Identification value analysis method and device, computer equipment and storage medium

Abstract

The invention discloses an identification value analysis method and device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence and the financial science and technology field, and the method comprises the steps: collecting an original sample set related to a target object to be subjected to identification value analysis, and determining the number of support vector regression models needing to be constructed; for each support vector regression model, extracting a plurality of samples from the original sample set to form a training set corresponding to each support vector regression model; for each training set, extracting a plurality of features from the all-feature set corresponding to the original sample set to form a feature subset corresponding to each training set; based on the training sets and the feature subsets corresponding to the training sets, constructing the support vector regression models of the model number; combining all the support vector regression models to generate an identification value analysis model; therefore, the identification value of the target object can be accurately analyzed and predicted through the identification value analysis model.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence technology and financial technology, and in particular to an identification value analysis method, device, computer equipment and computer-readable storage medium. Background Art

[0002] At present, with the development of computer technology, more and more technologies are applied in the financial field. The traditional financial industry is gradually transforming to financial technology (Fintech), and the identification value analysis technology is no exception. For example, in the credit assessment scenario of financial institutions (such as banks), when evaluating mortgage or personal loan applications, financial institutions can use the house-related identification value (such as rent) analysis technology to estimate the borrower's repayment ability. However, due to the security and real-time requirements of the financial industry, higher requirements are also placed on the identification value analysis technology.

[0003] At present, with the acceleration of urbanization, the housing rental market has ushered in an opportunity for rapid development. In the current economic environment, for migrant workers, low- and middle-income groups, and college students who have just entered society, housing rental has become the preferred way to solve their housing problems. However, the problems of information asymmetry and irregular intermediary services in the housing rental market have seriously troubled renters.

[0004] At present, renters mainly obtain rental information through channels such as real estate agencies and rental websites. Although these information sources provide convenience, they also have many problems. First, in order to attract customers, intermediaries may publish rental information that is inconsistent with the actual situation of the house, making it difficult for renters to obtain real and reliable house rental information; secondly, due to the opacity of house rental information, the relevant agency fees are not transparent and the charges are confusing, which increases the financial burden of renters; in addition, the rental website information is not updated in a timely manner, making it difficult for renters to grasp the latest rental information related to the dynamics of housing sources.

[0005] To sum up, how to provide an identification value analysis method, device, computer equipment and computer-readable storage medium that can achieve accurate analysis and prediction of the target object identification value by generating an identification value analysis model is a problem that urgently needs to be solved by technical personnel in this field. Summary of the invention

[0006] In view of the above-mentioned deficiencies in the prior art, the object of the present invention is to provide an identification value analysis method, apparatus, computer equipment and computer-readable storage medium, aiming to solve the problem of how to achieve accurate analysis and prediction of the target object identification value by generating an identification value analysis model.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides an identification value analysis method, which includes:

[0009] Collecting original sample sets related to the target object to be analyzed for identification value, and determining the number of support vector regression models to be constructed;

[0010] For each of the support vector regression models, extracting multiple samples from the original sample set to form a training set corresponding to each of the support vector regression models;

[0011] For each of the training sets, multiple features are extracted from the entire feature set corresponding to the original sample set to form a feature subset corresponding to each of the training sets;

[0012] Based on each of the training sets and the corresponding feature subsets, construct the support vector regression model of the model quantity;

[0013] Combining all the support vector regression models to generate an identification value analysis model;

[0014] Based on the identification value analysis model, an identification value analysis is performed on the target object.

[0015] In a second aspect, the present invention provides an identification value analysis device, comprising:

[0016] A collection module is used to collect original sample sets related to target objects to be analyzed for identification values, and determine the number of models of support vector regression models that need to be constructed;

[0017] A sample extraction module, used for extracting a plurality of samples from the original sample set for each support vector regression model to form a training set corresponding to each support vector regression model;

[0018] A feature extraction module, configured to extract, for each of the training sets, a plurality of features from the entire feature set corresponding to the original sample set, to form a feature subset corresponding to each of the training sets;

[0019] A construction module, used for constructing the support vector regression model of the model quantity based on each of the training sets and the corresponding feature subsets;

[0020] A combination module, used for combining all the support vector regression models to generate an identification value analysis model;

[0021] An analysis module is used to perform identification value analysis on the target object based on the identification value analysis model.

[0022] In a third aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the identification value analysis method as described above when executing the computer program.

[0023] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program implements the identification value analysis method as described above when executed by a processor.

