CN114819963A - Risk early warning method and device, electronic equipment and storage medium - Google Patents
Risk early warning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114819963A CN114819963A CN202110071008.7A CN202110071008A CN114819963A CN 114819963 A CN114819963 A CN 114819963A CN 202110071008 A CN202110071008 A CN 202110071008A CN 114819963 A CN114819963 A CN 114819963A
- Authority
- CN
- China
- Prior art keywords
- risk
- platform
- digital currency
- level
- historical
- 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.)
- Pending
Links
Images
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
- 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
-
- 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
- G06Q20/04—Payment circuits
- G06Q20/06—Private payment circuits, e.g. involving electronic currency used among participants of a common payment scheme
- G06Q20/065—Private payment circuits, e.g. involving electronic currency used among participants of a common payment scheme using e-cash
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention provides a risk early warning method, a risk early warning device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring platform data of a digital currency transaction platform to be analyzed; carrying out digital currency platform risk index quantification processing on the platform data to generate a risk index vector corresponding to a digital currency transaction platform; inputting the risk index vector into a preset risk early warning model of the digital currency transaction platform, and outputting a risk index corresponding to the digital currency transaction platform; and carrying out early warning on the risk of the digital currency transaction platform based on the risk index. The purpose of automatically carrying out early warning on the risk of the digital currency transaction platform can be realized, manual participation is not needed, the waste of time and energy is reduced, the risk discovery of the digital currency transaction platform is simple, and the accuracy and the timeliness of the risk discovery and disposal of the digital currency transaction platform are improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a risk early warning method and device, electronic equipment and a storage medium.
Background
The digital currency is a substitute currency in the form of electronic currency, the virtual gold currency, the password currency and the like belong to the digital currency, and the currently popular digital currencies include the bitcoin, the leite coin and the like. In view of the characteristics of decentralization of digital currency, a financial supervision department cannot directly control the digital currency, and the digital currency transaction platform is used as a carrier of digital currency transaction and provides an effective way for digital currency supervision, so that the digital currency transaction platform is supervised, and the method has important significance for maintaining the stability of a financial system.
In the related art, the supervision of a digital currency transaction platform currently depends on a traditional manual supervision mode. However, with the continuous development of digital currency and the continuous increase of the number of digital currency transaction platforms, a great challenge is brought to the prevention and disposal of the risk work of the digital currency transaction platform, at present, the digital currency transaction platform is supervised only by a traditional manual supervision mode, a great amount of time and energy are consumed, the risk discovery of the digital currency transaction platform is difficult, and the accuracy and timeliness of the risk discovery and disposal of the digital currency transaction platform are low.
Disclosure of Invention
The embodiment of the invention aims to provide a risk early warning method, a risk early warning device, electronic equipment and a storage medium, so that waste of time and energy is reduced, risk discovery of a digital currency transaction platform is simple, and accuracy and timeliness of risk discovery and disposal of the digital currency transaction platform are improved. The specific technical scheme is as follows:
in a first aspect of an embodiment of the present invention, a risk early warning method is provided first, where the method includes:
acquiring platform data of a digital currency transaction platform to be analyzed, wherein the platform data comprises platform digital currency data, platform operation data and/or platform user data;
carrying out digital currency platform risk index quantification processing on the platform data to generate a risk index vector corresponding to the digital currency transaction platform;
inputting the risk index vector into a preset digital currency transaction platform risk early warning model, and outputting a risk index corresponding to the digital currency transaction platform;
and early warning the risk of the digital currency transaction platform based on the risk index.
In an optional embodiment, the performing digital currency platform risk indicator quantization processing on the platform data to generate a risk indicator vector corresponding to the digital currency transaction platform includes:
determining a preset risk index tree of the digital currency transaction platform;
determining the platform data as the lowest level risk index in the digital currency trading platform risk indexes based on the risk index tree;
determining an i-grade risk index in the risk indexes of the digital currency trading platform based on the risk index tree, wherein the i-grade risk index is not the lowest-grade risk index, and i is a positive integer;
carrying out standardization processing on lower-level risk indexes of the i-level risk indexes, and carrying out weighting processing to obtain the i-level risk indexes;
and combining the lowest-level risk index and the i-level risk index based on the risk index tree to generate a risk index vector corresponding to the digital currency trading platform.
In an optional embodiment, the normalizing the lower level risk indicator of the i-level risk indicator and weighting to obtain the i-level risk indicator includes:
and standardizing the lower-level risk indexes of the i-level risk indexes by adopting dispersion standardization or z-score standardization, determining the weights of the lower-level risk indexes by adopting an analytic hierarchy process or an entropy weight process, and performing weighting calculation to obtain the i-level risk indexes.
In an optional embodiment, the pre-warning the digital currency transaction platform risk based on the risk index includes:
counting sample data of the digital currency transaction platform risk early warning model to obtain the maximum value and the minimum value of each level of risk indexes, wherein the sample data consists of each level of risk indexes;
inputting the risk index, the maximum value and the minimum value into a preset risk index quantitative conversion algorithm, and outputting a risk tendency degree corresponding to the digital currency trading platform;
and determining the corresponding risk of the digital currency transaction platform according to the risk tendency, and carrying out risk early warning on the digital currency transaction platform.
In an optional embodiment, the risk indicator quantitative conversion algorithm includes:
wherein a' is the risk propensity, a is the risk index, target (max) is the maximum value, and target (min) is the minimum value.
In an optional embodiment, the determining a risk corresponding to the digital currency transaction platform according to the risk tendency to perform risk early warning on the digital currency transaction platform includes:
determining a risk tendency degree interval corresponding to the risk tendency degree, and searching a platform risk corresponding to the risk tendency degree interval;
and determining the platform risk as the risk corresponding to the digital currency transaction platform, and performing digital currency transaction platform risk early warning.
In an optional embodiment, the digital currency transaction platform risk early warning model is obtained by:
acquiring platform historical data of different digital currency transaction platforms, wherein the platform historical data comprises platform digital currency historical data, platform operation historical data and/or platform user historical data;
carrying out digital currency platform risk index quantification processing on the platform historical data to generate risk index historical vectors corresponding to different digital currency transaction platforms;
determining a historical risk index corresponding to the risk index historical vector, and combining the historical risk index serving as a sample label with the risk index historical vector to generate sample data;
and acquiring a machine learning model, and carrying out supervised training on the machine learning model based on the sample data until a preset loss function meets a convergence condition.
