Production financial information intelligent service method and system based on block chain

Abstract

The invention discloses a production financial information intelligent service method and system based on a block chain, and relates to the technical field of financial information management. Production financial information service data is collected to construct a sample set, and the production financial information service data in the sample set is preprocessed; classifying the processed production financial information service data through a data classification method, analyzing the classified production financial information service data through a data analysis method after classification is completed, and storing the analyzed production financial information service data; and meanwhile, based on the analyzed production financial information service data, an evaluation system is constructed through an intelligent evaluation method, finally, real-time evaluation is performed on the user based on the established evaluation system, and the financial information service data required by the user is intelligently managed according to an evaluation result, so that the accuracy of financial information service management is improved.

Description

Technical Field

[0001] The present invention relates to the field of financial information management technology, and in particular to a blockchain-based production financial information intelligent service method and system. Background Art

[0002] With the deep integration of blockchain and the real economy, the flow of financial information is becoming more frequent, and the possibility of credit risk and loan fraud is also increasing.

[0003] Existing technology, such as the invention patent application with announcement number: CN114049213A, discloses an information-based financial data analysis system and analysis method, which includes: setting an interactive display interface on the user side to provide users with data display and interaction functions, and setting an intermediate layer data style interface for organizing data, and performing financial data display and analysis. At the same time, a transaction data balancing server is used to perform overall differentiated storage model analysis of transaction data to ensure differentiated storage strategies for some specific blocks, and a transaction data interpolation server is used to perform transaction data interpolation storage. Combined with the transaction data interpolation of the transaction data interpolation server and the count accumulation value of the transaction data balancing server, the information-based analysis of financial data is realized under the conditions of block-based decentralized storage and collaborative management of multiple servers, and differentiated query feedback for different user types is realized.

[0004] From the above solutions, it can be seen that the current information analysis of financial data focuses on user interaction and data display, lacks the mining and analysis of in-depth user information, and has certain limitations. Summary of the Invention

[0005] The purpose of the present invention is to provide a blockchain-based production financial information intelligent service method and system to solve the problems existing in the background technology.

[0006] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a production financial information intelligent service method based on blockchain, which specifically includes the following steps:

[0007] S1. Collect production financial information service data to construct a sample set, and pre-process the production financial information service data in the sample set to obtain processed production financial information service data;

[0008] S2. classifying the processed production financial information service data using a data classification method to obtain classified production financial information service data;

[0009] S3. Analyze the classified production and financial information service data using a data analysis method, and save the analyzed production and financial information service data;

[0010] S4. Based on the analyzed production and financial information service data, an evaluation system is constructed through intelligent evaluation methods;

[0011] S5. Collect the financial information service data required by users in real time, conduct real-time evaluation of users based on the established evaluation system, and intelligently manage the financial information service data required by users based on the evaluation results.

[0012] Preferably, the steps of collecting production finance information service data to construct a sample set, and preprocessing the production finance information service data in the sample set to obtain the processed production finance information service data include the following steps:

[0013] S11. Collect production financial information service data to build a sample set;

[0014] Assume that the production financial information service data is S = {s1,s2,s3,s4,...,s n};

[0015] Among them, s n represents the nth item of production financial information service data, S is the set of production financial information service data;

[0016] Each item of production financial information service data includes: historical debt repayment data, historical operating data, historical profit data, and historical contract performance data;

[0017] The production financial information service data subset is H = {h1, h2, h3, h4, h5};

[0018] Among them, H is the subset of production financial information service data, h1 represents historical debt repayment data, h2 represents historical operating data, h3 represents historical profit data, and h4 represents historical performance data;

[0019] S12. Preprocess the production financial information service data in the sample set.

