Financial risk control method and system based on big data

Abstract

The present invention discloses a financial risk control method and system based on big data, including an information collection unit, a data identification unit, an adaptive processing unit and an information output unit. The present invention relates to the technical field of financial risk control of big data, and solves the technical problem that the risk of an interactive platform cannot be well monitored, and different protections and early warnings cannot be performed according to different types of user data. The present invention classifies the transaction data of users and the transaction platforms, classifies the transaction data into public data and private data according to the user's tags, monitors the transaction platforms at the same time, encrypts and protects the risky transaction platforms during data interaction, and issues early warnings and encryption protection to normal platforms, thereby ensuring the security of user transaction data, and further monitors the transaction platforms to give reminders and early warnings to users.

Description

Technical Field

[0001] The present invention relates to the technical field of financial risk control based on big data, and specifically to a financial risk control method and system based on big data. Background Art

[0002] Financial data refers to market data, company data, industry indexes and pricing data involved in the financial industry. All data related to the financial industry can be included in the financial market big data system to provide a reference for practitioners to conduct market analysis. There are many academic definitions. For example, the price data of a certain stock over a period of time arranged in a given time sequence can be called a financial time series data.

[0003] According to the patent application number CN202210495736.5, the patent includes real-time acquisition of the current financial data image uploaded through each preset data transmission port, generation of a background rendering data image, and generation of an encrypted specific label, wherein the encrypted specific label corresponds to the background rendering data image one by one; and obtaining the current financial text data after the text data extraction is completed; based on the preset big data information storage module, the current electronic financial data matching the current financial data image is retrieved, the current financial text data is compared with the current electronic financial data, and a financial data storage risk control indication is generated after the comparison is completed. The present invention improves the reliability and ease of use of paper documents for preserving financial data, so as to provide a data basis for realizing efficient financial data risk control.

[0004] During the use of some existing financial risk control systems, some data are interacting. Due to security risks in the interactive platforms, risk monitoring of the interactive platforms cannot be performed, resulting in security impacts on the interactive data. Secondly, due to personal habits, data will be classified, and the necessity of protecting different data is even more important. However, some systems cannot distinguish between them when in use, resulting in data leakage during the data interaction process, which will further cause losses to the users' personal interests. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a financial risk control method and system based on big data, which solves the problems of not being able to monitor risks on the interactive platform well and not being able to provide different protections and warnings based on different types of user data.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a financial risk control system based on big data, comprising:

[0007] The information collection unit is used to obtain basic information of the target object, wherein the target object includes: transaction data, and the basic information includes: transaction data type, transaction platform, transaction number and transaction duration. It should be noted here that the transaction duration represents the real-time transaction duration, and transmit the obtained basic information of the target object to the data identification unit;

[0008] A data identification unit is used to obtain basic information of the target object to be transmitted, and to identify the transaction data type and transaction platform in the basic information, to classify the transaction data into public transaction data and private transaction data by identifying characteristic signals of the transaction data, and to integrate the two to generate data classification information, to classify the transaction platform into a normal transaction platform and a risky transaction platform by detecting the risk of the transaction platform, and to integrate the two to generate platform classification information, and to transmit the identified data classification information and platform classification information to the adaptive processing unit;

[0009] The adaptive processing unit is used to obtain the transmitted data classification information and the transaction platform classification information, and analyze the target objects corresponding to the normal transaction platform and the risky transaction platform respectively. First, the risky transaction platform is analyzed as the target object, and then the public data and the private data are processed according to the target docking data classification information to obtain the processing results, which include: risk signals, normal signals and reorganized data, and the processing results are transmitted to the information output unit;

[0010] Then, when it is determined that the transaction platform classification information is a normal transaction platform, the acquired data classification information is analyzed, and the corresponding risk information, normal information and encrypted information are generated by the analysis, and transmitted to the information output unit.

[0011] As a further solution of the present invention: the data identification unit specifically identifies the data type and the trading platform as follows:

[0012] Obtain the transmitted transaction data and determine whether there is a user tag. If there is a user tag, mark the corresponding transaction data as private data. Otherwise, if there is no user tag, mark the corresponding transaction data as public data.

