional data and in-depth analysis generated according to the characteristics of investor needs. The calculation expression is as follows:

[0154] R custom =R avg +G·F custom

[0155] , where R custom It is the final personalized analysis report;

[0156] The report combines basic data of the region with in-depth analysis of investor demand characteristics, such as accessibility of specific transportation nodes, ecological conditions or facility assessments, to fully meet the specific requirements of investors with special needs.

[0157] After the personalized analysis report is generated, its content is verified for accuracy and applicability:

[0158] Validity = h(R custom ,T current )

[0159] , where Validity is the validity of the report, function h represents the verification process, T current It is the latest data status at the current time, which is used to compare the timeliness of the report data. By checking the final personalized analysis report R custom Does the data in T meet the requirements? current The latest standards ensure the real-time and accurate analysis; ensure the report content is accurate and reflects the current actual situation;

[0160] The validity or accuracy of the report measures whether the generated personalized analysis report conforms to the current actual situation, whether the data is up-to-date, and whether it meets the personalized needs of investors. By verifying the validity of the report, it can ensure that the information in the report is practical and timely, providing investors with a reliable basis for decision-making.

[0161] If the verification does not meet the requirements, a re-update is triggered to ensure that the report provides accurate and up-to-date information for investors' decision-making.

[0162] The present invention comprehensively collects and analyzes investors' historical choices and demand preference data, and uses feature extraction and machine learning models to generate investment demand coefficients to accurately divide investors into two categories: general demand and special demand. For investors with general demand, the platform continues to provide standardized analysis reports generated based on average indicators to help them quickly understand the overall market situation in the region and meet their needs for macro indicators. For investors with special needs, the platform generates highly customized analysis reports based on their personalized needs, and adds detailed analysis of specific transportation nodes, ecological conditions, supporting facilities, etc. on the basis of standardized data. In this way, investors can obtain more accurate data support that better suits their needs, helping them make investment decisions that are more in line with expectations, and greatly improving investors' satisfaction and trust in the platform.

[0163] Through intelligent evaluation and demand division, the present invention allows the platform to effectively identify and meet the special needs of high-quality investors, avoiding waste of resources and investment errors caused by the "information smoothing" problem of average indicator reports. This precise demand matching mechanism helps to retain high-quality investors and prevent investors from leaving due to unmet needs. For the government and investment promotion agencies, this means that the success rate and quality of investment promotion will be significantly improved, which will help enhance the market attractiveness and economic competitiveness of the region. In addition, the precise matching mechanism can also improve the service quality and user experience of the platform, enable the platform to establish a good reputation and credibility in the market, and then form a positive brand effect, attract more investors to participate, and inject continuous impetus into the economic development of the region.

[0164] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. The land investment information platform is characterized by: The following steps are involved: First, the platform comprehensively collects investors’ historical choices and demand preference data during use. Through data collection, it has a comprehensive understanding of each investor’s needs; Extract features from the acquired investor historical selection and demand preference data, and use pre-learned machine learning models to intelligently evaluate investor needs based on the extracted features; Based on the evaluation results of the machine learning model, investors are divided into general demand investors and special demand investors; For ordinary investors, we will continue to use standardized analysis reports generated based on average indicators to help investors quickly understand the overall market picture and make wise investment decisions. For investors with special needs, based on the average indicator report, we combine investors' historical choices and demand preferences to re-formulate personalized analysis reports, provide highly customized analysis, and meet the unique requirements of investors with special needs.

2. The land investment promotion information platform according to claim 1 is characterized by: The platform comprehensively collects investors' historical choices and demand preference data during use. Through data collection, the specific steps to have a comprehensive understanding of each investor's needs are as follows: First, establish a comprehensive and efficient data collection mechanism to capture various behavioral data and preference information of investors in the process of using the platform; During the data collection process, ensure the legality and compliance of data collection; In order to effectively manage and quickly access the collected data, a unified data storage and management system should be established; After data storage, the collected data is cleaned and preprocessed to improve data quality and ensure the accuracy of analysis results.

3. The land investment promotion information platform according to claim 1 is characterized by: Feature extraction is performed on the acquired data on investors' historical choices and demand preferences. The extracted features include the degree of concentration of investors' attention on specific areas and the frequency and complexity of investors' personalized service requests to the platform. Within the detection window, the extracted degree of concentration of investors' attention on specific areas and the frequency and complexity of investors' personalized service requests to the platform are analyzed to generate an investment area focus index and a personalized service request index respectively. The investment area focus index and the personalized service request index are input into a pre-learned machine learning model, and an investment demand coefficient is generated by the machine learning model. Investors' needs are intelligently evaluated by the investment demand coefficient.

4. The land investment promotion information platform according to claim 3 is characterized by: The investment demand coefficient generated by analyzing the historical selection and demand preference data of investors obtained under the detection window is compared with the pre-set reference threshold of the investment demand coefficient to divide investors. The specific steps are as follows: If the investment demand coefficient is greater than or equal to the pre-set reference threshold of the investment demand coefficient, the investor is classified as a special demand investor; If the investment demand coefficient is less than the pre-set investment demand coefficient reference threshold, the investor will be classified as an ordinary demand investor.