[0024] Compared with the prior art, the present invention provides an identification value analysis method, apparatus, computer equipment and computer-readable storage medium, wherein, by collecting the original sample set related to the target object to be subjected to identification value analysis, and determining the number of support vector regression models that need to be constructed; for each of the support vector regression models, extracting multiple samples from the original sample set to form a training set corresponding to each of the support vector regression models; for each of the training sets, extracting multiple features from the entire feature set corresponding to the original sample set to form a feature subset corresponding to each of the training sets; based on each of the training sets and the corresponding feature subsets, constructing the support vector regression models of the number of models; combining all of the support vector regression models to generate an identification value analysis model; based on the identification value analysis model, performing identification value analysis on the target object; thus, the present invention can achieve accurate analysis and prediction of the identification value of the target object by generating an identification value analysis model. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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 be obtained based on these drawings without paying creative work.

[0026] Figure 1 A schematic diagram of an application environment of an identification value analysis method provided by an embodiment of the present invention.

[0027] Figure 2 A flowchart of an identification value analysis method provided by an embodiment of the present invention.

[0028] Figure 3 A schematic diagram of a program module of an identification value analysis device provided by an embodiment of the present invention.

[0029] Figure 4 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention.

[0030] Figure 5 Another structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0033] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0034] As used in the present specification and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0035] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0036] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0037] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0038] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0039] An identification value analysis method provided by an embodiment of the present invention can be applied in Figure 1 In the application environment shown, the client and the server communicate through the network. The client includes but is not limited to PDAs, desktop computers, laptops, ultra-mobile personal computers (UMPC), netbooks, cloud computing devices, personal digital assistants (PDA) and other computer devices. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0040] See also Figure 2 An embodiment of the present invention provides an identification value analysis method, wherein the method comprises the following steps:

[0041] S100, collecting original sample sets related to target objects to be analyzed for identification values, and determining the number of support vector regression models to be constructed;

[0042] S200: for each of the support vector regression models, extract multiple samples from the original sample set to form a training set corresponding to each of the support vector regression models;

[0043] S300, for each of the training sets, extracting multiple features from the entire feature set corresponding to the original sample set to form a feature subset corresponding to each of the training sets;

[0044] S400, constructing the support vector regression model of the model quantity based on each of the training sets and the corresponding feature subset;

[0045] S500, combining all the support vector regression models to generate an identification value analysis model;

[0046] S600: Perform identification value analysis on the target object based on the identification value analysis model.

[0047] In specific implementation, the identification value analysis method of this embodiment realizes accurate identification value analysis of the target object through systematic steps; first, by collecting the original sample set related to the target object to be analyzed for identification value and determining the model number of the support vector regression model, the comprehensiveness of the data and the diversity of the model are ensured; then, multiple samples are extracted from the original sample set to form a training set corresponding to each support vector regression model, and multiple features are selected from the entire feature set to construct a feature subset. This process effectively captures the key factors affecting the identification value of the target object; then, based on the corresponding training set and feature subset, a support vector regression model of the model number is constructed, and these models are combined by using the idea of ​​ensemble learning to generate a comprehensive identification value analysis model; finally, the comprehensive identification value analysis model can perform accurate identification value (such as rent) analysis and prediction based on the relevant information of the input target object (such as the target house), so as to help tenants and landlords make more informed decisions, thereby improving the transparency and efficiency of the rental market; through this method, the identification value analysis of this embodiment not only has a high accuracy, but also can adapt to market changes and provide real-time identification value evaluation of the target object.

[0048] Furthermore, in one embodiment, the identification value analysis method, wherein the target object is a target house, the step S100 of collecting an original sample set related to the target object to be subjected to identification value analysis and determining the number of models of the support vector regression model to be constructed specifically comprises the steps of:

[0049] Using a crawler tool to collect basic information of several houses; wherein the basic information includes the house address;

[0050] Based on the house addresses, using a map tool to output the longitude and latitude information of each house;

[0051] Based on the latitude and longitude information, using the map tool to obtain surrounding information within a predetermined range of each of the houses;

[0052] Integrate the surrounding situation information with the basic information to generate an original sample set related to the target house to be analyzed for identification value;

[0053] Determine the number of models you need to build for the Support Vector Regression model.