[0020] Preferably, the pre-processing of the production financial information service data in the sample set includes the following steps:

[0021] S121. Process missing data in the sample set to obtain filtered production and financial information service data;

[0022] The production financial information service data must include: historical debt repayment data, historical operating data, historical profit data, and historical contract performance data;

[0023] In the event that there are missing production and financial information service data, the missing production and financial information service data will be deleted;

[0024] S122. Smoothing the filtered production financial information service data to obtain processed production financial information service data;

[0025] The collected production financial information service data are divided into production financial information service observation data and production financial information service real data;

[0026] The relationship between the collected production financial information service observation data and the production financial information service real data is as follows:

[0027] g t =x t +ε t ; (1)

[0028] Among them, g t Expressed as the real value of production financial information services at time t, x t Expressed as the observed value of production financial information services at time t, ε t It is represented as the noise at time t, where the noise is the abnormal value that deviates from the normal data range;

[0029] In order to reduce the impact of noise, the production and financial information service observations at adjacent moments are added and averaged. The formula is as follows:

[0030]

[0031] Among them, q t Expressed as the filtering result at time t, x t-i represents the production financial information service observation value at time ti, x t+i represents the production financial information service observation value at time t+i, and n represents the sliding window radius;

[0032] Substituting formula (1) into formula (2) yields:

[0033]

[0034] Among them, g t-i represents the actual value of production financial information services at time ti, ε t-i represents the noise at time ti, ε t+i represents the noise at time t+i, g t+i represents the actual value of production financial information services at time t+i;

[0035] Setting the mean of the noise to 0, we can get:

[0036]

[0037] The calculated true value is used as the true value of production financial information service at time t;

[0038] The calculated true value of the production financial information service is set to the processed production financial information service data.

[0039] Preferably, the processing of the production finance information service data by classifying the data using a data classification method to obtain the classified production finance information service data comprises the following steps:

[0040] S21. constructing a decision tree based on the processed production and financial information service data;

[0041] Constructing a decision tree based on the processed production financial information service data includes the following steps:

[0042] S211. Randomly select Q samples with replacement from the processed production financial information service data in the training set, and build a decision tree based on the selected Q samples. Set the selected Q samples as the samples at the root node of the decision tree.

[0043] S212. When each sample has Z attributes, when each node of the decision tree needs to be classified, randomly select one attribute from the Z attributes, then set a range threshold for the selected attribute, and use the set range threshold as the classification attribute of the node;

[0044] Set each classification attribute to be selected only once, and each classification will only generate two nodes;

[0045] S213, classifying each node in the decision tree according to step S212 until the sample cannot be classified any further, and constructing a decision tree based on the classified nodes;

[0046] S22. Construct a random forest based on the constructed decision tree;

[0047] S23. Summarize the processed production and financial information service data in each classification of the random forest to obtain classified production and financial information service data.

[0048] Preferably, constructing a random forest based on the constructed decision tree comprises the following steps:

[0049] Set the number of decision trees to be constructed, and construct the required number of decision trees according to steps S211-S213;

[0050] Summarize the constructed decision trees and construct a random forest. Set the constructed random forest as a data set, and each decision tree as a set of data in the data set.

[0051] Summarize the classification results of each decision tree in the random forest, merge the same results, and use the classification attribute as the cluster center of the current classification result;

[0052] Output the summarized cluster centers of each category and the processed production and financial information service data in each category and save them.

[0053] Preferably, the analyzing the classified production finance information service data by a data analysis method and saving the analyzed production finance information service data comprises the following steps:

[0054] Set the sample set to {(x1,y1),(x2,y2),...,(x i ,y i )},x i ∈R d ,y i ∈{+1,-1};

[0055] Among them, x i Represents all indicators of the i-th sample, y i Indicates the risk level of the i-th sample, low risk is 1, and high risk is -1;

[0056] The objective function of the support vector machine algorithm is as follows:

[0057]

[0058] Among them, λ i ,λ j is the Lagrange multiplier factor, λ i ,λ j ≥0, i, j=1,2,3...,n, φ represents the mapping relationship, y j represents the jth sample, st represents the restriction;

[0059] The mathematical expression of the support vector machine algorithm is as follows:

[0060]

[0061] Among them, w represents the weight, b represents the bias value, φ(c) represents a nonlinear mapping from low-dimensional to high-dimensional space, f(x i ,y i ) represents the sample (x i ,y i ), K(x i ,y i ) represents the kernel function;

[0062] The support vector machine algorithm is used to predict and distinguish high-risk samples in production financial information service data.

