CN117474686A - Financial data prediction system based on blockchain and big data - Google Patents
Financial data prediction system based on blockchain and big data Download PDFInfo
- Publication number
- CN117474686A CN117474686A CN202311689321.2A CN202311689321A CN117474686A CN 117474686 A CN117474686 A CN 117474686A CN 202311689321 A CN202311689321 A CN 202311689321A CN 117474686 A CN117474686 A CN 117474686A
- Authority
- CN
- China
- Prior art keywords
- data
- financial
- abnormal
- module
- suspected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 claims description 92
- 238000004364 calculation method Methods 0.000 claims description 34
- 238000000926 separation method Methods 0.000 claims description 25
- 238000013075 data extraction Methods 0.000 claims description 17
- 238000013480 data collection Methods 0.000 claims description 10
- 238000012790 confirmation Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005266 casting Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Computer Security & Cryptography (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Technology Law (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a financial data prediction system based on blockchains and big data, which belongs to the field of data processing systems specially suitable for management purposes.
Description
Technical Field
The invention belongs to the technical field of data processing systems specially suitable for management purposes, and particularly relates to a financial data prediction system based on a blockchain and big data.
Background
In the process of selecting financial products, a purchaser mostly purchases financial products according to the profit situation of the front period of the financial products and the comment situation of the financial products, then the existing false financial products utilize the attention points of the purchaser to perform bill swiping camouflage, the false financial products cannot be predicted in false mode in the prior art, and the user's property loss is caused by blind follow-up of the false financial products by the user, so that the problems exist in the prior art;
for example, in chinese patent with publication number CN111798062B, a financial data prediction system based on blockchain and big data is disclosed, which includes a first data acquisition module, a second data acquisition module, a financial data preprocessing module, a blockchain storage module, a financial data prediction module and a visualization module, where the first data acquisition module is used to acquire historical financial time series data, the second data acquisition module is used to acquire real-time financial time series data, the financial data preprocessing module is used to process the financial data, the blockchain storage module is used to store the processed historical financial time series data, the financial data prediction module is used to predict future trend of current financial data, and the visualization module is used to display prediction result of the financial data prediction module. The invention has the beneficial effects that: the financial data prediction system based on the blockchain and the big data is provided, and the BP neural network is adopted to predict future trend of the financial data, so that the financial market can be known in time;
meanwhile, for example, in chinese patent with application publication number CN115526425a, a financial data prediction system based on blockchain and big data is disclosed, which relates to the blockchain technology and big data technology field, and includes a blockchain center, where the blockchain center is communicatively connected with a transaction module, an encryption module, a financial data prediction module and a service module; the transaction module is used for carrying out transactions between a user and a financial institution and generating financial data and financial data transaction records; the encryption module encrypts a financial data transaction record generated by a transaction; the financial data prediction module predicts the future development trend of financial data of a financial institution; the service module is used for inquiring financial data by a user or a financial institution and obtaining a financial data forecast inquiring result and a financial data transaction record; the user or the financial institution can be ensured to know the future development trend of the financial data of the financial institution more accurately, so that efficient financial data transaction is performed.
The problems proposed in the background art exist in the above patents: in the process of financial product selection, a purchaser mostly purchases financial products according to the profit situation of the front period of the financial products and the comment situation of the financial products, then the traditional false financial products utilize the attention points of the purchaser to conduct bill swiping camouflage, the false financial products cannot be subjected to false prediction in the prior art, and the user can blindly follow the false financial products to cause property loss of the user, so that the financial data prediction system based on block chains and big data is designed for solving the problems.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a financial data prediction system based on blockchain and big data, which is used for collecting financial data of financial products to be purchased through the blockchain and the big data, judging and separating suspected false data in the collected financial data of the financial products, leading the financial data of the separated financial products into a constructed abnormal data judging model to judge the abnormal data, judging threat scenes of the financial products according to the judgment of the abnormal data, predicting threat values of the financial products according to the threat scenes judged by the abnormal data, and broadcasting the abnormal financial products by a financial data prediction broadcasting module, wherein the predicted threat values are larger than or equal to a set threat threshold, thereby improving the accuracy of financial product risk prediction and avoiding the property loss of users caused by blind follow-up casting of the financial products by users.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the utility model provides a financial data prediction system based on blockchain and big data, its includes blockchain financial data collection module, financial data separation module, abnormal data extraction module, abnormal scene judgement module, financial data prediction report module and control module, including blockchain financial data collection module be used for gathering the financial data of the financial product that needs to purchase through blockchain and big data, financial data separation module is used for judging and separating the suspected false data in the financial product financial data of gathering, abnormal data extraction module is used for importing the decision of abnormal data in the financial data judgement model of construction with the financial product financial data of separation, abnormal scene judgement module is used for judging the threat scene of financial product according to the decision of abnormal data, financial data prediction module is used for carrying out threat value prediction to the financial product of the financial product according to the decision of abnormal data, financial data prediction module is used for carrying out abnormal financial product report to the financial product of prediction threat value more than or equal to the threat threshold value that sets for, control module is used for controlling blockchain financial data collection module, financial data separation module, abnormal data judgement module, abnormal data extraction module, prediction module and prediction module.