[0013] The specific method of trading platform identification is: obtain the trading platform of the target object and the prompt information of the trading platform at the same time. Then the system obtains the reminder information and identifies it, and classifies the trading platform according to the identified content. If the identified content contains risks, the corresponding trading platform will be classified as a risky platform. Conversely, if the identified content does not contain risks, the corresponding trading platform will be classified as a normal platform.

[0014] As a further solution of the present invention: when the adaptive processing unit determines that it is a risk trading platform, the specific processing method for public data is as follows:

[0015] S1: When the target object is public data, the system obtains the transaction duration, divides the transaction duration into valid transaction duration and invalid transaction duration, and then calculates the invalid value of the public data according to the divided valid transaction duration and invalid transaction duration. The specific calculation method is as follows:

[0016] S11: Denote the transaction duration as T, obtain the transaction duration with operations at the current time node as the valid transaction duration and denote it as Ty, and vice versa, the transaction duration without operations is denoted as the invalid operation duration and denoted as Tw;

[0017] S12: Then substitute the obtained invalid duration Tw and transaction duration T into the formula Calculate to obtain the invalid value Q, and then compare the invalid value Q. When Q≥YS, the system determines that the transaction data is risky and generates a risk signal. On the contrary, when Q<YS, the system determines that the transaction data is not risky and does not perform any processing. And YS is a preset value. It should be noted here that: the specific value of the preset value YS is obtained through big data calculation;

[0018] S13: Obtain the generated risk signal, analyze the risk signal to generate the corresponding warning information, and transmit the warning information to the information output unit.

[0019] As a further solution of the present invention: when the adaptive processing unit determines that it is a risk trading platform, the specific processing method for private data is as follows:

[0020] S2: When the target object is private data, obtain the transaction duration. Similarly to S1, classify the transaction duration into valid duration Ty and invalid duration Tw, then obtain the data capacity of the target object and denote it as RL, and divide the target object according to the data capacity RL of the target object, and perform encryption processing on the divided target object. The specific encryption method is as follows:

[0021] S21: Divide the target object data capacity RL according to the value of the valid duration Ty to generate Ty target object quantity capacity packages, and then obtain the invalid duration Tw and generate virtual data with the value of the invalid duration Tw at the same time. The specific generation method is: extract the target object data capacity packages at even positions in the Ty target object data capacity packages, and the number of extractions is Tw to generate virtual data. It should be noted here that: in the process of extracting the target object data capacity packages according to the number of Tw, if there is a shortage of even numbers, then extract from the beginning in the way of 1, 3, 5, 7,..., n+2 to generate virtual data;

[0022] S22: The time node of virtual data generation is obtained and recorded, and then the generated virtual data and the target object are recombined to generate recombined data, and the recombined data is filled into the invalid time length to generate corresponding recombined information.

[0023] As a further solution of the present invention: the specific processing method of the adaptive processing unit for public data when it is determined to be a normal trading platform is as follows:

[0024] P1: The target object is obtained as public data. At the same time, the system obtains the number of transactions and records it as CS. Then, the target object is analyzed based on the obtained number of transactions. The specific analysis method is as follows:

[0025] P11: Take time t as the period, obtain k periods before the current time node, and record the number of transactions in the k time period and record it as CSk. At the same time, obtain the number of abnormal transactions in the number of transactions and record it as YCk. It should be noted here that the abnormal number of transactions indicates that there are loss, garbled code and quality problems in the process of transaction data transmission, then the corresponding transaction number is marked as abnormal number, otherwise it is marked as normal number;

[0026] P12: Then calculate the difference in the number of transactions between two adjacent time periods k, and at the same time calculate the average value of the difference in the number of transactions in the k time periods, and compare it with zero. When the average value is greater than zero, it means that the number of transactions in the k time period is increasing, and an increase signal is generated. On the contrary, when the average value is less than zero, it means that the number of transactions in the k time period is decreasing, and a decrease signal is generated.