[0063] Preferably, the construction of an evaluation system based on the analyzed production financial information service data by an intelligent evaluation method comprises the following steps:

[0064] S41. Summarize the analyzed production and financial information service data, collect expert ratings of the analyzed production and financial information service data, and calculate the subjective ratings of the analyzed production and financial information service data;

[0065] The subjective rating calculation formula is as follows:

[0066]

[0067] in, represents the subjective score of the production and financial information service data after analysis, a t represents the scoring data of the t-th expert, T represents the number of experts, h c represents the cth item in the production financial information service data subset, ω c Indicates the weight of the corresponding data;

[0068] S42. Construct an evaluation system based on the subjective scores of the analyzed production and financial information service data.

[0069] Preferably, the subjective scoring of the analyzed production financial information service data is used to construct an evaluation system, which includes the following steps:

[0070] The correlation of expert rating data is calculated based on the Pearson correlation coefficient. The calculation formula is as follows:

[0071]

[0072] Among them, cov(X,Y) represents the covariance between expert X's scoring data and expert Y's scoring data, σ X represents the standard deviation of expert X's scoring data, σ Y represents the standard deviation of expert Y's rating data, ρ X,Y Represents the correlation between expert X's scoring data and expert Y's scoring data;

[0073] The calculation formula of the evaluation system is as follows:

[0074]

[0075] in, Indicates the constructed evaluation system.

[0076] Preferably, the real-time collection of financial information service data required by users, real-time evaluation of users based on an evaluation system, and intelligent management of the financial information service data required by users based on the evaluation results include the following steps:

[0077] An evaluation threshold is set. When the real-time evaluation result of the user's financial information service data is lower than the set evaluation threshold, the financial information service data required by the user will not be approved. When the real-time evaluation result of the user's financial information service data is higher than the set evaluation threshold, the financial information service data required by the user will be approved.

[0078] The present invention discloses a production financial information intelligent service system based on blockchain, which is used to implement a production financial information intelligent service method based on blockchain. The system includes: a data acquisition module, a data processing module, a data analysis module, an evaluation module and a management module;

[0079] The data acquisition module is used to collect production financial information service data in real time;

[0080] The data processing module is used to process the production financial information service data collected in real time to obtain the processed production financial information service data;

[0081] The data analysis module is used to analyze the processed production financial information service data to obtain analyzed production financial information service data;

[0082] The evaluation module is used to construct an evaluation system and score the analyzed production and financial information service data based on the constructed evaluation system;

[0083] The management module is used to manage the financial information service data required by the user according to the scoring results.

[0084] The beneficial effects of the present invention are:

[0085] (1) The present invention constructs a sample set by collecting production financial information service data, pre-processes the production financial information service data in the sample set, and classifies the processed production financial information service data through a data classification method. After the classification is completed, the classified production financial information service data is analyzed through a data analysis method, and the analyzed production financial information service data is saved; at the same time, based on the analyzed production financial information service data, an evaluation system is constructed through an intelligent evaluation method, and finally, users are evaluated in real time based on the constructed evaluation system, and the financial information service data required by users are intelligently managed according to the evaluation results, thereby improving the accuracy of financial information service management.

[0086] (2) The present invention constructs a sample set by collecting production financial information service data, and at the same time improves the accuracy of production financial information service data processing by processing missing data in the sample set and obtaining processed production financial information service data through data smoothing.

[0087] (3) The present invention constructs a random forest by building multiple decision trees, and classifies the processed production financial information service data based on the constructed random forest, thereby improving the rationality of the classification of the production financial information service data.

[0088] (4) The present invention completes the prediction and analysis of production financial information service data by setting the sample set and the support vector machine objective function, and distinguishes high-risk samples in the production financial information service data based on the analysis results of the support vector machine, thereby improving the reliability of the analysis of the production financial information service data.