[0054] In specific implementation, the identification value analysis in this embodiment refers to the rental analysis of the target house, that is, this embodiment realizes a comprehensive analysis of the factors affecting the house rent through automated data collection and processing; first, the basic information including the house address is collected by using a crawler tool to ensure the diversity and extensiveness of the data; then, the address is converted into longitude and latitude through a map tool, and surrounding information such as schools, transportation, and commerce are obtained. This surrounding information is an important factor affecting the house rent; then, this surrounding information is integrated with the basic information of the house to form a detailed original sample set, which provides a rich data foundation for building an accurate identification value analysis model; finally, by determining the model number of the support vector regression model, multiple models can be constructed and integrated to improve the accuracy and robustness of the prediction; overall, this embodiment not only improves the efficiency of data processing, but also enhances the reliability of house rent analysis and prediction, and provides a powerful decision support tool for real estate investors, renters, landlords, and policy makers.

[0055] The specific implementation process of the steps in this embodiment is roughly as follows:

[0056] 1. Collect basic information about the house:

[0057] Use web crawler tools to write scripts to crawl basic information about houses on real estate websites or online rental platforms;

[0058] Ensure that the crawler complies with the robots and txt rules of the target website and collects data legally and compliantly;

[0059] The collected data includes the address, area, room type, decoration, construction year, etc. of the house, which is stored in a database or data frame;

[0060] 2. Get the longitude and latitude information of the house:

[0061] Use a map tool API, such as Baidu Map API or Google Map API, to enter the house address and call the geocoding function to obtain the corresponding longitude and latitude information;

[0062] For each house address, send an HTTP request to the API endpoint and associate the returned latitude and longitude data with the basic house information;

[0063] 3. Get information about surrounding conditions:

[0064] Using the obtained house longitude and latitude information, call the nearby search function of the map tool API to obtain surrounding information within a predetermined range (such as 1 kilometer) centered on the house;

[0065] Surrounding information may include traffic conditions (such as subway stations, bus stops), commercial facilities (such as shopping malls, supermarkets), educational facilities (such as schools, kindergartens), medical facilities (such as hospitals, clinics), etc.;

[0066] At the same time, the school names in the surrounding information can be compared with the prepared list of district key / city key schools to obtain the surrounding education level indicators of the house;

[0067] 4. Integration to generate the original sample set:

[0068] Integrate the collected basic information of the house and the surrounding information together, and pre-process the data, including cleaning (removing invalid or erroneous data), formatting (unifying the data format), encoding (converting categorical data into numerical data), etc., to construct a comprehensive original sample set related to the target house to be analyzed for rent;

[0069] 5. Determine the number of support vector regression models:

[0070] Conduct preliminary data exploration and analysis to understand the relationship between different features and house rents, as well as the complexity requirements of the identification value analysis model;

[0071] Determine the number of support vector regression models that need to be built based on the identification value analysis model complexity, expected generalization ability, computing resources and other factors;

[0072] Design experiments, such as cross-validation, to evaluate the impact of different numbers of SVR models on analysis and prediction performance, so as to determine the optimal number of SVR models;

[0073] Among them, Support Vector Regression (SVR) is a regression method based on Support Vector Machine (SVM) and is used to predict continuous numerical data. It finds an optimal hyperplane in the feature space, which can minimize the error between the actual output value and the predicted output value, while keeping the complexity of the model at a low level to avoid overfitting. SVR can handle linear and nonlinear relationships, and uses kernel techniques to map data to high-dimensional space for linear segmentation, thereby capturing complex data patterns. The support vector regression model has shown excellent performance in many practical problems, such as financial market forecasting, weather forecasting, and house price forecasting.

[0074] Through the above process, this embodiment can construct an original sample set containing rich features and lay a foundation for building an accurate identification value analysis model.

[0075] Furthermore, in one embodiment, the identification value analysis method, wherein the step S200, for each support vector regression model, extracts multiple samples from the original sample set to form a training set corresponding to each support vector regression model, specifically comprises the steps of:

[0076] Determine the size M of the original sample set; wherein M represents a positive integer;

[0077] For each of the support vector regression models, M samples are randomly extracted with replacement from the original sample set using the bootstrapping method to form a training set corresponding to each of the support vector regression models.

[0078] In specific implementation, this embodiment determines the size M of the original sample set and applies the bootstrapping method to achieve efficient use of the original data and enhance the generalization ability of the model; wherein the bootstrapping method allows multiple training sets to be generated by sampling with replacement, each training set containing M samples, and this method helps to simulate larger data sets on limited data resources, thereby introducing randomness in each support vector regression model, reducing the risk of overfitting, and improving the stability and accuracy of the support vector regression model when predicting on unknown data; in addition, this method allows the construction of multiple different support vector regression models, providing a basis for subsequent support vector regression model integration and fusion, and enhancing the robustness of the final identification value analysis model.