Specifically, the blockchain financial data acquisition module comprises a financial product average interest rate acquisition unit, a financial product input unit acquisition unit, a financial product unit input amount acquisition unit and a financial product reporting data acquisition unit, wherein the financial product average interest rate acquisition unit is used for acquiring average interest rate data of a financial product in a preset period before selection, the financial product input unit acquisition unit is used for acquiring input unit information of input funds of the financial product, the financial product unit input amount acquisition unit is used for acquiring input amount information of input units of input funds of the financial product, and the financial product comment data acquisition unit is used for acquiring comment data of the financial product.
Specifically, the financial data separation module includes a suspected false data judgment unit and a suspected false data separation unit, the suspected false data judgment unit is used for judging financial suspected false data collected by the blockchain financial data collection module, the suspected false data separation unit is used for separating suspected false data obtained through judgment from residual data, the suspected false data judgment unit includes a suspected false data judgment strategy, and the suspected false data judgment strategy includes the following specific steps:
s11, extracting input unit information of input funds of the financial products and comment data of the financial products, which are acquired by a blockchain financial data acquisition module, wherein the input unit information of the input funds comprises data information of the number of times that the input units are reported due to fraud, and the comment data of the financial products comprises comment pictures and comment text data of the input units;
s12, extracting comment pictures and comment text data of an input unit, respectively importing the comment pictures and the comment text data into a cosine similarity calculation formula to calculate the similarity of the comment picturesComment text similarity->Substituting the data information of the number of times that the input unit is reported due to fraud, the calculated comment picture similarity and comment text similarity into a false information similarity calculation formula to calculate false information similarity, wherein the false information similarity calculation formula is as follows: />Wherein->Data information about the number of times a unit is reported due to fraud is input, < ->For comment picture similarity duty ratio coefficient, +.>The comment text similarity is a ratio coefficient, wherein +_>；
S13, comparing the calculated false information similarity with a set similarity threshold, if the false information similarity is larger than the set similarity threshold, setting an input unit corresponding to the false information as a suspected false unit, setting acquired data of the suspected false unit as suspected false data, and if the false information similarity is smaller than or equal to the set similarity threshold, setting the input unit corresponding to the false information as a normal unit and setting the acquired data of the normal unit as residual data;
it should be noted that at the same time forAnd the value of the similarity threshold, wherein the suspected false units are found out by 300 experts through collecting the collected data of 5000 financial products, then the picture similarity and the text similarity in the suspected false unit comments are calculated and substituted into the data fitting software, so that the ++ # -meeting the accuracy is obtained>And the value of the similarity threshold.
Specifically, the abnormal data extraction module includes an abnormal data judgment model, and the abnormal data judgment model includes the following specific steps:
s21, taking average interest rate data of the collected financial products in a preset period before selection, and simultaneously taking average interest rate data of the same type of products of the financial products in the preset period before selection;
s22, average interest rate data of the financial products in a preset period before selection and average interest rate data of the similar products of the financial products in the preset period before selectionThe average interest rate data is substituted into an average interest rate phase difference value calculation formula to calculate an average interest rate phase difference value, and the average interest rate phase difference value calculation formula is as follows:wherein->For the average interest rate data of the financial products in a predetermined period before selection +.>Average interest rate data in a predetermined period prior to selection for a product of the same type as the financial product;
s23, extracting the number of suspected false data and the number of residual data, and calculating the proportion of the number of suspected false data to the total number of the suspected false data, wherein the calculation formula is as follows:wherein->For suspected false data stripes, +.>The number of the remaining data strips;
s24, judging whether the calculated average interest rate phase difference value is larger than a set average interest rate phase difference value threshold, judging whether the proportion of the calculated suspected false data number to the total number is larger than a set duty ratio threshold, if the calculated average interest rate phase difference value is larger than the set average interest rate phase difference value threshold and/or the proportion of the calculated suspected false data number to the total number is larger than the set duty ratio threshold, setting the financial data of the financial product as abnormal data, otherwise setting the financial data of the financial product as normal data.