[0089] (5) The present invention summarizes and analyzes the production finance information service data, collects experts' scores on the analyzed production finance information service data, and constructs an evaluation system by calculating the correlation of the expert score data, thereby improving the rationality of the evaluation system construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0091] Figure 1 This is a flow chart of the production financial information intelligent service method of the blockchain of the present invention. DETAILED DESCRIPTION

[0092] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0093] In a specific embodiment of the present invention,

[0094] Reference Figure 1 As shown, the present invention provides a production financial information intelligent service method based on blockchain, comprising the following steps:

[0095] S1. Collect production financial information service data to construct a sample set, and pre-process the production financial information service data in the sample set to obtain processed production financial information service data;

[0096] S2. classifying the processed production financial information service data using a data classification method to obtain classified production financial information service data;

[0097] S3. Analyze the classified production and financial information service data using a data analysis method, and save the analyzed production and financial information service data;

[0098] S4. Based on the analyzed production and financial information service data, an evaluation system is constructed through intelligent evaluation methods;

[0099] S5. Collect the financial information service data required by users in real time, evaluate users in real time based on the established evaluation system, and intelligently manage the financial information service data required by users based on the evaluation results;

[0100] Further, refer to Figure 1 As shown, collecting production financial information service data to construct a sample set, and preprocessing the production financial information service data in the sample set to obtain the processed production financial information service data includes the following steps:

[0101] S11. Collect production financial information service data to build a sample set;

[0102] Assume that the production financial information service data is S = {s1,s2,s3,s4,...,s n};

[0103] Among them, s n represents the nth item of production financial information service data, S is the set of production financial information service data;

[0104] Each item of production financial information service data includes: historical debt repayment data, historical operating data, historical profit data, and historical contract performance data;

[0105] The production financial information service data subset is H = {h1, h2, h3, h4, h5};

[0106] Among them, H is the subset of production financial information service data, h1 represents historical debt repayment data, h2 represents historical operating data, h3 represents historical profit data, and h4 represents historical performance data;

[0107] S12. Preprocessing the production financial information service data in the sample set;

[0108] S121. Process missing data in the sample set to obtain filtered production and financial information service data;

[0109] The production financial information service data must include: historical debt repayment data, historical operating data, historical profit data, and historical contract performance data;

[0110] In the event that there are missing production and financial information service data, the missing production and financial information service data will be deleted;

[0111] S122. Smoothing the filtered production financial information service data to obtain processed production financial information service data;

[0112] The collected production financial information service data are divided into production financial information service observation data and production financial information service real data;

[0113] The relationship between the collected production financial information service observation data and the production financial information service real data is as follows:

[0114] g t =x t +ε t ; (1)

[0115] Among them, g t Expressed as the real value of production financial information services at time t, x t Expressed as the observed value of production financial information services at time t, ε t It is represented as the noise at time t, where the noise is the abnormal value that deviates from the normal data range;

[0116] In order to reduce the impact of noise, the production and financial information service observations at adjacent moments are added and averaged. The formula is as follows:

[0117]

[0118] Among them, q t Expressed as the filtering result at time t, x t-i represents the production financial information service observation value at time ti, x t+i represents the production financial information service observation value at time t+i, and n represents the sliding window radius;

[0119] Substituting formula (1) into formula (2) yields:

[0120]

[0121] Among them, g t-i represents the actual value of production financial information services at time ti, ε t-i represents the noise at time ti, ε t+i represents the noise at time t+i, g t+i represents the actual value of production financial information services at time t+i;

[0122] Setting the mean of the noise to 0, we can get:

[0123]

[0124] The calculated true value is used as the true value of production financial information service at time t;

[0125] Furthermore, the calculated true value of the production financial information service is set as the processed production financial information service data;

[0126] Further, refer to Figure 1 As shown, classifying the processed production financial information service data by a data classification method to obtain the classified production financial information service data includes the following steps:

[0127] The processed production and financial information service data are aggregated to construct a training set, and each set of processed production and financial information service data is used as a set of samples in the training set;

[0128] S21. constructing a decision tree based on the processed production and financial information service data;

[0129] Constructing a decision tree based on the processed production financial information service data includes the following steps:

[0130] S211. Randomly select Q samples with replacement from the processed production financial information service data in the training set, and build a decision tree based on the selected Q samples. Set the selected Q samples as the samples at the root node of the decision tree.

[0131] S212. When each sample has Z attributes, when each node of the decision tree needs to be classified, randomly select one attribute from the Z attributes, then set a range threshold for the selected attribute, and use the set range threshold as the classification attribute of the node;

[0132] Set each classification attribute to be selected only once, and each classification will only generate two nodes;

[0133] S213, classifying each node in the decision tree according to step S212 until the sample cannot be classified any further, and constructing a decision tree based on the classified nodes;

[0134] S22. Construct a random forest based on the constructed decision tree.