[0079] The specific implementation process of the steps in this embodiment is roughly as follows:

[0080] 1. Determine the size of the original sample set:

[0081] First, count the total number of samples in the original sample set and define this value as M; M is a positive integer;

[0082] 2. Perform Bootstrapping sampling:

[0083] For each support vector regression model, the following is done using the bootstrap method:

[0084] 21) Randomly select a sample from the original sample set and record its index;

[0085] 22) Put the selected sample back into the original sample set so that the sample may still be selected in the next sampling;

[0086] 23) Repeat the above sampling process M times to construct a training set containing M samples;

[0087] 3. Record and store training sets:

[0088] Store the training sets generated by each bootstrapping method and assign a unique identifier to each training set;

[0089] Make sure each training set is independent so that it can be used to train different support vector regression models;

[0090] 4. Repeat until all training sets are generated:

[0091] Repeat steps 2 and 3 above until the number of training sets for the model is generated, and each training set is used to train an independent support vector regression model;

[0092] Ensure that all training sets are generated randomly and independently to improve the generalization ability of subsequent identity value analysis models;

[0093] Through the above process, this embodiment can effectively generate a model number of training sets from the original sample set, and each training set can be used to train a support vector regression model.

[0094] Further, in one embodiment, the identification value analysis method, wherein the step S300, for each of the training sets, extracts multiple features from the entire feature set corresponding to the original sample set to form a feature subset corresponding to each of the training sets, specifically comprises the steps of:

[0095] Determine a feature selection strategy for the original sample set corresponding to the entire feature set;

[0096] For each of the training sets, multiple features are extracted from the entire feature set according to the feature selection strategy to form a feature subset corresponding to each of the training sets.

[0097] In specific implementation, this embodiment achieves accurate extraction of the most critical feature subsets for analysis and prediction of identification values ​​(such as rent) from the entire feature set through a carefully designed and determined feature selection strategy, thereby tailoring the feature combination that is most helpful in improving the analysis and prediction performance of the support vector regression model for each training set; this method not only improves the efficiency of support vector regression model training and reduces the waste of computing resources, but also reduces the complexity of the support vector regression model by eliminating irrelevant features, effectively prevents overfitting, and enhances the generalization ability of the support vector regression model to new data; in addition, the optimization of feature subsets also helps to improve the interpretability of the support vector regression model, making the prediction results of identification values ​​(such as rent) easier to understand and trust, providing solid data support for decision makers.

[0098] The specific implementation process of the steps in this embodiment is roughly as follows:

[0099] 1. Evaluate feature relevance:

[0100] Perform statistical analysis on the entire feature set of the original sample set to evaluate the correlation between each feature and the object identification value (such as house rent); statistical methods such as Pearson correlation coefficient and Spearman rank correlation coefficient can be used;

[0101] 2. Choose feature selection strategy:

[0102] Choose an appropriate feature selection strategy based on the evaluation results and domain knowledge; common strategies include filtering methods (such as variance selection, correlation coefficient method), wrapping methods (such as recursive feature elimination) and embedded methods (such as model-based feature selection).

[0103] 3. Apply feature selection strategy:

[0104] For each training set generated by bootstrapping, apply the selected feature selection strategy to select the most influential feature subset from the entire feature set; for example, if using model-based feature selection, you can train an initial support vector regression model and select the features with the largest weights;

[0105] 4. Optimize feature subsets:

[0106] Optimize feature subsets to improve the performance of the support vector regression model; this may include preprocessing steps such as combining features, binarizing features, and normalizing features;

[0107] 5. Verify the validity of the feature subset:

[0108] Use cross-validation and other methods to verify the effectiveness of the selected feature subset; evaluate the performance indicators of the support vector regression model, such as mean square error (MSE), coefficient of determination (R2), etc., to ensure that the feature subset can improve the analysis and prediction accuracy of the support vector regression model;

[0109] Through the above process, this embodiment can ensure that each training set contains the features that are most helpful in predicting the object identification value (such as house rent), thereby improving the performance of the support vector regression model.