Specifically, the specific content for judging the threat scene of the financial product according to the judgment of the abnormal data is as follows: if abnormal data exists in the financial data of the financial product, the financial product is set as a suspected fraud financial product, and if abnormal data does not exist in the financial data of the financial product, the financial product is set as a normal financial product.
Specifically, the financial data prediction module includes a threat value calculation strategy, where the threat value calculation strategy includes the following specific steps:
s31, extracting and calculating to obtain the average interest rate phase value of the suspected fraud financial products and the proportion of the suspected false data pieces to the total pieces;
s32, substituting the extracted data into a threat value calculation formula to calculate a data threat value, wherein the threat value calculation formula is as follows:wherein->For a set average interest rate phase difference value threshold, < ->For a set duty cycle threshold, +.>Is the average interest rate phase difference value duty ratio coefficient, < ->Is a duty ratio of duty ratio>。
Specifically, the financial data prediction broadcasting module comprises an abnormal financial product confirmation unit and an abnormal financial product broadcasting unit, wherein the abnormal financial product confirmation unit is used for setting a financial product with a predicted threat value greater than or equal to a set threat threshold value as an abnormal financial product, and the abnormal financial product broadcasting unit is used for performing acousto-optic broadcasting or short message broadcasting on user selection.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, financial data of financial products to be purchased are acquired through the blockchain and the big data, suspected false data in the acquired financial data of the financial products are judged and separated, the separated financial data of the financial products are imported into a constructed abnormal data judgment model to judge abnormal data, threat scenes of the financial products are judged according to the judgment of the abnormal data, threat value prediction is carried out according to the threat scenes of the financial products judged by the abnormal data, and the financial data prediction broadcast module is used for broadcasting abnormal financial products of the financial products with predicted threat values being greater than or equal to a set threat threshold, so that the accuracy of risk prediction of the financial products is improved, and property loss of users caused by blind follow-up casting of the financial products is avoided.
Drawings
FIG. 1 is a schematic diagram of an overall framework of a financial data prediction system based on blockchain and big data in accordance with the present invention;
FIG. 2 is a block chain financial data collection module frame schematic diagram of a block chain and big data based financial data prediction system of the present invention;
FIG. 3 is a schematic diagram of a financial data separation module framework of a financial data prediction system based on blockchain and big data according to the present invention;
fig. 4 is a schematic diagram of a financial data prediction broadcast module framework of the financial data prediction system based on blockchain and big data.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Example 1
Referring to fig. 1-2, an embodiment of the present invention is provided: the financial data prediction system based on the blockchain and the big data comprises a blockchain financial data acquisition module, a financial data separation module, an abnormal data extraction module, an abnormal scene judgment module, a financial data prediction broadcasting module and a control module, wherein the blockchain financial data acquisition module is used for acquiring financial data of financial products to be purchased through the blockchain and the big data, the financial data separation module is used for judging and separating suspected false data in the acquired financial data of the financial products, the abnormal data extraction module is used for leading the separated financial data of the financial products into a constructed abnormal data judgment model to judge the abnormal data, the abnormal scene judgment module is used for judging threat scenes of the financial products according to the judgment of the abnormal data, the financial data prediction broadcasting module is used for predicting threat values of the financial products judged according to the abnormal data, and the control module is used for controlling the blockchain financial data acquisition module, the financial data separation module, the abnormal data extraction module, the abnormal judgment module, the financial data prediction module and the financial data prediction module to operate;
in this embodiment, the blockchain financial data acquisition module includes a financial product average interest rate acquisition unit, a financial product input unit acquisition unit, a financial product input amount acquisition unit and a financial product report data acquisition unit, wherein the financial product average interest rate acquisition unit is used for acquiring average interest rate data of a financial product in a predetermined period before selection, the financial product input unit acquisition unit is used for acquiring input unit information of input funds of the financial product, the financial product input amount acquisition unit is used for acquiring input amount information of the input unit of the input funds of the financial product, and the financial product comment data acquisition unit is used for acquiring comment data of the financial product;