[0135] Set the number of decision trees to be constructed, and construct the required number of decision trees according to steps S211-S213;

[0136] Summarize the constructed decision trees and construct a random forest. Set the constructed random forest as a data set, and each decision tree as a set of data in the data set.

[0137] Summarize the classification results of each decision tree in the random forest, merge the same results, and use the classification attribute as the cluster center of the current classification result;

[0138] Output the aggregated cluster centers of each category and the processed production and financial information service data in each category, and save them;

[0139] S23. Summarize the processed production and financial information service data in each classification of the random forest to obtain classified production and financial information service data;

[0140] Further, refer to Figure 1 As shown, analyzing the classified production financial information service data by a data analysis method and saving the analyzed production financial information service data includes the following steps:

[0141] Set the sample set to {(x1,y1),(x2,y2),...,(x i ,y i )},x i ∈R d ,y i ∈{+1,-1};

[0142] Among them, x i Represents all indicators of the i-th sample, y i Indicates the risk level of the i-th sample, low risk is 1, and high risk is -1;

[0143] The objective function of the support vector machine algorithm is as follows:

[0144]

[0145] Among them, λ i ,λ j is the Lagrange multiplier factor, λ i ,λ j ≥0, i, j=1,2,3...,n, φ represents the mapping relationship, y j represents the jth sample, st represents the restriction;

[0146] The mathematical expression of the support vector machine algorithm is as follows:

[0147]

[0148] Among them, w represents the weight, b represents the bias value, φ(c) represents a nonlinear mapping from low-dimensional to high-dimensional space, f(x i ,y i ) represents the sample (x i ,y i ), K(xi ,y i ) represents the kernel function;

[0149] Furthermore, the support vector machine algorithm is used to predict and distinguish high-risk samples in production financial information service data;

[0150] Further, refer to Figure 1 As shown in the figure, based on the analyzed production and financial information service data, the evaluation system is constructed through the intelligent evaluation method, which includes the following steps:

[0151] S41. Summarize the analyzed production and financial information service data, collect expert ratings of the analyzed production and financial information service data, and calculate the subjective ratings of the analyzed production and financial information service data;

[0152] The subjective rating calculation formula is as follows:

[0153]

[0154] in, represents the subjective score of the production and financial information service data after analysis, a t represents the scoring data of the t-th expert, T represents the number of experts, h c represents the cth item in the production financial information service data subset, ω c Indicates the weight of the corresponding data;

[0155] S42. Construct an evaluation system based on the subjective scores of the analyzed production and financial information service data;

[0156] The correlation of expert rating data is calculated based on the Pearson correlation coefficient. The calculation formula is as follows:

[0157]

[0158] Among them, cov(X,Y) represents the covariance between expert X's scoring data and expert Y's scoring data, σ X represents the standard deviation of expert X's scoring data, σ Y represents the standard deviation of expert Y's rating data, ρ X,Y Represents the correlation between expert X's scoring data and expert Y's scoring data;

[0159] The calculation formula of the evaluation system is as follows:

[0160]

[0161] in, Indicates the constructed evaluation system;

[0162] Further, refer to Figure 1 As shown, real-time collection of financial information service data required by users, real-time evaluation of users based on an evaluation system, and intelligent management of the financial information service data required by users based on the evaluation results include the following steps:

[0163] Setting an evaluation threshold. When the real-time evaluation result of the user's financial information service data is lower than the set evaluation threshold, the financial information service data requested by the user will be rejected. When the real-time evaluation result of the user's financial information service data is higher than the set evaluation threshold, the financial information service data requested by the user will be approved.

[0164] In a specific embodiment, the blockchain-based production financial information intelligent service system is used to implement a blockchain-based production financial information intelligent service method, and the system includes: a data acquisition module, a data processing module, a data analysis module, an evaluation module, and a management module;

[0165] The data acquisition module is used to collect production financial information service data in real time;

[0166] The data processing module is used to process the production financial information service data collected in real time to obtain the processed production financial information service data;

[0167] The data analysis module is used to analyze the processed production financial information service data to obtain analyzed production financial information service data;

[0168] The evaluation module is used to construct an evaluation system and score the analyzed production and financial information service data based on the constructed evaluation system;

[0169] The management module is used to manage the financial information service data required by the user according to the scoring results.