[0027] P13: An increase signal is obtained, and the number of abnormal transactions YCk corresponding to the increase signal is obtained. When the number of transactions YCk increases, the system determines that there is a risk and generates risk information accordingly. When the number of transactions YCk decreases, the system generates normal information;

[0028] P14: A decrease signal is obtained, and at the same time, the number of abnormal transactions YCk corresponding to the decrease signal is obtained. When the number of transactions YCk increases, the system determines that there is a risk and generates corresponding risk information. When the number of transactions YCk decreases, the system generates normal information.

[0029] As a further solution of the present invention: the specific processing method of the adaptive processing unit for the privacy data when determining it as a normal trading platform is as follows:

[0030] P2: The target object is obtained as private data, and the data capacity of the target object is obtained and recorded as RL. Then the data capacity is evenly divided according to the nine-square grid to generate nine data capacity packages. It should be noted here that: according to the nine-square grid division, the capacity may be different after the division, and the nine data capacity packages after the division are encrypted to generate encrypted information. The specific encryption method is as follows:

[0031] P21: Obtain nine data capacity packages, label them and record them as j, where j=1, 2, ..., 9, and obtain the capacity of a single data capacity package, and generate garbled data of the same capacity and perform the same labeling on the generated garbled data;

[0032] P22: Combine the generated garbled data with the same label and the data capacity package with the label to generate a new target object, and generate encryption information and transmit the encrypted information to the information output unit. It should be noted here that: the system will automatically generate decoding information when generating encryption information, and transmit the decoding information to the storage end for storage, which further facilitates the subsequent decoding of the encrypted data.

[0033] The risk control method of the financial risk control system based on big data is characterized in that the method specifically comprises the following steps:

[0034] Step 1: Obtain transaction data and transaction platforms, and classify transaction data types into public data and private data, and classify transaction platforms into risky platforms and normal platforms;

[0035] Step 2: Analyze the transaction data in the classified risk platform. First, analyze the data classified as public to generate corresponding warning information, and then analyze the data classified as private to generate corresponding reorganized information.

[0036] Step 3: Analyze the transaction data in the classified normal platform. First, analyze the data classified as public to generate corresponding risk information and normal information. Then analyze the data classified as private to generate corresponding encrypted information.

[0037] Step 4: Display the generated warning information, reorganization information, risk information, normal information and encrypted information to the corresponding operators through the display device.

[0038] Beneficial Effects

[0039] The present invention provides a financial risk control method and system based on big data. Compared with the prior art, it has the following beneficial effects:

[0040] The present invention classifies transaction data of users and transaction platforms, classifies transaction data into public data and private data according to user tags, monitors transaction platforms at the same time, encrypts and protects risky transaction platforms during data interaction, and issues early warning and encryption protection to normal platforms, thereby ensuring the security of user transaction data. Further, the transaction platforms are monitored to provide reminders and early warnings to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a system block diagram of the present invention;

[0042] Figure 2 Figure 2 is a diagram of the method of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0044] For example, see Figure 1 , this application provides a financial risk control system based on big data, including:

[0045] The information collection unit is used to obtain the basic information of the target object, wherein the target object includes: transaction data, and the basic information includes: transaction data type, transaction platform, number of transactions and transaction duration. It should be noted here that the transaction duration represents the real-time transaction duration, and the obtained basic information of the target object is transmitted to the data identification unit.

[0046] The data identification unit is used to obtain the basic information of the target object to be transmitted, and identify the transaction data type and transaction platform in the basic information. By identifying the characteristic signals of the transaction data, the transaction data is classified into public transaction data and private transaction data, and the two are integrated to generate data classification information. By detecting the risks of the transaction platform, the transaction platform is classified into a normal transaction platform and a risky transaction platform, and the two are integrated to generate platform classification information. The identified data classification information and platform classification information are transmitted to the adaptive processing unit. The specific identification method of the transaction data is as follows:

[0047] Obtain the transmitted transaction data and determine whether there is a user tag. If there is a user tag, mark the corresponding transaction data as private data. Otherwise, if there is no user tag, mark the corresponding transaction data as public data.