in this embodiment, the financial data separation module includes a suspected spurious data determination unit and a suspected spurious data separation unit, the suspected spurious data determination unit is configured to determine financial suspected spurious data collected by the blockchain financial data collection module, the suspected spurious data separation unit is configured to separate suspected spurious data obtained by determination from remaining data, the suspected spurious data determination unit includes a suspected spurious data determination policy, and the suspected spurious data determination policy includes the following specific steps:
s11, extracting input unit information of input funds of the financial products and comment data of the financial products, which are acquired by a blockchain financial data acquisition module, wherein the input unit information of the input funds comprises data information of the number of times that the input units are reported due to fraud, and the comment data of the financial products comprises comment pictures and comment text data of the input units;
s12, extracting comment pictures and comment text data of an input unit, respectively importing the comment pictures and the comment text data into a cosine similarity calculation formula to calculate the similarity of the comment picturesComment text similarity->Substituting the data information of the number of times that the input unit is reported due to fraud, the calculated comment picture similarity and comment text similarity into a false information similarity calculation formula to calculate false information similarity, wherein the false information similarity calculation formula is as follows: />Wherein->Data information about the number of times a unit is reported due to fraud is input, < ->For comment picture similarity duty ratio coefficient, +.>The comment text similarity is a ratio coefficient, wherein +_>；
The following is a simple example code for extracting comment pictures and comment text data of an input unit, and importing the comment pictures and the comment text data into a cosine similarity calculation formula to calculate comment picture similarity and comment text similarity:
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#include<math.h>
comment picture data extraction
double* extractImageFeatures(const char* imagePath, int* featureCount) {
Logic for extracting picture features
The method returns a double-precision floating point number array to represent the extracted picture characteristics
The// featureCount variable will hold the number of extracted features
}
Comment text data extraction
char* extractTextFeatures(const char* comment) {
Logic for extracting comment text features
A character array representing the extracted character features is returned
}
Calculating cosine similarity
double cosineSimilarity(const double* features1, const double* features2, int featureCount) {
double dotProduct = 0;
double normFeatures1 = 0;
double normFeatures2 = 0;
for (int i = 0; i<featureCount; i++) {
dotProduct += features1[i] * features2[i];
normFeatures1 += features1[i] * features1[i];
normFeatures2 += features2[i] * features2[i];
}
Calculating cosine similarity
double similarity = dotProduct / (sqrt(normFeatures1) * sqrt(normFeatures2));
return similarity;
}
int main() {
const char* imagePath1 = "./image1.jpg";
const char* imagePath2 = "./image2.jpg";
const char x comment 1= "this is a comment 1";
const char x comment 2= "this is a comment 2";
int featureCount = 0;
double* imageFeatures1 = extractImageFeatures(imagePath1,&featureCount);
double* imageFeatures2 = extractImageFeatures(imagePath2,&featureCount);
char* textFeatures1 = extractTextFeatures(comment1);
char* textFeatures2 = extractTextFeatures(comment2);
double imageSimilarity = cosineSimilarity(imageFeatures1, imageFeatures2, featureCount);
double textSimilarity = cosineSimilarity(textFeatures1, textFeatures2, strlen(textFeatures1));
printf ("comment picture similarity:%. 2f)
", imageSimilarity);
printf ("comment text similarity:%. 2f)
", textSimilarity);
free(imageFeatures1);
free(imageFeatures2);
free(textFeatures1);
free(textFeatures2);
return 0;
}
The xtractviehates () function in the above code is used to extract features from a given image path, which is implemented on its own as required, and likewise, the extratextfeates () function is used to extract features from a given comment. You can implement this function as needed, cosinesimilitude () function is used to calculate cosine similarity between two feature vectors, in main () function we provide two example image paths and comments. Then we call related functions to extract the image and text features. Finally, we use cosine similarity to calculate comment picture similarity and comment text similarity.
Note that this is just a simple example code, lacking error handling and other implementation details that may be required, and that more verification and error handling may be required;
s13, comparing the calculated false information similarity with a set similarity threshold, if the false information similarity is larger than the set similarity threshold, setting an input unit corresponding to the false information as a suspected false unit, setting acquired data of the suspected false unit as suspected false data, and if the false information similarity is smaller than or equal to the set similarity threshold, setting the input unit corresponding to the false information as a normal unit and setting the acquired data of the normal unit as residual data;
it should be noted that at the same time forAnd the value of the similarity threshold, wherein the suspected false units are found out by 300 experts through collecting the collected data of 5000 financial products, then the picture similarity and the text similarity in the suspected false unit comments are calculated and substituted into the data fitting software, so that the ++ # -meeting the accuracy is obtained>And the value of the similarity threshold.
According to the embodiment of the invention, the financial data of the financial product to be purchased is acquired through the blockchain and the big data, and the suspected false data in the acquired financial data of the financial product is judged and separated, so that the accuracy of judging the abnormal financial product is further improved.