[0170] It should be noted that

[0171] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A production financial information intelligent service method based on blockchain, characterized in that: The following steps are involved: S1. Collect production financial information service data to construct a sample set, and pre-process the production financial information service data in the sample set to obtain processed production financial information service data; S2. classifying the processed production financial information service data using a data classification method to obtain classified production financial information service data; S3. Analyze the classified production and financial information service data using a data analysis method, and save the analyzed production and financial information service data; S4. Based on the analyzed production and financial information service data, an evaluation system is constructed through intelligent evaluation methods; S5. Collect the financial information service data required by users in real time, conduct real-time evaluation of users based on the established evaluation system, and intelligently manage the financial information service data required by users based on the evaluation results.

2. A blockchain-based production financial information intelligent service method according to claim 1, characterized in that: The collecting of production finance information service data to construct a sample set, and preprocessing the production finance information service data in the sample set to obtain the processed production finance information service data includes the following steps: S11. Collect production financial information service data to build a sample set; Assume that the production financial information service data is S = {s1,s2,s3,s4,...,s n }; Among them, s n represents the nth item of production financial information service data, S is the set of production financial information service data; Each item of production financial information service data includes: historical debt repayment data, historical operating data, historical profit data, and historical contract performance data; The production financial information service data subset is H = {h1, h2, h3, h4, h5}; Among them, H is the subset of production financial information service data, h1 represents historical debt repayment data, h2 represents historical operating data, h3 represents historical profit data, and h4 represents historical performance data; S12. Preprocess the production financial information service data in the sample set.

3. The blockchain-based production financial information intelligent service method according to claim 2 is characterized in that: The preprocessing of the production financial information service data in the sample set includes the following steps: S121. Process missing data in the sample set to obtain filtered production and financial information service data; The production financial information service data must include: historical debt repayment data, historical operating data, historical profit data, and historical contract performance data; In the event that there are missing production and financial information service data, the missing production and financial information service data will be deleted; S122. Smoothing the filtered production financial information service data to obtain processed production financial information service data; The collected production financial information service data are divided into production financial information service observation data and production financial information service real data; The relationship between the collected production financial information service observation data and the production financial information service real data is as follows: g t =x t +e t (1) Among them, g t Expressed as the real value of production financial information services at time t, x t Expressed as the observed value of production financial information services at time t, ε t It is represented as the noise at time t, where the noise is the abnormal value that deviates from the normal data range; In order to reduce the impact of noise, the production and financial information service observations at adjacent moments are added and averaged. The formula is as follows: Among them, q t Expressed as the filtering result at time t, x t-i represents the production financial information service observation value at time ti, x t+i represents the production financial information service observation value at time t+i, and n represents the sliding window radius; Substituting formula (1) into formula (2) yields: Among them, g t-i represents the actual value of production financial information services at time ti, ε t-i represents the noise at time ti, ε t+i represents the noise at time t+i, g t+i represents the actual value of production financial information services at time t+i; Setting the mean of the noise to 0, we can get: The calculated true value is used as the true value of production financial information service at time t; The calculated true value of the production financial information service is set to the processed production financial information service data.

4. The blockchain-based production financial information intelligent service method according to claim 1 is characterized in that: The processing of the production finance information service data by the data classification method to obtain the classified production finance information service data includes the following steps: S21. constructing a decision tree based on the processed production and financial information service data; Constructing a decision tree based on the processed production financial information service data includes the following steps: S211. Randomly select Q samples with replacement from the processed production financial information service data in the training set, and build a decision tree based on the selected Q samples. Set the selected Q samples as the samples at the root node of the decision tree. S212. When each sample has Z attributes, when each node of the decision tree needs to be classified, randomly select one attribute from the Z attributes, then set a range threshold for the selected attribute, and use the set range threshold as the classification attribute of the node; Set each classification attribute to be selected only once, and each classification will only generate two nodes; S213, classifying each node in the decision tree according to step S212 until the sample cannot be classified any further, and constructing a decision tree based on the classified nodes; S22. Construct a random forest based on the constructed decision tree; S23. Summarize the processed production and financial information service data in each classification of the random forest to obtain classified production and financial information service data.

5. The blockchain-based production financial information intelligent service method according to claim 4 is characterized in that: The random forest construction based on the constructed decision tree comprises the following steps: Set the number of decision trees to be constructed, and construct the required number of decision trees according to steps S211-S213; Summarize the constructed decision trees and construct a random forest. Set the constructed random forest as a data set, and each decision tree as a set of data in the data set. Summarize the classification results of each decision tree in the random forest, merge the same results, and use the classification attribute as the cluster center of the current classification result; Output the summarized cluster centers of each category and the processed production and financial information service data in each category and save them.

6. The blockchain-based production financial information intelligent service method according to claim 1 is characterized in that: The method of analyzing the classified production finance information service data by the data analysis method and saving the analyzed production finance information service data includes the following steps: Set the sample set to {(x1,y1),(x2,y2),...,(x i ,y i )},x i ∈R d ,y i ∈{+1,-1}; Among them, x i Represents all indicators of the i-th sample, y i Indicates the risk level of the i-th sample, low risk is 1, and high risk is -1; The objective function of the support vector machine algorithm is as follows: Among them, λ i ,λ j is the Lagrange multiplier factor, λ i ,λ j ≥0, i, j=1,2,3...,n, φ represents the mapping relationship, y j represents the jth sample, st represents the restriction; The mathematical expression of the support vector machine algorithm is as follows: Among them, w represents the weight, b represents the bias value, φ(c) represents a nonlinear mapping from low-dimensional to high-dimensional space, f(x i ,y i ) represents the sample (x i ,y i ), K(x i ,y i ) represents the kernel function; The support vector machine algorithm is used to predict and distinguish high-risk samples in production financial information service data.

7. The blockchain-based production financial information intelligent service method according to claim 1 is characterized in that: The evaluation system constructed by the intelligent evaluation method based on the analyzed production financial information service data includes the following steps: S41. Summarize the analyzed production and financial information service data, collect expert ratings of the analyzed production and financial information service data, and calculate the subjective ratings of the analyzed production and financial information service data; The subjective rating calculation formula is as follows: in, represents the subjective score of the production and financial information service data after analysis, a t represents the scoring data of the t-th expert, T represents the number of experts, h c represents the cth item in the production financial information service data subset, ω c Indicates the weight of the corresponding data; S42. Construct an evaluation system based on the subjective scores of the analyzed production and financial information service data.

8. The blockchain-based production financial information intelligent service method according to claim 1 is characterized in that: The evaluation system is constructed based on the subjective scoring of the analyzed production and financial information service data, and includes the following steps: The correlation of expert rating data is calculated based on the Pearson correlation coefficient. The calculation formula is as follows: Among them, cov(X,Y) represents the covariance between expert X's scoring data and expert Y's scoring data, σ X represents the standard deviation of expert X's scoring data, σ Y represents the standard deviation of expert Y's rating data, ρ X,Y Represents the correlation between expert X's scoring data and expert Y's scoring data; The calculation formula of the evaluation system is as follows: in, Indicates the constructed evaluation system.

9. The blockchain-based production financial information intelligent service method according to claim 1 is characterized in that: The real-time collection of financial information service data required by users, real-time evaluation of users based on the evaluation system, and intelligent management of the financial information service data required by users according to the evaluation results include the following steps: An evaluation threshold is set. When the real-time evaluation result of the user's financial information service data is lower than the set evaluation threshold, the financial information service data required by the user will not be approved. When the real-time evaluation result of the user's financial information service data is higher than the set evaluation threshold, the financial information service data required by the user will be approved.

10. A system for implementing the blockchain-based production financial information intelligent service method according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, data processing module, data analysis module, evaluation module and management module; The data acquisition module is used to collect production financial information service data in real time; The data processing module is used to process the production financial information service data collected in real time to obtain the processed production financial information service data; The data analysis module is used to analyze the processed production financial information service data to obtain analyzed production financial information service data; The evaluation module is used to construct an evaluation system and score the analyzed production and financial information service data based on the constructed evaluation system; The management module is used to manage the financial information service data required by the user according to the scoring results.

Images