5. The land investment information platform according to claim 4 is characterized in that: For investors with special needs, based on the average index report, combined with investors' historical choices and demand preferences, we re-formulate personalized analysis reports to provide highly customized analysis to meet the unique requirements of investors with special needs. The specific steps are as follows: First, generate a standardized analysis report based on regional average indicators R avg , this report provides the overall characteristics of the region, provides a reference for investors with general needs, and also provides a basis for subsequent customized reports; We extract personalized features of investors with special needs, extract the special concerns of investors when selecting land, and generate a customized feature set. The expression is as follows: F custom =g(H,A), In the formula, F custom is the investor's customized feature set, H represents the investor's historical selection record, A is the demand preference, and g is the feature extraction function; The weight of personalized analysis is determined based on the investment demand coefficient IDC; IDC≥IDC ref , then G=High IDC <IDC ref , then G=Low When the investment demand coefficient IDG is greater than or equal to the investment demand coefficient reference threshold IDC ref When the personalized analysis weight G is set to a high value (High), the personalized needs content is highlighted; When the investment demand coefficient IDG is less than the investment demand coefficient reference threshold IDC ref When the personalized analysis weight G is set to a low value (Low), the impact of personalized needs is reduced; According to the size of the investment demand coefficient, adjust the proportion of personalized analysis content in the final report to make the report content more in line with the actual demand intensity of investors; Standardize the report R avg The feature set F customized to investors custom Integrate according to the weight G to generate the final personalized analysis report. The calculation expression is as follows: R custom =R avg +G·F custom , In the formula, R custom It is the final personalized analysis report; After the personalized analysis report is generated, its content is verified for accuracy and applicability: Validity=h(R custom ,T current ), Where Validity is the validity of the report, function h represents the verification process, and T current It is the latest data status at the current time, which is used to compare the timeliness of report data; If the verification does not meet the requirements, a re-update is triggered to ensure that the report provides accurate and up-to-date information for investors' decision-making.

6. The land investment promotion information platform according to claim 3 is characterized in that: Under the detection window, the specific steps for analyzing the concentration of investors' attention on a specific region and generating the investment region focus index are as follows: Under the detection window, first calculate the basic attention intensity of investors to each region to reflect their interest in a specific region. The calculation expression is as follows: ， In the formula, BFI i，j is the basic attention intensity, that is, the basic attention intensity of investor i to region j, V i，j is the visit frequency, that is, the visit frequency of investor i to region j, W j is the weight of region j, D i，j is the time distance, i.e., the time interval from the last visit of investor i to region j, and C is a constant used to adjust the time distance; In basic focus intensity (BFI) i，j On this basis, the depth of investors’ preference for different regions is calculated to reflect their level of focus in different regions. The calculation expression is as follows: ， Where, DPF i，j is the regional preference depth, that is, the regional preference depth of investor i for region j, F i，j is the cumulative visit depth, that is, the cumulative visit depth of investor i to region j, T i，j is the specific behavior frequency, i.e., the specific behavior frequency of investor i towards region j, α is the preference index, which controls the influence weight of the cumulative visit depth, and γ is the preference depth index, which controls the sensitivity of the overall preference depth; Depth BFI based on regional preference i，j , calculate the concentration of investors' attention to each region to quantify whether they tend to prefer a specific region. The calculation expression is as follows: ， Where RCF i is the regional focus factor, i.e., the regional focus factor of investor i, S j is the market importance of region j, indicating the position of the region in the market, P i，j is the interaction depth coefficient, i.e., the interaction depth coefficient of investor i in region j, which indicates the interaction frequency and intensity of investors in this region. i，j is the geographical distance factor, i.e., the geographical distance factor between investor i and region j, which reflects the investor's preference for geographical location, δ is the concentration index, which is used to adjust the effect of distance on the regional concentration factor, and N is the total number of regions; Based on the regional concentration factor RCF i , generate the investment area focus index, the calculation expression is as follows: ， Where IAFI is the investment area focus index, U j is the future development potential of region j, Z i，j is the long-term attention of investor i to region j, and θ is the sensitivity adjustment index.

7. The land investment information platform according to claim 3 is characterized in that: Under the detection window, the frequency and complexity of investors' personalized service requests to the platform are analyzed. The specific steps for generating the personalized service request index are as follows: Under the detection window, the basic weight values ​​of the investor's request frequency and complexity within the monitoring window are defined, and the interaction term is introduced to capture the nonlinear relationship between frequency and complexity. The calculation expression is as follows: ， In the formula, B i is the basic weight value, that is, the basic weight value of investor i, R f is the request frequency, W f is the weight coefficient of the request frequency, W x is the weight coefficient of the request complexity, ω is the fine-tuning parameter, e is the natural base, C x is the request complexity; In order to accurately calculate the request response efficiency index, parameters and nonlinear terms are introduced so that the index can specifically reflect the platform's response speed and processing accuracy to investor requests. The calculation expression is as follows: ， In the formula, E i is the request response efficiency index, T r is the average processing time for the platform to respond to investor requests, reflecting the platform's response speed, ∈ is a small positive number, β is the response accuracy weight coefficient, A is the platform's actual response accuracy score for the request, is the adjustment coefficient, δ is the system constant; In order to more accurately measure investors' preference for personalized needs, the request preference intensity coefficient is calculated by adding a combination of logarithms, exponents, and multiple powers. The calculation expression is as follows: ， Where P s is the request preference strength coefficient, τ is the adjustment parameter; Based on the basic weight value B i , Request response efficiency index E i and the request preference strength coefficient P s , further adding nonlinear and interactive terms, we can more carefully characterize the complexity of investor needs and generate the final personalized service request index. The calculation expression is as follows: ， Where PSRI is the personalized service request index, η is the fine-tuning parameter, σ, κ and λ are adjustment parameters, and σ is used to control the request preference intensity coefficient P s The weight in the personalized service request index, κ is used to control the comprehensive weight in the whole formula, and λ controls the sine function term sin(R f ·C x ) volatility in the final index.

Images