Example 2
As shown in fig. 1-4, an embodiment of the present invention provides a financial data prediction system based on blockchain and big data: the financial data prediction system based on the blockchain and the big data comprises a blockchain financial data acquisition module, a financial data separation module, an abnormal data extraction module, an abnormal scene judgment module, a financial data prediction broadcasting module and a control module, wherein the blockchain financial data acquisition module is used for acquiring financial data of financial products to be purchased through the blockchain and the big data, the financial data separation module is used for judging and separating suspected false data in the acquired financial data of the financial products, the abnormal data extraction module is used for leading the separated financial data of the financial products into a constructed abnormal data judgment model to judge the abnormal data, the abnormal scene judgment module is used for judging threat scenes of the financial products according to the judgment of the abnormal data, the financial data prediction broadcasting module is used for predicting threat values of the financial products judged according to the abnormal data, and the control module is used for controlling the blockchain financial data acquisition module, the financial data separation module, the abnormal data extraction module, the abnormal judgment module, the financial data prediction module and the financial data prediction module to operate;
in this embodiment, the blockchain financial data acquisition module includes a financial product average interest rate acquisition unit, a financial product input unit acquisition unit, a financial product input amount acquisition unit and a financial product report data acquisition unit, wherein the financial product average interest rate acquisition unit is used for acquiring average interest rate data of a financial product in a predetermined period before selection, the financial product input unit acquisition unit is used for acquiring input unit information of input funds of the financial product, the financial product input amount acquisition unit is used for acquiring input amount information of the input unit of the input funds of the financial product, and the financial product comment data acquisition unit is used for acquiring comment data of the financial product;
in this embodiment, the financial data separation module includes a suspected spurious data determination unit and a suspected spurious data separation unit, the suspected spurious data determination unit is configured to determine financial suspected spurious data collected by the blockchain financial data collection module, the suspected spurious data separation unit is configured to separate suspected spurious data obtained by determination from remaining data, the suspected spurious data determination unit includes a suspected spurious data determination policy, and the suspected spurious data determination policy includes the following specific steps:
s11, extracting input unit information of input funds of the financial products and comment data of the financial products, which are acquired by a blockchain financial data acquisition module, wherein the input unit information of the input funds comprises data information of the number of times that the input units are reported due to fraud, and the comment data of the financial products comprises comment pictures and comment text data of the input units;
s12, extracting comment pictures and comment text data of an input unit, respectively importing the comment pictures and the comment text data into a cosine similarity calculation formula to calculate the similarity of the comment picturesComment text similarity->Substituting the data information of the number of times that the input unit is reported due to fraud, the calculated comment picture similarity and comment text similarity into a false information similarity calculation formula to calculate false information similarity, wherein the false information similarity calculation formula is as follows: />Wherein->Data information about the number of times a unit is reported due to fraud is input, < ->For comment picture similarity duty ratio coefficient, +.>The comment text similarity is a ratio coefficient, wherein +_>；
S13, comparing the calculated false information similarity with a set similarity threshold, if the false information similarity is larger than the set similarity threshold, setting an input unit corresponding to the false information as a suspected false unit, setting acquired data of the suspected false unit as suspected false data, and if the false information similarity is smaller than or equal to the set similarity threshold, setting the input unit corresponding to the false information as a normal unit and setting the acquired data of the normal unit as residual data;
it should be noted that at the same time forAnd the value of the similarity threshold, wherein the suspected false units are found out by 300 experts through collecting the collected data of 5000 financial products, then the picture similarity and the text similarity in the suspected false unit comments are calculated and substituted into the data fitting software, so that the ++ # -meeting the accuracy is obtained>And the value of the similarity threshold.
In this embodiment, the abnormal data extraction module includes an abnormal data judgment model, and the abnormal data judgment model includes the following specific steps:
s21, taking average interest rate data of the collected financial products in a preset period before selection, and simultaneously taking average interest rate data of the same type of products of the financial products in the preset period before selection;
s22, substituting average interest rate data of the financial products in a preset period before selection and average interest rate data of the similar products of the financial products in the preset period before selection into an average interest rate phase difference value calculation formula to calculate an average interest rate phase difference value, wherein the average interest rate phase difference value calculation formula is as follows:wherein->For the average interest rate data of the financial products in a predetermined period before selection +.>Average interest rate data in a predetermined period prior to selection for a product of the same type as the financial product;
s23, extracting the number of suspected false data and the number of residual data, and calculating the proportion of the number of suspected false data to the total number of the suspected false data, wherein the calculation formula is as follows:wherein->For suspected false data stripes, +.>The number of the remaining data strips;
s24, judging whether the calculated average interest rate phase difference value is larger than a set average interest rate phase difference value threshold, judging whether the proportion of the calculated suspected false data number to the total number is larger than a set duty ratio threshold, if the calculated average interest rate phase difference value is larger than the set average interest rate phase difference value threshold and/or the proportion of the calculated suspected false data number to the total number is larger than the set duty ratio threshold, setting the financial data of the financial product as abnormal data, otherwise setting the financial data of the financial product as normal data.