[0048] Combined with the analysis of actual application scenarios, when users enter transaction data, special marking processing will be performed on the privacy data. There may be various ways of marking, which may be the presence of special characters or marking with brackets. When the system identifies, if it is recognized that the corresponding transaction data is different from other transaction data, the corresponding transaction data will be identified as privacy transaction data, otherwise it will be identified as normal transaction data. The identification method in this application is only represented as one method of identification.

[0049] The specific method of trading platform identification is: obtain the trading platform of the target object and the prompt information of the trading platform at the same time. Then the system obtains the reminder information and identifies it, and classifies the trading platform according to the identified content. If the identified content contains risks, the corresponding trading platform will be classified as a risky platform. Conversely, if the identified content does not contain risks, the corresponding trading platform will be classified as a normal platform.

[0050] Combined with the analysis of actual application scenarios, the prompt information of the trading platform will remind the user when using it, and a corresponding dialog box will pop up. The system will then recognize the content of the dialog box, including the text of the prompt information. Then, it will be judged whether there is a risk based on the text information. If the text information indicates that there is a risk, the trading platform will be classified as a risky platform accordingly, otherwise it will be marked as a normal platform.

[0051] The adaptive processing unit is used to obtain the transmitted data classification information and the transaction platform classification information, and analyze the target objects corresponding to the normal transaction platform and the risk transaction platform respectively. It should be noted here that in the first embodiment, the target object is analyzed under the premise of being determined as a risk transaction platform, and then the public data and the private data are processed respectively according to the target docking data classification information to obtain the processing results, and the processing results include: risk signals, normal signals and reorganized data, and the processing results are transmitted to the information output unit. The specific processing method is as follows:

[0052] S1: The target object is obtained as public data, the system obtains the transaction time, and divides the transaction time into valid transaction time and invalid transaction time, and then calculates the invalid value of the public data according to the divided valid transaction time and invalid transaction time. The specific calculation method is as follows:

[0053] S11: Record the trading duration as T. Take the current time as a node and obtain the trading duration with operations as the effective trading duration, denoted as Ty. Conversely, the trading duration without operations is denoted as the invalid operation duration, denoted as Tw. Here, it should be noted that when users conduct transactions using the platform, the two trading parties must interact in real time. Therefore, the duration of real-time interaction is recorded as the effective duration, and the duration without real-time interaction is recorded as the invalid duration. When the duration without real-time interaction exceeds the preset value, the subsequent time is defined as the invalid duration, and the preset value is set by the operator himself;

[0054] S12: Then substitute the obtained invalid duration Tw and trading duration T into the formula Calculate the invalid value Q. Then compare the invalid value Q. When Q≥YS, the system determines that the transaction data has risks and generates a risk signal. Conversely, when Q<YS, the system determines that the transaction data has no risks and does not perform any processing. And YS is the preset value. Here, it should be noted that the specific value of the preset value YS is obtained through big data calculation;

[0055] S13: Obtain the generated risk signal, analyze the risk signal to generate the corresponding warning information, and transmit the warning information to the information output unit. Here, it should be noted that for the specific level division of the generated warning information, calculate the difference between the invalid value Q and the preset value YS. Then compare the difference. If the difference is between 0 and 0.3, generate a first-level warning information. If the difference is between 0.3 and 0.5, generate a second-level warning information. If the difference exceeds 0.5, generate a third-level warning information. From the first level to the third level, the severity gradually increases, with the third level being the highest and the first level being the lowest;

[0056] S2: Obtain that the target object is private data. Obtain the trading duration. Similarly to S1, classify the trading duration into the effective duration Ty and the invalid duration Tw. Then obtain the data capacity of the target object and denote it as RL. Divide the target object according to the data capacity RL of the target object, and perform encryption processing on the divided target object. The specific encryption method is as follows:

[0057] S21: Divide the data capacity RL of the target object into Ty target object quantity packages according to the value of the effective duration Ty. Then obtain the invalid duration Tw and generate virtual data with the value of the invalid duration Tw. The specific generation method is as follows: Extract the target object quantity packages at even positions from the Ty target object quantity packages, and the number of extracted packages is Tw to generate virtual data. Here, it should be noted that in the process of extracting the target object quantity packages according to the number Tw, if there is a shortage of even numbers, then extract from the beginning in the order of 1, 3, 5, 7,..., n + 2 to generate virtual data;

[0058] S22: Obtain the time node of virtual data generation and record it, then recombinant the generated virtual data with the target object to generate recombinant data, and fill the recombinant data into the invalid time to generate corresponding recombinant information. It should be noted here that: during the transaction of private data, the system encrypts the original private data for invalid transaction time, and then generates virtual data and fills it into the invalid transaction time, so as to protect the overall target object. Subsequently, in the process of effective real-time interaction, the recombinant data is decoded and displayed to the corresponding interacting personnel.

[0059] The information output unit is used to obtain the transmitted analysis results and transmit them to the operator through the display device.

[0060] Embodiment 2: The difference between Embodiment 2 of the present invention and Embodiment 1 is that Embodiment 2 analyzes the target object on the premise that the target object is determined to be a normal trading platform.

[0061] When the adaptive processing unit obtains the classification information of the trading platform as a normal trading platform, it then analyzes the obtained data classification information, generates corresponding risk information, normal information and encrypted information, and transmits them to the information output unit. The specific analysis method is as follows:

[0062] P1: The target object is obtained as public data. At the same time, the system obtains the number of transactions and records it as CS. Then, the target object is analyzed based on the obtained number of transactions. The specific analysis method is as follows:

[0063] P11: Take time t as the period, obtain k periods before the current time node, and record the number of transactions in the k time period and record it as CSk. At the same time, obtain the number of abnormal transactions in the number of transactions and record it as YCk. It should be noted here that the abnormal number of transactions indicates that there are loss, garbled code and quality problems in the process of transaction data transmission, then the corresponding transaction number is marked as abnormal number, otherwise it is marked as normal number;

[0064] P12: Then calculate the difference in the number of transactions between two adjacent time periods k, and at the same time calculate the average value of the difference in the number of transactions in the k time periods, and compare it with zero. When the average value is greater than zero, it means that the number of transactions in the k time period is increasing, and an increase signal is generated. On the contrary, when the average value is less than zero, it means that the number of transactions in the k time period is decreasing, and a decrease signal is generated.

[0065] P13: An increase signal is obtained, and the number of abnormal transactions YCk corresponding to the increase signal is obtained. When the number of transactions YCk increases, the system determines that there is a risk and generates risk information accordingly. When the number of transactions YCk decreases, the system generates normal information;

[0066] P14: A decrease signal is obtained, and at the same time, the number of abnormal transactions YCk corresponding to the decrease signal is obtained. When the number of transactions YCk increases, the system determines that there is a risk and generates risk information accordingly. When the number of transactions YCk decreases, the system generates normal information;

[0067] P2: The target object is obtained as private data, and the data capacity of the target object is obtained and recorded as RL. Then the data capacity is evenly divided according to the nine-square grid to generate nine data capacity packages. It should be noted here that: according to the nine-square grid division, the capacity may be different after the division, and the nine data capacity packages after the division are encrypted to generate encrypted information. The specific encryption method is as follows:

[0068] P21: Obtain nine data capacity packages, label them and record them as j, where j=1, 2, ..., 9, and obtain the capacity of a single data capacity package, and generate garbled data of the same capacity and perform the same labeling on the generated garbled data;

[0069] P22: Combine the generated garbled data with the same label and the data capacity package with the label to generate a new target object, and generate encryption information and transmit the encrypted information to the information output unit. It should be noted here that: the system will automatically generate decoding information when generating encryption information, and transmit the decoding information to the storage end for storage, which further facilitates the subsequent decoding of the encrypted data.

[0070] The information output unit is used to obtain the transmitted risk information, normal information and encrypted information, decode the encrypted information and decode the new target object, and then transmit the decoded target object to the operator.

[0071] Embodiment 3, as the embodiment 3 of the present invention, focuses on combining the implementation processes of embodiment 1 and embodiment 2 for implementation.

[0072] Example 4, please refer to Figure 2 As a fourth embodiment of the present invention, the present application provides a risk control method for a financial risk control system based on big data, and the method specifically includes the following steps:

[0073] Step 1: Obtain transaction data and transaction platforms, and classify transaction data types into public data and private data, and classify transaction platforms into risky platforms and normal platforms;

[0074] Step 2: Analyze the transaction data in the classified risk platform. First, analyze the data classified as public to generate corresponding warning information, and then analyze the data classified as private to generate corresponding reorganized information.

[0075] Step 3: Analyze the transaction data in the classified normal platform. First, analyze the data classified as public to generate corresponding risk information and normal information. Then analyze the data classified as private to generate corresponding encrypted information.

[0076] Step 4: Display the generated warning information, reorganization information, risk information, normal information and encrypted information to the corresponding operators through the display device.

[0077] Some of the data in the above formulas are numerically calculated by removing their dimensions. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0078] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The financial risk control system based on big data is characterized by: include: The information collection unit is used to obtain basic information of the target object, wherein the target object includes: transaction data, and the basic information includes: transaction data type, transaction platform, transaction number and transaction duration, and transmit the obtained basic information of the target object to the data identification unit; A data identification unit is used to obtain basic information of the target object to be transmitted, and to identify the transaction data type and transaction platform in the basic information, to classify the transaction data into public transaction data and private transaction data by identifying characteristic signals of the transaction data, and to integrate the two to generate data classification information, to classify the transaction platform into a normal transaction platform and a risky transaction platform by detecting the risk of the transaction platform, and to integrate the two to generate platform classification information, and to transmit the identified data classification information and platform classification information to the adaptive processing unit; The adaptive processing unit is used to obtain the transmitted data classification information and transaction platform classification information, and analyze the target objects corresponding to the normal transaction platform and the risk transaction platform respectively. First, the target object determined to be the risk transaction platform is analyzed, and then the public data and the private data are processed according to the target object data classification information to obtain the processing results, which include: risk signals and reorganized data, and the processing results are transmitted to the information output unit, and the processing method for the public data is as follows; S1: The target object is obtained as public data, the system obtains the transaction time, and divides the transaction time into valid transaction time and invalid transaction time, and then calculates the invalid value of the public data according to the divided valid transaction time and invalid transaction time. The specific calculation method is as follows: S11: record the transaction duration as T, take the current time as the node, obtain the transaction duration with operation as valid transaction duration and record it as Ty, otherwise record the transaction duration without operation as invalid transaction duration and record it as Tw; S12: Next, substitute the obtained invalid transaction duration Tw and the transaction duration T into the formula Calculate the obtained invalid value Q, and then compare the invalid value Q. When Q ≥ YS, the system determines that there is a risk in the transaction data and generates a risk signal. On the contrary, when Q < YS, the system determines that there is no risk in the transaction data, does not perform any processing, and YS is a preset value; S13: Obtain the generated risk signal, analyze the risk signal to generate corresponding warning information, and transmit the warning information to the information output unit; The way to handle private data is: S2: The target object is obtained as private data, and the transaction duration is obtained. Similarly, S1 classifies the transaction duration into valid transaction duration Ty and invalid transaction duration Tw, and then obtains the data capacity of the target object and records it as RL. The target object is segmented according to the target object data capacity RL, and the segmented target object is encrypted. The specific encryption method is as follows: S21: Split the target object data capacity RL according to the value of the valid transaction duration Ty to generate Ty target object data capacity packages, then obtain the invalid transaction duration Tw and generate virtual data with the invalid transaction duration Tw value, the specific generation method is: extract the target object data capacity packages at the even positions in the Ty target object data capacity packages, the number of extracted packages is Tw, and generate virtual data; S22: Obtain the time node of virtual data generation and record it, then reorganize the generated virtual data with the target object to generate reorganized data, and fill the reorganized data into the invalid transaction duration to generate corresponding reorganization information; Then, the target object determined to be a normal trading platform is analyzed, and then the acquired data classification information is analyzed, and corresponding risk information, normal information and encrypted information are generated respectively, and transmitted to the information output unit.

2. The financial risk control system based on big data according to claim 1 is characterized in that: The specific identification method of the data identification unit for the data type and the trading platform is as follows: Obtain the transmitted transaction data and determine whether there is a user tag. If there is a user tag, mark the corresponding transaction data as private data. Otherwise, if there is no user tag, mark the corresponding transaction data as public data. The specific method of trading platform identification is: obtain the trading platform of the target object and the prompt information of the trading platform at the same time. Then the system obtains the reminder information and identifies it, and classifies the trading platform according to the identified content. If the identified content contains risks, the corresponding trading platform will be classified as a risky trading platform. Conversely, if the identified content does not contain risks, the corresponding trading platform will be classified as a normal trading platform.

3. The financial risk control system based on big data according to claim 1 is characterized in that: The specific processing method of the adaptive processing unit for public data when it is determined to be a normal trading platform is as follows: P1: The target object is obtained as public data. At the same time, the system obtains the number of transactions and records it as CS. Then, the target object is analyzed based on the obtained number of transactions. The specific analysis method is as follows: P11: Taking time t as the period, obtain the k periods before the current time node, and record the number of transactions in the k time period and record it as CSk. At the same time, obtain the number of abnormal transactions in the transaction number and record it as YCk; P12: Then calculate the difference in the number of transactions between two adjacent time periods, and at the same time calculate the average value of the difference in the number of transactions in k time periods, and compare it with zero. When the average value is greater than zero, it means that the number of transactions in the k time period is increasing, and an increase signal is generated. On the contrary, when the average value is less than zero, it means that the number of transactions in the k time period is decreasing, and a decrease signal is generated. P13: An increase signal is obtained, and the number of abnormal transactions YCk corresponding to the increase signal is obtained. When the number of transactions YCk increases, the system determines that there is a risk and generates risk information accordingly. When the number of transactions YCk decreases, the system generates normal information; P14: A decrease signal is obtained, and at the same time, the number of abnormal transactions YCk corresponding to the decrease signal is obtained. When the number of transactions YCk increases, the system determines that there is a risk and generates corresponding risk information. When the number of transactions YCk decreases, the system generates normal information.

4. The financial risk control system based on big data according to claim 1 is characterized in that: The specific processing method of the adaptive processing unit for the privacy data when determining that the transaction platform is normal is as follows: P2: The target object is obtained as private data, and the data capacity of the target object is obtained and recorded as RL. Then the data capacity is evenly divided into nine data capacity packages according to the nine-square grid, and the nine data capacity packages are encrypted to generate encrypted information. The specific encryption method is as follows: P21: Obtain nine data capacity packages, label them and record them as j, where j=1, 2, ..., 9, and obtain the capacity of a single data capacity package, and generate garbled data of the same capacity and perform the same labeling on the generated garbled data; P22: Combine the generated garbled data with the same label with the data capacity package with the label to generate a new target object, and generate encrypted information and transmit the encrypted information to the information output unit.

5. The financial risk control system based on big data according to claim 1 is characterized in that: The information output unit is used to obtain the transmitted warning information, reorganization information, risk information, normal information and encrypted information and display them to the corresponding operators through the display device.

6. A risk control method for a financial risk control system based on big data according to any one of claims 1 to 5, characterized in that: The method specifically comprises the following steps: Step 1: Obtain transaction data and transaction platforms, and classify transaction data types into public data and private data, and classify transaction platforms into risky transaction platforms and normal transaction platforms; Step 2: Analyze the transaction data in the classified risk trading platform. First, analyze the data classified as public to generate corresponding warning information, and then analyze the data classified as private to generate corresponding reorganized information. Step 3: Analyze the transaction data in the classified normal trading platform. First, analyze the data classified as public to generate corresponding risk information and normal information. Then, analyze the data classified as private to generate corresponding encrypted information. Step 4: Display the generated warning information, reorganization information, risk information, normal information and encrypted information to the corresponding operators through the display device.

Images