[0110] Furthermore, in one embodiment, the identification value analysis method, wherein the step S400, constructing the support vector regression model of the model quantity based on each of the training sets and the feature subset corresponding thereto, specifically comprises the steps of:

[0111] Using each of the training sets and the corresponding feature subsets in turn to construct the support vector regression model;

[0112] The support vector regression model construction process is repeatedly executed until the support vector regression model of the model quantity is constructed.

[0113] In specific implementation, this embodiment constructs an independent support vector regression model by sequentially applying each training set and the corresponding feature subset, and continues this process until the preset number of models is reached, thereby realizing the construction of a collection of multiple independent models; this technical strategy not only improves the diversity of the model collection, because each support vector regression model can capture the inherent laws of the data from different angles, but also through integration methods (such as average or weighted average prediction results) can effectively improve the stability and prediction accuracy of the overall identification value analysis model; in addition, this method also helps to reduce the possible deviations of a single model, enhance the adaptability of the overall identification value analysis model to new data, and ultimately form a robust and generalizable identification value analysis model.

[0114] The specific implementation process of the steps in this embodiment is roughly as follows:

[0115] 1. Initialize the model building environment:

[0116] Prepare the environment required for building the support vector regression (SVR) model, including selecting the appropriate machine learning library and setting model parameters (such as regularization parameter C, kernel function type and corresponding parameters);

[0117] 2. Allocate training set and feature subsets:

[0118] For each support vector regression model to be constructed, a training set and its corresponding feature subset are allocated; these training sets are extracted from the original sample set by the bootstrap method;

[0119] 3. Build a support vector regression model:

[0120] Using the assigned training set and feature subset, a support vector regression model is constructed by selecting an appropriate kernel function and setting model parameters;

[0121] 4. Repeat the build process:

[0122] Save the support vector regression model constructed in step 3 above, and prepare a new training set and corresponding feature subset for the next support vector regression model;

[0123] Repeat step 3 to construct the next support vector regression model using the new training set and the corresponding feature subset until all support vector regression models of the model quantity are constructed;

[0124] 5. Model performance evaluation:

[0125] After the repeated construction process of step 4 above, a support vector regression model of the model quantity is finally constructed;

[0126] Evaluate the performance of each support vector regression model, record the parameters and performance indicators of each support vector regression model, and prepare for subsequent model combination;

[0127] Through the above process, this embodiment can systematically construct multiple independent support vector regression models, providing a basis for the final integrated model (identification value analysis model).

[0128] Furthermore, in one embodiment, the identification value analysis method, wherein the step S500, combining all the support vector regression models to generate an identification value analysis model, specifically comprises the steps of:

[0129] Determine the model combination strategy;

[0130] Based on the model combination strategy, all the support vector regression models are combined to generate an identification value analysis model.

[0131] In specific implementation, this embodiment achieves the technical effect of constructing an optimized identification value analysis model from multiple support vector regression models by carefully selecting and implementing a model combination strategy; wherein, the model combination strategy may involve averaging, weighting, or using more complex ensemble learning methods (such as stacking or boosting trees) the prediction results of each support vector regression model to reduce the variance and bias of the identification value analysis model and improve its analysis and prediction accuracy and robustness; through model combination, this embodiment can effectively utilize the advantages of each independent model, reduce the risk of overfitting that may exist in a single model, and can better capture the complex patterns and nonlinear relationships in the data, thereby generating a better performing and more reliable identification value analysis model.

[0132] The specific implementation process of the steps in this embodiment is roughly as follows:

[0133] 1. Evaluate model performance:

[0134] Before determining the model combination strategy, the performance of each independent support vector regression model is first evaluated. Usually, the cross-validation method is used to determine the accuracy and generalization ability of the analysis and prediction of each support vector regression model.

[0135] 2. Select model combination strategy:

[0136] According to the results of model performance evaluation, select an appropriate model combination strategy; common strategies include simple averaging, weighted averaging, stacking, boosting or bagging;

[0137] For example, if the performance of all support vector regression models is similar, a simple average method may be chosen; if the performance of each support vector regression model varies greatly, a weighted average method may be chosen, where the weights are related to the performance of the support vector regression model;

[0138] 3. Implement model combination strategy:

[0139] According to the selected model combination strategy, the prediction results of all support vector regression models are integrated; in the weighted average method, a weight needs to be assigned to each support vector regression model, and then the weighted average prediction result is calculated;

[0140] For stacking, it may be necessary to train a meta-learner to synthesize the predictions of the base learners;

[0141] 4. Training combined model:

[0142] If the model combination strategy requires training (such as a meta-learner in stacking), the predictions of all single models are used as features to train the combined model;

[0143] Adjust the parameters of the combined model and optimize them through the validation set to ensure the optimal performance of the combined model;

[0144] 5. Evaluate the combined model:

[0145] Evaluate the performance of the combined identity value analysis model using a test set or through cross-validation;

[0146] Compare the performance of the combined model with that of the individual models to verify whether the combined strategy improves forecast accuracy and robustness;

[0147] Through the above process, this embodiment can construct an identification value analysis model that integrates the model quantity support vector regression model. The identification value analysis model can more accurately predict the object identification value (such as house rent) and provide more reliable market analysis results.

[0148] Further, in one embodiment, the identification value analysis method, wherein the step S600, performing identification value analysis on the target object based on the identification value analysis model, specifically comprises the steps of:

[0149] Acquire housing information of the target house;

[0150] Inputting the house information into the identification value analysis model to generate an identification value analysis result of the target house;

[0151] The identification value analysis result is output or displayed.

[0152] In specific implementation, the identification value analysis in this embodiment refers to the rental analysis of the target house, that is, this embodiment takes the house information of the target house as input, and uses the trained identification value analysis model for analysis and prediction, thereby achieving accurate estimation of the rent of the target house; this process ensures the automation and efficiency of the rent analysis, and at the same time, by intuitively outputting or displaying the rent analysis results, the comprehensibility and usability of the rent analysis results are enhanced, so that landlords, tenants or investors can quickly obtain decision-making support, thereby making more informed choices in the house rental market; in addition, this embodiment also improves the transparency and consistency of rent analysis and prediction, which helps to improve the overall operational efficiency of the house rental market.

[0153] The specific implementation process of the steps in this embodiment is roughly as follows:

[0154] 1. Data collection:

[0155] Collect and obtain the house information of the target house, including but not limited to the basic information of the house and the surrounding information;

[0156] 2. Data preprocessing:

[0157] Preprocess the acquired housing information, including data cleaning (removing invalid or erroneous data), formatting (ensuring that the data format is consistent with the model input), encoding (converting categorical variables into numerical data), etc.

[0158] 3. Model analysis:

[0159] Input the preprocessed house information into the identification value analysis model; the model will analyze the input data and generate rental analysis results;

[0160] 4. Result output or display:

[0161] Output the rental analysis results generated by the identity value analysis model in an easily understandable format, which can be a numerical prediction, a graphical display, or displayed through the user interface of the application;

[0162] If necessary, explain the results of the rent analysis and provide information about the confidence intervals or forecast uncertainty of the predicted rents;

[0163] Through the above process, this embodiment can ensure that the rental analysis and prediction of the target house are both accurate and easy for users to understand and use.

[0164] It can be seen from the above method embodiments that the identification value analysis method provided by the present invention includes: collecting the original sample set related to the target object to be subjected to identification value analysis, and determining the number of support vector regression models that need to be constructed; for each of the support vector regression models, extracting multiple samples from the original sample set to form a training set corresponding to each of the support vector regression models; for each of the training sets, extracting multiple features from the entire feature set corresponding to the original sample set to form a feature subset corresponding to each of the training sets; based on each of the training sets and the corresponding feature subsets, constructing the support vector regression models of the number of models; combining all of the support vector regression models to generate an identification value analysis model; and performing identification value analysis on the target object based on the identification value analysis model. In this way, the method of the present invention can achieve accurate analysis and prediction of the identification value of the target object by generating an identification value analysis model.

[0165] It can be understood that the identification value analysis method provided in the embodiment of the present invention can be applied to identification value analysis scenarios related to the field of financial technology. Specifically, the identification value analysis function can be integrated into the corresponding credit assessment scenarios of financial institutions (such as banks). When evaluating mortgage or personal loan applications, financial institutions can use the identification value (such as rent) analysis method provided in the embodiment of the present invention to estimate the borrower's repayment ability, thereby reducing the financial risks of financial institutions.

[0166] It should be understood that, although the present application provides method operation steps as described in the embodiments or flowcharts, more or less operation steps may be included based on conventional or non-creative labor, and these operation steps are not necessarily performed in sequence according to the embodiment or flowchart. The order of steps listed in the embodiment or flowchart is only one way of executing the order of many steps, and does not represent the only execution order. It should be noted that there is not necessarily a certain order between the above steps. A person of ordinary skill in the art can understand from the description of the embodiment of the present invention that in different embodiments, the above steps may have different execution orders, that is, they may be executed in parallel, or they may be executed in exchange, etc. Moreover, at least a part of the steps in the embodiment or flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but may be executed in turn, alternately or synchronously with other steps or at least a part of the sub-steps or stages of other steps.

[0167] Based on the above method embodiment, please refer to Figure 3 Another embodiment of the present invention further provides an identification value analysis device, wherein the device comprises:

[0168] The collecting module 11 is used to collect the original sample set related to the target object to be analyzed for identification value, and determine the number of models of the support vector regression model to be constructed;

[0169] A sample extraction module 12 is used to extract a plurality of samples from the original sample set for each support vector regression model to form a training set corresponding to each support vector regression model;

[0170] A feature extraction module 13 is used to extract multiple features from the entire feature set corresponding to the original sample set for each training set to form a feature subset corresponding to each training set;

[0171] A construction module 14, configured to construct the support vector regression model of the model quantity based on each of the training sets and the feature subset corresponding thereto;

[0172] A combination module 15, used to combine all the support vector regression models to generate an identification value analysis model;

[0173] The analysis module 16 is used to perform identification value analysis on the target object based on the identification value analysis model.

[0174] Furthermore, in one embodiment, in the identification value analysis device, the collection module 11 is specifically used for:

[0175] Using a crawler tool to collect basic information of several houses; wherein the basic information includes the house address;

[0176] Based on the house addresses, using a map tool to output the longitude and latitude information of each house;

[0177] Based on the latitude and longitude information, using the map tool to obtain surrounding information within a predetermined range of each of the houses;

[0178] Integrate the surrounding situation information with the basic information to generate an original sample set related to the target house to be analyzed for identification value;

[0179] Determine the number of models you need to build for the Support Vector Regression model.

[0180] Furthermore, in one embodiment, in the identification value analysis device, the sample extraction module 12 is specifically used for:

[0181] Determine the size M of the original sample set; wherein M represents a positive integer;

[0182] For each of the support vector regression models, M samples are randomly extracted with replacement from the original sample set using the bootstrapping method to form a training set corresponding to each of the support vector regression models.

[0183] Furthermore, in one embodiment, in the identification value analysis device, the feature extraction module 13 is specifically used for:

[0184] Determine a feature selection strategy for the original sample set corresponding to the entire feature set;

[0185] For each of the training sets, multiple features are extracted from the entire feature set according to the feature selection strategy to form a feature subset corresponding to each of the training sets.

[0186] Furthermore, in one embodiment, in the identification value analysis device, the construction module 14 is specifically used to:

[0187] Using each of the training sets and the corresponding feature subsets in turn to construct the support vector regression model;

[0188] The support vector regression model construction process is repeatedly executed until the support vector regression model of the model quantity is constructed.

[0189] Furthermore, in one embodiment, in the identification value analysis device, the combination module 15 is specifically used for:

[0190] Determine the model combination strategy;

[0191] Based on the model combination strategy, all the support vector regression models are combined to generate an identification value analysis model.

[0192] Furthermore, in one embodiment, in the identification value analysis device, the analysis module 16 is specifically used to:

[0193] Acquire housing information of the target house;

[0194] Inputting the house information into the identification value analysis model to generate an identification value analysis result of the target house;

[0195] The identification value analysis result is output or displayed.

[0196] It should be noted that in the embodiment of the device of the present invention, the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the aforementioned method embodiment part and will not be repeated here.

[0197] Based on the above method embodiment, another embodiment of the present invention further provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the functions or steps of the identification value analysis method service side in any of the above method embodiments are implemented.

[0198] Based on the above method embodiment, another embodiment of the present invention further provides a computer device, which may be a client, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the functions or steps of the client side of the identification value analysis method in any of the above method embodiments are implemented.

[0199] Those skilled in the art will understand that Figure 4 and Figure 5 The structural schematic diagram shown in the figure is only a schematic diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0200] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, etc.

[0201] Among them, the memory includes a readable storage medium, an internal memory, etc., wherein the internal memory can be the memory of a computer device, and the internal memory provides an environment for the operation of an operating system and computer-readable instructions in the readable storage medium. The readable storage medium can be a hard disk of a computer device, and in other embodiments, it can also be an external storage device of a computer device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on a computer device. Further, the memory can also include both an internal storage unit of a computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of a computer program, etc. The memory can also be used to temporarily store data that has been output or is to be output.

[0202] Based on the above method embodiments, another embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the identification value analysis method in any of the above method embodiments is implemented. The computer-readable storage medium may be non-volatile or volatile.