In this embodiment, the specific content of determining the threat scenario of the financial product according to the determination of the abnormal data is: if abnormal data exists in the financial data of the financial product, the financial product is set as a suspected fraud financial product, and if abnormal data does not exist in the financial data of the financial product, the financial product is set as a normal financial product.
In this embodiment, the financial data prediction module includes a threat value calculation policy, where the threat value calculation policy includes the following specific steps:
s31, extracting and calculating to obtain the average interest rate phase value of the suspected fraud financial products and the proportion of the suspected false data pieces to the total pieces;
s32, substituting the extracted data into a threat value calculation formula to calculate a data threat value, wherein the threat value calculation formula is as follows:wherein->For a set average interest rate phase difference value threshold, < ->For a set duty cycle threshold, +.>Is the average interest rate phase difference value duty ratio coefficient, < ->Is a duty ratio of duty ratio>。
In this embodiment, the financial data prediction broadcast module includes an abnormal financial product confirmation unit and an abnormal financial product broadcast unit, the abnormal financial product confirmation unit is used for setting a financial product with a predicted threat value greater than or equal to a set threat threshold as an abnormal financial product, and the abnormal financial product broadcast unit is used for performing acousto-optic broadcast or short message broadcast on user selection.
Based on the embodiment, the financial data of the financial product to be purchased are collected through the blockchain and the big data, suspected false data in the collected financial data of the financial product are judged and separated, the separated financial data of the financial product is imported into the constructed abnormal data judgment model to judge the abnormal data, the threat scene of the financial product is judged according to the judgment of the abnormal data, threat value prediction is carried out according to the threat scene of the financial product judged by the abnormal data, and the financial data prediction broadcast module is used for broadcasting the abnormal financial product of the financial product with the predicted threat value being greater than or equal to the set threat threshold, so that the accuracy of risk prediction of the financial product is improved, and the property loss of a user caused by blind follow-up casting of the financial product by the user is avoided.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It should be understood that determining B from a does not mean determining B from a alone, but can also determine B from a and/or other information.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by way of wired or/and wireless networks from one website site, computer, server, or data center to another. Computer readable storage media can be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the partitioning of units is merely one way of partitioning, and there may be additional ways of partitioning in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of 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.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (8)
1. The financial data prediction system based on the blockchain and the big data is characterized by comprising a blockchain financial data acquisition module, a financial data separation module, an abnormal data extraction module, an abnormal scene judgment module, a financial data prediction broadcasting module and a control module, wherein the blockchain financial data acquisition module is used for acquiring financial data of financial products to be purchased through the blockchain and the big data, the financial data separation module is used for judging and separating suspected false data in the acquired financial data of the financial products, the abnormal data extraction module is used for leading the separated financial data of the financial products into a constructed abnormal data judgment model to judge the abnormal data, the abnormal scene judgment module is used for judging threat scenes of the financial products according to the judgment of the abnormal data, the financial data prediction module is used for predicting threat scenes of the financial products according to the judgment of the abnormal data, the financial data prediction broadcasting module is used for conducting abnormal financial product prediction on the financial products with predicted threat values being greater than or equal to a set threat threshold, and the control module is used for controlling the blockchain financial data judgment module, the financial data separation module, the financial data extraction module, the abnormal data prediction module and the financial data prediction module.
2. The blockchain and big data based financial data prediction system of claim 1, wherein the blockchain financial data collection module includes a financial product average interest rate collection unit for collecting average interest rate data of a financial product in a predetermined period before selection, a financial product input unit collection unit for collecting input unit information of input funds of the financial product, a financial product input unit collection unit for collecting input amount information of input units of input funds of the financial product, a financial product unit input amount collection unit for collecting comment data of the financial product, and a financial product report data collection unit.
3. The blockchain and big data-based financial data prediction system as in claim 2, wherein the financial data separation module includes a suspected spurious data judgment unit for judging the financial suspected spurious data collected by the blockchain financial data collection module and a suspected spurious data separation unit for separating the suspected spurious data obtained by the judgment from the remaining data, and the suspected spurious data judgment unit includes a suspected spurious data judgment policy.