In an optional embodiment, the performing digital currency platform risk indicator quantization processing on the platform history data to generate risk indicator history vectors corresponding to different digital currency transaction platforms includes:
determining a preset risk index tree of the digital currency transaction platform;
determining the platform historical data as the lowest level historical risk index in the historical risk indexes of different digital currency transaction platforms based on the risk index tree;
determining i-level historical risk indexes in historical risk indexes of different digital currency transaction platforms based on the risk index tree;
wherein the i-level historical risk indicator is not the lowest-level historical risk indicator, and i is a positive integer;
carrying out standardization processing on lower-level historical risk indexes of the i-level historical risk indexes, and carrying out weighting processing to obtain the i-level historical risk indexes;
and combining the lowest-level historical risk indexes and the i-level historical risk indexes based on the risk index tree to generate risk index historical vectors corresponding to different digital currency transaction platforms.
In an optional embodiment, the normalizing the lower-level historical risk indicator of the i-level historical risk indicator and weighting the lower-level historical risk indicator to obtain the i-level historical risk indicator includes:
and standardizing the lower-level historical risk indexes of the i-level historical risk indexes by adopting dispersion standardization or z-score standardization, determining the weights of the lower-level historical risk indexes by adopting an analytic hierarchy process or an entropy weight process, and performing weighting calculation to obtain the i-level historical risk indexes.
In a second aspect of the embodiments of the present invention, there is also provided a risk early warning apparatus, including:
the system comprises a data acquisition module, a data analysis module and a data analysis module, wherein the data acquisition module is used for acquiring platform data of a digital currency transaction platform to be analyzed, and the platform data comprises platform digital currency data, platform operation data and/or platform user data;
the vector generation module is used for carrying out digital currency platform risk index quantification processing on the platform data and generating a risk index vector corresponding to the digital currency trading platform;
the index output module is used for inputting the risk index vector to a preset digital currency transaction platform risk early warning model and outputting a risk index corresponding to the digital currency transaction platform;
and the risk early warning module is used for early warning the risk of the digital currency transaction platform based on the risk index.
In a third aspect of the embodiments of the present invention, there is further provided an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor, configured to implement the risk pre-warning method according to any one of the first aspect described above when executing a program stored in a memory.
In a fourth aspect of the embodiments of the present invention, there is further provided a storage medium, where instructions are stored, and when the storage medium runs on a computer, the storage medium causes the computer to execute the risk early warning method according to any one of the first aspect.
In a fifth aspect of the embodiments of the present invention, there is also provided a computer program product containing instructions, which when run on a computer, causes the computer to execute the risk pre-warning method according to any one of the first aspect.
According to the technical scheme provided by the embodiment of the invention, platform data of a digital currency transaction platform to be analyzed are obtained, wherein the platform data comprise platform digital currency data, platform operation data and/or platform user data, the platform data are subjected to digital currency platform risk index quantification processing to generate a risk index vector corresponding to the digital currency transaction platform, the risk index vector is input to a preset digital currency transaction platform risk early warning model, a risk index corresponding to the digital currency transaction platform is output, and the risk of the digital currency transaction platform is early warned based on the risk index. The risk index vector corresponding to the digital currency transaction platform is quantitatively processed by acquiring platform data of the digital currency transaction platform to be analyzed and is input into a digital currency transaction platform risk early warning model, and the risk of the digital currency transaction platform is early warned according to the risk index corresponding to the digital currency transaction platform output by the digital currency transaction platform risk early warning model, so that the aim of automatically early warning the risk of the digital currency transaction platform can be fulfilled, manual participation is not needed, waste of time and energy is reduced, the risk of the digital currency transaction platform is simple to discover, and the accuracy and timeliness of risk discovery and disposal of the digital currency transaction platform are improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flow chart illustrating an implementation of a risk early warning method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating the effect of determining a digital currency trading platform to be analyzed in an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating another implementation of a risk early warning method according to an embodiment of the present invention;
fig. 4 is a schematic flow chart illustrating an implementation of the digital currency platform risk indicator quantification processing on platform data according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating the effect of a 4-level risk indicator tree of a digital currency trading platform according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart illustrating an implementation of a machine learning model training method according to an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of an implementation flow of a digital currency platform risk indicator quantization process performed on platform history data according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a risk early warning apparatus according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device shown in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
As shown in fig. 1, an implementation flow diagram of a risk early warning method provided in an embodiment of the present invention is shown, and the method may be applied to a processor, and specifically may include the following steps.
S101, platform data of a digital currency transaction platform to be analyzed are obtained, wherein the platform data comprise platform digital currency data, platform operation data and/or platform user data.
At present, with the continuous development of digital currency, the number of digital currency transaction platforms is continuously increased, and in order to achieve the purpose of automatically early warning the risk of the digital currency transaction platform, the embodiment of the invention can determine the digital currency transaction platform to be analyzed, and further acquire the platform data of the digital currency transaction platform to be analyzed.
For example, the digital currency transaction platform set includes digital currency transaction platforms such as a digital currency transaction platform a, a digital currency transaction platform B, and a digital currency transaction platform C, and a user may designate one of the digital currency transaction platforms, as shown in fig. 2, obtain a platform identifier (a platform name, a platform ID, and the like) of the digital currency transaction platform designated by the user, determine a digital currency transaction platform to be analyzed, and further obtain platform data of the digital currency transaction platform to be analyzed.
It should be noted that the platform data generally includes platform digital currency data, platform operation data and/or platform user data. The platform digital currency data generally includes digital currency historical price data, digital currency policy data, digital currency public opinion data, etc., the platform operation data generally includes platform operation data, platform scale data, platform credit data, platform accident data, platform public opinion data, etc., and the platform user data generally includes user scale data, user transaction data, etc., which are not limited in the embodiments of the present invention.
In addition, it should be noted that, as for the manner of obtaining the platform data of the digital currency transaction platform to be analyzed, the platform data of the digital currency transaction platform to be analyzed may be obtained by a third party institution, or by a web crawler, that is, the platform data of the digital currency transaction platform to be analyzed may be obtained by the third party institution, or the platform data of the digital currency transaction platform to be analyzed may be obtained by the web crawler, which is not limited in the embodiment of the present invention.
And S102, carrying out digital currency platform risk index quantification processing on the platform data to generate a risk index vector corresponding to the digital currency trading platform.
For the platform data of the digital currency transaction platform to be analyzed, the embodiment of the invention can perform quantitative processing on the risk index of the digital currency platform on the platform data to generate the risk index vector corresponding to the digital currency transaction platform to be analyzed.
For example, for platform data of the digital currency transaction platform a, in the embodiment of the present invention, the platform data is subjected to digital currency platform risk indicator quantization processing, so as to generate a risk indicator vector corresponding to the digital currency transaction platform a.
S103, inputting the risk index vector into a preset digital currency transaction platform risk early warning model, and outputting a risk index corresponding to the digital currency transaction platform.
For the risk index vector corresponding to the digital currency transaction platform to be analyzed, the risk index vector can be input to a preset digital currency transaction platform risk early warning model in the embodiment of the invention, and then the risk index corresponding to the digital currency transaction platform to be analyzed, which is output by the digital currency transaction platform risk early warning model, is obtained.
For example, for a risk index vector corresponding to the digital currency transaction platform a, in the embodiment of the present invention, the risk index vector may be input to a preset digital currency transaction platform risk early warning model, so as to obtain a risk index corresponding to the digital currency transaction platform a output by the digital currency transaction platform risk early warning model.
It should be noted that the risk index may be embodied as a score, and a value interval may be, for example, 0 to 100, which is not limited in the embodiment of the present invention.
And S104, early warning the risk of the digital currency transaction platform based on the risk index.
For the risk index of the digital currency transaction platform to be analyzed, the risk of the digital currency transaction platform to be analyzed can be early warned based on the risk index, so that the aim of automatically early warning the risk of the digital currency transaction platform can be fulfilled, manual participation is not needed, waste of time and energy is reduced, the risk of the digital currency transaction platform is simple to discover, and the accuracy and timeliness of risk discovery and disposal of the digital currency transaction platform are improved.
For example, for a risk index corresponding to the digital currency transaction platform a, in the embodiment of the present invention, risk early warning may be performed on the digital currency transaction platform a based on the risk index, so that the purpose of automatically early warning the risk of the digital currency transaction platform a may be achieved, manual involvement is not required, waste of time and energy is reduced, risk discovery of the digital currency transaction platform a is simple, and accuracy and timeliness of risk discovery and disposal of the digital currency transaction platform a are improved.
Through the above description of the technical scheme provided by the embodiment of the invention, platform data of a digital currency transaction platform to be analyzed is obtained, wherein the platform data comprises platform digital currency data, platform operation data and/or platform user data, the platform data is subjected to digital currency platform risk index quantization processing to generate a risk index vector corresponding to the digital currency transaction platform, the risk index vector is input to a preset digital currency transaction platform risk early warning model, a risk index corresponding to the digital currency transaction platform is output, and the digital currency transaction platform risk is early warned based on the risk index.
The risk index vector corresponding to the digital currency transaction platform is quantitatively processed by acquiring platform data of the digital currency transaction platform to be analyzed and is input into a digital currency transaction platform risk early warning model, and the risk of the digital currency transaction platform is early warned according to the risk index corresponding to the digital currency transaction platform output by the digital currency transaction platform risk early warning model, so that the aim of automatically early warning the risk of the digital currency transaction platform can be fulfilled, manual participation is not needed, waste of time and energy is reduced, the risk of the digital currency transaction platform is simple to discover, and the accuracy and timeliness of risk discovery and disposal of the digital currency transaction platform are improved.
As shown in fig. 3, an implementation flow diagram of another risk early warning method provided in the embodiment of the present invention is shown, and the method may be applied to a processor, and specifically may include the following steps.
S301, platform data of a digital currency transaction platform to be analyzed is obtained, wherein the platform data comprises platform digital currency data, platform operation data and/or platform user data.
In the embodiment of the present invention, this step is similar to the step S101, and the details of the embodiment of the present invention are not repeated herein.
S302, carrying out digital currency platform risk index quantification processing on the platform data, and generating a risk index vector corresponding to the digital currency trading platform.
For the platform data of the digital currency transaction platform to be analyzed, the embodiment of the invention can perform quantitative processing on the risk index of the digital currency platform on the platform data to generate the risk index vector corresponding to the digital currency transaction platform to be analyzed.
As shown in fig. 4, an implementation flow diagram of performing digital currency platform risk indicator quantization processing on platform data according to an embodiment of the present invention is provided.
S401, determining a preset risk index tree of the digital currency transaction platform.
In the embodiment of the present invention, a digital currency transaction platform risk index tree may be preset, where the digital currency transaction platform risk index tree may generally be an n-level risk index tree of a digital currency transaction platform, which means that the digital currency transaction platform risk index tree includes n levels of risk indexes, each level of risk indexes may be multiple, and each level of risk indexes has a correlation, where n is a positive integer.
For example, as shown in fig. 5, a digital currency trading platform level 4 risk index tree is preset (level 3 risk index, level 4 risk index are not shown in the figure).
Wherein the level 1 risk indicators include: platform digital currency risk, platform operation risk, platform user risk.
The level 2 risk indicators associated with platform digital currency risk include: platform digital currency scale risk, platform digital currency price risk, platform digital currency policy risk, platform digital currency substitution risk.
The level 2 risk indicators associated with platform operational risk include: platform operation risk, platform mobility risk, platform credit risk, platform transaction process risk, and platform security event risk.
The level 2 risk indicators associated with platform user risk include: platform user scale risk, platform user transaction risk.
The level 3 risk indicators associated with platform digital currency scale risk include: total amount of digital currency, real-time total market value of digital currency, total market value of digital currency trades in last 24 hours, share of digital currency trades in last 24 hours, and digital currency circulation supply amount.
The level 3 risk indicators associated with platform digital currency price risk include digital currency real-time price, near 24 hour rise and fall amplitude, and near 7 day rise and fall amplitude.
Level 3 risk indicators associated with platform digital currency policy risk include: whether relevant laws and regulations are provided or not, attitude support, neutrality and opposition of relevant public opinions to digital currency.
The level 3 risk indicators associated with platform digital currency replacement risk include: recent new digital currency amount, official recent new digital currency amount.
The level 3 risk indicators associated with platform operational risk include: trading platform qualification risk, platform financial risk, platform team risk.
The class 3 risk indicators associated with platform liquidity risk include: the platform trading currency quantity, the total market value of the platform digital currency trading in the last 24 hours, the trading share of the platform digital currency trading in the last 24 hours and the average time interval of the platform trading in the last 24 hours.
The level 3 risk indicators associated with platform credit risk include: whether to carry out user identity identification, whether to have a practitioner auditing mechanism, whether to support the practitioner to participate in transactions, and whether to carry out third-party fund deposit and management on the platform.
The level 3 risk indicators associated with platform trading process risk include: digital currency transaction delay, transaction failure times of approximately 7 days, and transaction failure times of approximately 24 hours.
The level 3 risk indicators associated with platform security event risk include: the number of platform safety accidents and the related public opinion of the platform safety accidents.
The level 3 risk indicators associated with platform user scale risk include: the number of platform registered users, the number of platform transaction users, the number of newly-increased users in about 24 hours, the number of newly-increased users in about 7 days, the number of newly-increased transaction users in about 24 hours and the number of newly-increased transaction users in about 7 days.
The level 3 risk indicators associated with platform user transaction risk include: the platform user trades the total market value, the platform 24 digital currency trades the share, the platform 24 hour digital currency growth rate, the platform 24 hour trades the user proportion.
The class 4 risk indicators associated with platform qualification risk include: whether the platform is registered in a telecommunication management organization and whether the platform obtains the payment service permission.
The class 4 risk indicators associated with platform financial risk include: asset liability rate, liquidity rate, snap rate, accounts receivable turnover rate, inventory turnover rate, liability operation rate, interest earning fold, net profit rate for sale, cost expense profit rate.
The level 4 risk indicators associated with platform team risk include: the number of team personnel, the ratio of students in colleges and universities in the team, whether the change of high-management personnel exists, the number of newly added personnel in the last year and the number of personnel who leave the office in the last year.
S402, determining the platform data to be the lowest-level risk index in the risk indexes of the digital currency trading platform based on the risk index tree.
For the digital currency trading platform risk index tree, in the embodiment of the invention, the platform data of the digital currency trading platform to be analyzed can be determined to be the lowest-level risk index in the digital currency trading platform risk indexes to be analyzed based on the digital currency trading platform risk index tree.
For example, as shown in the digital currency transaction platform risk indicator tree shown in fig. 5, in the embodiment of the present invention, based on the digital currency transaction platform risk indicator tree, it may be determined that the platform data of the digital currency transaction platform a is the lowest-level risk indicator in the digital currency transaction platform a risk indicators.
It should be noted that, the lowest-level risk indicator is generally a statistical indicator, and can be directly quantified, that is, the lowest-level risk indicator is platform data of the digital currency transaction platform to be analyzed.
In addition, the lowest level risk indicators are typically leaf nodes in the risk indicator tree of the digital currency trading platform, such as the following: a level 3 risk indicator associated with platform digital currency scale risk, a level 3 risk indicator associated with platform digital currency price risk, a level 3 risk indicator associated with platform digital currency policy risk, a level 3 risk indicator associated with platform digital currency replacement risk, a level 3 risk indicator associated with platform liquidity risk, a level 3 risk indicator associated with platform credit risk, a level 3 risk indicator associated with platform trading process risk, a level 3 risk indicator associated with platform security event risk, a level 3 risk indicator associated with platform user scale risk, a level 3 risk indicator associated with platform user trading risk, a level 4 risk indicator associated with platform qualification risk, a level 4 risk indicator associated with platform financial risk, a level 4 risk indicator associated with platform team risk, and the like.
In addition, for attitude support, neutrality and opposition proportion indexes of the relevant public sentiments to the digital currency, the attitude analysis of the relevant public sentiments to the digital currency is used for obtaining the conditions of support, neutrality and opposition proportion. The analysis of the attitude of the relevant public sentiments to the digital currency can be realized by adopting a text viewpoint analysis technology. The platform security accident refers to the events that the platform is attacked by hackers, goes off-line and runs, cannot log in, and is suspected of illegal funding, and the frequency of the platform security accident and the public opinion related to the platform security accident are statistics related to the security event. For example, whether the platform is registered in the telecommunication management authority, whether the platform obtains a payment service license, and the like, the yes condition may be replaced by 1, and the no condition may be replaced by 0, which is not limited in the embodiment of the present invention.
And S403, determining an i-level risk index in the risk indexes of the digital currency trading platform based on the risk index tree, wherein the i-level risk index is not the lowest-level risk index, and i is a positive integer.
For the digital currency transaction platform risk index tree, in the embodiment of the present invention, an i-level risk index in the digital currency transaction platform risk indexes to be analyzed may be determined based on the digital currency transaction platform risk index tree, where the i-level risk index is not the lowest level risk index, and i is a positive integer.
For example, as shown in the digital currency transaction platform risk indicator tree shown in fig. 5, in the embodiment of the present invention, an i-level risk indicator in a risk indicator of a digital currency transaction platform a may be determined based on the digital currency transaction platform risk indicator tree, as follows: level 1 risk indicators, level 2 risk indicators associated with platform digital currency risks, level 2 risk indicators associated with platform operational risks, level 2 risk indicators associated with platform user risks, level 3 risk indicators associated with platform operational risks, and the like.
It should be noted that, the i-level risk indicator is generally a non-leaf node in a risk indicator tree of the digital currency transaction platform, such as the above-mentioned 1-level risk indicator, 2-level risk indicator associated with platform digital currency risk, 2-level risk indicator associated with platform operation risk, 2-level risk indicator associated with platform user risk, 3-level risk indicator associated with platform operation risk, and the like, which is not limited in the embodiment of the present invention.
S404, carrying out standardization processing on the lower risk indexes of the i-level risk indexes, and carrying out weighting processing to obtain the i-level risk indexes.
For the i-level risk index in the digital currency transaction platform risk index to be analyzed, the embodiment of the invention carries out standardization processing on the lower-level risk index of the i-level risk index, and carries out weighting processing to obtain the i-level risk index.
For example, taking a level 1 risk indicator (platform digital currency risk) as an example, a level 2 risk indicator associated with a platform digital currency risk includes: platform digital currency scale risk, platform digital currency price risk, platform digital currency policy risk, platform digital currency substitution risk.
It can be seen that the lower level risk indicators of the level 1 risk indicator (platform digital currency risk) include: the method comprises the steps of carrying out standard processing on lower-level risk indexes of a level 1 risk index (platform digital currency risk), and carrying out weighting processing to obtain the level 1 risk index (platform digital currency risk). And by analogy, carrying out standardization processing on the lower-level risk indexes of the i-level risk indexes, and carrying out weighting processing to obtain the i-level risk indexes.
In the embodiment of the invention, the lower-level risk index of the i-level risk index is subjected to standardization processing by adopting dispersion standardization or z-score standardization, the weight of the lower-level risk index is determined by adopting an analytic hierarchy process or an entropy weight method, and the i-level risk index is obtained by weighting calculation.
S405, combining the lowest-level risk index and the i-level risk index based on the risk index tree to generate a risk index vector corresponding to the digital currency trading platform.
For the digital currency transaction platform risk index tree, in the embodiment of the present invention, the lowest-level risk index and the i-level risk index may be combined based on the digital currency transaction platform risk index tree, and a risk index vector corresponding to the digital currency transaction platform to be analyzed is generated, that is, the risk index vector is composed of risk indexes (the lowest-level risk index and the i-level risk index) at different levels.
For example, as shown in fig. 5, the association relationship between each level of risk indicators in the risk indicator tree of the digital currency transaction platform combines the lowest level of risk indicators and the i-level of risk indicators based on the association relationship between each level of risk indicators to generate a risk indicator vector corresponding to the digital currency transaction platform a, that is, the risk indicator vector is composed of each level of risk indicators (the lowest level of risk indicators and the i-level of risk indicators).
And S303, inputting the risk index vector into a preset digital currency transaction platform risk early warning model, and outputting a risk index corresponding to the digital currency transaction platform.
In the embodiment of the present invention, this step is similar to the step S103, and the details of the embodiment of the present invention are not repeated herein.
S304, carrying out statistics on sample data of the digital currency transaction platform risk early warning model to obtain the maximum value and the minimum value of each level of risk indexes.
S305, inputting the risk index, the maximum value and the minimum value into a preset risk index quantitative conversion algorithm, and outputting the risk tendency corresponding to the digital currency trading platform.
S306, determining the corresponding risk of the digital currency transaction platform according to the risk tendency, and carrying out risk early warning on the digital currency transaction platform.
In the embodiment of the invention, the sample data of the digital currency transaction platform risk early warning model consists of all levels of risk indexes, the sample data of the digital currency transaction platform risk early warning model is counted, the maximum value and the minimum value of all levels of risk indexes are obtained, the risk index, the maximum value and the minimum value are input into a preset risk index quantitative conversion algorithm, the risk tendency corresponding to the digital currency transaction platform is output, the risk corresponding to the digital currency transaction platform to be analyzed is further determined according to the risk tendency, and the digital currency transaction platform risk early warning is carried out.
The risk indicator quantitative conversion algorithm is as follows:
wherein a' is the risk propensity, a is the risk index, target (max) is the maximum value, and target (min) is the minimum value.
It should be noted that, for the risk tendency degree, a risk tendency degree is generally described, and the larger the value is, the higher the risk is, and the value can be embodied in a form of score specifically, which is not limited in the embodiment of the present invention.
In addition, the embodiment of the invention can specifically determine a risk tendency degree interval corresponding to the risk tendency degree, search a platform risk corresponding to the risk tendency degree interval, determine that the platform risk is a risk corresponding to the digital currency transaction platform, and perform risk early warning on the digital currency transaction platform.
For example, in the embodiment of the present invention, different platform risks are pre-classified, and the corresponding relationship between the risk index score and the platform risk is shown in table 1 below.
TABLE 1
Determining a risk tendency degree interval corresponding to the risk tendency degree (75 points): and (3) searching a platform risk corresponding to the risk tendency degree interval, wherein the comprehensive risk score is more than or equal to 60 and less than 85: and (4) determining the platform risk as the risk corresponding to the digital currency transaction platform A, and performing high risk early warning on the digital currency transaction platform.
For another example, a risk tendency degree interval corresponding to the risk tendency degree (90 points) is determined: and (3) the comprehensive risk score is more than or equal to 85, and the platform risk corresponding to the risk tendency degree interval is searched: and (4) high risk, determining the platform risk as the risk corresponding to the digital currency transaction platform B, and performing high risk early warning on the digital currency transaction platform.
In addition, the secondary risk index in the risk index vector is more than or equal to 95, the high risk of the digital currency trading platform A can be determined, the secondary risk index in the risk index vector is more than or equal to 90 and less than 95, the high risk of the digital currency trading platform A can be determined, and the embodiment of the invention does not limit the high risk.
As shown in fig. 6, an implementation flow diagram of a machine learning model training method provided in an embodiment of the present invention is provided, and the method may be applied to a processor, and specifically may include the following steps.
S601, platform historical data of different digital currency transaction platforms are obtained, and the platform historical data comprise platform digital currency historical data, platform operation historical data and/or platform user historical data.
In the embodiment of the invention, platform historical data of different digital currency transaction platforms are acquired, wherein the platform historical data comprises platform digital currency historical data, platform operation historical data and/or platform user historical data.
For example, as shown in fig. 2, platform history data of different digital currency transaction platforms, such as a digital currency transaction platform a, a digital currency transaction platform B, a digital currency transaction platform C, etc., is acquired, and the platform history data includes platform digital currency history data, platform operation history data, and/or platform user history data.
It should be noted that, the platform digital currency historical data generally includes digital currency historical price data, digital currency policy historical data, digital currency public opinion historical data, and the like, the platform operation historical data generally includes platform operation historical data, platform scale historical data, platform credit historical data, platform accident historical data, platform public opinion historical data, and the like, and the platform user historical data generally includes user scale historical data, user transaction historical data, and the like, which is not limited in the embodiments of the present invention.
In addition, it should be noted that, for the manner of obtaining the platform history data of different digital currency transaction platforms, the platform history data may be obtained by a third party entity, or may be obtained by a web crawler, that is, the platform history data of different digital currency transaction platforms is obtained by the third party entity, or the platform history data of different digital currency transaction platforms is obtained by the web crawler, which is not limited in the embodiment of the present invention.
And S602, carrying out digital currency platform risk index quantification processing on the platform historical data, and generating risk index historical vectors corresponding to different digital currency trading platforms.
And for the platform historical data of different digital currency transaction platforms, carrying out digital currency platform risk index quantification processing on the platform historical data to generate risk index historical vectors corresponding to the different digital currency transaction platforms.
For example, for platform history data of different digital currency trading platforms such as the digital currency trading platform a, the digital currency trading platform B, and the digital currency trading platform C, the digital currency platform risk index quantization processing is performed on the platform history data to generate risk index history vectors corresponding to the different digital currency trading platforms.
As shown in fig. 7, an implementation flow diagram of performing digital currency platform risk indicator quantization processing on platform history data according to an embodiment of the present invention is provided.
S701, determining a preset risk index tree of the digital currency transaction platform.
In the embodiment of the present invention, this step is similar to the step S401, and details of the embodiment of the present invention are not repeated herein.
S702, determining the platform historical data to be the lowest level historical risk index in the historical risk indexes of different digital currency transaction platforms based on the risk index tree.
For the digital currency transaction platform risk index tree, in the embodiment of the invention, based on the digital currency transaction platform risk index tree, platform history data of different digital currency transaction platforms can be determined to be the lowest level historical risk index in the historical risk indexes of the different digital currency transaction platforms.
For example, as shown in the digital currency transaction platform risk indicator tree shown in fig. 5, in the embodiment of the present invention, based on the digital currency transaction platform risk indicator tree, platform history data of different digital currency transaction platforms may be determined to be a lowest-level history risk indicator in history risk indicators of different digital currency transaction platforms.
It should be noted that the lowest-level historical risk indicator is generally a statistical indicator, and may be directly quantified, that is, the lowest-level historical risk indicator is platform historical data. Further, the lowest level historical risk indicators generally correspond to leaf nodes in the digital currency trading platform risk indicator tree.
And S703, determining i-level historical risk indexes in the historical risk indexes of different digital currency transaction platforms based on the risk index tree.
For the digital currency transaction platform risk index tree, in the embodiment of the present invention, an i-level historical risk index in historical risk indexes of different digital currency transaction platforms may be determined based on the digital currency transaction platform risk index tree, where the i-level historical risk index is not a lowest-level historical risk index, and i is a positive integer.
It should be noted that, the i-level historical risk indicator generally corresponds to a non-leaf node in the risk indicator tree of the digital currency transaction platform, such as a level 1 historical risk indicator, a level 2 historical risk indicator, and the like, which is not limited in the embodiment of the present invention.
S704, standardizing the lower-level historical risk indexes of the i-level historical risk indexes, and weighting to obtain the i-level historical risk indexes.
For the i-level historical risk indexes in the historical risk indexes of different digital currency transaction platforms, the embodiment of the invention carries out standardization processing on the lower-level historical risk indexes of the i-level historical risk indexes and carries out weighting processing to obtain the i-level historical risk indexes.
For example, taking the level 1 historical risk indicator (platform digital currency historical risk) as an example, the level 2 historical risk indicators associated with the platform digital currency historical risk include: platform digital currency historical scale risk, platform digital currency historical price risk, platform digital currency historical policy risk, platform digital currency historical replacement risk.
As can be seen from this, the lower level historical risk indicators of the level 1 risk historical indicators (platform digital currency historical risk) include: the method comprises the steps of carrying out standardization processing on lower-level historical risk indexes of a level 1 historical risk index (platform digital currency historical risk), and carrying out weighting processing to obtain the level 1 historical risk index (platform digital currency historical risk). And by analogy, standardizing the lower-level historical risk indexes of the i-level historical risk indexes, and weighting to obtain the i-level historical risk indexes.
According to the embodiment of the invention, the lower-level historical risk index of the i-level historical risk index is subjected to standardization treatment by adopting dispersion standardization or z-score standardization, the lower-level historical risk index weight is determined by adopting an analytic hierarchy process or an entropy weight process, and the i-level historical risk index is obtained by weighting calculation.
S705, combining the lowest-level historical risk indexes and the i-level historical risk indexes based on the risk index tree to generate risk index historical vectors corresponding to different digital currency transaction platforms.
For the risk index tree of the digital currency transaction platform, in the embodiment of the present invention, the lowest-level historical risk index and the i-level historical risk index may be combined based on the risk index tree of the digital currency transaction platform, and risk index history vectors corresponding to different digital currency transaction platforms are generated, that is, the risk index history vectors are composed of history risk indexes (the lowest-level historical risk index and the i-level historical risk index) at different levels.
For example, as shown in fig. 5, the association relationship between each level of risk indicators in the risk indicator tree of the digital currency transaction platform combines the lowest level historical risk indicator and the i level historical risk indicator based on the association relationship between each level of risk indicators to generate the risk indicator history vectors corresponding to different digital currency transaction platforms, that is, the risk indicator history vectors are composed of each level of historical risk indicators (the lowest level historical risk indicator and the i level historical risk indicator).
S603, determining a historical risk index corresponding to the risk index historical vector, and combining the historical risk index serving as a sample label with the risk index historical vector to generate sample data.
In the embodiment of the invention, corresponding experts can score different digital currency transaction platforms and determine the corresponding scores of the different digital currency transaction platforms, and the scores of the experts aiming at the different digital currency transaction platforms are the risk index at a specific time, namely the sample label of sample data, namely the risk index.
Based on this, in the embodiment of the present invention, a historical risk index (specified by a relevant expert) corresponding to the risk indicator history vector may be determined, and the historical risk index is used as a sample label to be combined with the risk indicator history vector to generate sample data, so that sample data for model training may be obtained.
S604, obtaining a machine learning model, and performing supervised training on the machine learning model based on the sample data until a preset loss function meets a convergence condition.
In the embodiment of the invention, the machine learning model can be obtained, and supervised training is carried out on the machine learning model based on the sample data until the preset loss function meets the convergence condition, so that the risk early warning model of the digital currency transaction platform can be obtained.
The machine learning model may be, for example, a decision tree model, a logistic regression model, or the like, and the loss function may be, for example, an L2 loss function, or an L1 loss function, which is not limited in the embodiment of the present invention.
Corresponding to the above method embodiment, an embodiment of the present invention further provides a risk early warning apparatus, as shown in fig. 8, the apparatus may include: the system comprises a data acquisition module 810, a vector generation module 820, an index output module 830 and a risk early warning module 840.
A data obtaining module 810, configured to obtain platform data of a digital currency transaction platform to be analyzed, where the platform data includes platform digital currency data, platform operation data, and/or platform user data;
a vector generation module 820, configured to perform digital currency platform risk indicator quantization processing on the platform data, and generate a risk indicator vector corresponding to the digital currency transaction platform;
an index output module 830, configured to input the risk indicator vector to a preset risk early warning model of a digital currency transaction platform, and output a risk index corresponding to the digital currency transaction platform;
and the risk early warning module 840 is used for early warning the risk of the digital currency transaction platform based on the risk index.
In a specific implementation manner of the embodiment of the present invention, the vector generating module 820 specifically includes:
the index tree determining submodule is used for determining a preset digital currency transaction platform risk index tree;
a first index determination submodule, configured to determine, based on the risk index tree, that the platform data is a lowest-level risk index in the digital currency trading platform risk indexes;
a second index determining submodule, configured to determine an i-level risk index in the digital currency trading platform risk indexes based on the risk index tree, where the i-level risk index is not the lowest-level risk index, and i is a positive integer;
the index processing submodule is used for carrying out standardization processing on the lower-level risk indexes of the i-level risk indexes and carrying out weighting processing to obtain the i-level risk indexes;
and the vector generation submodule is used for combining the lowest-level risk index and the i-level risk index based on the risk index tree to generate a risk index vector corresponding to the digital currency trading platform.
In a specific implementation manner of the embodiment of the present invention, the index processing sub-module is specifically configured to:
and standardizing the lower-level risk indexes of the i-level risk indexes by adopting dispersion standardization or z-score standardization, determining the weights of the lower-level risk indexes by adopting an analytic hierarchy process or an entropy weight process, and performing weighting calculation to obtain the i-level risk indexes.