[0203] It should be noted that the above-mentioned functions or steps that can be implemented by the computer-readable storage medium or computer device, and the technical effects brought about by the functions / steps, can be found in the relevant descriptions in the aforementioned method embodiments. To avoid repetition, they will not be described one by one here.

[0204] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM). The disclosed memory components or memories of the operating environments described herein are intended to comprise one or more of these and / or any other suitable types of memory.

[0205] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, in the embodiment of the device of the present invention, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0206] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0207] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0208] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0209] It should be noted that if software tools or components other than those of the Company appear in the embodiments of the present application, they are only used for illustration and do not represent actual use. The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the above embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for analyzing an identification value, characterized in that: include: Collecting original sample sets related to the target object to be analyzed for identification value, and determining the number of support vector regression models to be constructed; For each of the support vector regression models, extracting multiple samples from the original sample set to form a training set corresponding to each of the support vector regression models; For each of the training sets, multiple features are extracted from the entire feature set corresponding to the original sample set to form a feature subset corresponding to each of the training sets; Based on each of the training sets and the corresponding feature subsets, construct the support vector regression model of the model quantity; Combining all the support vector regression models to generate an identification value analysis model; Based on the identification value analysis model, an identification value analysis is performed on the target object.

2. The identification value analysis method according to claim 1, characterized in that: The target object is a target house, and the collecting of the original sample set related to the target object to be analyzed for identification value, and determining the number of models of the support vector regression model to be constructed, includes: Using a crawler tool to collect basic information of several houses; wherein the basic information includes the house address; Based on the house addresses, using a map tool to output the longitude and latitude information of each house; Based on the latitude and longitude information, using the map tool to obtain surrounding information within a predetermined range of each of the houses; Integrate the surrounding situation information with the basic information to generate an original sample set related to the target house to be analyzed for identification value; Determine the number of models you need to build for the Support Vector Regression model.

3. The identification value analysis method according to claim 1, characterized in that: For each of the support vector regression models, extracting multiple samples from the original sample set to form a training set corresponding to each of the support vector regression models includes: Determine the size M of the original sample set; wherein M represents a positive integer; For each of the support vector regression models, M samples are randomly extracted with replacement from the original sample set using the bootstrapping method to form a training set corresponding to each of the support vector regression models.

4. The identification value analysis method according to claim 1, characterized in that: For each of the training sets, a plurality of features are extracted from the entire feature set corresponding to the original sample set to form a feature subset corresponding to each of the training sets, including: Determine a feature selection strategy for the original sample set corresponding to the entire feature set; For each of the training sets, multiple features are extracted from the entire feature set according to the feature selection strategy to form a feature subset corresponding to each of the training sets.

5. The identification value analysis method according to claim 1, characterized in that: The constructing the support vector regression model of the model quantity based on each of the training sets and the corresponding feature subsets includes: Using each of the training sets and the corresponding feature subsets in turn to construct the support vector regression model; The support vector regression model construction process is repeatedly executed until the support vector regression model of the model quantity is constructed.

6. The identification value analysis method according to claim 1, characterized in that: The step of combining all the support vector regression models to generate an identification value analysis model includes: Determine the model combination strategy; Based on the model combination strategy, all the support vector regression models are combined to generate an identification value analysis model.

7. The identification value analysis method according to any one of claims 2 to 6, characterized in that: The performing identification value analysis on the target object based on the identification value analysis model includes: Acquire housing information of the target house; Inputting the house information into the identification value analysis model to generate an identification value analysis result of the target house; The identification value analysis result is output or displayed.

8. An identification value analysis device, characterized in that: include: A collection module is used to collect original sample sets related to target objects to be analyzed for identification values, and determine the number of models of support vector regression models that need to be constructed; A sample extraction module, used for extracting a plurality of samples from the original sample set for each support vector regression model to form a training set corresponding to each support vector regression model; A feature extraction module, configured to extract, for each of the training sets, a plurality of features from the entire feature set corresponding to the original sample set, to form a feature subset corresponding to each of the training sets; A construction module, used for constructing the support vector regression model of the model quantity based on each of the training sets and the corresponding feature subsets; A combination module, used for combining all the support vector regression models to generate an identification value analysis model; An analysis module is used to perform identification value analysis on the target object based on the identification value analysis model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the identification value analysis method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the identification value analysis method according to any one of claims 1 to 7 is implemented.

Images