4. The blockchain and big data based financial data prediction system of claim 3, wherein the suspected spurious data judgment policy comprises the specific steps of:
s11, extracting input unit information of input funds of the financial products and comment data of the financial products, which are acquired by a blockchain financial data acquisition module, wherein the input unit information of the input funds comprises data information of the number of times that the input units are reported due to fraud, and the comment data of the financial products comprises comment pictures and comment text data of the input units;
s12, extracting comment pictures and comment text data of an input unit, respectively importing the comment pictures and the comment text data into a cosine similarity calculation formula to calculate the similarity of the comment picturesComment text similarity->Substituting the data information of the number of times that the input unit is reported due to fraud, the calculated comment picture similarity and comment text similarity into a false information similarity calculation formula to calculate false information similarity, wherein the false information similarity calculation formula is as follows: />Wherein->Data information about the number of times a unit is reported due to fraud is input, < ->For comment picture similarity duty ratio coefficient, +.>The comment text similarity is a ratio coefficient, wherein +_>；
S13, comparing the calculated false information similarity with a set similarity threshold, if the false information similarity is larger than the set similarity threshold, setting an input unit corresponding to the false information as a suspected false unit, setting acquired data of the suspected false unit as suspected false data, and if the false information similarity is smaller than or equal to the set similarity threshold, setting the input unit corresponding to the false information as a normal unit and setting the acquired data of the normal unit as residual data.
5. The blockchain and big data based financial data prediction system of claim 4, wherein the abnormal data extraction module includes an abnormal data judgment model, the abnormal data judgment model includes the following specific steps:
s21, taking average interest rate data of the collected financial products in a preset period before selection, and simultaneously taking average interest rate data of the same type of products of the financial products in the preset period before selection;
s22, substituting average interest rate data of the financial products in a preset period before selection and average interest rate data of the similar products of the financial products in the preset period before selection into an average interest rate phase difference value calculation formula to calculate an average interest rate phase difference value, wherein the average interest rate phase difference value calculation formula is as follows:wherein->For the average interest rate data of the financial products in a predetermined period before selection +.>Average interest rate data in a predetermined period prior to selection for a product of the same type as the financial product;
s23, extracting the number of suspected false data and the number of residual data, and calculating the proportion of the number of suspected false data to the total number of the suspected false data, wherein the calculation formula is as follows:wherein->For suspected false data stripes, +.>The number of the remaining data strips;
s24, judging whether the calculated average interest rate phase difference value is larger than a set average interest rate phase difference value threshold, judging whether the proportion of the calculated suspected false data number to the total number is larger than a set duty ratio threshold, and if the calculated average interest rate phase difference value is larger than the set average interest rate phase difference value threshold and/or the proportion of the calculated suspected false data number to the total number is larger than the set duty ratio threshold, setting the financial data of the financial product as abnormal data, otherwise setting the financial data of the financial product as normal data.
6. The blockchain and big data based financial data prediction system of claim 5, wherein the specific content of determining the threat scene of the financial product according to the determination of the abnormal data is: if abnormal data exists in the financial data of the financial product, the financial product is set as a suspected fraud financial product, and if abnormal data does not exist in the financial data of the financial product, the financial product is set as a normal financial product.
7. The blockchain and big data based financial data prediction system of claim 6, wherein the financial data prediction module includes a threat value calculation strategy, the threat value calculation strategy comprising the following specific steps:
s31, extracting and calculating to obtain the average interest rate phase value of the suspected fraud financial products and the proportion of the suspected false data pieces to the total pieces;
s32, substituting the extracted data into a threat value calculation formula to calculate a data threat value, wherein the threat value calculation formula is as follows:wherein->For a set average interest rate phase difference value threshold, < ->For a set duty cycle threshold, +.>Is the average interest rate phase difference value duty ratio coefficient, < ->Is a duty ratio of duty ratio>。