In a specific implementation manner of the embodiment of the present invention, the risk early warning module 840 specifically includes:
the data statistics submodule is used for carrying out statistics on sample data of the digital currency transaction platform risk early warning model to obtain the maximum value and the minimum value of each level of risk indexes, wherein the sample data consists of each level of risk indexes;
the tendency output submodule is used for inputting the risk index, the maximum value and the minimum value into a preset risk index quantitative conversion algorithm and outputting the risk tendency corresponding to the digital currency trading platform;
and the risk early warning sub-module is used for determining the risk corresponding to the digital currency transaction platform according to the risk tendency and carrying out risk early warning on the digital currency transaction platform.
In a specific implementation manner of the embodiment of the present invention, the risk indicator quantization conversion algorithm includes:
wherein a' is the risk propensity, a is the risk index, target (max) is the maximum value, and target (min) is the minimum value.
In a specific implementation manner of the embodiment of the present invention, the risk early warning sub-module is specifically configured to:
determining a risk tendency degree interval corresponding to the risk tendency degree, and searching a platform risk corresponding to the risk tendency degree interval;
and determining the platform risk as the risk corresponding to the digital currency transaction platform, and performing digital currency transaction platform risk early warning.
In a specific implementation manner of the embodiment of the present invention, the apparatus further includes a model training module, where the model training module specifically includes:
the historical data acquisition submodule is used for acquiring platform historical data of different digital currency transaction platforms, and the platform historical data comprises platform digital currency historical data, platform operation historical data and/or platform user historical data;
the history vector generation submodule is used for carrying out digital currency platform risk index quantification processing on the platform history data and generating risk index history vectors corresponding to different digital currency transaction platforms;
the sample data generation submodule is used for determining a historical risk index corresponding to the risk index historical vector, and combining the historical risk index serving as a sample label with the risk index historical vector to generate sample data;
and the model training submodule is used for acquiring a machine learning model and carrying out supervised training on the machine learning model based on the sample data until a preset loss function meets a convergence condition.
In a specific implementation manner of the embodiment of the present invention, the history vector generation sub-module specifically includes:
the index tree determining unit is used for determining a preset digital currency transaction platform risk index tree;
a first index determination unit, configured to determine, based on the risk index tree, that the platform history data is a lowest-level historical risk index among historical risk indexes of different digital currency trading platforms;
a second index determining unit, configured to determine an i-level historical risk index from historical risk indexes of different digital currency trading platforms based on the risk index tree;
wherein the i-level historical risk indicator is not the lowest-level historical risk indicator, and i is a positive integer;
the index processing unit is used for carrying out standardization processing on lower-level historical risk indexes of the i-level historical risk indexes and carrying out weighting processing to obtain the i-level historical risk indexes;
and the history vector generating unit is used for combining the lowest-level history risk index and the i-level history risk index based on the risk index tree and generating the risk index history vectors corresponding to different digital currency trading platforms.
In a specific implementation manner of the embodiment of the present invention, the index processing unit is specifically configured to:
and carrying out standardization processing on the lower-level historical risk indexes of the i-level historical risk indexes by adopting dispersion standardization or z-score standardization, determining the weights of the lower-level historical risk indexes by adopting an analytic hierarchy process or an entropy weight process, and carrying out weighting calculation to obtain the i-level historical risk indexes.
An embodiment of the present invention further provides an electronic device, as shown in fig. 9, which includes a processor 91, a communication interface 92, a memory 93, and a communication bus 94, where the processor 91, the communication interface 92, and the memory 93 complete mutual communication through the communication bus 94,
a memory 93 for storing a computer program;
the processor 91, when executing the program stored in the memory 93, implements the following steps:
acquiring platform data of a digital currency transaction platform to be analyzed, wherein the platform data comprises platform digital currency data, platform operation data and/or platform user data; performing digital currency platform risk index quantification processing on the platform data to generate a risk index vector corresponding to the digital currency transaction platform; inputting the risk index vector into a preset digital currency transaction platform risk early warning model, and outputting a risk index corresponding to the digital currency transaction platform; and early warning the risk of the digital currency transaction platform based on the risk index.
The communication bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components.
In another embodiment of the present invention, a storage medium is further provided, where instructions are stored in the storage medium, and when the instructions are executed on a computer, the computer is caused to execute the risk early warning method in any one of the above embodiments.
In yet another embodiment of the present invention, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the risk pre-warning method of any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a storage medium or transmitted from one storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium may be any available medium that can be accessed by a computer or a data storage device including one or more available media integrated servers, data centers, and the like. 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 (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (12)
1. A risk pre-warning method, the method comprising:
acquiring platform data of a digital currency transaction platform to be analyzed, wherein the platform data comprises platform digital currency data, platform operation data and/or platform user data;
carrying out digital currency platform risk index quantification processing on the platform data to generate a risk index vector corresponding to the digital currency transaction platform;
inputting the risk index vector into a preset digital currency transaction platform risk early warning model, and outputting a risk index corresponding to the digital currency transaction platform;
and early warning the risk of the digital currency transaction platform based on the risk index.
2. The method according to claim 1, wherein the performing digital currency platform risk indicator quantification processing on the platform data to generate a risk indicator vector corresponding to the digital currency trading platform comprises:
determining a preset risk index tree of the digital currency transaction platform;
determining the platform data as the lowest level risk index in the digital currency trading platform risk indexes based on the risk index tree;
determining an i-grade risk index in the risk indexes of the digital currency trading platform based on the risk index tree, wherein the i-grade risk index is not the lowest-grade risk index, and i is a positive integer;
carrying out standardization processing on lower-level risk indexes of the i-level risk indexes, and carrying out weighting processing to obtain the i-level risk indexes;
and combining the lowest-level risk index and the i-level risk index based on the risk index tree to generate a risk index vector corresponding to the digital currency trading platform.
3. The method according to claim 2, wherein the normalizing the lower-level risk indicators of the i-level risk indicator and weighting the lower-level risk indicators to obtain the i-level risk indicator comprises:
and carrying out standardization treatment on the lower-level risk indexes of the i-level risk indexes by adopting dispersion standardization or z-score standardization, determining the weights of the lower-level risk indexes by adopting an analytic hierarchy process or an entropy weight process, and carrying out weighting calculation to obtain the i-level risk indexes.
4. The method of claim 1, wherein the pre-warning of the digital currency trading platform risk based on the risk index comprises:
counting sample data of the digital currency transaction platform risk early warning model to obtain the maximum value and the minimum value of each level of risk indexes, wherein the sample data consists of each level of risk indexes;
inputting the risk index, the maximum value and the minimum value into a preset risk index quantitative conversion algorithm, and outputting a risk tendency degree corresponding to the digital currency trading platform;
and determining the corresponding risk of the digital currency transaction platform according to the risk tendency, and carrying out risk early warning on the digital currency transaction platform.
6. The method according to claim 4, wherein the step of determining the risk corresponding to the digital currency transaction platform according to the risk tendency to perform digital currency transaction platform risk early warning comprises the steps of:
determining a risk tendency degree interval corresponding to the risk tendency degree, and searching a platform risk corresponding to the risk tendency degree interval;
and determining the platform risk as the risk corresponding to the digital currency transaction platform, and performing digital currency transaction platform risk early warning.
7. The method according to any one of claims 1 to 6, wherein the digital currency transaction platform risk pre-warning model is obtained by:
acquiring platform historical data of different digital currency transaction platforms, wherein the platform historical data comprises platform digital currency historical data, platform operation historical data and/or platform user historical data;
carrying out digital currency platform risk index quantification processing on the platform historical data to generate risk index historical vectors corresponding to different digital currency transaction platforms;
determining a historical risk index corresponding to the risk index historical vector, and combining the historical risk index serving as a sample label with the risk index historical vector to generate sample data;
and acquiring a machine learning model, and carrying out supervised training on the machine learning model based on the sample data until a preset loss function meets a convergence condition.
8. The method according to claim 7, wherein the performing digital currency platform risk indicator quantization processing on the platform history data to generate risk indicator history vectors corresponding to different digital currency trading platforms includes:
determining a preset risk index tree of the digital currency transaction platform;
determining the platform historical data as the lowest level historical risk index in the historical risk indexes of different digital currency transaction platforms based on the risk index tree;
determining i-level historical risk indexes in historical risk indexes of different digital currency transaction platforms based on the risk index tree;
wherein the i-level historical risk indicator is not the lowest-level historical risk indicator, and i is a positive integer;
standardizing lower-level historical risk indexes of the i-level historical risk indexes, and weighting to obtain the i-level historical risk indexes;
and combining the lowest-level historical risk indexes and the i-level historical risk indexes based on the risk index tree to generate risk index historical vectors corresponding to different digital currency transaction platforms.
9. The method according to claim 8, wherein the normalizing the lower historical risk indicator of the i-level historical risk indicator and weighting the lower historical risk indicator to obtain the i-level historical risk indicator comprises:
and standardizing the lower-level historical risk indexes of the i-level historical risk indexes by adopting dispersion standardization or z-score standardization, determining the weights of the lower-level historical risk indexes by adopting an analytic hierarchy process or an entropy weight process, and performing weighting calculation to obtain the i-level historical risk indexes.
10. A risk early warning device, the device comprising:
the system comprises a data acquisition module, a data analysis module and a data analysis module, wherein the data acquisition module is used for acquiring platform data of a digital currency transaction platform to be analyzed, and the platform data comprises platform digital currency data, platform operation data and/or platform user data;
the vector generation module is used for carrying out digital currency platform risk index quantification processing on the platform data and generating a risk index vector corresponding to the digital currency trading platform;
the index output module is used for inputting the risk index vector to a preset digital currency transaction platform risk early warning model and outputting a risk index corresponding to the digital currency transaction platform;
and the risk early warning module is used for early warning the risk of the digital currency transaction platform based on the risk index.
11. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method steps of any one of claims 1 to 9 when executing a program stored in the memory.
12. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110071008.7A CN114819963A (en) | 2021-01-19 | 2021-01-19 | Risk early warning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110071008.7A CN114819963A (en) | 2021-01-19 | 2021-01-19 | Risk early warning method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114819963A true CN114819963A (en) | 2022-07-29 |
Family
ID=82524293
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110071008.7A Pending CN114819963A (en) | 2021-01-19 | 2021-01-19 | Risk early warning method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114819963A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117952619A (en) * | 2024-03-26 | 2024-04-30 | 南京赛融信息技术有限公司 | Risk behavior analysis method, system and computer readable medium based on digital RMB wallet account correlation |
-
2021
- 2021-01-19 CN CN202110071008.7A patent/CN114819963A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117952619A (en) * | 2024-03-26 | 2024-04-30 | 南京赛融信息技术有限公司 | Risk behavior analysis method, system and computer readable medium based on digital RMB wallet account correlation |
CN117952619B (en) * | 2024-03-26 | 2024-06-07 | 南京赛融信息技术有限公司 | Risk behavior analysis method, system and computer readable medium based on digital RMB wallet account correlation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20180260891A1 (en) | Systems and methods for generating and using optimized ensemble models | |
US20150242856A1 (en) | System and Method for Identifying Procurement Fraud/Risk | |
CN110689438A (en) | Enterprise financial risk scoring method and device, computer equipment and storage medium | |
CN110930218A (en) | Method and device for identifying fraudulent customer and electronic equipment | |
CN113609193A (en) | Method and device for training prediction model for predicting customer transaction behavior | |
CN115422173A (en) | Data management method and system in financial credit field | |
Byanjankar et al. | Data‐driven optimization of peer‐to‐peer lending portfolios based on the expected value framework | |
Qiu et al. | Multisource evidence theory‐based fraud risk assessment of China's listed companies | |
CN108737138B (en) | Service providing method and service platform | |
CN113469818B (en) | Investment risk early warning method and device, electronic equipment and computer readable medium | |
CN114092097B (en) | Training method of risk identification model, transaction risk determining method and device | |
CN111199473A (en) | Anti-cheating method, device and system based on transaction record information | |
CN114819963A (en) | Risk early warning method and device, electronic equipment and storage medium | |
CN112702410B (en) | Evaluation system, method and related equipment based on blockchain network | |
Owda et al. | Financial discussion boards irregularities detection system (fdbs-ids) using information extraction | |
CN109636627B (en) | Insurance product management method, device, medium and electronic equipment based on block chain | |
CN111209403A (en) | Data processing method, device, medium and electronic equipment | |
US11107139B1 (en) | Computing system learning of a merchant category code | |
CN115358894A (en) | Intellectual property life cycle trusteeship management method, device, equipment and medium | |
CN112053244B (en) | Information processing method, device and server | |
KR102271346B1 (en) | Credit loan platform using atypical-data and its operating method | |
CN115034685A (en) | Customer value evaluation method, customer value evaluation device and computer-readable storage medium | |
CN111681090A (en) | Account grouping method and device of business system, terminal equipment and storage medium | |
CN114298825A (en) | Method and device for extremely evaluating repayment volume | |
CN113962603A (en) | Risk assessment method and device, storage medium and electronic equipment |
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 |