8. The blockchain and big data based financial data prediction system of claim 7, wherein the financial data prediction broadcasting module includes an abnormal financial product confirmation unit and an abnormal financial product broadcasting unit, the abnormal financial product confirmation unit is used for setting a financial product with a predicted threat value greater than or equal to a set threat threshold as an abnormal financial product, and the abnormal financial product broadcasting unit is used for performing acousto-optic broadcasting or short message broadcasting on user selection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311689321.2A CN117474686B (en) | 2023-12-11 | 2023-12-11 | Financial data prediction system based on blockchain and big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311689321.2A CN117474686B (en) | 2023-12-11 | 2023-12-11 | Financial data prediction system based on blockchain and big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117474686A true CN117474686A (en) | 2024-01-30 |
| CN117474686B CN117474686B (en) | 2024-03-29 |
Family
ID=89633141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311689321.2A Active CN117474686B (en) | 2023-12-11 | 2023-12-11 | Financial data prediction system based on blockchain and big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117474686B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798062A (en) * | 2020-07-08 | 2020-10-20 | 洋浦美诺安电子科技有限责任公司 | Financial data prediction system based on block chain and big data |
| CN111798061A (en) * | 2020-07-08 | 2020-10-20 | 洋浦美诺安电子科技有限责任公司 | Financial data prediction system based on block chain and cloud computing |
| CN112700265A (en) * | 2021-03-23 | 2021-04-23 | 广州格鲁信息技术有限公司 | Anti-fraud system and method based on big data processing |
| CN112966189A (en) * | 2021-04-14 | 2021-06-15 | 刘蒙 | Fund product recommendation system |
| KR20220037597A (en) * | 2020-09-18 | 2022-03-25 | 주식회사 모자이크 | Personalized financial product evaluation system and method |
| KR102384763B1 (en) * | 2021-11-08 | 2022-04-08 | 농업회사법인 주식회사 유비무환 | Based on the user's location information, the system for providing reviews by each region through regional authentication |
| CN116611844A (en) * | 2023-07-21 | 2023-08-18 | 江苏金农股份有限公司 | Local financial consumer equity protection system based on blockchain |
-
2023
- 2023-12-11 CN CN202311689321.2A patent/CN117474686B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798062A (en) * | 2020-07-08 | 2020-10-20 | 洋浦美诺安电子科技有限责任公司 | Financial data prediction system based on block chain and big data |
| CN111798061A (en) * | 2020-07-08 | 2020-10-20 | 洋浦美诺安电子科技有限责任公司 | Financial data prediction system based on block chain and cloud computing |
| KR20220037597A (en) * | 2020-09-18 | 2022-03-25 | 주식회사 모자이크 | Personalized financial product evaluation system and method |
| CN112700265A (en) * | 2021-03-23 | 2021-04-23 | 广州格鲁信息技术有限公司 | Anti-fraud system and method based on big data processing |
| CN112966189A (en) * | 2021-04-14 | 2021-06-15 | 刘蒙 | Fund product recommendation system |
| KR102384763B1 (en) * | 2021-11-08 | 2022-04-08 | 농업회사법인 주식회사 유비무환 | Based on the user's location information, the system for providing reviews by each region through regional authentication |
| CN116611844A (en) * | 2023-07-21 | 2023-08-18 | 江苏金农股份有限公司 | Local financial consumer equity protection system based on blockchain |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117474686B (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647539B (en) | Prediction method and system for vehicle faults | |
| CN108053318B (en) | Method and device for identifying abnormal transactions | |
| CN106952158A (en) | Solve the problems, such as the bookkeeping methods and equipment of focus account | |
| CN110378575B (en) | Overdue event refund collection method and device and computer readable storage medium | |
| CN111325619A (en) | Credit card fraud detection model updating method and device based on joint learning | |
| CN111709756A (en) | Method and device for identifying suspicious communities, storage medium and computer equipment | |
| CN110807699B (en) | Overdue event payment collection method and device and computer readable storage medium | |
| CN115660262B (en) | Engineering intelligent quality inspection method, system and medium based on database application | |
| CN110675078A (en) | Marketing company risk diagnosis method, system, computer terminal and storage medium | |
| CN114372803A (en) | Quick anti-money laundering detection method based on transaction map | |
| CN111062602A (en) | Method, device and storage medium for enterprise credit risk assessment | |
| CN113393316B (en) | Loan overall process accurate wind control and management system based on massive big data and core algorithm | |
| CN117474686B (en) | Financial data prediction system based on blockchain and big data | |
| CA3172392A1 (en) | Systems and methods for anonymizing sensitive data and simulating accelerated schedule parameters using the anonymized data | |
| CN112819476A (en) | Risk identification method and device, nonvolatile storage medium and processor | |
| CN117827593A (en) | Method and system for determining abnormality cause based on abnormality recognition result | |
| CN116703568A (en) | Credit card abnormal transaction identification method and device | |
| Liu et al. | Nft wash trading detection | |
| CN113610633A (en) | Method and device for setting identity verification mode | |
| CN115577888A (en) | Method and device for determining enterprise risk, electronic equipment and storage medium | |
| CN112037049A (en) | Bank card charging method and device | |
| CN112598068A (en) | Loan purpose verification method, device and equipment | |
| CN113837512A (en) | Abnormal user identification method and device | |
| CN111932356A (en) | Method and device for determining credit risk level of enterprise | |
| CN117217900A (en) | Overflow payment risk monitoring method and device based on credit card information big data analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |